System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring activity data; means for acquiring audio data; artificial intelligence means for analyzing the acquired activity data and audio data; means for generating mental and physical healthcare advice based on the analysis; and means for providing the advice to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Workers are often overwhelmed by their daily work, which can lead to poor mental health due to stress and overwork, and a lack of exercise due to an office-centered lifestyle. This increases the risk of obesity and lifestyle-related diseases. Under these circumstances, it is difficult for workers to manage their own mental and physical health in both directions and maintain overall well-being. Furthermore, traditional healthcare systems often manage mental health and physical health separately, lacking a comprehensive approach. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means:

[0006] a means for acquiring activity data;

[0007] means for acquiring audio data;

[0008] artificial intelligence means for analyzing the acquired activity data and audio data;

[0009] means for generating mental and physical health care advice based on the analysis results;

[0010] means for providing said advice to a user;

[0011] The solution is to use a system including:

[0012] The present invention also provides a means for detecting a continuous abnormality in the user and a means for referring the user to a specialist or medical institution in response to the detected abnormality, thereby enabling the user to take appropriate measures regarding their health condition at an early stage.

[0013] Furthermore, by providing a means for assessing the user's emotional state based on voice data, the present invention makes it possible to detect subtle changes in the user's mental health and provide appropriate feedback quickly.

[0014] "Activity data" refers to physical information such as the user's daily exercise volume, heart rate, body temperature, and sleep time.

[0015] "Voice data" refers to information such as tone, speed, and pronunciation of speech recorded when a user interacts with an AI assistant.

[0016] "Artificial intelligence means" refers to the machine learning models and algorithms used to analyze the collected data and assess the user's mental and physical well-being.

[0017] "Means for generating advice" refers to the function that automatically creates specific behavioral suggestions and advice that will help improve the user's health based on the analysis results.

[0018] "Means for providing advice" refers to the function of notifying the user of the generated advice on their smartphone or wearable device.

[0019] "Continuous abnormality" refers to a condition in which a specific abnormality in a user's mental or physical health persists for a certain period of time.

[0020] "Means for referring users to specialists or medical institutions" refers to a function that guides users to appropriate counseling services or medical institutions when persistent abnormalities are detected.

[0021] "Means for assessing emotional state" refers to a function for analyzing changes in a user's emotions based on voice data and assessing stress and psychological state. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] This invention relates to an AI healthcare system that synchronizes the mental and physical health of workers. The system collects and analyzes the user's daily activity data and voice data to evaluate their health status. Based on the evaluation results, the system provides professional advice and, if necessary, refers the user to a specialist or medical institution.

[0044] System Configuration

[0045] 1. Data Collection Methods

[0046] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0047] Users can verbally greet and comment to the AI ​​assistant, providing voice data.

[0048] 2. Data upload method

[0049] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[0050] 3. Data Analysis Methods

[0051] The server analyzes the received data using artificial intelligence means, providing an emotional state assessment for the voice data and a physical health assessment based on the activity data.

[0052] 4. Advice Generation Methods

[0053] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[0054] 5. Means of providing advice

[0055] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the wearable device.

[0056] 6. Escalation Methods

[0057] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, such as if their mental health condition has been deteriorating for a certain period of time or if their physical data shows abnormal values.

[0058] Program processing

[0059] 1. Data Collection

[0060] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[0061] 2. Data upload

[0062] The device transmits the collected data to a server at set times, including activity data as well as information about the tone and speed of the voice.

[0063] 3. Data Analysis

[0064] The server inputs the transmitted data into a machine learning model to analyze the user's emotional and physical state, determining stress levels from voice data and exercise volume and health status from activity data.

[0065] 4. Advice Generation

[0066] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[0067] 5. Providing advice

[0068] The device then notifies the user of the advice it receives from the server. For example, the device displays a message on the smartphone screen saying, "Your stress levels are rising. Try meditating."

[0069] 6. Escalation

[0070] If the server detects persistent abnormalities, it will refer the user to an appropriate specialist or medical institution, allowing the user to receive professional support early on.

[0071] Specific examples

[0072] Example 1: Weekday status

[0073] 1. A user greets an AI assistant with "Good morning" in the morning.

[0074] 2. The device sends the collected voice data and the previous day's activity data to the server.

[0075] 3. The server analyzes the data and detects an increase in stress levels from the voice data.

[0076] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[0077] 5. The device notifies the user of the advice.

[0078] Example 2: Weekend Situation

[0079] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[0080] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[0081] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[0082] 4. The device notifies the user of the advice.

[0083] The above is an embodiment of the system of the present invention, which allows users to comprehensively manage their mental and physical health in their daily lives.

[0084] The processing flow will be explained below.

[0085] Step 1:

[0086] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[0087] Step 2:

[0088] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[0089] Step 3:

[0090] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is encrypted and transmitted securely.

[0091] Step 4:

[0092] The server analyzes the received data. Specifically,

[0093] Voice data analysis: Voice data is fed into machine learning models to assess the user's emotional state (e.g., stress level, changes in tone).

[0094] Activity data analysis: Analyzes step count, heart rate, body temperature, and sleep data to evaluate physical health status (e.g., exercise volume, fluctuations in health indicators).

[0095] Step 5:

[0096] The server generates advice for the user based on the results of the data analysis. Specifically,

[0097] Mental health advice: Generates relaxation and meditation suggestions when stress levels are high.

[0098] Physical health advice: Generates specific exercise and dietary suggestions if physical inactivity is detected.

[0099] Step 6:

[0100] The server sends the generated advice to the device, which then notifies the user. For example, the smartphone might say, "Your step count today is low, so try walking one station on your way home."

[0101] Step 7:

[0102] The device enters a loop where it receives feedback from the user and again sends data to the server, including whether or not the user actually tried the suggested action.

[0103] Step 8:

[0104] The server continuously monitors the data, and if an abnormality persists for a certain period of time, it will take action to refer the user to a specialist or medical institution, allowing the user to receive appropriate assistance early on.

[0105] Example 1

[0106] 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."

[0107] In today's world, comprehensive management of workers' mental and physical health is an important issue. However, many existing systems focus on one type of health condition, and few provide comprehensive support for both mental and physical health. Furthermore, there is a lack of appropriate ways to deal with ongoing abnormalities, making it difficult to provide early, specialized support. Therefore, there is a need for the development of a system that can achieve comprehensive health management for users.

[0108] 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.

[0109] In this invention, the server includes a means for acquiring activity data, a means for acquiring voice data, a means for transmitting the acquired activity data and voice data to the server at a predetermined time, a means for analyzing the transmitted data using artificial intelligence, a means for generating mental and physical health care advice based on the analysis results, and a means for notifying the user of the advice. This enables a comprehensive evaluation of the user's daily health condition and the provision of appropriate advice in real time. Furthermore, if abnormalities are detected over a long period of time, the server can refer the user to a specialist or medical institution, allowing the user to receive professional support early.

[0110] "Activity data" refers to data related to the user's physical activity in daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[0111] "Voice data" refers to data that records the voice spoken by a user, including the content of the conversation, tone, speed, etc.

[0112] "Server" refers to a computer system that receives data, analyzes it, and generates results, and is capable of communicating with terminals via a network.

[0113] "Artificial intelligence" refers to algorithms and systems that use techniques such as machine learning and deep learning to analyze data and discover patterns.

[0114] "Analysis results" are the results of analysis of data processed by artificial intelligence, based on which health and emotional state are assessed.

[0115] "Healthcare advice" refers to specific suggestions and guidelines for action to improve the user's health based on the analysis results.

[0116] A "persistent anomaly" refers to a situation in which an abnormal pattern is detected continuously over a period of time in a user's activity data or voice data.

[0117] "Referral to specialists or medical institutions" refers to the act of informing or recommending appropriate specialists or medical facilities to users as needed.

[0118] "Emotional state" refers to a psychological state assessed based on a user's voice data, and includes stress, joy, sadness, etc.

[0119] "Notification" refers to the means of communication, usually via a device, to convey generated advice or warnings to the user.

[0120] This invention relates to an AI healthcare system for comprehensively managing the mental and physical health of workers. This system collects and analyzes the user's daily activity data and voice data, evaluates their health status, and provides appropriate advice. Furthermore, if persistent abnormalities are detected, the system will refer the user to a specialist or medical institution. A detailed embodiment of this system is shown below.

[0121] Data collection methods

[0122] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. When the user verbally greets or comments to the AI ​​assistant, this voice data is also recorded. Specific hardware used includes a smartphone (e.g., Android, iPhone) or a wearable device (e.g., Fitbit, Apple Watch).

[0123] Example: A user says "Good morning" to an AI assistant in the morning, which collects voice data, while the wearable device simultaneously transmits the number of steps and heart rate recorded the previous day to a smartphone.

[0124] Data upload method

[0125] The device sends the collected data to the server at a set time. It can be set to upload data every morning at 9:00 and every evening at 9:00. The data sent includes activity data, voice tones, speed, etc.

[0126] Example: Every night at 9pm, the device automatically uploads data to the server, ensuring that fresh data is always stored on the server.

[0127] Data Analysis Methods

[0128] The server receives the data sent from the device and inputs it into machine learning models (e.g., TensorFlow, PyTorch). Voice data is used to assess stress levels using emotion analysis algorithms, and activity data is used to determine the user's physical health (e.g., amount of exercise, quality of sleep).

[0129] Example: A server analysis script uses a TensorFlow model to analyze audio data and classify the user's emotional state into "positive," "negative," or "neutral," thereby determining how stressed the user is.

[0130] Advice Generation Method

[0131] Based on the analysis results, the server generates appropriate health improvement advice for the user, suggesting relaxation methods if stress levels are high, and recommending specific exercises if exercise is lacking.

[0132] Example: A message such as "Your stress levels are rising. Try meditating for five minutes" is generated. If you are not getting enough exercise, specific advice such as "Set your goal for today to be a 30-minute walk" is provided.

[0133] Advice delivery methods

[0134] The device notifies the user of the generated advice via push notifications on smartphones or vibrations on wearable devices.

[0135] Example: At 9:00 a.m., your smartphone displays a push notification with the advice, "Good morning. Let's stay healthy today." Your wearable device also vibrates gently to notify you of this notification.

[0136] Escalation methods

[0137] The server continuously monitors the user's data and will refer the user to a specialist or medical institution if an abnormality is detected, for example, if stress levels remain high for a certain period of time or if physical data shows abnormal values.

[0138] Example: If the server detects a high stress level for one consecutive week, it generates a message saying, "You appear to be experiencing persistent stress. Perhaps you should seek professional counseling?" and the device notifies the user of this message.

[0139] In this way, the present invention can comprehensively evaluate the user's daily health condition and provide appropriate advice in real time. It also allows the user to receive professional support early on, making it possible to maintain and improve mental and physical health.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1: Data collection

[0142] The device will collect activity data (e.g., number of steps, heart rate, body temperature, and sleep time) using a smartphone or wearable device as the user goes about their daily life, and will also record voice data when the user speaks to the AI ​​assistant or expresses their thoughts.

[0143] Input: User activity and voice data.

[0144] Data processing: Activity data is automatically recorded by a pedometer and heart rate sensor, and audio data is collected by a microphone.

[0145] Output: Activity data and voice data stored in the smartphone.

[0146] How it works: When a user says "Good morning" to the AI ​​assistant, the voice is recorded by an application on the smartphone, and the wearable device simultaneously measures daily activity data such as steps taken and heart rate and sends the data to the smartphone.

[0147] Step 2: Upload data

[0148] The device periodically sends the collected data to the server, for example, uploading all data at 9:00 every morning and 9:00 every evening.

[0149] Input: Activity and voice data stored on the smartphone.

[0150] Data processing: The data is compressed, encrypted and sent to the server.

[0151] Output: Compressed data file uploaded to the server.

[0152] How it works: Every night at 9 p.m., the smartphone uploads the accumulated data to a cloud server via a dedicated application. At this time, the data is compressed and encrypted to ensure security.

[0153] Step 3: Data analysis

[0154] The server then analyzes the received data using artificial intelligence (AI) and machine learning models (e.g., TensorFlow, PyTorch). The voice data is used to assess emotional state, and the activity data is used to analyze physical health.

[0155] Input: The compressed data file uploaded to the server.

[0156] Data processing: Data decompression and preprocessing (e.g., noise removal, data cleaning) are performed.

[0157] Output: Emotional state and physical health analysis.

[0158] How it works: A Python script running on the server unpacks the uploaded data, performs preprocessing, and then uses machine learning models to assess emotional state from voice data and physical health from activity data. For example, a "high stress level" may be determined based on voice analysis.

[0159] Step 4: Advice Generation

[0160] The server generates health advice for the user based on the analysis results, recommending appropriate behaviors for the user in terms of both mental and physical health.

[0161] Input: Emotional state and physical health analysis results.

[0162] Data processing: Advice content is customized based on the analysis results.

[0163] Output: Customized advice to provide to the user.

[0164] Specific operation: For example, the server generates advice such as "Try 5 minutes of meditation" for a user who is analyzed as having a "high stress level."

[0165] Step 5: Providing advice

[0166] The device notifies the user of the generated advice using methods such as push notifications on smartphones or vibrations on wearable devices.

[0167] Input: Customized advice sent by the server.

[0168] Data processing: Display advice in a format that is easy for users to understand.

[0169] Output: Advice given to the user.

[0170] Specific operation: At 9 a.m., the smartphone displays a push notification saying, "Your stress level is high today. Try a 5-minute meditation," and the wearable device vibrates gently to notify the user.

[0171] Step 6: Escalation

[0172] The server continuously monitors the user's data and, if an abnormality is detected, will refer the user to a specialist or medical institution. If an abnormality is detected, the server will notify the user and provide information on the appropriate specialist.

[0173] Input: Continuously monitored user data.

[0174] Data processing: detecting outliers and selecting appropriate referrals from a list of specialists and medical institutions.

[0175] Output: Notification that an abnormality was detected and information for specialists or medical institutions.

[0176] Specific operation: The server detects a high stress level for one consecutive week, generates a message saying, "It appears that stress is continuing. Perhaps you should seek professional counseling?" and notifies the user of this message on the device.

[0177] (Application example 1)

[0178] 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."

[0179] In modern factories, managing the mental and physical health of workers is important. However, traditional methods have the drawback of being difficult to monitor in real time or respond quickly to abnormalities. It is also difficult for workers to accurately understand their own health status and take appropriate measures. This can lead to the accumulation of excessive stress and fatigue, which can lead to reduced productivity and an increased risk of workplace accidents.

[0180] 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.

[0181] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, and means for detecting an abnormal condition and referring the user to a specialist or medical institution when the user's physical or mental condition falls below a certain standard. This makes it possible to monitor the health condition of workers in real time and quickly respond to any abnormalities that occur.

[0182] "Activity Data" refers to data that quantifies a user's daily physical movements and activities, such as the number of steps taken, heart rate, body temperature, and sleep duration.

[0183] "Voice Data" refers to the audio information provided when a user converses with an AI assistant, including the tone, speed, and content of the speech.

[0184] "Artificial Intelligence Means" refers to the machine learning algorithms and artificial intelligence models used to analyze collected activity data and audio data.

[0185] "Mental and physical healthcare advice" refers to specific suggestions and instructions to improve a user's psychological and physical health based on the analysis results.

[0186] "User" refers to an individual who uses the system, including laborers and factory workers.

[0187] "Abnormal condition" refers to a state in which a user's physical or mental health falls below the standards set by the system.

[0188] "Expert" refers to a medical professional or counselor who can provide appropriate responses and advice to the user's abnormal condition.

[0189] "Medical Institution" refers to a hospital or clinic that provides specialized medical care or treatment required by the User.

[0190] "Real-time" refers to processing or response occurring almost immediately or with very little delay.

[0191] The higher expression of "physical" is defined as "physical." "Physical health" refers to "physical well-being."

[0192] The higher term for "mental" is defined as "psychological." "Mental health" refers to "psychological health."

[0193] The present invention is a system for monitoring the mental and physical health of workers in real time and providing appropriate advice. This system is implemented with the following configuration and procedures.

[0194] System Configuration

[0195] 1. Data Collection Methods

[0196] The device uses devices such as smartwatches and smartphones to collect data on a user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0197] Users provide voice data by verbally expressing greetings and impressions to the AI ​​assistant.

[0198] 2. Data upload method

[0199] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[0200] 3. Data Analysis Methods

[0201] The server analyzes the received data using artificial intelligence means (e.g., machine learning models), assessing emotional state based on the voice data and physical health status based on the activity data.

[0202] 4. Advice Generation Methods

[0203] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[0204] 5. Means of providing advice

[0205] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the smartwatch.

[0206] 6. Escalation Methods

[0207] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, for example, if their mental health condition has deteriorated over a certain period of time or if their physical data shows abnormal values.

[0208] Example of operation

[0209] Example 1: Weekday status

[0210] The user greets the AI ​​assistant with "Good morning" in the morning.

[0211] The device sends the collected voice data and the previous day's activity data to the server.

[0212] The server analyzes the data and detects rising stress levels from the voice data.

[0213] The server generates advice such as "Your stress is increasing. Try 5 minutes of meditation."

[0214] The device will notify the user of the advice.

[0215] Example 2: Weekend Situation

[0216] The user sends the heart rate and sleep time measured by the smartwatch to the server.

[0217] The server analyzes the data and detects whether the user is getting enough sleep.

[0218] The server generates advice such as, "We recommend keeping things light today and getting plenty of rest."

[0219] The device will notify the user of the advice.

[0220] Prompt Sentence Examples

[0221] "Analyze the following data and generate health advice for the user: Data: {'steps': 4500, 'heart_rate': 95, 'temperature': 37.5, 'sleep_hours': 5.5, 'voice_tone': 'stress'}"

[0222] The above is a specific embodiment of the system of the present invention, which allows workers to comprehensively manage their mental and physical health in their daily lives.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] Data collection:

[0226] The device uses a smartwatch or smartphone to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0227] Users can converse with the AI ​​assistant via voice and provide voice data.

[0228] Input: User activity data, voice data

[0229] Output: A set of collected activity and audio data

[0230] What it does: For example, a smartwatch counts steps, monitors heart rate, and records audio when you say "good morning."

[0231] Step 2:

[0232] Data Upload:

[0233] The terminal transmits the collected activity data and voice data to the server at regular intervals (for example, every morning).

[0234] Input: Collected activity and audio data

[0235] Output: Data sent to the server

[0236] Specific operation: The device uses Wi-Fi or mobile data connection to upload activity data (e.g., 4,500 steps) and audio data (e.g., audio tone is "stress") to a cloud server.

[0237] Step 3:

[0238] Data Analysis:

[0239] The server inputs the received data into artificial intelligence means (e.g., machine learning models) to analyze the user's mental and physical state.

[0240] Input: Activity and voice data sent to the server

[0241] Output: Mental and physical health assessment results

[0242] Specific behavior: For example, a machine learning model analyzes heart rate and voice tone to determine a user's stress level as "high," or analyzes steps taken and sleep time to assess physical health as "poor."

