System

Abstract

A system is provided.SOLUTION: A system for monitoring a mental and physical condition of a user, comprising: means for collecting facial expression data and vocal tone data through a camera and a microphone of an electronic device of the user; means for acquiring a frequency and a time of a meeting; means for acquiring a quantity and content of communication of the user; means for preprocessing data obtained by the collecting means and the acquiring means; means for analyzing the preprocessed data and recognizing a change related to the mental and physical condition of the user; and means for providing advice to the user based on the change.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] ---

[0005] In today's work environment, maintaining employees' physical and mental health is important, but in many cases, employees themselves find it difficult to notice changes in their own health or stress levels. Furthermore, effective measures for companies to properly manage their employees' mental health are limited. As a result, mental health problems can worsen, leading to long-term absences and reduced work efficiency. Therefore, there is a need for a system that can detect changes in employees' physical and mental health at an early stage and take appropriate measures. [Means for solving the problem]

[0006] The present invention relates to a system for monitoring a user's mental and physical state and proposing appropriate measures. Specifically, it includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, and means for acquiring the amount and content of the user's communication. It also provides means for preprocessing the data acquired by these collecting and acquiring means, and means for analyzing the preprocessed data to recognize changes in the user's mental and physical state. It also includes means for providing advice to the user based on the recognized changes. This system enables early detection of changes in mental and physical state that the user may not notice, allowing for appropriate refreshment and work adjustments.

[0007] ---

[0008] ---

[0009] "User" refers to an individual or organization that uses this system.

[0010] "Electronic devices" refers to data processing devices such as computers, smartphones, tablets, etc.

[0011] A "camera" is an image capturing device installed in an electronic device and is used to record the user's facial expressions and movements.

[0012] A "microphone" is a sound capture device installed in electronic devices and is used to record the user's voice and surrounding sounds.

[0013] "Facial expression data" refers to information that indicates the user's facial features and emotional state obtained through a camera.

[0014] "Voice Data" refers to information obtained through a microphone that indicates the tone, volume, tempo, and emotional nuances of a user's voice.

[0015] "Meeting frequency and duration" refers to the number of meetings a user participates in and the duration of each meeting.

[0016] "Amount and content of communication" refers to the number of messages and emails sent and received by the user and their content.

[0017] "Preprocessing" refers to the initial processing of acquired data to convert it into an analyzable form.

[0018] "Analysis" refers to the process of using pre-processed data to extract information and changes about the user's physical and mental state.

[0019] "Change recognition" refers to identifying significant changes from a user's normal state as a result of data analysis.

[0020] "Advice" refers to actions or measures suggested to the user based on a perceived change.

[0021] "Pop-up notification" refers to a visual notification that appears on the user's screen.

[0022] "Voice assistant" refers to software or devices that provide information or advice to users via voice.

[0023] "Manual input" refers to the act of a user manually reporting their physical and mental state and emotions. [Brief explanation of the drawings]

[0024] [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

[0025] 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.

[0026] First, the terms used in the following description will be explained.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] [First embodiment]

[0033] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0034] 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.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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."

[0045] ---

[0046] The present invention provides a system for monitoring a user's physical and mental state and proposing appropriate measures. This system operates on the user's electronic device (e.g., a computer, a smartphone, a tablet, etc.). Specific embodiments of this system are described in detail below.

[0047] In one embodiment of this system, the user first installs the application on their electronic device. After installation, the user enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the system is first launched. This information is used as the user's baseline data.

[0048] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[0049] The collected facial expression data and vocal tone data are pre-processed on the electronic device. In the pre-processing, the video data is passed through a facial recognition algorithm to extract facial features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[0050] The preprocessed data is sent to a server, which analyzes it in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns.

[0051] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expression indicating fatigue through the camera and a decrease in the tone of their voice through the microphone are collected. The server analyzes this data and determines whether the user is excessively tired.

[0052] Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice via a pop-up notification on the PC screen or a voice assistant.

[0053] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and manually report their state of mind. A pop-up will appear periodically, prompting users to enter their current mood and fatigue level.

[0054] This allows the system to effectively monitor the user's physical and mental state and propose appropriate measures. Users can quickly recognize physical and mental stress that they may not notice themselves, and by taking appropriate measures to refresh themselves and adjust their work, they can prevent mental disorders and make it easier to maintain motivation.

[0055] ---

[0056] The processing flow will be explained below.

[0057] ---

[0058] Step 1:

[0059] The user installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves in a questionnaire form that appears when the application is first launched.

[0060] Step 2:

[0061] The device activates the user's camera and microphone. It requires the user's permission and starts operation after receiving permission.

[0062] Step 3:

[0063] The device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner positions, etc.).

[0064] Step 4:

[0065] The device collects voice data via a microphone, including the tone, pitch, speed and emotional nuances of the user's voice.

[0066] Step 5:

[0067] The device obtains the frequency and duration of meetings. It connects with the APIs of calendar and meeting apps to collect the number of meetings and the duration of each meeting.

[0068] Step 6:

[0069] The device collects data on the volume and content of user communications. Data is collected to analyze the number of chats and emails sent and received and the tone of the content.

[0070] Step 7:

[0071] The facial expression data collected by the device is preprocessed, and the video data is passed through a facial recognition algorithm to extract facial expression features.

[0072] Step 8:

[0073] The device preprocesses the collected voice data, then passes the voice data through an emotion analysis algorithm to extract emotional features.

[0074] Step 9:

[0075] The device sends the preprocessed data to the server, which includes facial expression features, tone of voice features, frequency and duration of meetings, and the amount and tone of communication.

[0076] Step 10:

[0077] The server analyzes the received data in real time and identifies significant changes in facial expression (for example, a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[0078] Step 11:

[0079] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[0080] Step 12:

[0081] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[0082] Step 13:

[0083] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[0084] Step 14:

[0085] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[0086] Step 15:

[0087] Based on the changes the server recognizes, it generates specific advice for the user, such as "You have a series of back-to-back meetings. We recommend you take a five-minute break."

[0088] Step 16:

[0089] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[0090] Step 17:

[0091] Users can configure privacy settings, disable constant camera and microphone monitoring, and manually report their status. A pop-up periodically appears, prompting users to enter their current mood and fatigue level.

[0092] ---

[0093] Example 1

[0094] 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."

[0095] Conventional mental healthcare systems have struggled to closely monitor users' physical and mental conditions in real time and provide appropriate advice. Furthermore, they lacked mechanisms for collecting and analyzing data while respecting users' privacy. As a result, it was difficult for users to become aware of their own health conditions early and take appropriate measures.

[0096] 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.

[0097] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for transmitting the preprocessed data to the server, means for analyzing the transmitted data in real time and recognizing changes in the user's mental and physical state, and means for providing advice to the user based on the recognized changes. This makes it possible to monitor the user's mental and physical state in detail and in real time and provide appropriate advice. Furthermore, data can be collected and analyzed while respecting the user's privacy.

[0098] A "user" is an individual who uses this system.

[0099] "Physical and mental health" refers to the user's mental and physical health.

[0100] "Electronic devices" are devices used by users, such as computers, smartphones, and tablets.

[0101] "Camera and microphone" means a device that collects video and audio built into or connected to an electronic device.

[0102] "Facial expression data" is information on the user's facial movements and expressions collected using a camera.

[0103] "Voice data" refers to voice information such as the tone, pitch, and speed of a user's voice collected using a microphone.

[0104] A "means" is a device, software, algorithm, or method for achieving a particular function or purpose.

[0105] "Meeting frequency and duration" refers to the number of meetings a user participates in and the duration of each meeting.

[0106] "Amount and content of communication" refers to the number of communications a user makes and the detailed content of those communications.

[0107] "Preprocessing" is the process of shaping or transforming the raw data collected into a form suitable for analysis.

[0108] A "server" is a computer system that processes and stores data and communicates with users' electronic devices over a network.

[0109] "Real-time analysis" means processing data as soon as it is received and providing an immediate assessment of the user's situation.

[0110] "Recognizing changes" refers to comparing past data with current data to determine whether a significant change has occurred in the user's physical or mental state.

[0111] "Providing advice" means notifying the user of measures or recommendations based on the analysis results.

[0112] MODE FOR CARRYING OUT THE INVENTION

[0113] System Overview

[0114] The present invention is a system for monitoring a user's physical and mental state and proposing appropriate measures. This system is based on an application installed on the user's electronic device (e.g., computer, smartphone, tablet).

[0115] Hardware and software used

[0116] Electronic devices: computers, smartphones, tablets, etc.

[0117] Camera: an image-collecting device built into or connected to an electronic device

[0118] microphone: a sound-collecting device built into or connected to an electronic device

[0119] Face recognition library: OpenCV

[0120] Voice emotion recognition tools: Sentiment analysis algorithms (such as IBM Watson®)

[0121] Data transmission protocol: HTTPS

[0122] Program processing flow

[0123] When a user installs the application on their device, a questionnaire form is displayed the first time they start it. This form asks questions about the user's mental health, the type and workload of their work, and how they take breaks and refresh themselves, and this information is used as baseline data.

[0124] The device uses a camera and microphone to collect data in real time as the user performs their tasks: the camera captures key facial features (e.g., eye movements, mouth corner position), and the microphone records the tone, pitch, speed, and emotional nuances of the voice.

[0125] The device preprocesses the collected facial and vocal data, specifically using the OpenCV library for facial recognition and feature extraction, and for the voice data, it uses IBM Watson's voice emotion recognition tool to calculate an emotion score (e.g., 50% joy, 10% anger).

[0126] Data transmission and processing on the server

[0127] The pre-processed data is periodically sent to a server, which analyzes the data in real time to detect changes in the user's physical and mental state. Specifically, it evaluates the following:

[0128] Detecting user stress levels and emotional fluctuations from changes in facial expressions and tone of voice

[0129] Determine workload based on meeting volume and communication patterns

[0130] Advice Generation and Notifications

[0131] The server generates appropriate advice based on the analysis results, which is then sent to the device and notified to the user via a pop-up notification or voice assistant.

[0132] Specific examples

[0133] For example, if a user is continuously participating in online meetings for a long period of time, the device will record the frequency and duration of the meetings, the camera will detect fatigue from the user's facial expressions, and the microphone will capture a drop in the tone of their voice. The server will analyze this data and generate advice such as "You've been in a lot of meetings today. We recommend you take a five-minute break," and the device will notify the user.

[0134] Example prompt sentence:

[0135] What advice will the system give if a user is in an online meeting for three consecutive hours?

[0136] How can cameras and microphones be used to gather stress indicators for long work hours?

[0137] Privacy Settings

[0138] If users value privacy, they can disable constant camera and microphone monitoring and manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[0139] This allows the system to effectively monitor the user's physical and mental state and suggest appropriate measures, making it easier for the user to maintain their health.

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

[0141] Step 1: User installs the application

[0142] Description: A user installs an application on their electronic device (computer, smartphone, tablet, etc.). This installation process is done through an official website or app store.

[0143] Input: User's electronic device

[0144] Output: Installed applications

[0145] Step 2: Fill out the initial survey form

[0146] Description: When a user launches the application for the first time, a questionnaire form is displayed. The user enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves. This data is used as baseline data and will be the basis for future analysis.