[0243] Step 4:

[0244] Advice Generation:

[0245] Based on the analysis results, the server generates health improvement advice for the user, suggesting relaxation methods for mental health and exercise and rest for physical health.

[0246] Input: Mental and physical health assessment results

[0247] Output: Generated healthcare advice

[0248] Specific operation: For example, the server generates advice such as "Please meditate for five minutes" based on the evaluation result that "your stress level is high." Also, based on the evaluation result that your physical health is "poor," it generates advice such as "Please reduce your schedule for today and get plenty of rest."

[0249] Step 5:

[0250] Advice provided:

[0251] The terminal notifies the user of the advice received from the server.

[0252] Input: Generated healthcare advice

[0253] Output: User advice notice

[0254] Specific actions: For example, the smartphone screen will display a message saying, "Your stress is increasing. Try a 5-minute meditation." The smartwatch will also send a vibration notification.

[0255] Step 6:

[0256] escalation:

[0257] If the server detects persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[0258] Input: Continuous abnormal data

[0259] Output: Referral information for specialists and medical institutions

[0260] Specific operation: For example, if the server detects that a user's stress level has remained high for more than a week, it will notify the user by listing appropriate medical institutions, such as "Your stress level has remained high. We recommend that you consult the medical institution listed below."

[0261] These are the specific processing steps of the system, which enables comprehensive management of the user's mental and physical health in real time.

[0262] 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.

[0263] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. This system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[0264] System Configuration

[0265] 1. Data Collection Methods

[0266] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0267] Users interact with the AI ​​assistant and provide voice data, which includes information such as the user's tone and speed.

[0268] 2. Data upload method

[0269] The device sends the collected data to a server at regular intervals. For example, by uploading data every morning and evening, it is possible to monitor health conditions in real time.

[0270] 3. Data Analysis Methods

[0271] The server is equipped with artificial intelligence means for analyzing the received data, using an emotion engine to assess the user's emotional state from the voice data, and physical health status from the activity data.

[0272] The emotion engine analyzes voice data to determine the user's stress level and emotional state. The engine captures changes in the user's emotions through detailed analysis of the tone, speed, rhythm, etc. of the voice.

[0273] 4. Advice Generation Methods

[0274] Based on the analysis results, the server generates appropriate health improvement advice for the user, such as stress management and relaxation methods for mental health, and exercise and diet suggestions for physical health.

[0275] For example, if the emotion engine detects a user's high stress state, it will generate mental health advice such as "Try five minutes of meditation."

[0276] 5. Means of providing advice

[0277] The device then notifies the user of the generated advice. By providing real-time advice via a smartphone or wearable device, the user can take immediate action.

[0278] 6. Escalation Methods

[0279] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist.

[0280] This escalation feature allows users to take appropriate action regarding their health condition early on.

[0281] Program processing

[0282] 1. Data Collection

[0283] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[0284] 2. Data upload

[0285] The device transmits the collected data to a server at scheduled times, including activity data as well as information about the tone and speed of the voice.

[0286] 3. Data Analysis

[0287] The server inputs the transmitted data into a machine learning model and emotion engine to analyze the user's emotional and physical state. The server evaluates the user's emotional state (e.g., stress level, tone changes) from the voice data and their physical health status (e.g., exercise volume, fluctuations in health indicators) from the activity data.

[0288] 4. Advice Generation

[0289] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[0290] 5. Providing advice

[0291] The device then notifies the user of the advice it receives from the server. For example, a message like "Your stress levels are rising. Try meditation" will appear on the smartphone screen.

[0292] 6. Escalation

[0293] If a persistent abnormality is detected, the server will refer the user to an appropriate specialist or medical institution, ensuring that the user receives appropriate assistance early on.

[0294] Specific examples

[0295] Example 1: Weekday status

[0296] 1. A user greets an AI assistant with "Good morning" in the morning.

[0297] 2. The device sends the collected voice data and the previous day's activity data to the server.

[0298] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[0299] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[0300] 5. The device notifies the user of the advice.

[0301] Example 2: Weekend Situation

[0302] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[0303] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[0304] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[0305] 4. The device notifies the user of the advice.

[0306] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[0307] The processing flow will be explained below.

[0308] Step 1:

[0309] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[0310] Step 2:

[0311] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[0312] Step 3:

[0313] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is securely encrypted before being transferred.

[0314] Step 4:

[0315] The server analyzes the received data. Specifically,

[0316] Voice data analysis: Voice data is fed into an emotion engine to assess the user's emotional state (e.g., stress level, changes in tone).

[0317] Activity data analysis: Analyzes the number of steps, heart rate, body temperature, and sleep data collected to evaluate physical health status (e.g., amount of exercise, fluctuations in health indicators).

[0318] Step 5:

[0319] The emotion engine analyzes the voice data in detail to determine the user's emotional state, for example, measuring stress levels based on the tone and speed of the voice.

[0320] Step 6:

[0321] The server generates advice for the user based on the results of the data analysis. Specifically,

[0322] Mental health advice: If you are experiencing high stress, we suggest relaxation techniques and meditation.

[0323] Physical health advice: If lack of exercise is detected, specific exercise and dietary suggestions will be provided.

[0324] Step 7:

[0325] The server sends the generated advice to the device, which then notifies the user. For example, the device displays a message on the smartphone screen saying, "Your stress is increasing. Try meditation."

[0326] Step 8:

[0327] The device receives feedback from the user and sends updated data back to the server, including the status of the proposed action.

[0328] Step 9:

[0329] The server continuously monitors the data and, if an abnormal condition persists for a certain period of time, will refer the user to a specialist or medical institution. For example, if the emotion engine detects high stress levels for three consecutive days, it will notify the user that "we recommend consulting a mental health professional."

[0330] Step 10:

[0331] The server generates and provides a comprehensive report on the user's health status, allowing the user to understand their long-term health status and take appropriate measures.

[0332] Example 2

[0333] 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."

[0334] In modern society, managing the mental and physical health of working people is becoming increasingly important. However, with busy daily schedules, it can be difficult to accurately understand one's own health status and take appropriate measures. Health problems caused by stress and lack of exercise are of particular concern. Conventional methods for addressing this issue can only respond based on limited data, making it difficult to provide comprehensive health management.

[0335] 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.

[0336] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, means for evaluating the emotional state and physical condition, means for detecting ongoing abnormalities, and means for referring the user to a specialist or medical institution when an abnormality is detected. This allows for precise management of the user's daily health condition, providing appropriate advice, and enabling early consultation with a specialist.

[0337] "Activity data" refers to data measuring the user's physical activity in their daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[0338] "Voice data" refers to voice information acquired when a user interacts with an AI assistant, etc., and includes information such as tone, speed, and rhythm.

[0339] "Artificial intelligence means" refers to machine learning models or other AI technologies used to analyze collected data and assess a user's health status.

[0340] "Emotional state" refers to the mental health status of a user as determined from their voice data, including stress levels and emotional fluctuations.

[0341] "Expert" refers to a medical or psychological professional who can assess the user's health status and provide necessary support or measures.

[0342] "Medical Institution" refers to an organization such as a hospital or clinic that provides diagnosis or treatment for a user's health condition.

[0343] "Advice generation means" refers to a function that creates healthcare advice appropriate for the user based on the analysis results obtained by the artificial intelligence means.

[0344] "Emotion engine" refers to technology that analyzes voice data to determine a user's stress level and emotional state.

[0345] "Escalation" refers to a function that encourages users to consult with a specialist or medical institution if their health condition is consistently abnormal.

[0346] "Health management" refers to the process of observing and assessing a user's mental and physical state and providing remedial measures as needed.

[0347] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. The system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[0348] System Configuration

[0349] 1. Data Collection Methods

[0350] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. The user then interacts with the AI ​​assistant and provides voice data, which includes information such as the user's tone and speed.

[0351] 2. Data upload method

[0352] The device periodically sends the collected data to a server. For example, by uploading data every morning and evening, real-time health monitoring is possible. The transmitted data is encrypted and reaches the server via a secure communication channel.

[0353] 3. Data Analysis Methods

[0354] The server is equipped with artificial intelligence means for analyzing the received data. For the voice data, it uses an emotion engine to assess the user's emotional state, and for the activity data, it assesses the user's physical health status. This analysis is performed using machine learning models to identify the emotional state (e.g., stress level, tone changes) from the voice data and to detect fluctuations in health indicators from the activity data.

[0355] 4. Advice Generation Methods

[0356] Based on the analysis results, the server generates appropriate health improvement advice for the user. For mental health, it suggests stress management and relaxation methods, and for physical health, it suggests exercise and diet. For example, if the emotion engine detects that the user is in a high-stress state, it generates mental health advice such as "Try five minutes of meditation."

[0357] 5. Means of providing advice

[0358] The device then notifies the user of the generated advice. Smartphones and wearable devices provide real-time advice, allowing users to take immediate action. Notifications are provided via push notifications or voice assistants.

[0359] 6. Escalation Methods

[0360] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist. This escalation function allows users to take appropriate measures regarding their health condition early.

[0361] Specific examples

[0362] Example 1: Weekday status

[0363] 1. A user greets an AI assistant with "Good morning" in the morning.

[0364] 2. The device sends the collected voice data and the previous day's activity data to the server.

[0365] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[0366] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[0367] 5. The device notifies the user of the advice.

[0368] Example 2: Weekend Situation

[0369] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[0370] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[0371] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[0372] 4. The device notifies the user of the advice.

[0373] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[0374] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0375] Step 1: Data collection

[0376] The device collects data about the user's daily activities.

[0377] Input: Sensor data from smartphones and wearable devices (step count, heart rate, body temperature, sleep time, etc.)

[0378] Output: Collected activity data

[0379] How it works: The smartwatch measures the user's steps and heart rate in real time and sends that data via Bluetooth to a smartphone, which collects additional data using GPS and accelerometers.

[0380] Users interact with the AI ​​assistant and provide voice data.

[0381] Input: User's voice (e.g., speaking to an AI assistant)

[0382] Output: Collected audio data

[0383] How it works: A user speaks into the smartphone microphone, and the audio data is recorded by the AI ​​assistant application. The audio file contains information about tone, speed, and pitch.

[0384] Step 2: Upload data

[0385] The terminal transmits the collected data to the server.

[0386] Input: Collected activity and voice data

[0387] Output: Data sent to the server

[0388] How it works: Your smartphone periodically uploads collected data to a server over Wi-Fi or mobile data networks. This data is encrypted and transmitted using a secure communication protocol.

[0389] Step 3: Data analysis

[0390] The server analyzes the transmitted data.

[0391] Input: Uploaded activity data and audio data

[0392] Output: Analysis results (emotional state, physical health assessment)

[0393] Specific operation: The server inputs the received data into the machine learning model and emotion engine for analysis. The emotion engine analyzes the voice data to evaluate stress levels and emotional changes. Activity data is used to evaluate fluctuations in exercise volume and health indicators. For example, the emotion engine detects signs of stress from changes in voice tone and speed.

[0394] Step 4: Advice Generation

[0395] The server generates advice based on the analysis results.

[0396] Input: Analysis results (emotional state, physical health assessment)

[0397] Output: Healthcare advice

[0398] Specific operation: The server generates appropriate healthcare advice based on the analysis results. For example, if the analysis result is "high stress level," the server generates the advice "try five minutes of meditation." If the result is "lack of exercise," the server generates the advice "we recommend a 20-minute walk."

[0399] Step 5: Providing advice

[0400] The terminal notifies the user of the generated advice.

[0401] Enter: Healthcare Advice

[0402] Output: Advice given to the user

[0403] What it does: The smartphone will display advice to the user through the notification system. For example, a push notification might say, "Your stress is increasing. Try meditation." The AI ​​assistant can also provide a voice alert.

[0404] Step 6: Escalation

[0405] If the server detects any persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[0406] Input: Continuous abnormal condition detection

[0407] Output: Referral notification to specialists and medical institutions

[0408] Specific operation: The server continuously monitors the analysis results, and if an abnormality persists for a certain period of time (for example, high stress for three consecutive days), it generates a notification urging the user to consult a specialist. This notification is sent to the user via the smartphone notification system or email.

[0409] (Application example 2)

[0410] 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."

[0411] In conventional work environments, there has been no system for comprehensively managing and monitoring the mental and physical health of workers, and there has been a problem of workers' stress and fatigue not being properly managed, especially in factories. This can lead to reduced work efficiency and an increased risk of accidents, which can ultimately have a serious impact on workers' health. This invention aims to achieve both improved work efficiency and health management by monitoring workers' health status in real time and providing appropriate advice.

[0412] 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.

[0413] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the worker, and means for automatically prompting the worker to contact a specialist if an abnormality is detected. This allows the worker's health condition to be monitored in real time, and appropriate action to be taken immediately if an abnormality is detected.

[0414] The "means for acquiring activity data" refers to a device or system for collecting information on a worker's physical activities, such as the number of steps taken, heart rate, and working hours.

[0415] The "means for acquiring voice data" refers to a device or system for picking up and collecting conversations with workers and voice instructions.

[0416] "Artificial intelligence means" refers to computational algorithms or programs that analyze collected activity data and voice data and assess the mental and physical health status of workers.

[0417] The "means for generating healthcare advice" is a device or system for proposing health improvement measures and relaxation methods to a worker based on the analysis results using artificial intelligence means.

[0418] A "means for providing advice to a worker" is a device or system for notifying or presenting the generated healthcare advice to a worker.

[0419] "Means for automatically encouraging contact with an expert when an abnormality is detected" refers to a device or system that automatically encourages contact with an expert or medical institution when an abnormality is continuously detected in a worker's health condition.

[0420] The "means for assessing the worker's emotional state" is a device or system for analyzing the voice data and determining the worker's emotional state (e.g., stress level).

[0421] This invention relates to a system for monitoring and managing the mental and physical health of workers in factories in real time. This system collects and analyzes worker activity data and voice data, and provides health care advice based on the results.

[0422] System Overview

[0423] The system consists of the following main components:

[0424] 1. Data collection methods:

[0425] Use a wearable device (e.g., Apple Watch, Fitbit) to collect activity data.

[0426] Use a voice input device and a robotic assistant (e.g., Pepper) to collect voice data.

[0427] 2. Data upload method:

[0428] The collected data is sent to the server at regular intervals and stored in an AWS S3 bucket.

[0429] 3. Data analysis methods:

[0430] We use server-side artificial intelligence tools (e.g., Google Speech-to-Text API, IBM Watson Tone Analyzer, TensorFlow) to analyze activity data and voice data. Voice data is converted to text using Google Speech-to-Text API, and sentiment analysis is performed using IBM Watson Tone Analyzer. Activity data is analyzed using machine learning models using TensorFlow.

[0431] 4. Advice Generation Methods:

[0432] Based on the analysis results, specific health improvement advice (e.g., stretching and relaxation methods) is generated for the worker.

[0433] 5. Advice delivery methods:

[0434] Using Firebase, notifications are sent in real time directly from workers' smartphones or robot assistants.

[0435] 6. Escalation Methods:

[0436] If a persistent abnormality is detected, a notification will be automatically sent based on the abnormal data, prompting the user to contact a specialist or medical institution.

[0437] Example

[0438] On weekdays, worker A working in the factory uses the system in the following way.

[0439] 1. Data Collection:

[0440] Worker A wears a wearable device, which collects activity data such as heart rate and number of steps in real time.

[0441] The robot assistant and worker A have a short conversation, and the audio data is recorded.

[0442] 2. Data upload:

[0443] Collected activity and audio data is uploaded to an AWS S3 bucket every hour.

[0444] 3. Data Analysis:

[0445] The server converts the audio data into text using the Google Speech-to-Text API and performs sentiment analysis using IBM Watson Tone Analyzer.

[0446] Activity data is analyzed using TensorFlow to assess physical health status.

[0447] 4. Advice Generation:

[0448] If the server analyzes that the stress level is high, it generates advice to suggest relaxation methods (e.g., deep breathing).

[0449] 5. Providing advice:

[0450] The advice generated by the server is sent to worker A's smartphone and robot assistant via Firebase.

[0451] A message appears on Worker A's smartphone saying, "Your stress is increasing. Try taking some deep breaths."

[0452] Prompt Sentence Examples

[0453] "Analyze my stress level based on this morning's heart rate data and yesterday's work hours data."

[0454] "Please evaluate the emotional state of worker C from his / her voice data and generate stress advice."

[0455] A system configured in this way allows for real-time management of workers' health conditions, and if any abnormalities are detected, appropriate action can be taken immediately.

[0456] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0457] Step 1:

[0458] The terminal collects the worker's activity data (e.g., number of steps, heart rate, working hours) through a wearable device. The input is the activity information obtained from the wearable device, and the output is the collected activity data. Specifically, the terminal updates the data using Bluetooth communication and records it in its internal storage.

[0459] Step 2:

[0460] The terminal collects voice data through dialogue with the robot assistant. The input is the worker's voice, and the output is the captured voice data. The robot assistant periodically asks the worker questions and captures their answers with a voice sensor.

[0461] Step 3:

[0462] The device uploads the collected activity data and voice data to the server at regular intervals. The input is the data stored on the device, and the output is the data stored in the server's database. Specifically, the device uses an internet connection to send the data to an AWS S3 bucket.

[0463] Step 4:

[0464] The server converts the uploaded audio data into text data using the Google Speech-to-Text API. The input is audio data and the output is text data. The server makes an API call to convert the audio file into text format.

[0465] Step 5:

[0466] The server performs sentiment analysis on the text data using IBM Watson Tone Analyzer. The input is text data, and the output is an evaluation of the emotional state (e.g., stress level). The server sends the text data to the sentiment engine and receives the analysis results.

[0467] Step 6:

[0468] The server inputs the activity data into a machine learning model using TensorFlow to evaluate the physical health status. The input is the activity data, and the output is the physical status evaluation result. The server feeds the data to the model and records the output.

[0469] Step 7:

[0470] The server generates healthcare advice for the worker based on the analysis results. The input is the emotional state and physical health assessment results, and the output is a specific advice message. The server creates advice using a predefined template.

[0471] Step 8:

[0472] The server generates advice and notifies the worker's device using Firebase. The input is the advice message, and the output is the advice displayed on the worker's smartphone or robot assistant. The server sends messages in real time via the notification system.

[0473] Step 9:

[0474] If the server detects a persistent anomaly, it automatically sends a notification urging the user to contact an expert. The input is the abnormal data, and the output is a notification recommending consultation with an expert. The server runs an anomaly detection algorithm and sends an escalation notification if the anomaly persists.

[0475] The above are the specific processing steps of the system for carrying out the invention.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 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.

[0482] 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).

[0483] 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.

[0484] 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.

[0485] 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).

[0486] 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. 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] In the smart glasses 214, 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.

[0491] 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."

[0492] This invention relates to an AI healthcare system that synchronizes the mental and physical health of workers. The system collects and analyzes the user's daily activity data and voice data to evaluate their health status. Based on the evaluation results, the system provides professional advice and, if necessary, refers the user to a specialist or medical institution.

[0493] System Configuration

[0494] 1. Data Collection Methods

[0495] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0496] Users can verbally greet and comment to the AI ​​assistant, providing voice data.

[0497] 2. Data upload method

[0498] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[0499] 3. Data Analysis Methods

[0500] The server analyzes the received data using artificial intelligence means, providing an emotional state assessment for the voice data and a physical health assessment based on the activity data.

[0501] 4. Advice Generation Methods

[0502] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[0503] 5. Means of providing advice

[0504] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the wearable device.

[0505] 6. Escalation Methods

[0506] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, such as if their mental health condition has been deteriorating for a certain period of time or if their physical data shows abnormal values.

[0507] Program processing

[0508] 1. Data Collection

[0509] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[0510] 2. Data upload

[0511] The device transmits the collected data to a server at set times, including activity data as well as information about the tone and speed of the voice.

[0512] 3. Data Analysis

[0513] The server inputs the transmitted data into a machine learning model to analyze the user's emotional and physical state, determining stress levels from voice data and exercise volume and health status from activity data.

[0514] 4. Advice Generation

[0515] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[0516] 5. Providing advice

[0517] The device then notifies the user of the advice it receives from the server. For example, the device displays a message on the smartphone screen saying, "Your stress levels are rising. Try meditating."

[0518] 6. Escalation

[0519] If the server detects persistent abnormalities, it will refer the user to an appropriate specialist or medical institution, allowing the user to receive professional support early on.

[0520] Specific examples

[0521] Example 1: Weekday status

[0522] 1. A user greets an AI assistant with "Good morning" in the morning.

[0523] 2. The device sends the collected voice data and the previous day's activity data to the server.

[0524] 3. The server analyzes the data and detects an increase in stress levels from the voice data.

[0525] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[0526] 5. The device notifies the user of the advice.

[0527] Example 2: Weekend Situation

[0528] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[0529] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[0530] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[0531] 4. The device notifies the user of the advice.

[0532] The above is an embodiment of the system of the present invention, which allows users to comprehensively manage their mental and physical health in their daily lives.

[0533] The processing flow will be explained below.

[0534] Step 1:

[0535] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[0536] Step 2:

[0537] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[0538] Step 3:

[0539] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is encrypted and transmitted securely.

[0540] Step 4:

[0541] The server analyzes the received data. Specifically,

[0542] Voice data analysis: Voice data is fed into machine learning models to assess the user's emotional state (e.g., stress level, changes in tone).

[0543] Activity data analysis: Analyzes step count, heart rate, body temperature, and sleep data to evaluate physical health status (e.g., exercise volume, fluctuations in health indicators).

[0544] Step 5:

[0545] The server generates advice for the user based on the results of the data analysis. Specifically,

[0546] Mental health advice: Generates relaxation and meditation suggestions when stress levels are high.

[0547] Physical health advice: Generates specific exercise and dietary suggestions if physical inactivity is detected.

[0548] Step 6:

[0549] The server sends the generated advice to the device, which then notifies the user. For example, the smartphone might say, "Your step count today is low, so try walking one station on your way home."

[0550] Step 7:

[0551] The device enters a loop where it receives feedback from the user and again sends data to the server, including whether or not the user actually tried the suggested action.

[0552] Step 8:

[0553] The server continuously monitors the data, and if an abnormality persists for a certain period of time, it will take action to refer the user to a specialist or medical institution, allowing the user to receive appropriate assistance early on.

[0554] Example 1

[0555] 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."

[0556] In today's world, comprehensive management of workers' mental and physical health is an important issue. However, many existing systems focus on one type of health condition, and few provide comprehensive support for both mental and physical health. Furthermore, there is a lack of appropriate ways to deal with ongoing abnormalities, making it difficult to provide early, specialized support. Therefore, there is a need for the development of a system that can achieve comprehensive health management for users.

[0557] 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.

[0558] In this invention, the server includes a means for acquiring activity data, a means for acquiring voice data, a means for transmitting the acquired activity data and voice data to the server at a predetermined time, a means for analyzing the transmitted data using artificial intelligence, a means for generating mental and physical health care advice based on the analysis results, and a means for notifying the user of the advice. This enables a comprehensive evaluation of the user's daily health condition and the provision of appropriate advice in real time. Furthermore, if abnormalities are detected over a long period of time, the server can refer the user to a specialist or medical institution, allowing the user to receive professional support early.

[0559] "Activity data" refers to data related to the user's physical activity in daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[0560] "Voice data" refers to data that records the voice spoken by a user, including the content of the conversation, tone, speed, etc.

[0561] "Server" refers to a computer system that receives data, analyzes it, and generates results, and is capable of communicating with terminals via a network.

[0562] "Artificial intelligence" refers to algorithms and systems that use techniques such as machine learning and deep learning to analyze data and discover patterns.

[0563] "Analysis results" are the results of analysis of data processed by artificial intelligence, based on which health and emotional state are assessed.

[0564] "Healthcare advice" refers to specific suggestions and guidelines for action to improve the user's health based on the analysis results.

[0565] A "persistent anomaly" refers to a situation in which an abnormal pattern is detected continuously over a period of time in a user's activity data or voice data.

[0566] "Referral to specialists or medical institutions" refers to the act of informing or recommending appropriate specialists or medical facilities to users as needed.

[0567] "Emotional state" refers to a psychological state assessed based on a user's voice data, and includes stress, joy, sadness, etc.

[0568] "Notification" refers to the means of communication, usually via a device, to convey generated advice or warnings to the user.

[0569] This invention relates to an AI healthcare system for comprehensively managing the mental and physical health of workers. This system collects and analyzes the user's daily activity data and voice data, evaluates their health status, and provides appropriate advice. Furthermore, if persistent abnormalities are detected, the system will refer the user to a specialist or medical institution. A detailed embodiment of this system is shown below.

[0570] Data collection methods

[0571] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. When the user verbally greets or comments to the AI ​​assistant, this voice data is also recorded. Specific hardware used includes a smartphone (e.g., Android, iPhone) or a wearable device (e.g., Fitbit, Apple Watch).

[0572] Example: A user says "Good morning" to an AI assistant in the morning, which collects voice data, while the wearable device simultaneously transmits the number of steps and heart rate recorded the previous day to a smartphone.

[0573] Data upload method

[0574] The device sends the collected data to the server at a set time. It can be set to upload data every morning at 9:00 and every evening at 9:00. The data sent includes activity data, voice tones, speed, etc.

[0575] Example: Every night at 9pm, the device automatically uploads data to the server, ensuring that fresh data is always stored on the server.

[0576] Data Analysis Methods

[0577] The server receives the data sent from the device and inputs it into machine learning models (e.g., TensorFlow, PyTorch). Voice data is used to assess stress levels using emotion analysis algorithms, and activity data is used to determine the user's physical health (e.g., amount of exercise, quality of sleep).

[0578] Example: A server analysis script uses a TensorFlow model to analyze audio data and classify the user's emotional state into "positive," "negative," or "neutral," thereby determining how stressed the user is.

[0579] Advice Generation Method

[0580] Based on the analysis results, the server generates appropriate health improvement advice for the user, suggesting relaxation methods if stress levels are high, and recommending specific exercises if exercise is lacking.

[0581] Example: A message such as "Your stress levels are rising. Try meditating for five minutes" is generated. If you are not getting enough exercise, specific advice such as "Set your goal for today to be a 30-minute walk" is provided.

[0582] Advice delivery methods

[0583] The device notifies the user of the generated advice via push notifications on smartphones or vibrations on wearable devices.

[0584] Example: At 9:00 a.m., your smartphone displays a push notification with the advice, "Good morning. Let's stay healthy today." Your wearable device also vibrates gently to notify you of this notification.

[0585] Escalation methods

[0586] The server continuously monitors the user's data and will refer the user to a specialist or medical institution if an abnormality is detected, for example, if stress levels remain high for a certain period of time or if physical data shows abnormal values.

[0587] Example: If the server detects a high stress level for one consecutive week, it generates a message saying, "You appear to be experiencing persistent stress. Perhaps you should seek professional counseling?" and the device notifies the user of this message.

[0588] In this way, the present invention can comprehensively evaluate the user's daily health condition and provide appropriate advice in real time. It also allows the user to receive professional support early on, making it possible to maintain and improve mental and physical health.

[0589] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0590] Step 1: Data collection

[0591] The device will collect activity data (e.g., number of steps, heart rate, body temperature, and sleep time) using a smartphone or wearable device as the user goes about their daily life, and will also record voice data when the user speaks to the AI ​​assistant or expresses their thoughts.

[0592] Input: User activity and voice data.

[0593] Data processing: Activity data is automatically recorded by a pedometer and heart rate sensor, and audio data is collected by a microphone.

[0594] Output: Activity data and voice data stored in the smartphone.

[0595] How it works: When a user says "Good morning" to the AI ​​assistant, the voice is recorded by an application on the smartphone, and the wearable device simultaneously measures daily activity data such as steps taken and heart rate and sends the data to the smartphone.

[0596] Step 2: Upload data

[0597] The device periodically sends the collected data to the server, for example, uploading all data at 9:00 every morning and 9:00 every evening.

[0598] Input: Activity and voice data stored on the smartphone.

[0599] Data processing: The data is compressed, encrypted and sent to the server.

[0600] Output: Compressed data file uploaded to the server.

[0601] How it works: Every night at 9 p.m., the smartphone uploads the accumulated data to a cloud server via a dedicated application. At this time, the data is compressed and encrypted to ensure security.

[0602] Step 3: Data analysis

[0603] The server then analyzes the received data using artificial intelligence (AI) and machine learning models (e.g., TensorFlow, PyTorch). The voice data is used to assess emotional state, and the activity data is used to analyze physical health.

[0604] Input: The compressed data file uploaded to the server.

[0605] Data processing: Data decompression and preprocessing (e.g., noise removal, data cleaning) are performed.

[0606] Output: Emotional state and physical health analysis.

[0607] How it works: A Python script running on the server unpacks the uploaded data, performs preprocessing, and then uses machine learning models to assess emotional state from voice data and physical health from activity data. For example, a "high stress level" may be determined based on voice analysis.

[0608] Step 4: Advice Generation

[0609] The server generates health advice for the user based on the analysis results, recommending appropriate behaviors for the user in terms of both mental and physical health.

[0610] Input: Emotional state and physical health analysis results.

[0611] Data processing: Advice content is customized based on the analysis results.

[0612] Output: Customized advice to provide to the user.

[0613] Specific operation: For example, the server generates advice such as "Try 5 minutes of meditation" for a user who is analyzed as having a "high stress level."

[0614] Step 5: Providing advice

[0615] The device notifies the user of the generated advice using methods such as push notifications on smartphones or vibrations on wearable devices.

[0616] Input: Customized advice sent by the server.

[0617] Data processing: Display advice in a format that is easy for users to understand.

[0618] Output: Advice given to the user.

[0619] Specific operation: At 9 a.m., the smartphone displays a push notification saying, "Your stress level is high today. Try a 5-minute meditation," and the wearable device vibrates gently to notify the user.

[0620] Step 6: Escalation

[0621] The server continuously monitors the user's data and, if an abnormality is detected, will refer the user to a specialist or medical institution. If an abnormality is detected, the server will notify the user and provide information on the appropriate specialist.

[0622] Input: Continuously monitored user data.

[0623] Data processing: detecting outliers and selecting appropriate referrals from a list of specialists and medical institutions.

[0624] Output: Notification that an abnormality was detected and information for specialists or medical institutions.

[0625] Specific operation: The server detects a high stress level for one consecutive week, generates a message saying, "It appears that stress is continuing. Perhaps you should seek professional counseling?" and notifies the user of this message on the device.

[0626] (Application example 1)

[0627] 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."

[0628] In modern factories, managing the mental and physical health of workers is important. However, traditional methods have the drawback of being difficult to monitor in real time or respond quickly to abnormalities. It is also difficult for workers to accurately understand their own health status and take appropriate measures. This can lead to the accumulation of excessive stress and fatigue, which can lead to reduced productivity and an increased risk of workplace accidents.

[0629] 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.

[0630] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, and means for detecting an abnormal condition and referring the user to a specialist or medical institution when the user's physical or mental condition falls below a certain standard. This makes it possible to monitor the health condition of workers in real time and quickly respond to any abnormalities that occur.

[0631] "Activity Data" refers to data that quantifies a user's daily physical movements and activities, such as the number of steps taken, heart rate, body temperature, and sleep duration.

[0632] "Voice Data" refers to the audio information provided when a user converses with an AI assistant, including the tone, speed, and content of the speech.

[0633] "Artificial Intelligence Means" refers to the machine learning algorithms and artificial intelligence models used to analyze collected activity data and audio data.

[0634] "Mental and physical healthcare advice" refers to specific suggestions and instructions to improve a user's psychological and physical health based on the analysis results.

[0635] "User" refers to an individual who uses the system, including laborers and factory workers.

[0636] "Abnormal condition" refers to a state in which a user's physical or mental health falls below the standards set by the system.

[0637] "Expert" refers to a medical professional or counselor who can provide appropriate responses and advice to the user's abnormal condition.

[0638] "Medical Institution" refers to a hospital or clinic that provides specialized medical care or treatment required by the User.

[0639] "Real-time" refers to processing or response occurring almost immediately or with very little delay.

[0640] The higher expression of "physical" is defined as "physical." "Physical health" refers to "physical well-being."

[0641] The higher term for "mental" is defined as "psychological." "Mental health" refers to "psychological health."

[0642] The present invention is a system for monitoring the mental and physical health of workers in real time and providing appropriate advice. This system is implemented with the following configuration and procedures.

[0643] System Configuration

[0644] 1. Data Collection Methods

[0645] The device uses devices such as smartwatches and smartphones to collect data on a user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0646] Users provide voice data by verbally expressing greetings and impressions to the AI ​​assistant.

[0647] 2. Data upload method

[0648] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[0649] 3. Data Analysis Methods

[0650] The server analyzes the received data using artificial intelligence means (e.g., machine learning models), assessing emotional state based on the voice data and physical health status based on the activity data.

[0651] 4. Advice Generation Methods

[0652] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[0653] 5. Means of providing advice

[0654] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the smartwatch.

[0655] 6. Escalation Methods

[0656] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, for example, if their mental health condition has deteriorated over a certain period of time or if their physical data shows abnormal values.

[0657] Example of operation

[0658] Example 1: Weekday status

[0659] The user greets the AI ​​assistant with "Good morning" in the morning.

[0660] The device sends the collected voice data and the previous day's activity data to the server.

[0661] The server analyzes the data and detects rising stress levels from the voice data.

[0662] The server generates advice such as "Your stress is increasing. Try 5 minutes of meditation."

[0663] The device will notify the user of the advice.

[0664] Example 2: Weekend Situation

[0665] The user sends the heart rate and sleep time measured by the smartwatch to the server.

[0666] The server analyzes the data and detects whether the user is getting enough sleep.

[0667] The server generates advice such as, "We recommend keeping things light today and getting plenty of rest."

[0668] The device will notify the user of the advice.

[0669] Prompt Sentence Examples

[0670] "Analyze the following data and generate health advice for the user: Data: {'steps': 4500, 'heart_rate': 95, 'temperature': 37.5, 'sleep_hours': 5.5, 'voice_tone': 'stress'}"

[0671] The above is a specific embodiment of the system of the present invention, which allows workers to comprehensively manage their mental and physical health in their daily lives.

[0672] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0673] Step 1:

[0674] Data collection:

[0675] The device uses a smartwatch or smartphone to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0676] Users can converse with the AI ​​assistant via voice and provide voice data.

[0677] Input: User activity data, voice data

[0678] Output: A set of collected activity and audio data

[0679] What it does: For example, a smartwatch counts steps, monitors heart rate, and records audio when you say "good morning."

[0680] Step 2:

[0681] Data Upload:

[0682] The terminal transmits the collected activity data and voice data to the server at regular intervals (for example, every morning).

[0683] Input: Collected activity and audio data

[0684] Output: Data sent to the server

[0685] Specific operation: The device uses Wi-Fi or mobile data connection to upload activity data (e.g., 4,500 steps) and audio data (e.g., audio tone is "stress") to a cloud server.

[0686] Step 3:

[0687] Data Analysis:

[0688] The server inputs the received data into artificial intelligence means (e.g., machine learning models) to analyze the user's mental and physical state.

[0689] Input: Activity and voice data sent to the server

[0690] Output: Mental and physical health assessment results

[0691] Specific behavior: For example, a machine learning model analyzes heart rate and voice tone to determine a user's stress level as "high," or analyzes steps taken and sleep time to assess physical health as "poor."

[0692] Step 4:

[0693] Advice Generation:

[0694] Based on the analysis results, the server generates health improvement advice for the user, suggesting relaxation methods for mental health and exercise and rest for physical health.

[0695] Input: Mental and physical health assessment results

[0696] Output: Generated healthcare advice

[0697] Specific operation: For example, the server generates advice such as "Please meditate for five minutes" based on the evaluation result that "your stress level is high." Also, based on the evaluation result that your physical health is "poor," it generates advice such as "Please reduce your schedule for today and get plenty of rest."

[0698] Step 5:

[0699] Advice provided:

[0700] The terminal notifies the user of the advice received from the server.

[0701] Input: Generated healthcare advice

[0702] Output: User advice notice

[0703] Specific actions: For example, the smartphone screen will display a message saying, "Your stress is increasing. Try a 5-minute meditation." The smartwatch will also send a vibration notification.

[0704] Step 6:

[0705] escalation:

[0706] If the server detects persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[0707] Input: Continuous abnormal data

[0708] Output: Referral information for specialists and medical institutions

[0709] Specific operation: For example, if the server detects that a user's stress level has remained high for more than a week, it will notify the user by listing appropriate medical institutions, such as "Your stress level has remained high. We recommend that you consult the medical institution listed below."

[0710] These are the specific processing steps of the system, which enables comprehensive management of the user's mental and physical health in real time.

[0711] 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.

[0712] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. This system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[0713] System Configuration

[0714] 1. Data Collection Methods

[0715] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0716] Users interact with the AI ​​assistant and provide voice data, which includes information such as the user's tone and speed.

[0717] 2. Data upload method

[0718] The device sends the collected data to a server at regular intervals. For example, by uploading data every morning and evening, it is possible to monitor health conditions in real time.

[0719] 3. Data Analysis Methods

[0720] The server is equipped with artificial intelligence means for analyzing the received data, using an emotion engine to assess the user's emotional state from the voice data, and physical health status from the activity data.

[0721] The emotion engine analyzes voice data to determine the user's stress level and emotional state. The engine captures changes in the user's emotions through detailed analysis of the tone, speed, rhythm, etc. of the voice.

[0722] 4. Advice Generation Methods

[0723] Based on the analysis results, the server generates appropriate health improvement advice for the user, such as stress management and relaxation methods for mental health, and exercise and diet suggestions for physical health.