[0147] Input: User's own mental health status, type and workload of work, methods of rest and refreshment

[0148] Output: Baseline data

[0149] Step 3: Data Collection (Camera and Microphone)

[0150] Description: The device uses a camera and microphone to collect data in real time as the user goes about their daily tasks. The camera captures key facial features (eye movements, mouth corner position, etc.), and the microphone records the tone, pitch, speed, and emotional nuances of the user's voice.

[0151] Input: Real-time video and audio data

[0152] Output: Raw facial expression data, voice data

[0153] Step 4: Preprocessing the data

[0154] Description: The device preprocesses the collected facial expression and voice data. Specifically, it uses the OpenCV library to perform facial recognition and extract feature points. For voice data, it also uses IBM Watson's voice emotion recognition tool to extract emotional features.

[0155] Input: Raw facial expression data, voice data

[0156] Output: Preprocessed facial expression feature data, emotion feature data

[0157] Specific operation:

[0158] Using OpenCV, the positions of eyes and mouth corners are detected from video data.

[0159] Calculates emotion scores from voice data using IBM Watson

[0160] Step 5: Sending data to the server

[0161] Description: The device periodically sends pre-processed data to the server using a secure protocol (e.g. HTTPS).

[0162] Input: Preprocessed facial expression feature data, emotion feature data

[0163] Output: Data sent to the server

[0164] Step 6: Data analysis by the server

[0165] Description: The server analyzes the received data in real time and recognizes changes in the user's physical and mental state. Specifically, it detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determines workload from the number of meetings and communication patterns.

[0166] Input: Preprocessed facial expression feature data, emotion feature data

[0167] Output: Evaluation results of the user's mental and physical state

[0168] Specific operation:

[0169] Evaluate changes in stress levels by comparing with past data stored in a database

[0170] Analyze meeting duration and frequency to calculate workload

[0171] Step 7: Advice generation and notification

[0172] Description: The server generates appropriate advice based on the analysis results and sends it to the device, which then communicates this advice to the user via a pop-up notification or voice assistant.

[0173] Input: Evaluation results of the user's mental and physical state

[0174] Output: Advice notice to user

[0175] Specific operation:

[0176] Generate notification messages such as "You've had a lot of meetings today. We suggest you take a 5-minute break."

[0177] Notify users via pop-ups or voice assistants

[0178] Step 8: Change your privacy settings

[0179] Description: If the user values ​​privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting that allows the user to manually report their status. A pop-up will appear periodically, prompting the user to enter their current mood and fatigue level.

[0180] Input: User privacy settings, manually entered mood and fatigue levels

[0181] Output: Updated user data and privacy settings

[0182] Specific operation:

[0183] In the Privacy Settings menu, select "Disable camera and microphone monitoring"

[0184] A popup for manual input appears, allowing the user to enter their mood and fatigue level.

[0185] (Application example 1)

[0186] 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."

[0187] Conventional in-vehicle driver physical and mental state monitoring systems lack the technology to properly detect driver fatigue and stress and provide the driver with countermeasures in real time. Furthermore, they are unable to automatically switch the vehicle's driving mode based on the driver's physical and mental state, making it difficult to ensure the driver's safety and comfort. To solve these problems, a system is needed that precisely monitors the driver's physical and mental state and provides advice at the appropriate time.

[0188] 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.

[0189] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for analyzing the preprocessed data and recognizing changes in the user's mental and physical state, means for providing advice to the user based on the changes, means for collecting facial expression data and voice data of the driver in the vehicle and monitoring the driver's mental and physical state, and means for switching driving modes based on the driver's mental and physical state. This makes it possible to precisely monitor the driver's mental and physical state and provide appropriate advice in real time, thereby ensuring the driver's safety and comfort.

[0190] The "system for monitoring the user's mental and physical state" is a mechanism for monitoring the user's mental and physical state by collecting and analyzing the user's facial expression data and tone of voice data.

[0191] "Electronic devices" is a general term for devices capable of collecting and processing digital data, such as personal computers, tablets, smartphones, and head-mounted displays.

[0192] A "camera" is a device that captures image data or video data.

[0193] A "microphone" is a device for collecting audio data.

[0194] "Facial expression data" refers to data about the features and movements of a user's face, acquired through a camera.

[0195] "Vocal timbre data" is data obtained through a microphone regarding the tone, pitch, rate, and emotional nuances of a user's voice.

[0196] "Data preprocessing" refers to a series of processes for converting acquired data into a format that is easy to analyze.

[0197] "Analysis" is the process of using pre-processed data to evaluate the user's physical and mental state and recognize changes in it.

[0198] "Means for providing advice" refers to a mechanism for suggesting appropriate actions or breaks to users based on the analysis results.

[0199] "Driving mode" refers to a mode that indicates how a vehicle is driven, and includes an automatic driving mode and a manual driving mode.

[0200] "Means for collecting facial expression data and voice data of the driver inside the vehicle" refers to a mechanism for collecting the driver's facial expressions and voice using a camera and microphone installed in the vehicle.

[0201] The "means for switching driving modes based on the user's physical and mental state" is a mechanism for automatically changing the driving mode of a vehicle in accordance with collected data on the user's physical and mental state.

[0202] The present invention is a system for monitoring the mental and physical state of a driver, switching the driving mode of a vehicle based on the state, and providing appropriate advice. The system is configured as follows.

[0203] First, the user installs the system in the vehicle. After installation, the head-mounted display (HMD) and in-car microphone are set up, and the system is ready to collect the driver's facial expression data and voice data.

[0204] While driving, the system collects facial expression data from the driver using a camera attached to the HMD, and collects audio data through an in-car microphone. The collected facial expression data includes key facial features such as eye movements and the position of the corners of the mouth, while the audio data includes tone, pitch, speed, and emotional nuances of the voice.

[0205] Once the data is collected, the device's software preprocesses it. This includes running the video data from the camera through a facial recognition algorithm (e.g., OpenCV) to extract facial features, and it also includes running the audio data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features.

[0206] The preprocessed data is sent to a server, which then analyzes the driver's physical and mental state in real time. The server detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. For example, if the server's analysis determines that the driver is feeling fatigued or stressed, the system will suggest that the driver take a break.

[0207] Furthermore, if a car is equipped with an autonomous driving function, it can automatically switch to autonomous driving mode depending on the driver's physical and mental state, ensuring safe driving even when the driver is fatigued.

[0208] The notification method is to provide advice to the driver through a pop-up notification or voice assistant, for example, "The system has detected that the driver has been driving continuously for a long period of time, so it is recommended that you take a five-minute break."

[0209] Furthermore, if the driver is concerned about privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting where the driver can manually report their condition. For example, a pop-up will appear periodically, and the driver can input their "current mood and fatigue level," and the system can provide advice based on that information.

[0210] As a concrete example, a prompt using a generative AI model could be, "If a driver has been driving for a long time and is fatigued, how can we use the autonomous driving function to suggest a break?"

[0211] In this way, the system is able to precisely monitor the driver's physical and mental state and provide appropriate advice in real time, providing a safe and comfortable driving environment.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] The device sets up a camera and microphone on the user's electronic device and starts collecting the driver's facial expression data and voice data. The camera captures key features of the driver's face (e.g., eye movements, position of the corners of the mouth, etc.), and the microphone records the driver's voice data (tone, pitch, speed, emotional nuances). The input is the camera image and voice data, and the output is the collected facial expression data and voice data.

[0215] Step 2:

[0216] The device passes the collected facial expression data through a facial recognition algorithm (e.g., OpenCV) to extract facial expression features. It also passes the voice data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features. The input is the facial expression data and voice data collected in step 1, and the output is the facial expression data and voice data from which features have been extracted.

[0217] Step 3:

[0218] The device sends the preprocessed data (facial expression data and voice data from which features have been extracted) to the server. The server receives this data in real time and starts analysis according to the situation. The input is the facial expression data and voice data from which features have been extracted, and the output is the preprocessed data sent to the server.

[0219] Step 4:

[0220] The server analyzes the driver's physical and mental state in real time based on the received data. Specifically, it detects the driver's stress level and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. The input is preprocessed data, and the output is the driver's physical and mental state and any changes therein.

[0221] Step 5:

[0222] Based on the analysis results, the server generates advice for the driver to take a break and sends it to the terminal. For example, a notification may be created in the form of, "The driver has been driving continuously for a long period of time, so we recommend that you take a five-minute break." The input is the results regarding the driver's physical and mental state and any changes therein, and the output is advice to the driver.

[0223] Step 6:

[0224] The terminal notifies the driver of the advice provided by the server. Notification methods include pop-up notifications and voice assistants. Advice such as suggestions for taking a break is displayed to the driver at appropriate times. The input is the advice sent from the server, and the output is the advice notified to the driver.

[0225] Step 7:

[0226] The terminal also has a means for automatically switching to autonomous driving mode depending on the driver's physical and mental state. If the system determines that the driver is excessively fatigued, a command to switch to autonomous driving mode is sent from the terminal to the vehicle's control device. The input is the decision to switch to autonomous driving based on the driver's physical and mental state, and the output is the vehicle being switched to autonomous driving mode.

[0227] 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.

[0228] ---

[0229] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[0230] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[0231] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[0232] The collected facial expression and tone data are pre-processed on the device. In pre-processing, the video data is passed through a facial recognition algorithm to extract facial expression features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[0233] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns. This is where the emotion engine plays an important role.

[0234] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[0235] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expressions indicating fatigue through the camera and a decrease in the tone of their voice through the microphone is collected. Furthermore, the emotion engine uses this data to accurately recognize the user's fatigue and stress.

[0236] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen or a voice assistant.

[0237] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and switch to a setting where they can manually report their state of mind: periodically, a pop-up appears, prompting the user to enter their current mood and fatigue level.

[0238] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[0239] ---

[0240] The processing flow will be explained below.

[0241] ---

[0242] Step 1:

[0243] The user installs the application on their electronic device and enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched.

[0244] Step 2:

[0245] The device will ask the user for permission to use the camera and microphone, and if the user grants permission, will activate these devices.

[0246] Step 3:

[0247] While the user is working, the device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner position, etc.).

[0248] Step 4:

[0249] At the same time, the device collects voice data through the microphone, including the user's voice tone, pitch, speed and emotional nuances.

[0250] Step 5:

[0251] The device connects to the API of the calendar or meeting app to obtain data on the frequency and duration of meetings.

[0252] Step 6:

[0253] The device collects the number and content of the user's chat and email communications, and collects the volume and tone of communication.

[0254] Step 7:

[0255] The facial expression data collected by the device is preprocessed and passed through a facial recognition algorithm to extract facial features.

[0256] Step 8:

[0257] The voice data collected by the device is preprocessed and passed through an emotion analysis algorithm to extract emotional features.

[0258] Step 9:

[0259] The device sends the preprocessed data to the server, which includes facial expression features, vocal tone features, meeting frequency and duration, and communication volume and tone.

[0260] Step 10:

[0261] The server analyzes the received data in real time and identifies significant changes in facial expression (e.g., a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[0262] Step 11:

[0263] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[0264] Step 12:

[0265] The server uses an emotion engine to recognize the user's emotion from the facial expression data and tone of voice data, for example, if the emotion is classified as "sadness" or "fatigue", the server generates the data.

[0266] Step 13:

[0267] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[0268] Step 14:

[0269] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[0270] Step 15:

[0271] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[0272] Step 16:

[0273] Based on the changes and emotion data recognized by the server, the server generates specific advice for the user, such as "You have a series of consecutive meetings. We recommend you take a five-minute break."