[0724] For example, if the emotion engine detects a user's high stress state, it will generate mental health advice such as "Try five minutes of meditation."

[0725] 5. Means of providing advice

[0726] The device then notifies the user of the generated advice. By providing real-time advice via a smartphone or wearable device, the user can take immediate action.

[0727] 6. Escalation Methods

[0728] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist.

[0729] This escalation feature allows users to take appropriate action regarding their health condition early on.

[0730] Program processing

[0731] 1. Data Collection

[0732] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[0733] 2. Data upload

[0734] The device transmits the collected data to a server at scheduled times, including activity data as well as information about the tone and speed of the voice.

[0735] 3. Data Analysis

[0736] The server inputs the transmitted data into a machine learning model and emotion engine to analyze the user's emotional and physical state. The server evaluates the user's emotional state (e.g., stress level, tone changes) from the voice data and their physical health status (e.g., exercise volume, fluctuations in health indicators) from the activity data.

[0737] 4. Advice Generation

[0738] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[0739] 5. Providing advice

[0740] The device then notifies the user of the advice it receives from the server. For example, a message like "Your stress levels are rising. Try meditation" will appear on the smartphone screen.

[0741] 6. Escalation

[0742] If a persistent abnormality is detected, the server will refer the user to an appropriate specialist or medical institution, ensuring that the user receives appropriate assistance early on.

[0743] Specific examples

[0744] Example 1: Weekday status

[0745] 1. A user greets an AI assistant with "Good morning" in the morning.

[0746] 2. The device sends the collected voice data and the previous day's activity data to the server.

[0747] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[0748] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[0749] 5. The device notifies the user of the advice.

[0750] Example 2: Weekend Situation

[0751] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[0752] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[0753] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[0754] 4. The device notifies the user of the advice.

[0755] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[0756] The processing flow will be explained below.

[0757] Step 1:

[0758] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[0759] Step 2:

[0760] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[0761] Step 3:

[0762] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is securely encrypted before being transferred.

[0763] Step 4:

[0764] The server analyzes the received data. Specifically,

[0765] Voice data analysis: Voice data is fed into an emotion engine to assess the user's emotional state (e.g., stress level, changes in tone).

[0766] Activity data analysis: Analyzes the number of steps, heart rate, body temperature, and sleep data collected to evaluate physical health status (e.g., amount of exercise, fluctuations in health indicators).

[0767] Step 5:

[0768] The emotion engine analyzes the voice data in detail to determine the user's emotional state, for example, measuring stress levels based on the tone and speed of the voice.

[0769] Step 6:

[0770] The server generates advice for the user based on the results of the data analysis. Specifically,

[0771] Mental health advice: If you are experiencing high stress, we suggest relaxation techniques and meditation.

[0772] Physical health advice: If lack of exercise is detected, specific exercise and dietary suggestions will be provided.

[0773] Step 7:

[0774] The server sends the generated advice to the device, which then notifies the user. For example, the device displays a message on the smartphone screen saying, "Your stress is increasing. Try meditation."

[0775] Step 8:

[0776] The device receives feedback from the user and sends updated data back to the server, including the status of the proposed action.

[0777] Step 9:

[0778] The server continuously monitors the data and, if an abnormal condition persists for a certain period of time, will refer the user to a specialist or medical institution. For example, if the emotion engine detects high stress levels for three consecutive days, it will notify the user that "we recommend consulting a mental health professional."

[0779] Step 10:

[0780] The server generates and provides a comprehensive report on the user's health status, allowing the user to understand their long-term health status and take appropriate measures.

[0781] Example 2

[0782] 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."

[0783] In modern society, managing the mental and physical health of working people is becoming increasingly important. However, with busy daily schedules, it can be difficult to accurately understand one's own health status and take appropriate measures. Health problems caused by stress and lack of exercise are of particular concern. Conventional methods for addressing this issue can only respond based on limited data, making it difficult to provide comprehensive health management.

[0784] 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.

[0785] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, means for evaluating the emotional state and physical condition, means for detecting ongoing abnormalities, and means for referring the user to a specialist or medical institution when an abnormality is detected. This allows for precise management of the user's daily health condition, providing appropriate advice, and enabling early consultation with a specialist.

[0786] "Activity data" refers to data measuring the user's physical activity in their daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[0787] "Voice data" refers to voice information acquired when a user interacts with an AI assistant, etc., and includes information such as tone, speed, and rhythm.

[0788] "Artificial intelligence means" refers to machine learning models or other AI technologies used to analyze collected data and assess a user's health status.

[0789] "Emotional state" refers to the mental health status of a user as determined from their voice data, including stress levels and emotional fluctuations.

[0790] "Expert" refers to a medical or psychological professional who can assess the user's health status and provide necessary support or measures.

[0791] "Medical Institution" refers to an organization such as a hospital or clinic that provides diagnosis or treatment for a user's health condition.

[0792] "Advice generation means" refers to a function that creates healthcare advice appropriate for the user based on the analysis results obtained by the artificial intelligence means.

[0793] "Emotion engine" refers to technology that analyzes voice data to determine a user's stress level and emotional state.

[0794] "Escalation" refers to a function that encourages users to consult with a specialist or medical institution if their health condition is consistently abnormal.

[0795] "Health management" refers to the process of observing and assessing a user's mental and physical state and providing remedial measures as needed.

[0796] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. The system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[0797] System Configuration

[0798] 1. Data Collection Methods

[0799] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. The user then interacts with the AI ​​assistant and provides voice data, which includes information such as the user's tone and speed.

[0800] 2. Data upload method

[0801] The device periodically sends the collected data to a server. For example, by uploading data every morning and evening, real-time health monitoring is possible. The transmitted data is encrypted and reaches the server via a secure communication channel.

[0802] 3. Data Analysis Methods

[0803] The server is equipped with artificial intelligence means for analyzing the received data. For the voice data, it uses an emotion engine to assess the user's emotional state, and for the activity data, it assesses the user's physical health status. This analysis is performed using machine learning models to identify the emotional state (e.g., stress level, tone changes) from the voice data and to detect fluctuations in health indicators from the activity data.

[0804] 4. Advice Generation Methods

[0805] Based on the analysis results, the server generates appropriate health improvement advice for the user. For mental health, it suggests stress management and relaxation methods, and for physical health, it suggests exercise and diet. For example, if the emotion engine detects that the user is in a high-stress state, it generates mental health advice such as "Try five minutes of meditation."

[0806] 5. Means of providing advice

[0807] The device then notifies the user of the generated advice. Smartphones and wearable devices provide real-time advice, allowing users to take immediate action. Notifications are provided via push notifications or voice assistants.

[0808] 6. Escalation Methods

[0809] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist. This escalation function allows users to take appropriate measures regarding their health condition early.

[0810] Specific examples

[0811] Example 1: Weekday status

[0812] 1. A user greets an AI assistant with "Good morning" in the morning.

[0813] 2. The device sends the collected voice data and the previous day's activity data to the server.

[0814] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[0815] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[0816] 5. The device notifies the user of the advice.

[0817] Example 2: Weekend Situation

[0818] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[0819] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[0820] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[0821] 4. The device notifies the user of the advice.

[0822] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[0823] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0824] Step 1: Data collection

[0825] The device collects data about the user's daily activities.

[0826] Input: Sensor data from smartphones and wearable devices (step count, heart rate, body temperature, sleep time, etc.)

[0827] Output: Collected activity data

[0828] How it works: The smartwatch measures the user's steps and heart rate in real time and sends that data via Bluetooth to a smartphone, which collects additional data using GPS and accelerometers.

[0829] Users interact with the AI ​​assistant and provide voice data.

[0830] Input: User's voice (e.g., speaking to an AI assistant)

[0831] Output: Collected audio data

[0832] How it works: A user speaks into the smartphone microphone, and the audio data is recorded by the AI ​​assistant application. The audio file contains information about tone, speed, and pitch.

[0833] Step 2: Upload data

[0834] The terminal transmits the collected data to the server.

[0835] Input: Collected activity and voice data

[0836] Output: Data sent to the server

[0837] How it works: Your smartphone periodically uploads collected data to a server over Wi-Fi or mobile data networks. This data is encrypted and transmitted using a secure communication protocol.

[0838] Step 3: Data analysis

[0839] The server analyzes the transmitted data.

[0840] Input: Uploaded activity data and audio data

[0841] Output: Analysis results (emotional state, physical health assessment)

[0842] Specific operation: The server inputs the received data into the machine learning model and emotion engine for analysis. The emotion engine analyzes the voice data to evaluate stress levels and emotional changes. Activity data is used to evaluate fluctuations in exercise volume and health indicators. For example, the emotion engine detects signs of stress from changes in voice tone and speed.

[0843] Step 4: Advice Generation

[0844] The server generates advice based on the analysis results.

[0845] Input: Analysis results (emotional state, physical health assessment)

[0846] Output: Healthcare advice

[0847] Specific operation: The server generates appropriate healthcare advice based on the analysis results. For example, if the analysis result is "high stress level," the server generates the advice "try five minutes of meditation." If the result is "lack of exercise," the server generates the advice "we recommend a 20-minute walk."

[0848] Step 5: Providing advice

[0849] The terminal notifies the user of the generated advice.

[0850] Enter: Healthcare Advice

[0851] Output: Advice given to the user

[0852] What it does: The smartphone will display advice to the user through the notification system. For example, a push notification might say, "Your stress is increasing. Try meditation." The AI ​​assistant can also provide a voice alert.

[0853] Step 6: Escalation

[0854] If the server detects any persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[0855] Input: Continuous abnormal condition detection

[0856] Output: Referral notification to specialists and medical institutions

[0857] Specific operation: The server continuously monitors the analysis results, and if an abnormality persists for a certain period of time (for example, high stress for three consecutive days), it generates a notification urging the user to consult a specialist. This notification is sent to the user via the smartphone notification system or email.

[0858] (Application example 2)

[0859] 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."

[0860] In conventional work environments, there has been no system for comprehensively managing and monitoring the mental and physical health of workers, and there has been a problem of workers' stress and fatigue not being properly managed, especially in factories. This can lead to reduced work efficiency and an increased risk of accidents, which can ultimately have a serious impact on workers' health. This invention aims to achieve both improved work efficiency and health management by monitoring workers' health status in real time and providing appropriate advice.

[0861] 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.

[0862] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the worker, and means for automatically prompting the worker to contact a specialist if an abnormality is detected. This allows the worker's health condition to be monitored in real time, and appropriate action to be taken immediately if an abnormality is detected.

[0863] The "means for acquiring activity data" refers to a device or system for collecting information on a worker's physical activities, such as the number of steps taken, heart rate, and working hours.

[0864] The "means for acquiring voice data" refers to a device or system for picking up and collecting conversations with workers and voice instructions.

[0865] "Artificial intelligence means" refers to computational algorithms or programs that analyze collected activity data and voice data and assess the mental and physical health status of workers.

[0866] The "means for generating healthcare advice" is a device or system for proposing health improvement measures and relaxation methods to a worker based on the analysis results using artificial intelligence means.

[0867] A "means for providing advice to a worker" is a device or system for notifying or presenting the generated healthcare advice to a worker.

[0868] "Means for automatically encouraging contact with an expert when an abnormality is detected" refers to a device or system that automatically encourages contact with an expert or medical institution when an abnormality is continuously detected in a worker's health condition.

[0869] The "means for assessing the worker's emotional state" is a device or system for analyzing the voice data and determining the worker's emotional state (e.g., stress level).

[0870] This invention relates to a system for monitoring and managing the mental and physical health of workers in factories in real time. This system collects and analyzes worker activity data and voice data, and provides health care advice based on the results.

[0871] System Overview

[0872] The system consists of the following main components:

[0873] 1. Data collection methods:

[0874] Use a wearable device (e.g., Apple Watch, Fitbit) to collect activity data.

[0875] Use a voice input device and a robotic assistant (e.g., Pepper) to collect voice data.

[0876] 2. Data upload method:

[0877] The collected data is sent to the server at regular intervals and stored in an AWS S3 bucket.

[0878] 3. Data analysis methods:

[0879] We use server-side artificial intelligence tools (e.g., Google Speech-to-Text API, IBM Watson Tone Analyzer, TensorFlow) to analyze activity data and voice data. Voice data is converted to text using Google Speech-to-Text API, and sentiment analysis is performed using IBM Watson Tone Analyzer. Activity data is analyzed using machine learning models using TensorFlow.

[0880] 4. Advice Generation Methods:

[0881] Based on the analysis results, specific health improvement advice (e.g., stretching and relaxation methods) is generated for the worker.

[0882] 5. Advice delivery methods:

[0883] Using Firebase, notifications are sent in real time directly from workers' smartphones or robot assistants.

[0884] 6. Escalation Methods:

[0885] If a persistent abnormality is detected, a notification will be automatically sent based on the abnormal data, prompting the user to contact a specialist or medical institution.

[0886] Example

[0887] On weekdays, worker A working in the factory uses the system in the following way.

[0888] 1. Data Collection:

[0889] Worker A wears a wearable device, which collects activity data such as heart rate and number of steps in real time.

[0890] The robot assistant and worker A have a short conversation, and the audio data is recorded.

[0891] 2. Data upload:

[0892] Collected activity and audio data is uploaded to an AWS S3 bucket every hour.

[0893] 3. Data Analysis:

[0894] The server converts the audio data into text using the Google Speech-to-Text API and performs sentiment analysis using IBM Watson Tone Analyzer.

[0895] Activity data is analyzed using TensorFlow to assess physical health status.

[0896] 4. Advice Generation:

[0897] If the server analyzes that the stress level is high, it generates advice to suggest relaxation methods (e.g., deep breathing).

[0898] 5. Providing advice:

[0899] The advice generated by the server is sent to worker A's smartphone and robot assistant via Firebase.

[0900] A message appears on Worker A's smartphone saying, "Your stress is increasing. Try taking some deep breaths."

[0901] Prompt Sentence Examples

[0902] "Analyze my stress level based on this morning's heart rate data and yesterday's work hours data."

[0903] "Please evaluate the emotional state of worker C from his / her voice data and generate stress advice."

[0904] A system configured in this way allows for real-time management of workers' health conditions, and if any abnormalities are detected, appropriate action can be taken immediately.

[0905] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0906] Step 1:

[0907] The terminal collects the worker's activity data (e.g., number of steps, heart rate, working hours) through a wearable device. The input is the activity information obtained from the wearable device, and the output is the collected activity data. Specifically, the terminal updates the data using Bluetooth communication and records it in its internal storage.

[0908] Step 2:

[0909] The terminal collects voice data through dialogue with the robot assistant. The input is the worker's voice, and the output is the captured voice data. The robot assistant periodically asks the worker questions and captures their answers with a voice sensor.

[0910] Step 3:

[0911] The device uploads the collected activity data and voice data to the server at regular intervals. The input is the data stored on the device, and the output is the data stored in the server's database. Specifically, the device uses an internet connection to send the data to an AWS S3 bucket.

[0912] Step 4:

[0913] The server converts the uploaded audio data into text data using the Google Speech-to-Text API. The input is audio data and the output is text data. The server makes an API call to convert the audio file into text format.

[0914] Step 5:

[0915] The server performs sentiment analysis on the text data using IBM Watson Tone Analyzer. The input is text data, and the output is an evaluation of the emotional state (e.g., stress level). The server sends the text data to the sentiment engine and receives the analysis results.

[0916] Step 6:

[0917] The server inputs the activity data into a machine learning model using TensorFlow to evaluate the physical health status. The input is the activity data, and the output is the physical status evaluation result. The server feeds the data to the model and records the output.

[0918] Step 7:

[0919] The server generates healthcare advice for the worker based on the analysis results. The input is the emotional state and physical health assessment results, and the output is a specific advice message. The server creates advice using a predefined template.

[0920] Step 8:

[0921] The server generates advice and notifies the worker's device using Firebase. The input is the advice message, and the output is the advice displayed on the worker's smartphone or robot assistant. The server sends messages in real time via the notification system.

[0922] Step 9:

[0923] If the server detects a persistent anomaly, it automatically sends a notification urging the user to contact an expert. The input is the abnormal data, and the output is a notification recommending consultation with an expert. The server runs an anomaly detection algorithm and sends an escalation notification if the anomaly persists.

[0924] The above are the specific processing steps of the system for carrying out the invention.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] [Third embodiment]

[0929] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0930] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0931] 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).

[0932] 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.

[0933] 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.

[0934] 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).

[0935] 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. 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.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] 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.

[0940] 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."

[0941] This invention relates to an AI healthcare system that synchronizes the mental and physical health of workers. The system collects and analyzes the user's daily activity data and voice data to evaluate their health status. Based on the evaluation results, the system provides professional advice and, if necessary, refers the user to a specialist or medical institution.

[0942] System Configuration

[0943] 1. Data Collection Methods

[0944] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[0945] Users can verbally greet and comment to the AI ​​assistant, providing voice data.

[0946] 2. Data upload method

[0947] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[0948] 3. Data Analysis Methods

[0949] The server analyzes the received data using artificial intelligence means, providing an emotional state assessment for the voice data and a physical health assessment based on the activity data.

[0950] 4. Advice Generation Methods

[0951] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[0952] 5. Means of providing advice

[0953] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the wearable device.

[0954] 6. Escalation Methods

[0955] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, such as if their mental health condition has been deteriorating for a certain period of time or if their physical data shows abnormal values.

[0956] Program processing

[0957] 1. Data Collection

[0958] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[0959] 2. Data upload

[0960] The device transmits the collected data to a server at set times, including activity data as well as information about the tone and speed of the voice.

[0961] 3. Data Analysis

[0962] The server inputs the transmitted data into a machine learning model to analyze the user's emotional and physical state, determining stress levels from voice data and exercise volume and health status from activity data.

[0963] 4. Advice Generation

[0964] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[0965] 5. Providing advice

[0966] The device then notifies the user of the advice it receives from the server. For example, the device displays a message on the smartphone screen saying, "Your stress levels are rising. Try meditating."

[0967] 6. Escalation

[0968] If the server detects persistent abnormalities, it will refer the user to an appropriate specialist or medical institution, allowing the user to receive professional support early on.

[0969] Specific examples

[0970] Example 1: Weekday status

[0971] 1. A user greets an AI assistant with "Good morning" in the morning.

[0972] 2. The device sends the collected voice data and the previous day's activity data to the server.

[0973] 3. The server analyzes the data and detects an increase in stress levels from the voice data.

[0974] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[0975] 5. The device notifies the user of the advice.

[0976] Example 2: Weekend Situation

[0977] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[0978] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[0979] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[0980] 4. The device notifies the user of the advice.

[0981] The above is an embodiment of the system of the present invention, which allows users to comprehensively manage their mental and physical health in their daily lives.

[0982] The processing flow will be explained below.

[0983] Step 1:

[0984] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[0985] Step 2:

[0986] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[0987] Step 3:

[0988] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is encrypted and transmitted securely.

[0989] Step 4:

[0990] The server analyzes the received data. Specifically,

[0991] Voice data analysis: Voice data is fed into machine learning models to assess the user's emotional state (e.g., stress level, changes in tone).

[0992] Activity data analysis: Analyzes step count, heart rate, body temperature, and sleep data to evaluate physical health status (e.g., exercise volume, fluctuations in health indicators).

[0993] Step 5:

[0994] The server generates advice for the user based on the results of the data analysis. Specifically,

[0995] Mental health advice: Generates relaxation and meditation suggestions when stress levels are high.

[0996] Physical health advice: Generates specific exercise and dietary suggestions if physical inactivity is detected.

[0997] Step 6:

[0998] The server sends the generated advice to the device, which then notifies the user. For example, the smartphone might say, "Your step count today is low, so try walking one station on your way home."

[0999] Step 7:

[1000] The device enters a loop where it receives feedback from the user and again sends data to the server, including whether or not the user actually tried the suggested action.

[1001] Step 8:

[1002] The server continuously monitors the data, and if an abnormality persists for a certain period of time, it will take action to refer the user to a specialist or medical institution, allowing the user to receive appropriate assistance early on.

[1003] Example 1

[1004] 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."

[1005] In today's world, comprehensive management of workers' mental and physical health is an important issue. However, many existing systems focus on one type of health condition, and few provide comprehensive support for both mental and physical health. Furthermore, there is a lack of appropriate ways to deal with ongoing abnormalities, making it difficult to provide early, specialized support. Therefore, there is a need for the development of a system that can achieve comprehensive health management for users.

[1006] 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.

[1007] In this invention, the server includes a means for acquiring activity data, a means for acquiring voice data, a means for transmitting the acquired activity data and voice data to the server at a predetermined time, a means for analyzing the transmitted data using artificial intelligence, a means for generating mental and physical health care advice based on the analysis results, and a means for notifying the user of the advice. This enables a comprehensive evaluation of the user's daily health condition and the provision of appropriate advice in real time. Furthermore, if abnormalities are detected over a long period of time, the server can refer the user to a specialist or medical institution, allowing the user to receive professional support early.

[1008] "Activity data" refers to data related to the user's physical activity in daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[1009] "Voice data" refers to data that records the voice spoken by a user, including the content of the conversation, tone, speed, etc.

[1010] "Server" refers to a computer system that receives data, analyzes it, and generates results, and is capable of communicating with terminals via a network.

[1011] "Artificial intelligence" refers to algorithms and systems that use techniques such as machine learning and deep learning to analyze data and discover patterns.

[1012] "Analysis results" are the results of analysis of data processed by artificial intelligence, based on which health and emotional state are assessed.

[1013] "Healthcare advice" refers to specific suggestions and guidelines for action to improve the user's health based on the analysis results.

[1014] A "persistent anomaly" refers to a situation in which an abnormal pattern is detected continuously over a period of time in a user's activity data or voice data.

[1015] "Referral to specialists or medical institutions" refers to the act of informing or recommending appropriate specialists or medical facilities to users as needed.

[1016] "Emotional state" refers to a psychological state assessed based on a user's voice data, and includes stress, joy, sadness, etc.

[1017] "Notification" refers to the means of communication, usually via a device, to convey generated advice or warnings to the user.

[1018] This invention relates to an AI healthcare system for comprehensively managing the mental and physical health of workers. This system collects and analyzes the user's daily activity data and voice data, evaluates their health status, and provides appropriate advice. Furthermore, if persistent abnormalities are detected, the system will refer the user to a specialist or medical institution. A detailed embodiment of this system is shown below.

[1019] Data collection methods

[1020] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. When the user verbally greets or comments to the AI ​​assistant, this voice data is also recorded. Specific hardware used includes a smartphone (e.g., Android, iPhone) or a wearable device (e.g., Fitbit, Apple Watch).

[1021] Example: A user says "Good morning" to an AI assistant in the morning, which collects voice data, while the wearable device simultaneously transmits the number of steps and heart rate recorded the previous day to a smartphone.

[1022] Data upload method

[1023] The device sends the collected data to the server at a set time. It can be set to upload data every morning at 9:00 and every evening at 9:00. The data sent includes activity data, voice tones, speed, etc.

[1024] Example: Every night at 9pm, the device automatically uploads data to the server, ensuring that fresh data is always stored on the server.

[1025] Data Analysis Methods

[1026] The server receives the data sent from the device and inputs it into machine learning models (e.g., TensorFlow, PyTorch). Voice data is used to assess stress levels using emotion analysis algorithms, and activity data is used to determine the user's physical health (e.g., amount of exercise, quality of sleep).

[1027] Example: A server analysis script uses a TensorFlow model to analyze audio data and classify the user's emotional state into "positive," "negative," or "neutral," thereby determining how stressed the user is.

[1028] Advice Generation Method

[1029] Based on the analysis results, the server generates appropriate health improvement advice for the user, suggesting relaxation methods if stress levels are high, and recommending specific exercises if exercise is lacking.

[1030] Example: A message such as "Your stress levels are rising. Try meditating for five minutes" is generated. If you are not getting enough exercise, specific advice such as "Set your goal for today to be a 30-minute walk" is provided.

[1031] Advice delivery methods

[1032] The device notifies the user of the generated advice via push notifications on smartphones or vibrations on wearable devices.

[1033] Example: At 9:00 a.m., your smartphone displays a push notification with the advice, "Good morning. Let's stay healthy today." Your wearable device also vibrates gently to notify you of this notification.

[1034] Escalation methods

[1035] The server continuously monitors the user's data and will refer the user to a specialist or medical institution if an abnormality is detected, for example, if stress levels remain high for a certain period of time or if physical data shows abnormal values.

[1036] Example: If the server detects a high stress level for one consecutive week, it generates a message saying, "You appear to be experiencing persistent stress. Perhaps you should seek professional counseling?" and the device notifies the user of this message.

[1037] In this way, the present invention can comprehensively evaluate the user's daily health condition and provide appropriate advice in real time. It also allows the user to receive professional support early on, making it possible to maintain and improve mental and physical health.

[1038] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1039] Step 1: Data collection

[1040] The device will collect activity data (e.g., number of steps, heart rate, body temperature, and sleep time) using a smartphone or wearable device as the user goes about their daily life, and will also record voice data when the user speaks to the AI ​​assistant or expresses their thoughts.

[1041] Input: User activity and voice data.

[1042] Data processing: Activity data is automatically recorded by a pedometer and heart rate sensor, and audio data is collected by a microphone.

[1043] Output: Activity data and voice data stored in the smartphone.

[1044] How it works: When a user says "Good morning" to the AI ​​assistant, the voice is recorded by an application on the smartphone, and the wearable device simultaneously measures daily activity data such as steps taken and heart rate and sends the data to the smartphone.

[1045] Step 2: Upload data

[1046] The device periodically sends the collected data to the server, for example, uploading all data at 9:00 every morning and 9:00 every evening.

[1047] Input: Activity and voice data stored on the smartphone.

[1048] Data processing: The data is compressed, encrypted and sent to the server.

[1049] Output: Compressed data file uploaded to the server.

[1050] How it works: Every night at 9 p.m., the smartphone uploads the accumulated data to a cloud server via a dedicated application. At this time, the data is compressed and encrypted to ensure security.

[1051] Step 3: Data analysis

[1052] The server then analyzes the received data using artificial intelligence (AI) and machine learning models (e.g., TensorFlow, PyTorch). The voice data is used to assess emotional state, and the activity data is used to analyze physical health.

[1053] Input: The compressed data file uploaded to the server.

[1054] Data processing: Data decompression and preprocessing (e.g., noise removal, data cleaning) are performed.

[1055] Output: Emotional state and physical health analysis.

[1056] How it works: A Python script running on the server unpacks the uploaded data, performs preprocessing, and then uses machine learning models to assess emotional state from voice data and physical health from activity data. For example, a "high stress level" may be determined based on voice analysis.

[1057] Step 4: Advice Generation

[1058] The server generates health advice for the user based on the analysis results, recommending appropriate behaviors for the user in terms of both mental and physical health.

[1059] Input: Emotional state and physical health analysis results.

[1060] Data processing: Advice content is customized based on the analysis results.

[1061] Output: Customized advice to provide to the user.

[1062] Specific operation: For example, the server generates advice such as "Try 5 minutes of meditation" for a user who is analyzed as having a "high stress level."

[1063] Step 5: Providing advice

[1064] The device notifies the user of the generated advice using methods such as push notifications on smartphones or vibrations on wearable devices.

[1065] Input: Customized advice sent by the server.

[1066] Data processing: Display advice in a format that is easy for users to understand.

[1067] Output: Advice given to the user.

[1068] Specific operation: At 9 a.m., the smartphone displays a push notification saying, "Your stress level is high today. Try a 5-minute meditation," and the wearable device vibrates gently to notify the user.

[1069] Step 6: Escalation

[1070] The server continuously monitors the user's data and, if an abnormality is detected, will refer the user to a specialist or medical institution. If an abnormality is detected, the server will notify the user and provide information on the appropriate specialist.

[1071] Input: Continuously monitored user data.

[1072] Data processing: detecting outliers and selecting appropriate referrals from a list of specialists and medical institutions.

[1073] Output: Notification that an abnormality was detected and information for specialists or medical institutions.

[1074] Specific operation: The server detects a high stress level for one consecutive week, generates a message saying, "It appears that stress is continuing. Perhaps you should seek professional counseling?" and notifies the user of this message on the device.

[1075] (Application example 1)

[1076] 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."

[1077] In modern factories, managing the mental and physical health of workers is important. However, traditional methods have the drawback of being difficult to monitor in real time or respond quickly to abnormalities. It is also difficult for workers to accurately understand their own health status and take appropriate measures. This can lead to the accumulation of excessive stress and fatigue, which can lead to reduced productivity and an increased risk of workplace accidents.

[1078] 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.

[1079] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, and means for detecting an abnormal condition and referring the user to a specialist or medical institution when the user's physical or mental condition falls below a certain standard. This makes it possible to monitor the health condition of workers in real time and quickly respond to any abnormalities that occur.

[1080] "Activity Data" refers to data that quantifies a user's daily physical movements and activities, such as the number of steps taken, heart rate, body temperature, and sleep duration.

[1081] "Voice Data" refers to the audio information provided when a user converses with an AI assistant, including the tone, speed, and content of the speech.

[1082] "Artificial Intelligence Means" refers to the machine learning algorithms and artificial intelligence models used to analyze collected activity data and audio data.

[1083] "Mental and physical healthcare advice" refers to specific suggestions and instructions to improve a user's psychological and physical health based on the analysis results.

[1084] "User" refers to an individual who uses the system, including laborers and factory workers.

[1085] "Abnormal condition" refers to a state in which a user's physical or mental health falls below the standards set by the system.

[1086] "Expert" refers to a medical professional or counselor who can provide appropriate responses and advice to the user's abnormal condition.

[1087] "Medical Institution" refers to a hospital or clinic that provides specialized medical care or treatment required by the User.

[1088] "Real-time" refers to processing or response occurring almost immediately or with very little delay.

[1089] The higher expression of "physical" is defined as "physical." "Physical health" refers to "physical well-being."

[1090] The higher term for "mental" is defined as "psychological." "Mental health" refers to "psychological health."

[1091] The present invention is a system for monitoring the mental and physical health of workers in real time and providing appropriate advice. This system is implemented with the following configuration and procedures.

[1092] System Configuration

[1093] 1. Data Collection Methods

[1094] The device uses devices such as smartwatches and smartphones to collect data on a user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[1095] Users provide voice data by verbally expressing greetings and impressions to the AI ​​assistant.

[1096] 2. Data upload method

[1097] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[1098] 3. Data Analysis Methods

[1099] The server analyzes the received data using artificial intelligence means (e.g., machine learning models), assessing emotional state based on the voice data and physical health status based on the activity data.

[1100] 4. Advice Generation Methods

[1101] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[1102] 5. Means of providing advice

[1103] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the smartwatch.

[1104] 6. Escalation Methods

[1105] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, for example, if their mental health condition has deteriorated over a certain period of time or if their physical data shows abnormal values.

[1106] Example of operation

[1107] Example 1: Weekday status

[1108] The user greets the AI ​​assistant with "Good morning" in the morning.

[1109] The device sends the collected voice data and the previous day's activity data to the server.

[1110] The server analyzes the data and detects rising stress levels from the voice data.

[1111] The server generates advice such as "Your stress is increasing. Try 5 minutes of meditation."

[1112] The device will notify the user of the advice.

[1113] Example 2: Weekend Situation

[1114] The user sends the heart rate and sleep time measured by the smartwatch to the server.

[1115] The server analyzes the data and detects whether the user is getting enough sleep.

[1116] The server generates advice such as, "We recommend keeping things light today and getting plenty of rest."

[1117] The device will notify the user of the advice.

[1118] Prompt Sentence Examples

[1119] "Analyze the following data and generate health advice for the user: Data: {'steps': 4500, 'heart_rate': 95, 'temperature': 37.5, 'sleep_hours': 5.5, 'voice_tone': 'stress'}"

[1120] The above is a specific embodiment of the system of the present invention, which allows workers to comprehensively manage their mental and physical health in their daily lives.

[1121] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1122] Step 1:

[1123] Data collection:

[1124] The device uses a smartwatch or smartphone to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep duration.

[1125] Users can converse with the AI ​​assistant via voice and provide voice data.

[1126] Input: User activity data, voice data

[1127] Output: A set of collected activity and audio data

[1128] What it does: For example, a smartwatch counts steps, monitors heart rate, and records audio when you say "good morning."

[1129] Step 2:

[1130] Data Upload:

[1131] The terminal transmits the collected activity data and voice data to the server at regular intervals (for example, every morning).

[1132] Input: Collected activity and audio data

[1133] Output: Data sent to the server

[1134] Specific operation: The device uses Wi-Fi or mobile data connection to upload activity data (e.g., 4,500 steps) and audio data (e.g., audio tone is "stress") to a cloud server.

[1135] Step 3:

[1136] Data Analysis:

[1137] The server inputs the received data into artificial intelligence means (e.g., machine learning models) to analyze the user's mental and physical state.

[1138] Input: Activity and voice data sent to the server

[1139] Output: Mental and physical health assessment results

[1140] Specific behavior: For example, a machine learning model analyzes heart rate and voice tone to determine a user's stress level as "high," or analyzes steps taken and sleep time to assess physical health as "poor."

[1141] Step 4:

[1142] Advice Generation:

[1143] Based on the analysis results, the server generates health improvement advice for the user, suggesting relaxation methods for mental health and exercise and rest for physical health.

[1144] Input: Mental and physical health assessment results

[1145] Output: Generated healthcare advice

[1146] Specific operation: For example, the server generates advice such as "Please meditate for five minutes" based on the evaluation result that "your stress level is high." Also, based on the evaluation result that your physical health is "poor," it generates advice such as "Please reduce your schedule for today and get plenty of rest."

[1147] Step 5:

[1148] Advice provided:

[1149] The terminal notifies the user of the advice received from the server.

[1150] Input: Generated healthcare advice

[1151] Output: User advice notice

[1152] Specific actions: For example, the smartphone screen will display a message saying, "Your stress is increasing. Try a 5-minute meditation." The smartwatch will also send a vibration notification.

[1153] Step 6:

[1154] escalation:

[1155] If the server detects persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[1156] Input: Continuous abnormal data

[1157] Output: Referral information for specialists and medical institutions

[1158] Specific operation: For example, if the server detects that a user's stress level has remained high for more than a week, it will notify the user by listing appropriate medical institutions, such as "Your stress level has remained high. We recommend that you consult the medical institution listed below."

[1159] These are the specific processing steps of the system, which enables comprehensive management of the user's mental and physical health in real time.

[1160] 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.

[1161] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. This system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[1162] System Configuration

[1163] 1. Data Collection Methods

[1164] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[1165] Users interact with the AI ​​assistant and provide voice data, which includes information such as the user's tone and speed.

[1166] 2. Data upload method

[1167] The device sends the collected data to a server at regular intervals. For example, by uploading data every morning and evening, it is possible to monitor health conditions in real time.

[1168] 3. Data Analysis Methods

[1169] The server is equipped with artificial intelligence means for analyzing the received data, using an emotion engine to assess the user's emotional state from the voice data, and physical health status from the activity data.

[1170] The emotion engine analyzes voice data to determine the user's stress level and emotional state. The engine captures changes in the user's emotions through detailed analysis of the tone, speed, rhythm, etc. of the voice.

[1171] 4. Advice Generation Methods

[1172] Based on the analysis results, the server generates appropriate health improvement advice for the user, such as stress management and relaxation methods for mental health, and exercise and diet suggestions for physical health.

[1173] For example, if the emotion engine detects a user's high stress state, it will generate mental health advice such as "Try five minutes of meditation."

[1174] 5. Means of providing advice

[1175] The device then notifies the user of the generated advice. By providing real-time advice via a smartphone or wearable device, the user can take immediate action.

[1176] 6. Escalation Methods

[1177] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist.

[1178] This escalation feature allows users to take appropriate action regarding their health condition early on.

[1179] Program processing

[1180] 1. Data Collection

[1181] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[1182] 2. Data upload

[1183] The device transmits the collected data to a server at scheduled times, including activity data as well as information about the tone and speed of the voice.

[1184] 3. Data Analysis

[1185] The server inputs the transmitted data into a machine learning model and emotion engine to analyze the user's emotional and physical state. The server evaluates the user's emotional state (e.g., stress level, tone changes) from the voice data and their physical health status (e.g., exercise volume, fluctuations in health indicators) from the activity data.

[1186] 4. Advice Generation

[1187] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[1188] 5. Providing advice

[1189] The device then notifies the user of the advice it receives from the server. For example, a message like "Your stress levels are rising. Try meditation" will appear on the smartphone screen.

[1190] 6. Escalation

[1191] If a persistent abnormality is detected, the server will refer the user to an appropriate specialist or medical institution, ensuring that the user receives appropriate assistance early on.

[1192] Specific examples

[1193] Example 1: Weekday status

[1194] 1. A user greets an AI assistant with "Good morning" in the morning.

[1195] 2. The device sends the collected voice data and the previous day's activity data to the server.

[1196] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[1197] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[1198] 5. The device notifies the user of the advice.

[1199] Example 2: Weekend Situation

[1200] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[1201] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[1202] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[1203] 4. The device notifies the user of the advice.

[1204] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[1205] The processing flow will be explained below.

[1206] Step 1:

[1207] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[1208] Step 2:

[1209] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[1210] Step 3:

[1211] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is securely encrypted before being transferred.

[1212] Step 4:

[1213] The server analyzes the received data. Specifically,

[1214] Voice data analysis: Voice data is fed into an emotion engine to assess the user's emotional state (e.g., stress level, changes in tone).

[1215] Activity data analysis: Analyzes the number of steps, heart rate, body temperature, and sleep data collected to evaluate physical health status (e.g., amount of exercise, fluctuations in health indicators).