[0274] Step 17:

[0275] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[0276] Step 18:

[0277] Users can adjust their privacy settings to disable constant camera and microphone monitoring, and can manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[0278] ---

[0279] Following this step, the system can effectively monitor changes in the user's physical and mental state and emotions and suggest appropriate measures.

[0280] Example 2

[0281] 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."

[0282] Conventional systems face the challenge of effectively monitoring a user's physical and mental state and providing appropriate measures based on that information. In particular, there is a lack of means to accurately assess a user's stress and fatigue by collecting and analyzing facial expression and tone of voice data in real time. Furthermore, there is a need for a method to collect the necessary data while ensuring user privacy.

[0283] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via a photographing device and a voice input device of the user's electronic device, means for acquiring the frequency and duration of communication, and means for acquiring the amount and content of the user's communication. This makes it possible to recognize changes in the user's mental and physical state in real time and provide appropriate countermeasures. In addition, the server is equipped with a data collection means for evaluating emotions and a means for evaluating workload, making it possible to accurately recognize the user's accurate emotional state and workload. Combining these means makes it possible to effectively manage the user's mental health and prevent excessive stress and fatigue.

[0284] "User's Electronic Device" refers to electronic devices used by a User, such as a computer, smartphone, or tablet.

[0285] "Photography device" refers to a video input device such as a camera or webcam installed in an electronic device.

[0286] "Audio input device" refers to a microphone or audio collection device installed in an electronic device.

[0287] "Facial expression data" refers to digital information obtained from key facial features of a user and is used to assess emotions and stress levels.

[0288] "Voice data" refers to digital information derived from the tone, pitch, rate and emotional nuances of a user's voice, which is used to assess emotions and stress levels.

[0289] "Frequency of communication" refers to the number of communications a user makes using an electronic device.

[0290] "Communication time" refers to the total time a user communicates using an electronic device.

[0291] "Volume of communication" refers to the amount of data a user sends and receives via electronic devices.

[0292] "Content of communication" refers to the specific content and nature of the communication a user makes through an electronic device.

[0293] "Preprocessing" refers to the process of converting collected raw data into an analyzable format, including feature extraction and data shaping.

[0294] "Preprocessed data" refers to data that has been converted into an analyzable format by preprocessing.

[0295] "User's physical and mental state" refers to the user's mental and physical health, including emotions, stress, fatigue, etc.

[0296] "Measures" refers to advice and guidelines provided to improve a user's physical or mental condition.

[0297] A "pop-up notification" refers to a message window that suddenly appears on the screen of an electronic device.

[0298] "Audio output device" refers to an audio output device such as a speaker or a headphone that is installed in an electronic device.

[0299] "Means for assessing emotions" refers to algorithms or processes that use facial expression data and tone of voice data to recognize and assess a user's emotional state.

[0300] "Means for assessing workload" refers to the process of analyzing data such as a user's work history and the frequency, time, and content of communications to assess the workload level.

[0301]

[0302] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[0303] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[0304] Next, data is collected using the user's camera and voice input devices. While the user is working using a PC or smartphone, facial expression data is collected through the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected through the voice input device. This voice tone data includes the user's voice tone, pitch, speed, and emotional nuances.

[0305] The collected facial expression data and vocal tone data are pre-processed on the device. During pre-processing, the video data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib) to extract facial expression features. The audio data is passed through an emotion analysis algorithm (e.g., Google® Speech API, Azure® Cognitive Services) to extract emotional features.

[0306] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in the frequency, time, volume, and content of communication. This is where the emotion engine plays an important role.

[0307] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[0308] As a concrete example, consider the case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as whether the user's facial expression indicates fatigue through a camera device and whether the tone of their voice is declining through a voice input device is collected. Based on this data, the emotion engine recognizes the user's fatigue and stress with high accuracy.

[0309] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen and an audio output device.

[0310] Furthermore, if users value privacy, they can disable the continuous monitoring of the camera and audio input devices and switch to a setting where they can manually report their condition by entering their current mood and fatigue level in a pop-up that appears periodically.

[0311] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[0312] Examples of prompts for generative AI models include:

[0313] "Please explain in detail how the system detects user fatigue and suggests appropriate breaks when the user is participating in long, continuous online meetings. Please also include the collection method for facial expression and tone of voice data, pre-processing steps, real-time analysis process, and specific notification methods."

[0314] Based on this prompt, a more detailed understanding can be gained by referring to the explanation provided by the generative AI model.

[0315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0316] Step 1:

[0317] A user installs an application on an electronic device (e.g., a computer, a smartphone, a tablet, etc.).

[0318] Input: Application installer

[0319] Output: Installed applications

[0320] What happens: A user runs an application installer and follows the installation wizard to complete the installation.

[0321] Step 2:

[0322] When a user launches the application for the first time, they fill out a questionnaire form with information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves.

[0323] Input: Survey form

[0324] Output: Baseline data

[0325] Specific operation: The user fills in each item on the questionnaire form and presses the "Submit" button. The device saves the input data and generates baseline data.

[0326] Step 3:

[0327] The user turns on the photographing device and the audio input device of the electronic device.

[0328] Input: Camera and audio input devices

[0329] Output: Devices ready for use

[0330] Specific behavior: The user checks the camera and microphone settings and turns them on.

[0331] Step 4:

[0332] The device collects the user's facial expression data through a camera, and uses a facial recognition algorithm (e.g., OpenCV) to detect key facial features (e.g., eye movements, mouth corners, etc.).

[0333] Input: Camera image

[0334] Output: Facial expression data

[0335] Specific operation: The device processes camera footage in real time, applies a facial recognition algorithm to extract facial features, and generates facial expression data.

[0336] Step 5:

[0337] The device collects the user's voice data through the voice input device and uses a speech recognition algorithm (e.g., Google Speech API) to detect the tone, pitch, rate, and emotional nuances of the voice.

[0338] Input: Voice input

[0339] Output: Voice tone data

[0340] Specific operation: The device processes the voice data collected from the microphone in real time, applies a voice recognition algorithm to extract voice characteristics, and generates voice data.

[0341] Step 6:

[0342] The collected facial expression and vocal tone data are preprocessed: the facial expression data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib), and the vocal data is passed through a sentiment analysis algorithm (e.g., Google Speech API, Azure Cognitive Services).

[0343] Input: Facial expression data, voice data

[0344] Output: Preprocessed data

[0345] Specific operation: The device passes the facial expression data through a facial recognition algorithm to extract facial expression features, and passes the voice data through an emotion analysis algorithm to extract emotional features.

[0346] Step 7:

[0347] The preprocessed data is sent to the server.

[0348] Input: Preprocessed data

[0349] Output: Data sent to the server

[0350] Specific operation: The device sends the preprocessed data to the server over the network, where a secure data transfer protocol (e.g., HTTPS) is used.

[0351] Step 8:

[0352] The server analyzes the received data in real time, and uses an emotion engine to detect the user's stress level and emotional fluctuations from changes in facial expressions and tone of voice.

[0353] Input: Received data

[0354] Output: Emotion and stress level assessment results

[0355] How it works: The server uses an emotion engine to analyze the received data and evaluate the user's emotions and stress level.

[0356] Step 9:

[0357] To assess workload, the server analyzes data on the frequency, time, volume, and content of communications, and compares it with historical data on work to determine the user's workload.

[0358] Input: communication data, business history data

[0359] Output: Workload evaluation results

[0360] Specific operation: The server analyzes the communication data and compares it with work history data to determine the user's workload level.

[0361] Step 10:

[0362] The server provides the user with measures based on the analysis results, such as generating a message like, "You've been in a lot of meetings lately and are feeling tired. We recommend you take a five-minute break."

[0363] Input: Evaluation result

[0364] Output: Solution message

[0365] Specific operation: The server generates an appropriate countermeasure message based on the evaluation results and sends it to the terminal.

[0366] Step 11:

[0367] The device receives the countermeasure message from the server and notifies the user using a pop-up notification or audio output device.

[0368] Input: Action message

[0369] Output: User notification

[0370] Specific actions: The device will present the countermeasure message to the user via a pop-up notification or audio output device.

[0371] Step 12:

[0372] If the user adjusts their privacy settings and disables continuous monitoring of the camera and audio input devices, they can manually switch to reporting the status.

[0373] Input: Privacy Settings Request

[0374] Output: New configuration state

[0375] What it does: The user changes the privacy settings in the app's settings menu to disable continuous camera and microphone monitoring. The device periodically displays a pop-up allowing the user to manually enter their current mood and fatigue level.

[0376] (Application example 2)

[0377] 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."

[0378] Delivery workers' long working hours and irregular working environments can damage their physical and mental health. For this reason, there is a need for a system that monitors workers' stress and fatigue in real time and encourages them to take breaks at appropriate times. However, conventional monitoring systems have limitations, making it difficult to provide effective notifications and advice. The present invention aims to solve these problems and provide a system that efficiently maintains and improves workers' mental health.

[0379] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of situations, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting means and acquiring means, means for analyzing the preprocessed data using a generative AI model to recognize changes in the user's mental and physical state, and means for providing advice to the user via prompt sentences based on the changes. This makes it possible to monitor the mental health of delivery personnel in real time and propose necessary measures at the appropriate time.

[0380] "User's physical and mental state" refers to the user's psychological and physiological health.

[0381] "Electronic devices" refers to electronic devices such as computers, smartphones, and tablets.

[0382] A "camera" refers to a device that captures images or videos and records them as data.

[0383] A "microphone" refers to a device that collects sound and records it as data.

[0384] "Facial expression data" refers to information about a user's facial expressions.

[0385] "Voice Data" refers to information about the tone, pitch, rate, and emotional nuances of a user's voice.

[0386] "Frequency and duration of a situation" refers to how often a user performs a particular activity and the amount of time spent on that activity.

[0387] "Volume and content of communication" refers to the volume and content of messages exchanged by users.

[0388] "Preprocessing" refers to the preliminary processing of collected data to convert it into a format that can be analyzed.

[0389] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and recognize the user's emotions and state.

[0390] A "prompt" refers to an instruction or advice sentence that is input into a generative AI model.

[0391] "Means for providing advice" refers to means for providing appropriate measures or notifications to users based on their physical or mental condition.

[0392] "Pop-up notification" refers to a notification message that appears on the screen.

[0393] A "voice assistant" refers to software that interacts with users through voice and responds or takes action based on instructions.

[0394] The present invention is a system that monitors the physical and mental state of delivery workers in real time and encourages them to take breaks at appropriate times. This system is composed of an application installed on the user's electronic device (such as a smartphone) and a server. A specific embodiment of this system is described below.

[0395] First, the user installs the application on their smartphone. When they first launch it, they enter information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves. This information is then saved on the server as the user's baseline data.

[0396] Next, data is collected using the smartphone's camera and microphone during delivery operations. The camera collects facial expression data, and the microphone collects voice data. Specifically, data is collected on facial features, voice tone, pitch, speed, etc.

[0397] The collected data is preprocessed on the smartphone. In preprocessing, facial recognition algorithms such as OpenCV are used to extract facial expression features. In addition, emotion analysis algorithms (usually VoiceEmotionAnalyzer, etc.) are used to extract features from the voice data.

[0398] The preprocessed data is sent to a server, which then analyzes it using a generative AI model (such as the EmotionEngine API). The generative AI model analyzes the data and recognizes changes in the user's mental and physical state and emotions. Specifically, the following prompts are used to input emotional data into the AI:

[0399] "User facial expression and voice data:

[0400] Facial expression data: {cameraData}

[0401] Voice data: {microphoneData}

[0402] Analyze your emotional state and provide appropriate suggestions for mental health management.

[0403] Based on the analysis results, the server generates appropriate advice for the user. This advice is conveyed via a smartphone pop-up notification or voice assistant. For example, a message such as "Your current stress level is high. We recommend you take a five-minute break" is displayed.

[0404] Additionally, users can set it up so they can limit camera and microphone usage for privacy reasons, and manually report their situation and self-assess their emotional state at specified intervals.

[0405] In this way, the system can monitor the user's physical and mental state in real time and provide effective advice at the appropriate time, thereby protecting the mental health of delivery workers and improving their work efficiency.

[0406] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0407] Step 1:

[0408] The user installs the application on their smartphone and, when they first start it, enters information such as their mental health status, the type and workload of their work, and how they take breaks. This information is then saved on the server as baseline data.

[0409] Input: User-entered mental health status, work information

[0410] Output: Baseline data is saved to the server

[0411] Step 2:

[0412] The terminal (smartphone) uses a camera and microphone to collect facial expression data and tone of voice data of the user during delivery work.

[0413] Input: User's face and voice data

[0414] Output: Collected facial expression data and voice data

[0415] Step 3:

[0416] The device preprocesses the collected data. Specifically, it uses OpenCV to extract facial features and VoiceEmotionAnalyzer to extract voice features.

[0417] Input: facial expression data, voice data

[0418] Output: Data converted into features

[0419] Step 4:

[0420] The terminal transmits the preprocessed data to the server.

[0421] Input: Feature data

[0422] Output: Data is sent to the server

[0423] Step 5:

[0424] The server analyzes the transmitted data using a generative AI model (such as the EmotionEngine API), inputs the user's emotional state into the AI ​​via prompt sentences, and recognizes the user's physical and mental state and emotional changes.

[0425] Input: "User's facial expression and voice data:

[0426] Facial expression data: {cameraData}

[0427] Voice data: {microphoneData}

[0428] Analyze your emotional state and provide appropriate suggestions for mental health management.

[0429] Output: Parsed user emotional state data

[0430] Step 6:

[0431] The server generates appropriate advice for the user based on the analysis results.

[0432] Input: Analysis results

[0433] Output: Advice statement

[0434] Step 7:

[0435] The device receives advice from the server and conveys it to the user via a pop-up notification or voice assistant.

[0436] Input: Advice from the server

[0437] Output: Pop-up notification or audio notification

[0438] Step 8:

[0439] If a user wants to restrict camera and microphone usage, they manually report their status to the application and self-assess their emotional state.

[0440] Input: Manually reported data by the user

[0441] Output: Manually reported data is sent to the server and updated as baseline data.

[0442] 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.

[0443] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0444] 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.

[0445] [Second embodiment]

[0446] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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).

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0457] 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."

[0458] ---

[0459] The present invention provides a system for monitoring a user's physical and mental state and proposing appropriate measures. This system operates on the user's electronic device (e.g., a computer, a smartphone, a tablet, etc.). Specific embodiments of this system are described in detail below.

[0460] In one embodiment of this system, the user first installs the application on their electronic device. After installation, the user enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the system is first launched. This information is used as the user's baseline data.

[0461] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[0462] The collected facial expression data and vocal tone data are pre-processed on the electronic device. In the pre-processing, the video data is passed through a facial recognition algorithm to extract facial features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[0463] The preprocessed data is sent to a server, which analyzes it in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns.

[0464] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expression indicating fatigue through the camera and a decrease in the tone of their voice through the microphone are collected. The server analyzes this data and determines whether the user is excessively tired.

[0465] Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice via a pop-up notification on the PC screen or a voice assistant.

[0466] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and manually report their state of mind. A pop-up will appear periodically, prompting users to enter their current mood and fatigue level.

[0467] This allows the system to effectively monitor the user's physical and mental state and propose appropriate measures. Users can quickly recognize physical and mental stress that they may not notice themselves, and by taking appropriate measures to refresh themselves and adjust their work, they can prevent mental disorders and make it easier to maintain motivation.

[0468] ---

[0469] The processing flow will be explained below.

[0470] ---

[0471] Step 1:

[0472] The user installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves in a questionnaire form that appears when the application is first launched.

[0473] Step 2:

[0474] The device activates the user's camera and microphone. It requires the user's permission and starts operation after receiving permission.

[0475] Step 3:

[0476] The device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner positions, etc.).

[0477] Step 4:

[0478] The device collects voice data via a microphone, including the tone, pitch, speed and emotional nuances of the user's voice.

[0479] Step 5:

[0480] The device obtains the frequency and duration of meetings. It connects with the APIs of calendar and meeting apps to collect the number of meetings and the duration of each meeting.

[0481] Step 6:

[0482] The device collects data on the volume and content of user communications. Data is collected to analyze the number of chats and emails sent and received and the tone of the content.

[0483] Step 7:

[0484] The facial expression data collected by the device is preprocessed, and the video data is passed through a facial recognition algorithm to extract facial expression features.

[0485] Step 8:

[0486] The device preprocesses the collected voice data, then passes the voice data through an emotion analysis algorithm to extract emotional features.

[0487] Step 9:

[0488] The device sends the preprocessed data to the server, which includes facial expression features, vocal tone features, meeting frequency and duration, and communication volume and tone.

[0489] Step 10:

[0490] The server analyzes the received data in real time and identifies significant changes in facial expression (for example, a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[0491] Step 11:

[0492] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[0493] Step 12:

[0494] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[0495] Step 13:

[0496] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[0497] Step 14:

[0498] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[0499] Step 15:

[0500] Based on the changes the server recognizes, it generates specific advice for the user, such as "You have a series of back-to-back meetings. We recommend you take a five-minute break."

[0501] Step 16:

[0502] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[0503] Step 17:

[0504] Users can configure privacy settings, disable constant camera and microphone monitoring, and manually report their status. A pop-up periodically appears, prompting users to enter their current mood and fatigue level.

[0505] ---

[0506] Example 1

[0507] 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."

[0508] Conventional mental healthcare systems have struggled to closely monitor users' physical and mental conditions in real time and provide appropriate advice. Furthermore, they lacked mechanisms for collecting and analyzing data while respecting users' privacy. As a result, it was difficult for users to become aware of their own health conditions early and take appropriate measures.

[0509] 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.

[0510] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for transmitting the preprocessed data to the server, means for analyzing the transmitted data in real time and recognizing changes in the user's mental and physical state, and means for providing advice to the user based on the recognized changes. This makes it possible to monitor the user's mental and physical state in detail and in real time and provide appropriate advice. Furthermore, data can be collected and analyzed while respecting the user's privacy.

[0511] A "user" is an individual who uses this system.

[0512] "Physical and mental health" refers to the user's mental and physical health.

[0513] "Electronic devices" are devices used by users, such as computers, smartphones, and tablets.

[0514] "Camera and microphone" means a device that collects video and audio built into or connected to an electronic device.

[0515] "Facial expression data" is information on the user's facial movements and expressions collected using a camera.

[0516] "Voice data" refers to voice information such as the tone, pitch, and speed of a user's voice collected using a microphone.

[0517] A "means" is a device, software, algorithm, or method for achieving a particular function or purpose.

[0518] "Meeting frequency and duration" refers to the number of meetings a user participates in and the duration of each meeting.

[0519] "Amount and content of communication" refers to the number of communications a user makes and the detailed content of those communications.

[0520] "Preprocessing" is the process of shaping or transforming the raw data collected into a form suitable for analysis.

[0521] A "server" is a computer system that processes and stores data and communicates with users' electronic devices over a network.

[0522] "Real-time analysis" means processing data as soon as it is received and providing an immediate assessment of the user's situation.

[0523] "Recognizing changes" refers to comparing past data with current data to determine whether a significant change has occurred in the user's physical or mental state.

[0524] "Providing advice" means notifying the user of measures or recommendations based on the analysis results.

[0525] MODE FOR CARRYING OUT THE INVENTION

[0526] System Overview

[0527] The present invention is a system for monitoring a user's physical and mental state and proposing appropriate measures. This system is based on an application installed on the user's electronic device (e.g., computer, smartphone, tablet).

[0528] Hardware and software used

[0529] Electronic devices: computers, smartphones, tablets, etc.

[0530] Camera: an image-collecting device built into or connected to an electronic device

[0531] microphone: a sound-collecting device built into or connected to an electronic device

[0532] Face recognition library: OpenCV

[0533] Voice emotion recognition tools: Sentiment analysis algorithms (e.g. IBM Watson)

[0534] Data transmission protocol: HTTPS

[0535] Program processing flow

[0536] When a user installs the application on their device, a questionnaire form is displayed the first time they start it. This form asks questions about the user's mental health, the type and workload of their work, and how they take breaks and refresh themselves, and this information is used as baseline data.

[0537] The device uses a camera and microphone to collect data in real time as the user performs their tasks: the camera captures key facial features (e.g., eye movements, mouth corner position), and the microphone records the tone, pitch, speed, and emotional nuances of the voice.

[0538] The device preprocesses the collected facial and vocal data, specifically using the OpenCV library for facial recognition and feature extraction, and for the voice data, it uses IBM Watson's voice emotion recognition tool to calculate an emotion score (e.g., 50% joy, 10% anger).

[0539] Data transmission and processing on the server

[0540] The pre-processed data is periodically sent to a server, which analyzes the data in real time to detect changes in the user's physical and mental state. Specifically, it evaluates the following:

[0541] Detecting user stress levels and emotional fluctuations from changes in facial expressions and tone of voice

[0542] Determine workload based on meeting volume and communication patterns

[0543] Advice Generation and Notifications

[0544] The server generates appropriate advice based on the analysis results, which is then sent to the device and notified to the user via a pop-up notification or voice assistant.

[0545] Specific examples

[0546] For example, if a user is continuously participating in online meetings for a long period of time, the device will record the frequency and duration of the meetings, the camera will detect fatigue from the user's facial expressions, and the microphone will capture a drop in the tone of their voice. The server will analyze this data and generate advice such as "You've been in a lot of meetings today. We recommend you take a five-minute break," and the device will notify the user.

[0547] Example prompt sentence:

[0548] What advice will the system give if a user is in an online meeting for three consecutive hours?

[0549] How can cameras and microphones be used to gather stress indicators for long work hours?

[0550] Privacy Settings

[0551] If users value privacy, they can disable constant camera and microphone monitoring and manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[0552] This allows the system to effectively monitor the user's physical and mental state and suggest appropriate measures, making it easier for the user to maintain their health.

[0553] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0554] Step 1: User installs the application

[0555] Description: A user installs an application on their electronic device (computer, smartphone, tablet, etc.). This installation process is done through an official website or app store.

[0556] Input: User's electronic device

[0557] Output: Installed applications

[0558] Step 2: Fill out the initial survey form

[0559] Description: When a user launches the application for the first time, a questionnaire form is displayed. The user enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves. This data is used as baseline data and will be the basis for future analysis.