[1216] Step 5:

[1217] The emotion engine analyzes the voice data in detail to determine the user's emotional state, for example, measuring stress levels based on the tone and speed of the voice.

[1218] Step 6:

[1219] The server generates advice for the user based on the results of the data analysis. Specifically,

[1220] Mental health advice: If you are experiencing high stress, we suggest relaxation techniques and meditation.

[1221] Physical health advice: If lack of exercise is detected, specific exercise and dietary suggestions will be provided.

[1222] Step 7:

[1223] The server sends the generated advice to the device, which then notifies the user. For example, the device displays a message on the smartphone screen saying, "Your stress is increasing. Try meditation."

[1224] Step 8:

[1225] The device receives feedback from the user and sends updated data back to the server, including the status of the proposed action.

[1226] Step 9:

[1227] The server continuously monitors the data and, if an abnormal condition persists for a certain period of time, will refer the user to a specialist or medical institution. For example, if the emotion engine detects high stress levels for three consecutive days, it will notify the user that "we recommend consulting a mental health professional."

[1228] Step 10:

[1229] The server generates and provides a comprehensive report on the user's health status, allowing the user to understand their long-term health status and take appropriate measures.

[1230] Example 2

[1231] 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."

[1232] In modern society, managing the mental and physical health of working people is becoming increasingly important. However, with busy daily schedules, it can be difficult to accurately understand one's own health status and take appropriate measures. Health problems caused by stress and lack of exercise are of particular concern. Conventional methods for addressing this issue can only respond based on limited data, making it difficult to provide comprehensive health management.

[1233] 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.

[1234] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, means for evaluating the emotional state and physical condition, means for detecting ongoing abnormalities, and means for referring the user to a specialist or medical institution when an abnormality is detected. This allows for precise management of the user's daily health condition, providing appropriate advice, and enabling early consultation with a specialist.

[1235] "Activity data" refers to data measuring the user's physical activity in their daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[1236] "Voice data" refers to voice information acquired when a user interacts with an AI assistant, etc., and includes information such as tone, speed, and rhythm.

[1237] "Artificial intelligence means" refers to machine learning models or other AI technologies used to analyze collected data and assess a user's health status.

[1238] "Emotional state" refers to the mental health status of a user as determined from their voice data, including stress levels and emotional fluctuations.

[1239] "Expert" refers to a medical or psychological professional who can assess the user's health status and provide necessary support or measures.

[1240] "Medical Institution" refers to an organization such as a hospital or clinic that provides diagnosis or treatment for a user's health condition.

[1241] "Advice generation means" refers to a function that creates healthcare advice appropriate for the user based on the analysis results obtained by the artificial intelligence means.

[1242] "Emotion engine" refers to technology that analyzes voice data to determine a user's stress level and emotional state.

[1243] "Escalation" refers to a function that encourages users to consult with a specialist or medical institution if their health condition is consistently abnormal.

[1244] "Health management" refers to the process of observing and assessing a user's mental and physical state and providing remedial measures as needed.

[1245] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. The system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[1246] System Configuration

[1247] 1. Data Collection Methods

[1248] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. The user then interacts with the AI ​​assistant and provides voice data, which includes information such as the user's tone and speed.

[1249] 2. Data upload method

[1250] The device periodically sends the collected data to a server. For example, by uploading data every morning and evening, real-time health monitoring is possible. The transmitted data is encrypted and reaches the server via a secure communication channel.

[1251] 3. Data Analysis Methods

[1252] The server is equipped with artificial intelligence means for analyzing the received data. For the voice data, it uses an emotion engine to assess the user's emotional state, and for the activity data, it assesses the user's physical health status. This analysis is performed using machine learning models to identify the emotional state (e.g., stress level, tone changes) from the voice data and to detect fluctuations in health indicators from the activity data.

[1253] 4. Advice Generation Methods

[1254] Based on the analysis results, the server generates appropriate health improvement advice for the user. For mental health, it suggests stress management and relaxation methods, and for physical health, it suggests exercise and diet. For example, if the emotion engine detects that the user is in a high-stress state, it generates mental health advice such as "Try five minutes of meditation."

[1255] 5. Means of providing advice

[1256] The device then notifies the user of the generated advice. Smartphones and wearable devices provide real-time advice, allowing users to take immediate action. Notifications are provided via push notifications or voice assistants.

[1257] 6. Escalation Methods

[1258] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist. This escalation function allows users to take appropriate measures regarding their health condition early.

[1259] Specific examples

[1260] Example 1: Weekday status

[1261] 1. A user greets an AI assistant with "Good morning" in the morning.

[1262] 2. The device sends the collected voice data and the previous day's activity data to the server.

[1263] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[1264] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[1265] 5. The device notifies the user of the advice.

[1266] Example 2: Weekend Situation

[1267] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[1268] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[1269] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[1270] 4. The device notifies the user of the advice.

[1271] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[1272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1273] Step 1: Data collection

[1274] The device collects data about the user's daily activities.

[1275] Input: Sensor data from smartphones and wearable devices (step count, heart rate, body temperature, sleep time, etc.)

[1276] Output: Collected activity data

[1277] How it works: The smartwatch measures the user's steps and heart rate in real time and sends that data via Bluetooth to a smartphone, which collects additional data using GPS and accelerometers.

[1278] Users interact with the AI ​​assistant and provide voice data.

[1279] Input: User's voice (e.g., speaking to an AI assistant)

[1280] Output: Collected audio data

[1281] How it works: A user speaks into the smartphone microphone, and the audio data is recorded by the AI ​​assistant application. The audio file contains information about tone, speed, and pitch.

[1282] Step 2: Upload data

[1283] The terminal transmits the collected data to the server.

[1284] Input: Collected activity and voice data

[1285] Output: Data sent to the server

[1286] How it works: Your smartphone periodically uploads collected data to a server over Wi-Fi or mobile data networks. This data is encrypted and transmitted using a secure communication protocol.

[1287] Step 3: Data analysis

[1288] The server analyzes the transmitted data.

[1289] Input: Uploaded activity data and audio data

[1290] Output: Analysis results (emotional state, physical health assessment)

[1291] Specific operation: The server inputs the received data into the machine learning model and emotion engine for analysis. The emotion engine analyzes the voice data to evaluate stress levels and emotional changes. Activity data is used to evaluate fluctuations in exercise volume and health indicators. For example, the emotion engine detects signs of stress from changes in voice tone and speed.

[1292] Step 4: Advice Generation

[1293] The server generates advice based on the analysis results.

[1294] Input: Analysis results (emotional state, physical health assessment)

[1295] Output: Healthcare advice

[1296] Specific operation: The server generates appropriate healthcare advice based on the analysis results. For example, if the analysis result is "high stress level," the server generates the advice "try five minutes of meditation." If the result is "lack of exercise," the server generates the advice "we recommend a 20-minute walk."

[1297] Step 5: Providing advice

[1298] The terminal notifies the user of the generated advice.

[1299] Enter: Healthcare Advice

[1300] Output: Advice given to the user

[1301] What it does: The smartphone will display advice to the user through the notification system. For example, a push notification might say, "Your stress is increasing. Try meditation." The AI ​​assistant can also provide a voice alert.

[1302] Step 6: Escalation

[1303] If the server detects any persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[1304] Input: Continuous abnormal condition detection

[1305] Output: Referral notification to specialists and medical institutions

[1306] Specific operation: The server continuously monitors the analysis results, and if an abnormality persists for a certain period of time (for example, high stress for three consecutive days), it generates a notification urging the user to consult a specialist. This notification is sent to the user via the smartphone notification system or email.

[1307] (Application example 2)

[1308] 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."

[1309] In conventional work environments, there has been no system for comprehensively managing and monitoring the mental and physical health of workers, and there has been a problem of workers' stress and fatigue not being properly managed, especially in factories. This can lead to reduced work efficiency and an increased risk of accidents, which can ultimately have a serious impact on workers' health. This invention aims to achieve both improved work efficiency and health management by monitoring workers' health status in real time and providing appropriate advice.

[1310] 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.

[1311] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the worker, and means for automatically prompting the worker to contact a specialist if an abnormality is detected. This allows the worker's health condition to be monitored in real time, and appropriate action to be taken immediately if an abnormality is detected.

[1312] The "means for acquiring activity data" refers to a device or system for collecting information on a worker's physical activities, such as the number of steps taken, heart rate, and working hours.

[1313] The "means for acquiring voice data" refers to a device or system for picking up and collecting conversations with workers and voice instructions.

[1314] "Artificial intelligence means" refers to computational algorithms or programs that analyze collected activity data and voice data and assess the mental and physical health status of workers.

[1315] The "means for generating healthcare advice" is a device or system for proposing health improvement measures and relaxation methods to a worker based on the analysis results using artificial intelligence means.

[1316] A "means for providing advice to a worker" is a device or system for notifying or presenting the generated healthcare advice to a worker.

[1317] "Means for automatically encouraging contact with an expert when an abnormality is detected" refers to a device or system that automatically encourages contact with an expert or medical institution when an abnormality is continuously detected in a worker's health condition.

[1318] The "means for assessing the worker's emotional state" is a device or system for analyzing the voice data and determining the worker's emotional state (e.g., stress level).

[1319] This invention relates to a system for monitoring and managing the mental and physical health of workers in factories in real time. This system collects and analyzes worker activity data and voice data, and provides health care advice based on the results.

[1320] System Overview

[1321] The system consists of the following main components:

[1322] 1. Data collection methods:

[1323] Use a wearable device (e.g., Apple Watch, Fitbit) to collect activity data.

[1324] Use a voice input device and a robotic assistant (e.g., Pepper) to collect voice data.

[1325] 2. Data upload method:

[1326] The collected data is sent to the server at regular intervals and stored in an AWS S3 bucket.

[1327] 3. Data analysis methods:

[1328] We use server-side artificial intelligence tools (e.g., Google Speech-to-Text API, IBM Watson Tone Analyzer, TensorFlow) to analyze activity data and voice data. Voice data is converted to text using Google Speech-to-Text API, and sentiment analysis is performed using IBM Watson Tone Analyzer. Activity data is analyzed using machine learning models using TensorFlow.

[1329] 4. Advice Generation Methods:

[1330] Based on the analysis results, specific health improvement advice (e.g., stretching and relaxation methods) is generated for the worker.

[1331] 5. Advice delivery methods:

[1332] Using Firebase, notifications are sent in real time directly from workers' smartphones or robot assistants.

[1333] 6. Escalation Methods:

[1334] If a persistent abnormality is detected, a notification will be automatically sent based on the abnormal data, prompting the user to contact a specialist or medical institution.

[1335] Example

[1336] On weekdays, worker A working in the factory uses the system in the following way.

[1337] 1. Data Collection:

[1338] Worker A wears a wearable device, which collects activity data such as heart rate and number of steps in real time.

[1339] The robot assistant and worker A have a short conversation, and the audio data is recorded.

[1340] 2. Data upload:

[1341] Collected activity and audio data is uploaded to an AWS S3 bucket every hour.

[1342] 3. Data Analysis:

[1343] The server converts the audio data into text using the Google Speech-to-Text API and performs sentiment analysis using IBM Watson Tone Analyzer.

[1344] Activity data is analyzed using TensorFlow to assess physical health status.

[1345] 4. Advice Generation:

[1346] If the server analyzes that the stress level is high, it generates advice to suggest relaxation methods (e.g., deep breathing).

[1347] 5. Providing advice:

[1348] The advice generated by the server is sent to worker A's smartphone and robot assistant via Firebase.

[1349] A message appears on Worker A's smartphone saying, "Your stress is increasing. Try taking some deep breaths."

[1350] Prompt Sentence Examples

[1351] "Analyze my stress level based on this morning's heart rate data and yesterday's work hours data."

[1352] "Please evaluate the emotional state of worker C from his / her voice data and generate stress advice."

[1353] A system configured in this way allows for real-time management of workers' health conditions, and if any abnormalities are detected, appropriate action can be taken immediately.

[1354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1355] Step 1:

[1356] The terminal collects the worker's activity data (e.g., number of steps, heart rate, working hours) through a wearable device. The input is the activity information obtained from the wearable device, and the output is the collected activity data. Specifically, the terminal updates the data using Bluetooth communication and records it in its internal storage.

[1357] Step 2:

[1358] The terminal collects voice data through dialogue with the robot assistant. The input is the worker's voice, and the output is the captured voice data. The robot assistant periodically asks the worker questions and captures their answers with a voice sensor.

[1359] Step 3:

[1360] The device uploads the collected activity data and voice data to the server at regular intervals. The input is the data stored on the device, and the output is the data stored in the server's database. Specifically, the device uses an internet connection to send the data to an AWS S3 bucket.

[1361] Step 4:

[1362] The server converts the uploaded audio data into text data using the Google Speech-to-Text API. The input is audio data and the output is text data. The server makes an API call to convert the audio file into text format.

[1363] Step 5:

[1364] The server performs sentiment analysis on the text data using IBM Watson Tone Analyzer. The input is text data, and the output is an evaluation of the emotional state (e.g., stress level). The server sends the text data to the sentiment engine and receives the analysis results.

[1365] Step 6:

[1366] The server inputs the activity data into a machine learning model using TensorFlow to evaluate the physical health status. The input is the activity data, and the output is the physical status evaluation result. The server feeds the data to the model and records the output.

[1367] Step 7:

[1368] The server generates healthcare advice for the worker based on the analysis results. The input is the emotional state and physical health assessment results, and the output is a specific advice message. The server creates advice using a predefined template.

[1369] Step 8:

[1370] The server generates advice and notifies the worker's device using Firebase. The input is the advice message, and the output is the advice displayed on the worker's smartphone or robot assistant. The server sends messages in real time via the notification system.

[1371] Step 9:

[1372] If the server detects a persistent anomaly, it automatically sends a notification urging the user to contact an expert. The input is the abnormal data, and the output is a notification recommending consultation with an expert. The server runs an anomaly detection algorithm and sends an escalation notification if the anomaly persists.

[1373] The above are the specific processing steps of the system for carrying out the invention.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] [Fourth embodiment]

[1378] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1379] 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.

[1380] 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).

[1381] 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.

[1382] 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.

[1383] 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).

[1384] 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. 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.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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."

[1391] This invention relates to an AI healthcare system that synchronizes the mental and physical health of workers. The system collects and analyzes the user's daily activity data and voice data to evaluate their health status. Based on the evaluation results, the system provides professional advice and, if necessary, refers the user to a specialist or medical institution.

[1392] System Configuration

[1393] 1. Data Collection Methods

[1394] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[1395] Users can verbally greet and comment to the AI ​​assistant, providing voice data.

[1396] 2. Data upload method

[1397] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[1398] 3. Data Analysis Methods

[1399] The server analyzes the received data using artificial intelligence means, providing an emotional state assessment for the voice data and a physical health assessment based on the activity data.

[1400] 4. Advice Generation Methods

[1401] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[1402] 5. Means of providing advice

[1403] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the wearable device.

[1404] 6. Escalation Methods

[1405] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, such as if their mental health condition has been deteriorating for a certain period of time or if their physical data shows abnormal values.

[1406] Program processing

[1407] 1. Data Collection

[1408] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[1409] 2. Data upload

[1410] The device transmits the collected data to a server at set times, including activity data as well as information about the tone and speed of the voice.

[1411] 3. Data Analysis

[1412] The server inputs the transmitted data into a machine learning model to analyze the user's emotional and physical state, determining stress levels from voice data and exercise volume and health status from activity data.

[1413] 4. Advice Generation

[1414] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[1415] 5. Providing advice

[1416] The device then notifies the user of the advice it receives from the server. For example, the device displays a message on the smartphone screen saying, "Your stress levels are rising. Try meditating."

[1417] 6. Escalation

[1418] If the server detects persistent abnormalities, it will refer the user to an appropriate specialist or medical institution, allowing the user to receive professional support early on.

[1419] Specific examples

[1420] Example 1: Weekday status

[1421] 1. A user greets an AI assistant with "Good morning" in the morning.

[1422] 2. The device sends the collected voice data and the previous day's activity data to the server.

[1423] 3. The server analyzes the data and detects an increase in stress levels from the voice data.

[1424] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[1425] 5. The device notifies the user of the advice.

[1426] Example 2: Weekend Situation

[1427] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[1428] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[1429] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[1430] 4. The device notifies the user of the advice.

[1431] The above is an embodiment of the system of the present invention, which allows users to comprehensively manage their mental and physical health in their daily lives.

[1432] The processing flow will be explained below.

[1433] Step 1:

[1434] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[1435] Step 2:

[1436] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[1437] Step 3:

[1438] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is encrypted and transmitted securely.

[1439] Step 4:

[1440] The server analyzes the received data. Specifically,

[1441] Voice data analysis: Voice data is fed into machine learning models to assess the user's emotional state (e.g., stress level, changes in tone).

[1442] Activity data analysis: Analyzes step count, heart rate, body temperature, and sleep data to evaluate physical health status (e.g., exercise volume, fluctuations in health indicators).

[1443] Step 5:

[1444] The server generates advice for the user based on the results of the data analysis. Specifically,

[1445] Mental health advice: Generates relaxation and meditation suggestions when stress levels are high.

[1446] Physical health advice: Generates specific exercise and dietary suggestions if physical inactivity is detected.

[1447] Step 6:

[1448] The server sends the generated advice to the device, which then notifies the user. For example, the smartphone might say, "Your step count today is low, so try walking one station on your way home."

[1449] Step 7:

[1450] The device enters a loop where it receives feedback from the user and again sends data to the server, including whether or not the user actually tried the suggested action.

[1451] Step 8:

[1452] The server continuously monitors the data, and if an abnormality persists for a certain period of time, it will take action to refer the user to a specialist or medical institution, allowing the user to receive appropriate assistance early on.

[1453] Example 1

[1454] 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."

[1455] In today's world, comprehensive management of workers' mental and physical health is an important issue. However, many existing systems focus on one type of health condition, and few provide comprehensive support for both mental and physical health. Furthermore, there is a lack of appropriate ways to deal with ongoing abnormalities, making it difficult to provide early, specialized support. Therefore, there is a need for the development of a system that can achieve comprehensive health management for users.

[1456] 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.

[1457] In this invention, the server includes a means for acquiring activity data, a means for acquiring voice data, a means for transmitting the acquired activity data and voice data to the server at a predetermined time, a means for analyzing the transmitted data using artificial intelligence, a means for generating mental and physical health care advice based on the analysis results, and a means for notifying the user of the advice. This enables a comprehensive evaluation of the user's daily health condition and the provision of appropriate advice in real time. Furthermore, if abnormalities are detected over a long period of time, the server can refer the user to a specialist or medical institution, allowing the user to receive professional support early.

[1458] "Activity data" refers to data related to the user's physical activity in daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[1459] "Voice data" refers to data that records the voice spoken by a user, including the content of the conversation, tone, speed, etc.