[0560] Input: User's own mental health status, type and workload of work, methods of rest and refreshment

[0561] Output: Baseline data

[0562] Step 3: Data Collection (Camera and Microphone)

[0563] Description: The device uses a camera and microphone to collect data in real time as the user goes about their daily tasks. The camera captures key facial features (eye movements, mouth corner position, etc.), and the microphone records the tone, pitch, speed, and emotional nuances of the user's voice.

[0564] Input: Real-time video and audio data

[0565] Output: Raw facial expression data, voice data

[0566] Step 4: Preprocessing the data

[0567] Description: The device preprocesses the collected facial expression and voice data. Specifically, it uses the OpenCV library to perform facial recognition and extract feature points. For voice data, it also uses IBM Watson's voice emotion recognition tool to extract emotional features.

[0568] Input: Raw facial expression data, voice data

[0569] Output: Preprocessed facial expression feature data, emotion feature data

[0570] Specific operation:

[0571] Using OpenCV, the positions of eyes and mouth corners are detected from video data.

[0572] Calculates emotion scores from voice data using IBM Watson

[0573] Step 5: Sending data to the server

[0574] Description: The device periodically sends pre-processed data to the server using a secure protocol (e.g. HTTPS).

[0575] Input: Preprocessed facial expression feature data, emotion feature data

[0576] Output: Data sent to the server

[0577] Step 6: Data analysis by the server

[0578] Description: The server analyzes the received data in real time and recognizes changes in the user's physical and mental state. Specifically, it detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determines workload from the number of meetings and communication patterns.

[0579] Input: Preprocessed facial expression feature data, emotion feature data

[0580] Output: Evaluation results of the user's mental and physical state

[0581] Specific operation:

[0582] Evaluate changes in stress levels by comparing with past data stored in a database

[0583] Analyze meeting duration and frequency to calculate workload

[0584] Step 7: Advice generation and notification

[0585] Description: The server generates appropriate advice based on the analysis results and sends it to the device, which then communicates this advice to the user via a pop-up notification or voice assistant.

[0586] Input: Evaluation results of the user's mental and physical state

[0587] Output: Advice notice to user

[0588] Specific operation:

[0589] Generate notification messages such as "You've had a lot of meetings today. We suggest you take a 5-minute break."

[0590] Notify users via pop-ups or voice assistants

[0591] Step 8: Change your privacy settings

[0592] Description: If the user values ​​privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting that allows the user to manually report their status. A pop-up will appear periodically, prompting the user to enter their current mood and fatigue level.

[0593] Input: User privacy settings, manually entered mood and fatigue levels

[0594] Output: Updated user data and privacy settings

[0595] Specific operation:

[0596] In the Privacy Settings menu, select "Disable camera and microphone monitoring"

[0597] A popup for manual input appears, allowing the user to enter their mood and fatigue level.

[0598] (Application example 1)

[0599] 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."

[0600] Conventional in-vehicle driver physical and mental state monitoring systems lack the technology to properly detect driver fatigue and stress and provide the driver with countermeasures in real time. Furthermore, they are unable to automatically switch the vehicle's driving mode based on the driver's physical and mental state, making it difficult to ensure the driver's safety and comfort. To solve these problems, a system is needed that precisely monitors the driver's physical and mental state and provides advice at the appropriate time.

[0601] 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.

[0602] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for analyzing the preprocessed data and recognizing changes in the user's mental and physical state, means for providing advice to the user based on the changes, means for collecting facial expression data and voice data of the driver in the vehicle and monitoring the driver's mental and physical state, and means for switching driving modes based on the driver's mental and physical state. This makes it possible to precisely monitor the driver's mental and physical state and provide appropriate advice in real time, thereby ensuring the driver's safety and comfort.

[0603] The "system for monitoring the user's mental and physical state" is a mechanism for monitoring the user's mental and physical state by collecting and analyzing the user's facial expression data and tone of voice data.

[0604] "Electronic devices" is a general term for devices capable of collecting and processing digital data, such as personal computers, tablets, smartphones, and head-mounted displays.

[0605] A "camera" is a device that captures image data or video data.

[0606] A "microphone" is a device for collecting audio data.

[0607] "Facial expression data" refers to data about the features and movements of a user's face, acquired through a camera.

[0608] "Vocal timbre data" is data obtained through a microphone regarding the tone, pitch, rate, and emotional nuances of a user's voice.

[0609] "Data preprocessing" refers to a series of processes for converting acquired data into a format that is easy to analyze.

[0610] "Analysis" is the process of using pre-processed data to evaluate the user's physical and mental state and recognize changes in it.

[0611] "Means for providing advice" refers to a mechanism for suggesting appropriate actions or breaks to users based on the analysis results.

[0612] "Driving mode" refers to a mode that indicates how a vehicle is driven, and includes an automatic driving mode and a manual driving mode.

[0613] "Means for collecting facial expression data and voice data of the driver inside the vehicle" refers to a mechanism for collecting the driver's facial expressions and voice using a camera and microphone installed in the vehicle.

[0614] The "means for switching driving modes based on the user's physical and mental state" is a mechanism for automatically changing the driving mode of a vehicle in accordance with collected data on the user's physical and mental state.

[0615] The present invention is a system for monitoring the mental and physical state of a driver, switching the driving mode of a vehicle based on the state, and providing appropriate advice. The system is configured as follows.

[0616] First, the user installs the system in the vehicle. After installation, the head-mounted display (HMD) and in-car microphone are set up, and the system is ready to collect the driver's facial expression data and voice data.

[0617] While driving, the system collects facial expression data from the driver using a camera attached to the HMD, and collects audio data through an in-car microphone. The collected facial expression data includes key facial features such as eye movements and the position of the corners of the mouth, while the audio data includes tone, pitch, speed, and emotional nuances of the voice.

[0618] Once the data is collected, the device's software preprocesses it. This includes running the video data from the camera through a facial recognition algorithm (e.g., OpenCV) to extract facial features, and it also includes running the audio data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features.

[0619] The preprocessed data is sent to a server, which then analyzes the driver's physical and mental state in real time. The server detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. For example, if the server's analysis determines that the driver is feeling fatigued or stressed, the system will suggest that the driver take a break.

[0620] Furthermore, if a car is equipped with an autonomous driving function, it can automatically switch to autonomous driving mode depending on the driver's physical and mental state, ensuring safe driving even when the driver is fatigued.

[0621] The notification method is to provide advice to the driver through a pop-up notification or voice assistant, for example, "The system has detected that the driver has been driving continuously for a long period of time, so it is recommended that you take a five-minute break."

[0622] Furthermore, if the driver is concerned about privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting where the driver can manually report their condition. For example, a pop-up will appear periodically, and the driver can input their "current mood and fatigue level," and the system can provide advice based on that information.

[0623] As a concrete example, a prompt using a generative AI model could be, "If a driver has been driving for a long time and is fatigued, how can we use the autonomous driving function to suggest a break?"

[0624] In this way, the system is able to precisely monitor the driver's physical and mental state and provide appropriate advice in real time, providing a safe and comfortable driving environment.

[0625] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0626] Step 1:

[0627] The device sets up a camera and microphone on the user's electronic device and starts collecting the driver's facial expression data and voice data. The camera captures key features of the driver's face (e.g., eye movements, position of the corners of the mouth, etc.), and the microphone records the driver's voice data (tone, pitch, speed, emotional nuances). The input is the camera image and voice data, and the output is the collected facial expression data and voice data.

[0628] Step 2:

[0629] The device passes the collected facial expression data through a facial recognition algorithm (e.g., OpenCV) to extract facial expression features. It also passes the voice data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features. The input is the facial expression data and voice data collected in step 1, and the output is the facial expression data and voice data from which features have been extracted.

[0630] Step 3:

[0631] The device sends the preprocessed data (facial expression data and voice data from which features have been extracted) to the server. The server receives this data in real time and starts analysis according to the situation. The input is the facial expression data and voice data from which features have been extracted, and the output is the preprocessed data sent to the server.

[0632] Step 4:

[0633] The server analyzes the driver's physical and mental state in real time based on the received data. Specifically, it detects the driver's stress level and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. The input is preprocessed data, and the output is the driver's physical and mental state and any changes therein.

[0634] Step 5:

[0635] Based on the analysis results, the server generates advice for the driver to take a break and sends it to the terminal. For example, a notification may be created in the form of, "The driver has been driving continuously for a long period of time, so we recommend that you take a five-minute break." The input is the results regarding the driver's physical and mental state and any changes therein, and the output is advice to the driver.

[0636] Step 6:

[0637] The terminal notifies the driver of the advice provided by the server. Notification methods include pop-up notifications and voice assistants. Advice such as suggestions for taking a break is displayed to the driver at appropriate times. The input is the advice sent from the server, and the output is the advice notified to the driver.

[0638] Step 7:

[0639] The terminal also has a means for automatically switching to autonomous driving mode depending on the driver's physical and mental state. If the system determines that the driver is excessively fatigued, a command to switch to autonomous driving mode is sent from the terminal to the vehicle's control device. The input is the decision to switch to autonomous driving based on the driver's physical and mental state, and the output is the vehicle being switched to autonomous driving mode.

[0640] 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.

[0641] ---

[0642] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[0643] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[0644] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[0645] The collected facial expression and tone data are pre-processed on the device. In pre-processing, the video data is passed through a facial recognition algorithm to extract facial features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[0646] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns. This is where the emotion engine plays an important role.

[0647] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[0648] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expressions indicating fatigue through the camera and a decrease in the tone of their voice through the microphone is collected. Furthermore, the emotion engine uses this data to accurately recognize the user's fatigue and stress.

[0649] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen or a voice assistant.

[0650] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and switch to a setting where they can manually report their state of mind: periodically, a pop-up appears, prompting the user to enter their current mood and fatigue level.

[0651] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[0652] ---

[0653] The processing flow will be explained below.

[0654] ---

[0655] Step 1:

[0656] The user installs the application on their electronic device and enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched.

[0657] Step 2:

[0658] The device will ask the user for permission to use the camera and microphone, and if the user grants permission, will activate these devices.

[0659] Step 3:

[0660] While the user is working, the device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner position, etc.).

[0661] Step 4:

[0662] At the same time, the device collects voice data through the microphone, including the user's voice tone, pitch, speed and emotional nuances.

[0663] Step 5:

[0664] The device connects to the API of the calendar or meeting app to obtain data on the frequency and duration of meetings.

[0665] Step 6:

[0666] The device collects the number and content of the user's chat and email communications, and collects the volume and tone of communication.

[0667] Step 7:

[0668] The facial expression data collected by the device is preprocessed and passed through a facial recognition algorithm to extract facial features.

[0669] Step 8:

[0670] The voice data collected by the device is preprocessed and passed through an emotion analysis algorithm to extract emotional features.

[0671] Step 9:

[0672] The device sends the preprocessed data to the server, which includes facial expression features, vocal tone features, meeting frequency and duration, and communication volume and tone.

[0673] Step 10:

[0674] The server analyzes the received data in real time and identifies significant changes in facial expression (e.g., a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[0675] Step 11:

[0676] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[0677] Step 12:

[0678] The server uses an emotion engine to recognize the user's emotion from the facial expression data and tone of voice data, for example, if the emotion is classified as "sadness" or "fatigue", the server generates the data.

[0679] Step 13:

[0680] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[0681] Step 14:

[0682] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[0683] Step 15:

[0684] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[0685] Step 16:

[0686] Based on the changes and emotion data recognized by the server, the server generates specific advice for the user, such as "You have a series of consecutive meetings. We recommend you take a five-minute break."

[0687] Step 17:

[0688] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[0689] Step 18:

[0690] Users can adjust their privacy settings to disable constant camera and microphone monitoring, and can manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[0691] ---

[0692] Following this step, the system can effectively monitor changes in the user's physical and mental state and emotions and suggest appropriate measures.

[0693] Example 2

[0694] 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."

[0695] Conventional systems face the challenge of effectively monitoring a user's physical and mental state and providing appropriate measures based on that information. In particular, there is a lack of means to accurately assess a user's stress and fatigue by collecting and analyzing facial expression and tone of voice data in real time. Furthermore, there is a need for a method to collect the necessary data while ensuring user privacy.

[0696] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via a photographing device and a voice input device of the user's electronic device, means for acquiring the frequency and duration of communication, and means for acquiring the amount and content of the user's communication. This makes it possible to recognize changes in the user's mental and physical state in real time and provide appropriate countermeasures. In addition, the server is equipped with a data collection means for evaluating emotions and a means for evaluating workload, making it possible to accurately recognize the user's accurate emotional state and workload. Combining these means makes it possible to effectively manage the user's mental health and prevent excessive stress and fatigue.

[0697] "User's Electronic Device" refers to electronic devices used by a User, such as a computer, smartphone, or tablet.

[0698] "Photography device" refers to a video input device such as a camera or webcam installed in an electronic device.

[0699] "Audio input device" refers to a microphone or audio collection device installed in an electronic device.

[0700] "Facial expression data" refers to digital information obtained from key facial features of a user and is used to assess emotions and stress levels.

[0701] "Voice data" refers to digital information derived from the tone, pitch, rate and emotional nuances of a user's voice, which is used to assess emotions and stress levels.

[0702] "Frequency of communication" refers to the number of communications a user makes using an electronic device.

[0703] "Communication time" refers to the total time a user communicates using an electronic device.

[0704] "Volume of communication" refers to the amount of data a user sends and receives via electronic devices.

[0705] "Content of communication" refers to the specific content and nature of the communication a user makes through an electronic device.

[0706] "Preprocessing" refers to the process of converting collected raw data into an analyzable format, including feature extraction and data shaping.

[0707] "Preprocessed data" refers to data that has been converted into an analyzable format by preprocessing.

[0708] "User's physical and mental state" refers to the user's mental and physical health, including emotions, stress, fatigue, etc.

[0709] "Measures" refers to advice and guidelines provided to improve a user's physical or mental condition.

[0710] A "pop-up notification" refers to a message window that suddenly appears on the screen of an electronic device.

[0711] "Audio output device" refers to an audio output device such as a speaker or a headphone that is installed in an electronic device.

[0712] "Means for assessing emotions" refers to algorithms or processes that use facial expression data and tone of voice data to recognize and assess a user's emotional state.

[0713] "Means for assessing workload" refers to the process of analyzing data such as a user's work history and the frequency, time, and content of communications to assess the workload level.

[0714]

[0715] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[0716] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[0717] Next, data is collected using the user's camera and voice input devices. While the user is working using a PC or smartphone, facial expression data is collected through the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected through the voice input device. This voice tone data includes the user's voice tone, pitch, speed, and emotional nuances.

[0718] The collected facial expression and tone data are pre-processed on the device. During pre-processing, the video data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib) to extract facial expression features, and the audio data is passed through an emotion analysis algorithm (e.g., Google Speech API, Azure Cognitive Services) to extract emotional features.

[0719] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in the frequency, time, volume, and content of communication. This is where the emotion engine plays an important role.

[0720] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[0721] As a concrete example, consider the case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as whether the user's facial expression indicates fatigue through a camera device and whether the tone of their voice is declining through a voice input device is collected. Based on this data, the emotion engine recognizes the user's fatigue and stress with high accuracy.

[0722] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen and an audio output device.

[0723] Furthermore, if users value privacy, they can disable the continuous monitoring of the camera and audio input devices and switch to a setting where they can manually report their condition by entering their current mood and fatigue level in a pop-up that appears periodically.

[0724] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[0725] Examples of prompts for generative AI models include:

[0726] "Please explain in detail how the system detects user fatigue and suggests appropriate breaks when the user is participating in long, continuous online meetings. Please also include the collection method for facial expression and tone of voice data, pre-processing steps, real-time analysis process, and specific notification methods."

[0727] Based on this prompt, a more detailed understanding can be gained by referring to the explanation provided by the generative AI model.

[0728] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0729] Step 1:

[0730] A user installs an application on an electronic device (e.g., a computer, a smartphone, a tablet, etc.).

[0731] Input: Application installer

[0732] Output: Installed applications

[0733] What happens: A user runs an application installer and follows the installation wizard to complete the installation.

[0734] Step 2:

[0735] When a user launches the application for the first time, they fill out a questionnaire form with information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves.

[0736] Input: Survey form

[0737] Output: Baseline data

[0738] Specific operation: The user fills in each item on the questionnaire form and presses the "Submit" button. The device saves the input data and generates baseline data.

[0739] Step 3:

[0740] The user turns on the photographing device and the audio input device of the electronic device.

[0741] Input: Camera and audio input devices

[0742] Output: Devices ready for use

[0743] Specific behavior: The user checks the camera and microphone settings and turns them on.

[0744] Step 4:

[0745] The device collects the user's facial expression data through a camera, and uses a facial recognition algorithm (e.g., OpenCV) to detect key facial features (e.g., eye movements, mouth corners, etc.).

[0746] Input: Camera image

[0747] Output: Facial expression data

[0748] Specific operation: The device processes camera footage in real time, applies a facial recognition algorithm to extract facial features, and generates facial expression data.

[0749] Step 5:

[0750] The device collects the user's voice data through the voice input device and uses a speech recognition algorithm (e.g., Google Speech API) to detect the tone, pitch, rate, and emotional nuances of the voice.

[0751] Input: Voice input

[0752] Output: Voice tone data

[0753] Specific operation: The device processes the voice data collected from the microphone in real time, applies a voice recognition algorithm to extract voice characteristics, and generates voice data.

[0754] Step 6:

[0755] The collected facial expression and vocal tone data are preprocessed: the facial expression data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib), and the vocal data is passed through a sentiment analysis algorithm (e.g., Google Speech API, Azure Cognitive Services).

[0756] Input: Facial expression data, voice data

[0757] Output: Preprocessed data

[0758] Specific operation: The device passes the facial expression data through a facial recognition algorithm to extract facial expression features, and passes the voice data through an emotion analysis algorithm to extract emotional features.

[0759] Step 7:

[0760] The preprocessed data is sent to the server.

[0761] Input: Preprocessed data

[0762] Output: Data sent to the server

[0763] Specific operation: The device sends the preprocessed data to the server over the network, where a secure data transfer protocol (e.g., HTTPS) is used.

[0764] Step 8:

[0765] The server analyzes the received data in real time, and uses an emotion engine to detect the user's stress level and emotional fluctuations from changes in facial expressions and tone of voice.

[0766] Input: Received data

[0767] Output: Emotion and stress level assessment results

[0768] How it works: The server uses an emotion engine to analyze the received data and evaluate the user's emotions and stress level.

[0769] Step 9:

[0770] To assess workload, the server analyzes data on the frequency, time, volume, and content of communications, and compares it with historical data on work to determine the user's workload.

[0771] Input: communication data, business history data

[0772] Output: Workload evaluation results

[0773] Specific operation: The server analyzes the communication data and compares it with work history data to determine the user's workload level.

[0774] Step 10:

[0775] The server provides the user with measures based on the analysis results, such as generating a message like, "You've been in a lot of meetings lately and are feeling tired. We recommend you take a five-minute break."

[0776] Input: Evaluation result

[0777] Output: Solution message

[0778] Specific operation: The server generates an appropriate countermeasure message based on the evaluation results and sends it to the terminal.

[0779] Step 11:

[0780] The device receives the countermeasure message from the server and notifies the user using a pop-up notification or audio output device.

[0781] Input: Action message

[0782] Output: User notification

[0783] Specific actions: The device will present the countermeasure message to the user via a pop-up notification or audio output device.

[0784] Step 12:

[0785] If the user adjusts their privacy settings and disables continuous monitoring of the camera and audio input devices, they can manually switch to reporting the status.

[0786] Input: Privacy Settings Request

[0787] Output: New configuration state

[0788] What it does: The user changes the privacy settings in the app's settings menu to disable continuous camera and microphone monitoring. The device periodically displays a pop-up allowing the user to manually enter their current mood and fatigue level.

[0789] (Application example 2)

[0790] 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."

[0791] Delivery workers' long working hours and irregular working environments can damage their physical and mental health. For this reason, there is a need for a system that monitors workers' stress and fatigue in real time and encourages them to take breaks at appropriate times. However, conventional monitoring systems have limitations, making it difficult to provide effective notifications and advice. The present invention aims to solve these problems and provide a system that efficiently maintains and improves workers' mental health.

[0792] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of situations, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting means and acquiring means, means for analyzing the preprocessed data using a generative AI model to recognize changes in the user's mental and physical state, and means for providing advice to the user via prompt sentences based on the changes. This makes it possible to monitor the mental health of delivery personnel in real time and propose necessary measures at the appropriate time.

[0793] "User's physical and mental state" refers to the user's psychological and physiological health.

[0794] "Electronic devices" refers to electronic devices such as computers, smartphones, and tablets.

[0795] A "camera" refers to a device that captures images or videos and records them as data.

[0796] A "microphone" refers to a device that collects sound and records it as data.

[0797] "Facial expression data" refers to information about a user's facial expressions.

[0798] "Voice Data" refers to information about the tone, pitch, rate, and emotional nuances of a user's voice.

[0799] "Frequency and duration of a situation" refers to how often a user performs a particular activity and the amount of time spent on that activity.

[0800] "Volume and content of communication" refers to the volume and content of messages exchanged by users.

[0801] "Preprocessing" refers to the preliminary processing of collected data to convert it into a format that can be analyzed.

[0802] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and recognize the user's emotions and state.

[0803] A "prompt" refers to an instruction or advice sentence that is input into a generative AI model.

[0804] "Means for providing advice" refers to means for providing appropriate measures or notifications to users based on their physical or mental condition.

[0805] "Pop-up notification" refers to a notification message that appears on the screen.

[0806] A "voice assistant" refers to software that interacts with users through voice and responds or takes action based on instructions.

[0807] The present invention is a system that monitors the physical and mental state of delivery workers in real time and encourages them to take breaks at appropriate times. This system is composed of an application installed on the user's electronic device (such as a smartphone) and a server. A specific embodiment of this system is described below.

[0808] First, the user installs the application on their smartphone. When they first launch it, they enter information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves. This information is then saved on the server as the user's baseline data.

[0809] Next, data is collected using the smartphone's camera and microphone during delivery operations. The camera collects facial expression data, and the microphone collects voice data. Specifically, data is collected on facial features, voice tone, pitch, speed, etc.

[0810] The collected data is preprocessed on the smartphone. In preprocessing, facial recognition algorithms such as OpenCV are used to extract facial expression features. In addition, emotion analysis algorithms (usually VoiceEmotionAnalyzer, etc.) are used to extract features from the voice data.