[1460] "Server" refers to a computer system that receives data, analyzes it, and generates results, and is capable of communicating with terminals via a network.

[1461] "Artificial intelligence" refers to algorithms and systems that use techniques such as machine learning and deep learning to analyze data and discover patterns.

[1462] "Analysis results" are the results of analysis of data processed by artificial intelligence, based on which health and emotional state are assessed.

[1463] "Healthcare advice" refers to specific suggestions and guidelines for action to improve the user's health based on the analysis results.

[1464] A "persistent anomaly" refers to a situation in which an abnormal pattern is detected continuously over a period of time in a user's activity data or voice data.

[1465] "Referral to specialists or medical institutions" refers to the act of informing or recommending appropriate specialists or medical facilities to users as needed.

[1466] "Emotional state" refers to a psychological state assessed based on a user's voice data, and includes stress, joy, sadness, etc.

[1467] "Notification" refers to the means of communication, usually via a device, to convey generated advice or warnings to the user.

[1468] This invention relates to an AI healthcare system for comprehensively managing the mental and physical health of workers. This system collects and analyzes the user's daily activity data and voice data, evaluates their health status, and provides appropriate advice. Furthermore, if persistent abnormalities are detected, the system will refer the user to a specialist or medical institution. A detailed embodiment of this system is shown below.

[1469] Data collection methods

[1470] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. When the user verbally greets or comments to the AI ​​assistant, this voice data is also recorded. Specific hardware used includes a smartphone (e.g., Android, iPhone) or a wearable device (e.g., Fitbit, Apple Watch).

[1471] Example: A user says "Good morning" to an AI assistant in the morning, which collects voice data, while the wearable device simultaneously transmits the number of steps and heart rate recorded the previous day to a smartphone.

[1472] Data upload method

[1473] The device sends the collected data to the server at a set time. It can be set to upload data every morning at 9:00 and every evening at 9:00. The data sent includes activity data, voice tones, speed, etc.

[1474] Example: Every night at 9pm, the device automatically uploads data to the server, ensuring that fresh data is always stored on the server.

[1475] Data Analysis Methods

[1476] The server receives the data sent from the device and inputs it into machine learning models (e.g., TensorFlow, PyTorch). Voice data is used to assess stress levels using emotion analysis algorithms, and activity data is used to determine the user's physical health (e.g., amount of exercise, quality of sleep).

[1477] Example: A server analysis script uses a TensorFlow model to analyze audio data and classify the user's emotional state into "positive," "negative," or "neutral," thereby determining how stressed the user is.

[1478] Advice Generation Method

[1479] Based on the analysis results, the server generates appropriate health improvement advice for the user, suggesting relaxation methods if stress levels are high, and recommending specific exercises if exercise is lacking.

[1480] Example: A message such as "Your stress levels are rising. Try meditating for five minutes" is generated. If you are not getting enough exercise, specific advice such as "Set your goal for today to be a 30-minute walk" is provided.

[1481] Advice delivery methods

[1482] The device notifies the user of the generated advice via push notifications on smartphones or vibrations on wearable devices.

[1483] Example: At 9:00 a.m., your smartphone displays a push notification with the advice, "Good morning. Let's stay healthy today." Your wearable device also vibrates gently to notify you of this notification.

[1484] Escalation methods

[1485] The server continuously monitors the user's data and will refer the user to a specialist or medical institution if an abnormality is detected, for example, if stress levels remain high for a certain period of time or if physical data shows abnormal values.

[1486] Example: If the server detects a high stress level for one consecutive week, it generates a message saying, "You appear to be experiencing persistent stress. Perhaps you should seek professional counseling?" and the device notifies the user of this message.

[1487] In this way, the present invention can comprehensively evaluate the user's daily health condition and provide appropriate advice in real time. It also allows the user to receive professional support early on, making it possible to maintain and improve mental and physical health.

[1488] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1489] Step 1: Data collection

[1490] The device will collect activity data (e.g., number of steps, heart rate, body temperature, and sleep time) using a smartphone or wearable device as the user goes about their daily life, and will also record voice data when the user speaks to the AI ​​assistant or expresses their thoughts.

[1491] Input: User activity and voice data.

[1492] Data processing: Activity data is automatically recorded by a pedometer and heart rate sensor, and audio data is collected by a microphone.

[1493] Output: Activity data and voice data stored in the smartphone.

[1494] How it works: When a user says "Good morning" to the AI ​​assistant, the voice is recorded by an application on the smartphone, and the wearable device simultaneously measures daily activity data such as steps taken and heart rate and sends the data to the smartphone.

[1495] Step 2: Upload data

[1496] The device periodically sends the collected data to the server, for example, uploading all data at 9:00 every morning and 9:00 every evening.

[1497] Input: Activity and voice data stored on the smartphone.

[1498] Data processing: The data is compressed, encrypted and sent to the server.

[1499] Output: Compressed data file uploaded to the server.

[1500] How it works: Every night at 9 p.m., the smartphone uploads the accumulated data to a cloud server via a dedicated application. At this time, the data is compressed and encrypted to ensure security.

[1501] Step 3: Data analysis

[1502] The server then analyzes the received data using artificial intelligence (AI) and machine learning models (e.g., TensorFlow, PyTorch). The voice data is used to assess emotional state, and the activity data is used to analyze physical health.

[1503] Input: The compressed data file uploaded to the server.

[1504] Data processing: Data decompression and preprocessing (e.g., noise removal, data cleaning) are performed.

[1505] Output: Emotional state and physical health analysis.

[1506] How it works: A Python script running on the server unpacks the uploaded data, performs preprocessing, and then uses machine learning models to assess emotional state from voice data and physical health from activity data. For example, a "high stress level" may be determined based on voice analysis.

[1507] Step 4: Advice Generation

[1508] The server generates health advice for the user based on the analysis results, recommending appropriate behaviors for the user in terms of both mental and physical health.

[1509] Input: Emotional state and physical health analysis results.

[1510] Data processing: Advice content is customized based on the analysis results.

[1511] Output: Customized advice to provide to the user.

[1512] Specific operation: For example, the server generates advice such as "Try 5 minutes of meditation" for a user who is analyzed as having a "high stress level."

[1513] Step 5: Providing advice

[1514] The device notifies the user of the generated advice using methods such as push notifications on smartphones or vibrations on wearable devices.

[1515] Input: Customized advice sent by the server.

[1516] Data processing: Display advice in a format that is easy for users to understand.

[1517] Output: Advice given to the user.

[1518] Specific operation: At 9 a.m., the smartphone displays a push notification saying, "Your stress level is high today. Try a 5-minute meditation," and the wearable device vibrates gently to notify the user.

[1519] Step 6: Escalation

[1520] The server continuously monitors the user's data and, if an abnormality is detected, will refer the user to a specialist or medical institution. If an abnormality is detected, the server will notify the user and provide information on the appropriate specialist.

[1521] Input: Continuously monitored user data.

[1522] Data processing: detecting outliers and selecting appropriate referrals from a list of specialists and medical institutions.

[1523] Output: Notification that an abnormality was detected and information for specialists or medical institutions.

[1524] Specific operation: The server detects a high stress level for one consecutive week, generates a message saying, "It appears that stress is continuing. Perhaps you should seek professional counseling?" and notifies the user of this message on the device.

[1525] (Application example 1)

[1526] 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."

[1527] In modern factories, managing the mental and physical health of workers is important. However, traditional methods have the drawback of being difficult to monitor in real time or respond quickly to abnormalities. It is also difficult for workers to accurately understand their own health status and take appropriate measures. This can lead to the accumulation of excessive stress and fatigue, which can lead to reduced productivity and an increased risk of workplace accidents.

[1528] 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.

[1529] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, and means for detecting an abnormal condition and referring the user to a specialist or medical institution when the user's physical or mental condition falls below a certain standard. This makes it possible to monitor the health condition of workers in real time and quickly respond to any abnormalities that occur.

[1530] "Activity Data" refers to data that quantifies a user's daily physical movements and activities, such as the number of steps taken, heart rate, body temperature, and sleep duration.

[1531] "Voice Data" refers to the audio information provided when a user converses with an AI assistant, including the tone, speed, and content of the speech.

[1532] "Artificial Intelligence Means" refers to the machine learning algorithms and artificial intelligence models used to analyze collected activity data and audio data.

[1533] "Mental and physical healthcare advice" refers to specific suggestions and instructions to improve a user's psychological and physical health based on the analysis results.

[1534] "User" refers to an individual who uses the system, including laborers and factory workers.

[1535] "Abnormal condition" refers to a state in which a user's physical or mental health falls below the standards set by the system.

[1536] "Expert" refers to a medical professional or counselor who can provide appropriate responses and advice to the user's abnormal condition.

[1537] "Medical Institution" refers to a hospital or clinic that provides specialized medical care or treatment required by the User.

[1538] "Real-time" refers to processing or response occurring almost immediately or with very little delay.

[1539] The higher expression of "physical" is defined as "physical." "Physical health" refers to "physical well-being."

[1540] The higher term for "mental" is defined as "psychological." "Mental health" refers to "psychological health."

[1541] The present invention is a system for monitoring the mental and physical health of workers in real time and providing appropriate advice. This system is implemented with the following configuration and procedures.

[1542] System Configuration

[1543] 1. Data Collection Methods

[1544] The device uses devices such as smartwatches and smartphones to collect data on a user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[1545] Users provide voice data by verbally expressing greetings and impressions to the AI ​​assistant.

[1546] 2. Data upload method

[1547] The device sends the collected data to the server at regular intervals, for example, uploading the data collectively every morning or evening.

[1548] 3. Data Analysis Methods

[1549] The server analyzes the received data using artificial intelligence means (e.g., machine learning models), assessing emotional state based on the voice data and physical health status based on the activity data.

[1550] 4. Advice Generation Methods

[1551] The server generates appropriate health improvement advice for the user based on the analysis results, such as relaxation and stress management methods for mental health, and exercise and diet suggestions for physical health.

[1552] 5. Means of providing advice

[1553] The device will notify the user of the generated advice, which can be displayed on the smartphone or on the smartwatch.

[1554] 6. Escalation Methods

[1555] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution, for example, if their mental health condition has deteriorated over a certain period of time or if their physical data shows abnormal values.

[1556] Example of operation

[1557] Example 1: Weekday status

[1558] The user greets the AI ​​assistant with "Good morning" in the morning.

[1559] The device sends the collected voice data and the previous day's activity data to the server.

[1560] The server analyzes the data and detects rising stress levels from the voice data.

[1561] The server generates advice such as "Your stress is increasing. Try 5 minutes of meditation."

[1562] The device will notify the user of the advice.

[1563] Example 2: Weekend Situation

[1564] The user sends the heart rate and sleep time measured by the smartwatch to the server.

[1565] The server analyzes the data and detects whether the user is getting enough sleep.

[1566] The server generates advice such as, "We recommend keeping things light today and getting plenty of rest."

[1567] The device will notify the user of the advice.

[1568] Prompt Sentence Examples

[1569] "Analyze the following data and generate health advice for the user: Data: {'steps': 4500, 'heart_rate': 95, 'temperature': 37.5, 'sleep_hours': 5.5, 'voice_tone': 'stress'}"

[1570] The above is a specific embodiment of the system of the present invention, which allows workers to comprehensively manage their mental and physical health in their daily lives.

[1571] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1572] Step 1:

[1573] Data collection:

[1574] The device uses a smartwatch or smartphone to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep duration.

[1575] Users can converse with the AI ​​assistant via voice and provide voice data.

[1576] Input: User activity data, voice data

[1577] Output: A set of collected activity and audio data

[1578] What it does: For example, a smartwatch counts steps, monitors heart rate, and records audio when you say "good morning."

[1579] Step 2:

[1580] Data Upload:

[1581] The terminal transmits the collected activity data and voice data to the server at regular intervals (for example, every morning).

[1582] Input: Collected activity and audio data

[1583] Output: Data sent to the server

[1584] Specific operation: The device uses Wi-Fi or mobile data connection to upload activity data (e.g., 4,500 steps) and audio data (e.g., audio tone is "stress") to a cloud server.

[1585] Step 3:

[1586] Data Analysis:

[1587] The server inputs the received data into artificial intelligence means (e.g., machine learning models) to analyze the user's mental and physical state.

[1588] Input: Activity and voice data sent to the server

[1589] Output: Mental and physical health assessment results

[1590] Specific behavior: For example, a machine learning model analyzes heart rate and voice tone to determine a user's stress level as "high," or analyzes steps taken and sleep time to assess physical health as "poor."

[1591] Step 4:

[1592] Advice Generation:

[1593] Based on the analysis results, the server generates health improvement advice for the user, suggesting relaxation methods for mental health and exercise and rest for physical health.

[1594] Input: Mental and physical health assessment results

[1595] Output: Generated healthcare advice

[1596] Specific operation: For example, the server generates advice such as "Please meditate for five minutes" based on the evaluation result that "your stress level is high." Also, based on the evaluation result that your physical health is "poor," it generates advice such as "Please reduce your schedule for today and get plenty of rest."

[1597] Step 5:

[1598] Advice provided:

[1599] The terminal notifies the user of the advice received from the server.

[1600] Input: Generated healthcare advice

[1601] Output: User advice notice

[1602] Specific actions: For example, the smartphone screen will display a message saying, "Your stress is increasing. Try a 5-minute meditation." The smartwatch will also send a vibration notification.

[1603] Step 6:

[1604] escalation:

[1605] If the server detects persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[1606] Input: Continuous abnormal data

[1607] Output: Referral information for specialists and medical institutions

[1608] Specific operation: For example, if the server detects that a user's stress level has remained high for more than a week, it will notify the user by listing appropriate medical institutions, such as "Your stress level has remained high. We recommend that you consult the medical institution listed below."

[1609] These are the specific processing steps of the system, which enables comprehensive management of the user's mental and physical health in real time.

[1610] 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.

[1611] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. This system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[1612] System Configuration

[1613] 1. Data Collection Methods

[1614] The device uses smartphones and wearable devices to collect data on the user's daily activities, including the number of steps taken, heart rate, body temperature, and sleep duration.

[1615] Users interact with the AI ​​assistant and provide voice data, which includes information such as the user's tone and speed.

[1616] 2. Data upload method

[1617] The device sends the collected data to a server at regular intervals. For example, by uploading data every morning and evening, it is possible to monitor health conditions in real time.

[1618] 3. Data Analysis Methods

[1619] The server is equipped with artificial intelligence means for analyzing the received data, using an emotion engine to assess the user's emotional state from the voice data, and physical health status from the activity data.

[1620] The emotion engine analyzes voice data to determine the user's stress level and emotional state. The engine captures changes in the user's emotions through detailed analysis of the tone, speed, rhythm, etc. of the voice.

[1621] 4. Advice Generation Methods

[1622] Based on the analysis results, the server generates appropriate health improvement advice for the user, such as stress management and relaxation methods for mental health, and exercise and diet suggestions for physical health.

[1623] For example, if the emotion engine detects a user's high stress state, it will generate mental health advice such as "Try five minutes of meditation."

[1624] 5. Means of providing advice

[1625] The device then notifies the user of the generated advice. By providing real-time advice via a smartphone or wearable device, the user can take immediate action.

[1626] 6. Escalation Methods

[1627] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist.

[1628] This escalation feature allows users to take appropriate action regarding their health condition early on.

[1629] Program processing

[1630] 1. Data Collection

[1631] The device will collect data on the number of steps taken, heart rate, body temperature, and sleep as the user goes about their daily life, and will also record voice data when the user converses with the AI ​​assistant.

[1632] 2. Data upload

[1633] The device transmits the collected data to a server at scheduled times, including activity data as well as information about the tone and speed of the voice.

[1634] 3. Data Analysis

[1635] The server inputs the transmitted data into a machine learning model and emotion engine to analyze the user's emotional and physical state. The server evaluates the user's emotional state (e.g., stress level, tone changes) from the voice data and their physical health status (e.g., exercise volume, fluctuations in health indicators) from the activity data.

[1636] 4. Advice Generation

[1637] The server generates advice to provide to users based on the analysis results, such as suggesting relaxation methods to users experiencing high stress levels, or recommending specific exercises to users who are not getting enough exercise.

[1638] 5. Providing advice

[1639] The device then notifies the user of the advice it receives from the server. For example, a message like "Your stress levels are rising. Try meditation" will appear on the smartphone screen.

[1640] 6. Escalation

[1641] If a persistent abnormality is detected, the server will refer the user to an appropriate specialist or medical institution, ensuring that the user receives appropriate assistance early on.

[1642] Specific examples

[1643] Example 1: Weekday status

[1644] 1. A user greets an AI assistant with "Good morning" in the morning.

[1645] 2. The device sends the collected voice data and the previous day's activity data to the server.

[1646] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[1647] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[1648] 5. The device notifies the user of the advice.

[1649] Example 2: Weekend Situation

[1650] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[1651] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[1652] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[1653] 4. The device notifies the user of the advice.

[1654] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[1655] The processing flow will be explained below.

[1656] Step 1:

[1657] Users put on a smartphone or wearable device and begin their daily activities, which collects activity data such as the number of steps taken, heart rate, body temperature, and sleep time in real time.

[1658] Step 2:

[1659] The device stores the user's daily activity data in its memory, and also collects voice data when the user greets the AI ​​assistant with "Good morning."

[1660] Step 3:

[1661] The device sends the collected activity and voice data to a server at 8:00 a.m. and 8:00 p.m. every day. This data is securely encrypted before being transferred.

[1662] Step 4:

[1663] The server analyzes the received data. Specifically,

[1664] Voice data analysis: Voice data is fed into an emotion engine to assess the user's emotional state (e.g., stress level, changes in tone).

[1665] Activity data analysis: Analyzes the number of steps, heart rate, body temperature, and sleep data collected to evaluate physical health status (e.g., amount of exercise, fluctuations in health indicators).

[1666] Step 5:

[1667] The emotion engine analyzes the voice data in detail to determine the user's emotional state, for example, measuring stress levels based on the tone and speed of the voice.

[1668] Step 6:

[1669] The server generates advice for the user based on the results of the data analysis. Specifically,

[1670] Mental health advice: If you are experiencing high stress, we suggest relaxation techniques and meditation.

[1671] Physical health advice: If lack of exercise is detected, specific exercise and dietary suggestions will be provided.

[1672] Step 7:

[1673] The server sends the generated advice to the device, which then notifies the user. For example, the device displays a message on the smartphone screen saying, "Your stress is increasing. Try meditation."

[1674] Step 8:

[1675] The device receives feedback from the user and sends updated data back to the server, including the status of the proposed action.

[1676] Step 9:

[1677] The server continuously monitors the data and, if an abnormal condition persists for a certain period of time, will refer the user to a specialist or medical institution. For example, if the emotion engine detects high stress levels for three consecutive days, it will notify the user that "we recommend consulting a mental health professional."

[1678] Step 10:

[1679] The server generates and provides a comprehensive report on the user's health status, allowing the user to understand their long-term health status and take appropriate measures.

[1680] Example 2

[1681] 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."

[1682] In modern society, managing the mental and physical health of working people is becoming increasingly important. However, with busy daily schedules, it can be difficult to accurately understand one's own health status and take appropriate measures. Health problems caused by stress and lack of exercise are of particular concern. Conventional methods for addressing this issue can only respond based on limited data, making it difficult to provide comprehensive health management.

[1683] 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.

[1684] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the user, means for evaluating the emotional state and physical condition, means for detecting ongoing abnormalities, and means for referring the user to a specialist or medical institution when an abnormality is detected. This allows for precise management of the user's daily health condition, providing appropriate advice, and enabling early consultation with a specialist.

[1685] "Activity data" refers to data measuring the user's physical activity in their daily life, including the number of steps taken, heart rate, body temperature, and sleep time.

[1686] "Voice data" refers to voice information acquired when a user interacts with an AI assistant, etc., and includes information such as tone, speed, and rhythm.

[1687] "Artificial intelligence means" refers to machine learning models or other AI technologies used to analyze collected data and assess a user's health status.

[1688] "Emotional state" refers to the mental health status of a user as determined from their voice data, including stress levels and emotional fluctuations.

[1689] "Expert" refers to a medical or psychological professional who can assess the user's health status and provide necessary support or measures.

[1690] "Medical Institution" refers to an organization such as a hospital or clinic that provides diagnosis or treatment for a user's health condition.

[1691] "Advice generation means" refers to a function that creates healthcare advice appropriate for the user based on the analysis results obtained by the artificial intelligence means.

[1692] "Emotion engine" refers to technology that analyzes voice data to determine a user's stress level and emotional state.

[1693] "Escalation" refers to a function that encourages users to consult with a specialist or medical institution if their health condition is consistently abnormal.

[1694] "Health management" refers to the process of observing and assessing a user's mental and physical state and providing remedial measures as needed.

[1695] This invention relates to an AI healthcare system that synchronizes the mental and physical health of working people. The system collects and analyzes the user's daily activity data and voice data, and provides professional healthcare advice based on the results. Furthermore, by using an emotion engine that recognizes the user's emotions, it achieves more advanced mental healthcare.

[1696] System Configuration

[1697] 1. Data Collection Methods

[1698] The device uses a smartphone or wearable device to collect the user's daily activity data, including the number of steps taken, heart rate, body temperature, and sleep time. The user then interacts with the AI ​​assistant and provides voice data, which includes information such as the user's tone and speed.

[1699] 2. Data upload method

[1700] The device periodically sends the collected data to a server. For example, by uploading data every morning and evening, real-time health monitoring is possible. The transmitted data is encrypted and reaches the server via a secure communication channel.

[1701] 3. Data Analysis Methods

[1702] The server is equipped with artificial intelligence means for analyzing the received data. For the voice data, it uses an emotion engine to assess the user's emotional state, and for the activity data, it assesses the user's physical health status. This analysis is performed using machine learning models to identify the emotional state (e.g., stress level, tone changes) from the voice data and to detect fluctuations in health indicators from the activity data.

[1703] 4. Advice Generation Methods

[1704] Based on the analysis results, the server generates appropriate health improvement advice for the user. For mental health, it suggests stress management and relaxation methods, and for physical health, it suggests exercise and diet. For example, if the emotion engine detects that the user is in a high-stress state, it generates mental health advice such as "Try five minutes of meditation."

[1705] 5. Means of providing advice

[1706] The device then notifies the user of the generated advice. Smartphones and wearable devices provide real-time advice, allowing users to take immediate action. Notifications are provided via push notifications or voice assistants.

[1707] 6. Escalation Methods

[1708] If the server detects a persistent abnormality in the user, it will refer them to a specialist or medical institution. For example, if the emotion engine detects a high stress state for three consecutive days, it will notify the user to consult a mental health specialist. This escalation function allows users to take appropriate measures regarding their health condition early.

[1709] Specific examples

[1710] Example 1: Weekday status

[1711] 1. A user greets an AI assistant with "Good morning" in the morning.

[1712] 2. The device sends the collected voice data and the previous day's activity data to the server.

[1713] 3. The server analyzes the data, and the emotion engine detects rising stress levels from the voice data.

[1714] 4. The server generates the advice, "Your stress is increasing. Try 5 minutes of meditation."

[1715] 5. The device notifies the user of the advice.

[1716] Example 2: Weekend Situation

[1717] 1. The user sends the heart rate and sleep time measured by the wearable device to the server.

[1718] 2. The server analyzes the data and detects whether the user is getting enough sleep.

[1719] 3. The server generates the advice, "We recommend keeping things light today and getting plenty of rest."

[1720] 4. The device notifies the user of the advice.

[1721] In this way, by combining the emotion engine, it is possible to create a system that can more precisely manage the user's mental and physical health and support their overall well-being.

[1722] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1723] Step 1: Data collection

[1724] The device collects data about the user's daily activities.

[1725] Input: Sensor data from smartphones and wearable devices (step count, heart rate, body temperature, sleep time, etc.)

[1726] Output: Collected activity data

[1727] How it works: The smartwatch measures the user's steps and heart rate in real time and sends that data via Bluetooth to a smartphone, which collects additional data using GPS and accelerometers.

[1728] Users interact with the AI ​​assistant and provide voice data.

[1729] Input: User's voice (e.g., speaking to an AI assistant)

[1730] Output: Collected audio data

[1731] How it works: A user speaks into the smartphone microphone, and the audio data is recorded by the AI ​​assistant application. The audio file contains information about tone, speed, and pitch.

[1732] Step 2: Upload data

[1733] The terminal transmits the collected data to the server.

[1734] Input: Collected activity and voice data

[1735] Output: Data sent to the server

[1736] How it works: Your smartphone periodically uploads collected data to a server over Wi-Fi or mobile data networks. This data is encrypted and transmitted using a secure communication protocol.

[1737] Step 3: Data analysis

[1738] The server analyzes the transmitted data.

[1739] Input: Uploaded activity data and audio data

[1740] Output: Analysis results (emotional state, physical health assessment)

[1741] Specific operation: The server inputs the received data into the machine learning model and emotion engine for analysis. The emotion engine analyzes the voice data to evaluate stress levels and emotional changes. Activity data is used to evaluate fluctuations in exercise volume and health indicators. For example, the emotion engine detects signs of stress from changes in voice tone and speed.

[1742] Step 4: Advice Generation

[1743] The server generates advice based on the analysis results.

[1744] Input: Analysis results (emotional state, physical health assessment)

[1745] Output: Healthcare advice

[1746] Specific operation: The server generates appropriate healthcare advice based on the analysis results. For example, if the analysis result is "high stress level," the server generates the advice "try five minutes of meditation." If the result is "lack of exercise," the server generates the advice "we recommend a 20-minute walk."

[1747] Step 5: Providing advice

[1748] The terminal notifies the user of the generated advice.

[1749] Enter: Healthcare Advice

[1750] Output: Advice given to the user

[1751] What it does: The smartphone will display advice to the user through the notification system. For example, a push notification might say, "Your stress is increasing. Try meditation." The AI ​​assistant can also provide a voice alert.

[1752] Step 6: Escalation

[1753] If the server detects any persistent abnormalities in the user, it will refer them to a specialist or medical institution.

[1754] Input: Continuous abnormal condition detection

[1755] Output: Referral notification to specialists and medical institutions

[1756] Specific operation: The server continuously monitors the analysis results, and if an abnormality persists for a certain period of time (for example, high stress for three consecutive days), it generates a notification urging the user to consult a specialist. This notification is sent to the user via the smartphone notification system or email.

[1757] (Application example 2)

[1758] 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."

[1759] In conventional work environments, there has been no system for comprehensively managing and monitoring the mental and physical health of workers, and there has been a problem of workers' stress and fatigue not being properly managed, especially in factories. This can lead to reduced work efficiency and an increased risk of accidents, which can ultimately have a serious impact on workers' health. This invention aims to achieve both improved work efficiency and health management by monitoring workers' health status in real time and providing appropriate advice.

[1760] 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.

[1761] In this invention, the server includes means for acquiring activity data, means for acquiring voice data, artificial intelligence means for analyzing the acquired activity data and voice data, means for generating mental and physical health care advice based on the analysis results, means for providing the advice to the worker, and means for automatically prompting the worker to contact a specialist if an abnormality is detected. This allows the worker's health condition to be monitored in real time, and appropriate action to be taken immediately if an abnormality is detected.

[1762] The "means for acquiring activity data" refers to a device or system for collecting information on a worker's physical activities, such as the number of steps taken, heart rate, and working hours.

[1763] The "means for acquiring voice data" refers to a device or system for picking up and collecting conversations with workers and voice instructions.

[1764] "Artificial intelligence means" refers to computational algorithms or programs that analyze collected activity data and voice data and assess the mental and physical health status of workers.

[1765] The "means for generating healthcare advice" is a device or system for proposing health improvement measures and relaxation methods to a worker based on the analysis results using artificial intelligence means.

[1766] A "means for providing advice to a worker" is a device or system for notifying or presenting the generated healthcare advice to a worker.

[1767] "Means for automatically encouraging contact with an expert when an abnormality is detected" refers to a device or system that automatically encourages contact with an expert or medical institution when an abnormality is continuously detected in a worker's health condition.

[1768] The "means for assessing the worker's emotional state" is a device or system for analyzing the voice data and determining the worker's emotional state (e.g., stress level).

[1769] This invention relates to a system for monitoring and managing the mental and physical health of workers in factories in real time. This system collects and analyzes worker activity data and voice data, and provides health care advice based on the results.

[1770] System Overview

[1771] The system consists of the following main components:

[1772] 1. Data collection methods:

[1773] Use a wearable device (e.g., Apple Watch, Fitbit) to collect activity data.

[1774] Use a voice input device and a robotic assistant (e.g., Pepper) to collect voice data.

[1775] 2. Data upload method:

[1776] The collected data is sent to the server at regular intervals and stored in an AWS S3 bucket.

[1777] 3. Data analysis methods:

[1778] We use server-side artificial intelligence tools (e.g., Google Speech-to-Text API, IBM Watson Tone Analyzer, TensorFlow) to analyze activity data and voice data. Voice data is converted to text using Google Speech-to-Text API, and sentiment analysis is performed using IBM Watson Tone Analyzer. Activity data is analyzed using machine learning models using TensorFlow.

[1779] 4. Advice Generation Methods:

[1780] Based on the analysis results, specific health improvement advice (e.g., stretching and relaxation methods) is generated for the worker.

[1781] 5. Advice delivery methods:

[1782] Using Firebase, notifications are sent in real time directly from workers' smartphones or robot assistants.

[1783] 6. Escalation Methods:

[1784] If a persistent abnormality is detected, a notification will be automatically sent based on the abnormal data, prompting the user to contact a specialist or medical institution.

[1785] Example

[1786] On weekdays, worker A working in the factory uses the system in the following way.

[1787] 1. Data Collection:

[1788] Worker A wears a wearable device, which collects activity data such as heart rate and number of steps in real time.

[1789] The robot assistant and worker A have a short conversation, and the audio data is recorded.

[1790] 2. Data upload:

[1791] Collected activity and audio data is uploaded to an AWS S3 bucket every hour.

[1792] 3. Data Analysis:

[1793] The server converts the audio data into text using the Google Speech-to-Text API and performs sentiment analysis using IBM Watson Tone Analyzer.

[1794] Activity data is analyzed using TensorFlow to assess physical health status.

[1795] 4. Advice Generation:

[1796] If the server analyzes that the stress level is high, it generates advice to suggest relaxation methods (e.g., deep breathing).

[1797] 5. Providing advice:

[1798] The advice generated by the server is sent to worker A's smartphone and robot assistant via Firebase.

[1799] A message appears on Worker A's smartphone saying, "Your stress is increasing. Try taking some deep breaths."

[1800] Prompt Sentence Examples

[1801] "Analyze my stress level based on this morning's heart rate data and yesterday's work hours data."

[1802] "Please evaluate the emotional state of worker C from his / her voice data and generate stress advice."

[1803] A system configured in this way allows for real-time management of workers' health conditions, and if any abnormalities are detected, appropriate action can be taken immediately.

[1804] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1805] Step 1:

[1806] The terminal collects the worker's activity data (e.g., number of steps, heart rate, working hours) through a wearable device. The input is the activity information obtained from the wearable device, and the output is the collected activity data. Specifically, the terminal updates the data using Bluetooth communication and records it in its internal storage.

[1807] Step 2:

[1808] The terminal collects voice data through dialogue with the robot assistant. The input is the worker's voice, and the output is the captured voice data. The robot assistant periodically asks the worker questions and captures their answers with a voice sensor.

[1809] Step 3:

[1810] The device uploads the collected activity data and voice data to the server at regular intervals. The input is the data stored on the device, and the output is the data stored in the server's database. Specifically, the device uses an internet connection to send the data to an AWS S3 bucket.

[1811] Step 4:

[1812] The server converts the uploaded audio data into text data using the Google Speech-to-Text API. The input is audio data and the output is text data. The server makes an API call to convert the audio file into text format.

[1813] Step 5:

[1814] The server performs sentiment analysis on the text data using IBM Watson Tone Analyzer. The input is text data, and the output is an evaluation of the emotional state (e.g., stress level). The server sends the text data to the sentiment engine and receives the analysis results.

[1815] Step 6:

[1816] The server inputs the activity data into a machine learning model using TensorFlow to evaluate the physical health status. The input is the activity data, and the output is the physical status evaluation result. The server feeds the data to the model and records the output.

[1817] Step 7:

[1818] The server generates healthcare advice for the worker based on the analysis results. The input is the emotional state and physical health assessment results, and the output is a specific advice message. The server creates advice using a predefined template.

[1819] Step 8:

[1820] The server generates advice and notifies the worker's device using Firebase. The input is the advice message, and the output is the advice displayed on the worker's smartphone or robot assistant. The server sends messages in real time via the notification system.

[1821] Step 9:

[1822] If the server detects a persistent anomaly, it automatically sends a notification urging the user to contact an expert. The input is the abnormal data, and the output is a notification recommending consultation with an expert. The server runs an anomaly detection algorithm and sends an escalation notification if the anomaly persists.

[1823] The above are the specific processing steps of the system for carrying out the invention.

[1824] 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.

[1825] 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.

[1826] 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.

[1827] 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.

[1828] 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.

[1829] 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.

[1830] 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).

[1831] 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.

[1832] 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."

[1833] 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.

[1834] 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).

[1835] 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.

[1836] 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.

[1837] 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.

[1838] 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.

[1839] 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.

[1840] 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.

[1841] 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.

[1842] 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.

[1843] 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.

[1844] 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.

[1845] The following is further disclosed regarding the above embodiment.

[1846] (Claim 1)

[1847] a means for acquiring activity data;

[1848] means for acquiring audio data;

[1849] artificial intelligence means for analyzing the acquired activity data and audio data;

[1850] means for generating mental and physical health care advice based on the analysis results;

[1851] means for providing said advice to a user;

[1852] A system including:

[1853] (Claim 2)

[1854] a means of detecting persistent user anomalies;

[1855] A means of referring patients to specialists or medical institutions depending on the abnormalities detected;

[1856] The system of claim 1 further comprising:

[1857] (Claim 3)

[1858] 10. The system of claim 1, further comprising means for assessing an emotional state of the user based on the audio data.

[1859] "Example 1"

[1860] (Claim 1)

[1861] a means for acquiring activity data;

[1862] means for acquiring audio data;

[1863] means for transmitting the acquired activity data and voice data to a server at a predetermined time;

[1864] means for analyzing the transmitted data using artificial intelligence;

[1865] a means for generating mental and physical healthcare advice based on the analysis results;

[1866] means for notifying a user of said advice;

[1867] A system including:

[1868] (Claim 2)

[1869] a means of detecting persistent user anomalies;

[1870] A means of referring patients to specialists or medical institutions depending on the abnormalities detected;

[1871] The system of claim 1 further comprising:

[1872] (Claim 3)

[1873] 10. The system of claim 1, further comprising means for assessing an emotional state of the user based on the audio data.

[1874] "Application Example 1"

[1875] (Claim 1)

[1876] a means for acquiring activity data;

[1877] means for acquiring audio data;

[1878] artificial intelligence means for analyzing the acquired activity data and audio data;

[1879] means for generating mental and physical health care advice based on the analysis results;

[1880] means for providing said advice to a user;

[1881] If the user's physical or mental condition falls below a certain standard, the system will detect abnormal conditions and refer them to specialists or medical institutions.

[1882] A system including:

[1883] (Claim 2)

[1884] 10. The system of claim 1, further comprising means for notifying a user of said healthcare advice in real time.

[1885] (Claim 3)

[1886] means for assessing the emotional state of the user based on the audio data;

[1887] A means to periodically provide users with advice generated based on their daily activity data and voice data;

[1888] 10. The system of claim 1, further comprising means for storing historical advice delivery data and for improving advice accuracy based on ongoing analysis.

[1889] "Example 2: Combining Emotion Engines"

[1890] (Claim 1)

[1891] a means for acquiring activity data;

[1892] means for acquiring audio data;

[1893] artificial intelligence means for analyzing the acquired activity data and audio data;

[1894] means for generating mental and physical health care advice based on the analysis results;

[1895] means for providing said advice to a user;

[1896] a means of assessing emotional and physical state;

[1897] a means for detecting persistent anomalies;

[1898] A means of referring patients to specialists and medical institutions in the event of an emergency,

[1899] A system including:

[1900] (Claim 2)

[1901] 10. The system of claim 1, wherein the system accumulates daily activity data of a user.

[1902] (Claim 3)

[1903] 10. The system of claim 1, further comprising means for finely analyzing the tone, rate, and rhythm of the voice.

[1904] "Application example 2 when combining emotion engines"

[1905] (Claim 1)

[1906] a means for acquiring activity data;

[1907] means for acquiring audio data;

[1908] artificial intelligence means for analyzing the acquired activity data and audio data;

[1909] means for generating mental and physical health care advice based on the analysis results;

[1910] means for providing said advice to a worker;

[1911] A means to automatically prompt contact with experts when an abnormality is detected,

[1912] A system including:

[1913] (Claim 2)

[1914] The system of claim 1, which continuously monitors the patient's health after surgery and refers them to a specialist or medical institution if any abnormalities are found.

[1915] (Claim 3)

[1916] 10. The system of claim 1, further comprising means for assessing the worker's emotional state based on the audio data. [Explanation of symbols]

[1917] 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 activity data; means for acquiring audio data; artificial intelligence means for analyzing the acquired activity data and audio data; means for generating mental and physical health care advice based on the analysis results; means for providing said advice to a user; A system including:

2. a means of detecting persistent user anomalies; A means of referring patients to specialists or medical institutions depending on the abnormalities detected; The system of claim 1 further comprising:

3. 10. The system of claim 1, further comprising means for assessing the emotional state of the user based on the audio data.

Images