[0811] The preprocessed data is sent to a server, which then analyzes it using a generative AI model (such as the EmotionEngine API). The generative AI model analyzes the data and recognizes changes in the user's mental and physical state and emotions. Specifically, the following prompts are used to input emotional data into the AI:

[0812] "User facial expression and voice data:

[0813] Facial expression data: {cameraData}

[0814] Voice data: {microphoneData}

[0815] Analyze your emotional state and provide appropriate suggestions for mental health management.

[0816] Based on the analysis results, the server generates appropriate advice for the user. This advice is conveyed via a smartphone pop-up notification or voice assistant. For example, a message such as "Your current stress level is high. We recommend you take a five-minute break" is displayed.

[0817] Additionally, users can set it up so they can limit camera and microphone usage for privacy reasons, and manually report their situation and self-assess their emotional state at specified intervals.

[0818] In this way, the system can monitor the user's physical and mental state in real time and provide effective advice at the appropriate time, thereby protecting the mental health of delivery workers and improving their work efficiency.

[0819] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0820] Step 1:

[0821] The user installs the application on their smartphone and, when they first start it, enters information such as their mental health status, the type and workload of their work, and how they take breaks. This information is then saved on the server as baseline data.

[0822] Input: User-entered mental health status, work information

[0823] Output: Baseline data is saved to the server

[0824] Step 2:

[0825] The terminal (smartphone) uses a camera and microphone to collect facial expression data and tone of voice data of the user during delivery work.

[0826] Input: User's face and voice data

[0827] Output: Collected facial expression data and voice data

[0828] Step 3:

[0829] The device preprocesses the collected data. Specifically, it uses OpenCV to extract facial features and VoiceEmotionAnalyzer to extract voice features.

[0830] Input: facial expression data, voice data

[0831] Output: Data converted into features

[0832] Step 4:

[0833] The terminal transmits the preprocessed data to the server.

[0834] Input: Feature data

[0835] Output: Data is sent to the server

[0836] Step 5:

[0837] The server analyzes the transmitted data using a generative AI model (such as the EmotionEngine API), inputs the user's emotional state into the AI ​​via prompt sentences, and recognizes the user's physical and mental state and emotional changes.

[0838] Input: "User's facial expression and voice data:

[0839] Facial expression data: {cameraData}

[0840] Voice data: {microphoneData}

[0841] Analyze your emotional state and provide appropriate suggestions for mental health management.

[0842] Output: Parsed user emotional state data

[0843] Step 6:

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

[0845] Input: Analysis results

[0846] Output: Advice statement

[0847] Step 7:

[0848] The device receives advice from the server and conveys it to the user via a pop-up notification or voice assistant.

[0849] Input: Advice from the server

[0850] Output: Pop-up notification or audio notification

[0851] Step 8:

[0852] If a user wants to restrict camera and microphone usage, they manually report their status to the application and self-assess their emotional state.

[0853] Input: Manually reported data by the user

[0854] Output: Manually reported data is sent to the server and updated as baseline data.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] [Third embodiment]

[0859] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0860] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0861] 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).

[0862] 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.

[0863] 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.

[0864] 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).

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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."

[0871] ---

[0872] The present invention provides a system for monitoring a user's physical and mental state and proposing appropriate measures. This system operates on the user's electronic device (e.g., a computer, a smartphone, a tablet, etc.). Specific embodiments of this system are described in detail below.

[0873] In one embodiment of this system, the user first installs the application on their electronic device. After installation, the user enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the system is first launched. This information is used as the user's baseline data.

[0874] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[0875] The collected facial expression data and vocal tone data are pre-processed on the electronic device. In the pre-processing, the video data is passed through a facial recognition algorithm to extract facial features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[0876] The preprocessed data is sent to a server, which analyzes it in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns.

[0877] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expression indicating fatigue through the camera and a decrease in the tone of their voice through the microphone are collected. The server analyzes this data and determines whether the user is excessively tired.

[0878] Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice via a pop-up notification on the PC screen or a voice assistant.

[0879] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and manually report their state of mind. A pop-up will appear periodically, prompting users to enter their current mood and fatigue level.

[0880] This allows the system to effectively monitor the user's physical and mental state and propose appropriate measures. Users can quickly recognize physical and mental stress that they may not notice themselves, and by taking appropriate measures to refresh themselves and adjust their work, they can prevent mental disorders and make it easier to maintain motivation.

[0881] ---

[0882] The processing flow will be explained below.

[0883] ---

[0884] Step 1:

[0885] The user installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves in a questionnaire form that appears when the application is first launched.

[0886] Step 2:

[0887] The device activates the user's camera and microphone. It requires the user's permission and starts operation after receiving permission.

[0888] Step 3:

[0889] The device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner positions, etc.).

[0890] Step 4:

[0891] The device collects voice data via a microphone, including the tone, pitch, speed and emotional nuances of the user's voice.

[0892] Step 5:

[0893] The device obtains the frequency and duration of meetings. It connects with the APIs of calendar and meeting apps to collect the number of meetings and the duration of each meeting.

[0894] Step 6:

[0895] The device collects data on the volume and content of user communications. Data is collected to analyze the number of chats and emails sent and received and the tone of the content.

[0896] Step 7:

[0897] The facial expression data collected by the device is preprocessed, and the video data is passed through a facial recognition algorithm to extract facial expression features.

[0898] Step 8:

[0899] The device preprocesses the collected voice data, then passes the voice data through an emotion analysis algorithm to extract emotional features.

[0900] Step 9:

[0901] The device sends the preprocessed data to the server, which includes facial expression features, vocal tone features, meeting frequency and duration, and communication volume and tone.

[0902] Step 10:

[0903] The server analyzes the received data in real time and identifies significant changes in facial expression (for example, a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[0904] Step 11:

[0905] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[0906] Step 12:

[0907] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[0908] Step 13:

[0909] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[0910] Step 14:

[0911] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[0912] Step 15:

[0913] Based on the changes the server recognizes, it generates specific advice for the user, such as "You have a series of back-to-back meetings. We recommend you take a five-minute break."

[0914] Step 16:

[0915] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[0916] Step 17:

[0917] Users can configure privacy settings, disable constant camera and microphone monitoring, and manually report their status. A pop-up periodically appears, prompting users to enter their current mood and fatigue level.

[0918] ---

[0919] Example 1

[0920] 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."

[0921] Conventional mental healthcare systems have struggled to closely monitor users' physical and mental conditions in real time and provide appropriate advice. Furthermore, they lacked mechanisms for collecting and analyzing data while respecting users' privacy. As a result, it was difficult for users to become aware of their own health conditions early and take appropriate measures.

[0922] 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.

[0923] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for transmitting the preprocessed data to the server, means for analyzing the transmitted data in real time and recognizing changes in the user's mental and physical state, and means for providing advice to the user based on the recognized changes. This makes it possible to monitor the user's mental and physical state in detail and in real time and provide appropriate advice. Furthermore, data can be collected and analyzed while respecting the user's privacy.

[0924] A "user" is an individual who uses this system.

[0925] "Physical and mental health" refers to the user's mental and physical health.

[0926] "Electronic devices" are devices used by users, such as computers, smartphones, and tablets.

[0927] "Camera and microphone" means a device that collects video and audio built into or connected to an electronic device.

[0928] "Facial expression data" is information on the user's facial movements and expressions collected using a camera.

[0929] "Voice data" refers to voice information such as the tone, pitch, and speed of a user's voice collected using a microphone.

[0930] A "means" is a device, software, algorithm, or method for achieving a particular function or purpose.

[0931] "Meeting frequency and duration" refers to the number of meetings a user participates in and the duration of each meeting.

[0932] "Amount and content of communication" refers to the number of communications a user makes and the detailed content of those communications.

[0933] "Preprocessing" is the process of shaping or transforming the raw data collected into a form suitable for analysis.

[0934] A "server" is a computer system that processes and stores data and communicates with users' electronic devices over a network.

[0935] "Real-time analysis" means processing data as soon as it is received and providing an immediate assessment of the user's situation.

[0936] "Recognizing changes" refers to comparing past data with current data to determine whether a significant change has occurred in the user's physical or mental state.

[0937] "Providing advice" means notifying the user of measures or recommendations based on the analysis results.

[0938] MODE FOR CARRYING OUT THE INVENTION

[0939] System Overview

[0940] The present invention is a system for monitoring a user's physical and mental state and proposing appropriate measures. This system is based on an application installed on the user's electronic device (e.g., computer, smartphone, tablet).

[0941] Hardware and software used

[0942] Electronic devices: computers, smartphones, tablets, etc.

[0943] Camera: an image-collecting device built into or connected to an electronic device

[0944] microphone: a sound-collecting device built into or connected to an electronic device

[0945] Face recognition library: OpenCV

[0946] Voice emotion recognition tools: Sentiment analysis algorithms (e.g. IBM Watson)

[0947] Data transmission protocol: HTTPS

[0948] Program processing flow

[0949] When a user installs the application on their device, a questionnaire form is displayed the first time they start it. This form asks questions about the user's mental health, the type and workload of their work, and how they take breaks and refresh themselves, and this information is used as baseline data.

[0950] The device uses a camera and microphone to collect data in real time as the user performs their tasks: the camera captures key facial features (e.g., eye movements, mouth corner position), and the microphone records the tone, pitch, speed, and emotional nuances of the voice.

[0951] The device preprocesses the collected facial and vocal data, specifically using the OpenCV library for facial recognition and feature extraction, and for the voice data, it uses IBM Watson's voice emotion recognition tool to calculate an emotion score (e.g., 50% joy, 10% anger).

[0952] Data transmission and processing on the server

[0953] The pre-processed data is periodically sent to a server, which analyzes the data in real time to detect changes in the user's physical and mental state. Specifically, it evaluates the following:

[0954] Detecting user stress levels and emotional fluctuations from changes in facial expressions and tone of voice

[0955] Determine workload based on meeting volume and communication patterns

[0956] Advice Generation and Notifications

[0957] The server generates appropriate advice based on the analysis results, which is then sent to the device and notified to the user via a pop-up notification or voice assistant.

[0958] Specific examples

[0959] For example, if a user is continuously participating in online meetings for a long period of time, the device will record the frequency and duration of the meetings, the camera will detect fatigue from the user's facial expressions, and the microphone will capture a drop in the tone of their voice. The server will analyze this data and generate advice such as "You've been in a lot of meetings today. We recommend you take a five-minute break," and the device will notify the user.

[0960] Example prompt sentence:

[0961] What advice will the system give if a user is in an online meeting for three consecutive hours?

[0962] How can cameras and microphones be used to gather stress indicators for long work hours?

[0963] Privacy Settings

[0964] If users value privacy, they can disable constant camera and microphone monitoring and manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[0965] This allows the system to effectively monitor the user's physical and mental state and suggest appropriate measures, making it easier for the user to maintain their health.

[0966] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0967] Step 1: User installs the application

[0968] Description: A user installs an application on their electronic device (computer, smartphone, tablet, etc.). This installation process is done through an official website or app store.

[0969] Input: User's electronic device

[0970] Output: Installed applications

[0971] Step 2: Fill out the initial survey form

[0972] Description: When a user launches the application for the first time, a questionnaire form is displayed. The user enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves. This data is used as baseline data and will be the basis for future analysis.

[0973] Input: User's own mental health status, type and workload of work, methods of rest and refreshment

[0974] Output: Baseline data

[0975] Step 3: Data Collection (Camera and Microphone)

[0976] Description: The device uses a camera and microphone to collect data in real time as the user goes about their daily tasks. The camera captures key facial features (eye movements, mouth corner position, etc.), and the microphone records the tone, pitch, speed, and emotional nuances of the user's voice.

[0977] Input: Real-time video and audio data

[0978] Output: Raw facial expression data, voice data

[0979] Step 4: Preprocessing the data

[0980] Description: The device preprocesses the collected facial expression and voice data. Specifically, it uses the OpenCV library to perform facial recognition and extract feature points. For voice data, it also uses IBM Watson's voice emotion recognition tool to extract emotional features.

[0981] Input: Raw facial expression data, voice data

[0982] Output: Preprocessed facial expression feature data, emotion feature data

[0983] Specific operation:

[0984] Using OpenCV, the positions of eyes and mouth corners are detected from video data.

[0985] Calculates emotion scores from voice data using IBM Watson

[0986] Step 5: Sending data to the server

[0987] Description: The device periodically sends pre-processed data to the server using a secure protocol (e.g. HTTPS).

[0988] Input: Preprocessed facial expression feature data, emotion feature data

[0989] Output: Data sent to the server

[0990] Step 6: Data analysis by the server

[0991] Description: The server analyzes the received data in real time and recognizes changes in the user's physical and mental state. Specifically, it detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determines workload from the number of meetings and communication patterns.

[0992] Input: Preprocessed facial expression feature data, emotion feature data

[0993] Output: Evaluation results of the user's mental and physical state

[0994] Specific operation:

[0995] Evaluate changes in stress levels by comparing with past data stored in a database

[0996] Analyze meeting duration and frequency to calculate workload

[0997] Step 7: Advice generation and notification

[0998] Description: The server generates appropriate advice based on the analysis results and sends it to the device, which then communicates this advice to the user via a pop-up notification or voice assistant.

[0999] Input: Evaluation results of the user's mental and physical state

[1000] Output: Advice notice to user

[1001] Specific operation:

[1002] Generate notification messages such as "You've had a lot of meetings today. We suggest you take a 5-minute break."

[1003] Notify users via pop-ups or voice assistants

[1004] Step 8: Change your privacy settings

[1005] Description: If the user values ​​privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting that allows the user to manually report their status. A pop-up will appear periodically, prompting the user to enter their current mood and fatigue level.

[1006] Input: User privacy settings, manually entered mood and fatigue levels

[1007] Output: Updated user data and privacy settings

[1008] Specific operation:

[1009] In the Privacy Settings menu, select "Disable camera and microphone monitoring"

[1010] A popup for manual input appears, allowing the user to enter their mood and fatigue level.

[1011] (Application example 1)

[1012] 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."

[1013] Conventional in-vehicle driver physical and mental state monitoring systems lack the technology to properly detect driver fatigue and stress and provide the driver with countermeasures in real time. Furthermore, they are unable to automatically switch the vehicle's driving mode based on the driver's physical and mental state, making it difficult to ensure the driver's safety and comfort. To solve these problems, a system is needed that precisely monitors the driver's physical and mental state and provides advice at the appropriate time.

[1014] 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.

[1015] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for analyzing the preprocessed data and recognizing changes in the user's mental and physical state, means for providing advice to the user based on the changes, means for collecting facial expression data and voice data of the driver in the vehicle and monitoring the driver's mental and physical state, and means for switching driving modes based on the driver's mental and physical state. This makes it possible to precisely monitor the driver's mental and physical state and provide appropriate advice in real time, thereby ensuring the driver's safety and comfort.

[1016] The "system for monitoring the user's mental and physical state" is a mechanism for monitoring the user's mental and physical state by collecting and analyzing the user's facial expression data and tone of voice data.

[1017] "Electronic devices" is a general term for devices capable of collecting and processing digital data, such as personal computers, tablets, smartphones, and head-mounted displays.

[1018] A "camera" is a device that captures image data or video data.

[1019] A "microphone" is a device for collecting audio data.

[1020] "Facial expression data" refers to data about the features and movements of a user's face, acquired through a camera.

[1021] "Vocal timbre data" is data obtained through a microphone regarding the tone, pitch, rate, and emotional nuances of a user's voice.

[1022] "Data preprocessing" refers to a series of processes for converting acquired data into a format that is easy to analyze.

[1023] "Analysis" is the process of using pre-processed data to evaluate the user's physical and mental state and recognize changes in it.

[1024] "Means for providing advice" refers to a mechanism for suggesting appropriate actions or breaks to users based on the analysis results.

[1025] "Driving mode" refers to a mode that indicates how a vehicle is driven, and includes an automatic driving mode and a manual driving mode.

[1026] "Means for collecting facial expression data and voice data of the driver inside the vehicle" refers to a mechanism for collecting the driver's facial expressions and voice using a camera and microphone installed in the vehicle.

[1027] The "means for switching driving modes based on the user's physical and mental state" is a mechanism for automatically changing the driving mode of a vehicle in accordance with collected data on the user's physical and mental state.

[1028] The present invention is a system for monitoring the mental and physical state of a driver, switching the driving mode of a vehicle based on the state, and providing appropriate advice. The system is configured as follows.

[1029] First, the user installs the system in the vehicle. After installation, the head-mounted display (HMD) and in-car microphone are set up, and the system is ready to collect the driver's facial expression data and voice data.

[1030] While driving, the system collects facial expression data from the driver using a camera attached to the HMD, and collects audio data through an in-car microphone. The collected facial expression data includes key facial features such as eye movements and the position of the corners of the mouth, while the audio data includes tone, pitch, speed, and emotional nuances of the voice.

[1031] Once the data is collected, the device's software preprocesses it. This includes running the video data from the camera through a facial recognition algorithm (e.g., OpenCV) to extract facial features, and it also includes running the audio data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features.

[1032] The preprocessed data is sent to a server, which then analyzes the driver's physical and mental state in real time. The server detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. For example, if the server's analysis determines that the driver is feeling fatigued or stressed, the system will suggest that the driver take a break.

[1033] Furthermore, if a car is equipped with an autonomous driving function, it can automatically switch to autonomous driving mode depending on the driver's physical and mental state, ensuring safe driving even when the driver is fatigued.

[1034] The notification method is to provide advice to the driver through a pop-up notification or voice assistant, for example, "The system has detected that the driver has been driving continuously for a long period of time, so it is recommended that you take a five-minute break."

[1035] Furthermore, if the driver is concerned about privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting where the driver can manually report their condition. For example, a pop-up will appear periodically, and the driver can input their "current mood and fatigue level," and the system can provide advice based on that information.

[1036] As a concrete example, a prompt using a generative AI model could be, "If a driver has been driving for a long time and is fatigued, how can we use the autonomous driving function to suggest a break?"

[1037] In this way, the system is able to precisely monitor the driver's physical and mental state and provide appropriate advice in real time, providing a safe and comfortable driving environment.

[1038] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1039] Step 1:

[1040] The device sets up a camera and microphone on the user's electronic device and starts collecting the driver's facial expression data and voice data. The camera captures key features of the driver's face (e.g., eye movements, position of the corners of the mouth, etc.), and the microphone records the driver's voice data (tone, pitch, speed, emotional nuances). The input is the camera image and voice data, and the output is the collected facial expression data and voice data.

[1041] Step 2:

[1042] The device passes the collected facial expression data through a facial recognition algorithm (e.g., OpenCV) to extract facial expression features. It also passes the voice data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features. The input is the facial expression data and voice data collected in step 1, and the output is the facial expression data and voice data from which features have been extracted.

[1043] Step 3:

[1044] The device sends the preprocessed data (facial expression data and voice data from which features have been extracted) to the server. The server receives this data in real time and starts analysis according to the situation. The input is the facial expression data and voice data from which features have been extracted, and the output is the preprocessed data sent to the server.

[1045] Step 4:

[1046] The server analyzes the driver's physical and mental state in real time based on the received data. Specifically, it detects the driver's stress level and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. The input is preprocessed data, and the output is the driver's physical and mental state and any changes therein.

[1047] Step 5:

[1048] Based on the analysis results, the server generates advice for the driver to take a break and sends it to the terminal. For example, a notification may be created in the form of, "The driver has been driving continuously for a long period of time, so we recommend that you take a five-minute break." The input is the results regarding the driver's physical and mental state and any changes therein, and the output is advice to the driver.

[1049] Step 6:

[1050] The terminal notifies the driver of the advice provided by the server. Notification methods include pop-up notifications and voice assistants. Advice such as suggestions for taking a break is displayed to the driver at appropriate times. The input is the advice sent from the server, and the output is the advice notified to the driver.

[1051] Step 7:

[1052] The terminal also has a means for automatically switching to autonomous driving mode depending on the driver's physical and mental state. If the system determines that the driver is excessively fatigued, a command to switch to autonomous driving mode is sent from the terminal to the vehicle's control device. The input is the decision to switch to autonomous driving based on the driver's physical and mental state, and the output is the vehicle being switched to autonomous driving mode.

[1053] 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.

[1054] ---

[1055] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[1056] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[1057] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[1058] The collected facial expression and tone data are pre-processed on the device. In pre-processing, the video data is passed through a facial recognition algorithm to extract facial expression features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[1059] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns. This is where the emotion engine plays an important role.

[1060] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[1061] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expressions indicating fatigue through the camera and a decrease in the tone of their voice through the microphone is collected. Furthermore, the emotion engine uses this data to accurately recognize the user's fatigue and stress.

[1062] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen or a voice assistant.

[1063] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and switch to a setting where they can manually report their state of mind: periodically, a pop-up appears, prompting the user to enter their current mood and fatigue level.

[1064] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[1065] ---

[1066] The processing flow will be explained below.

[1067] ---

[1068] Step 1:

[1069] The user installs the application on their electronic device and enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched.

[1070] Step 2:

[1071] The device will ask the user for permission to use the camera and microphone, and if the user grants permission, will activate these devices.

[1072] Step 3:

[1073] While the user is working, the device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner position, etc.).

[1074] Step 4:

[1075] At the same time, the device collects voice data through the microphone, including the user's voice tone, pitch, speed and emotional nuances.

[1076] Step 5:

[1077] The device connects to the API of the calendar or meeting app to obtain data on the frequency and duration of meetings.

[1078] Step 6:

[1079] The device collects the number and content of the user's chat and email communications, and collects the volume and tone of communication.

[1080] Step 7:

[1081] The facial expression data collected by the device is preprocessed and passed through a facial recognition algorithm to extract facial features.

[1082] Step 8:

[1083] The voice data collected by the device is preprocessed and passed through an emotion analysis algorithm to extract emotional features.

[1084] Step 9:

[1085] The device sends the preprocessed data to the server, which includes facial expression features, vocal tone features, meeting frequency and duration, and communication volume and tone.

[1086] Step 10:

[1087] The server analyzes the received data in real time and identifies significant changes in facial expression (e.g., a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[1088] Step 11:

[1089] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[1090] Step 12:

[1091] The server uses an emotion engine to recognize the user's emotion from the facial expression data and tone of voice data, for example, if the emotion is classified as "sadness" or "fatigue", the server generates the data.

[1092] Step 13:

[1093] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[1094] Step 14:

[1095] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[1096] Step 15:

[1097] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[1098] Step 16:

[1099] Based on the changes and emotion data recognized by the server, the server generates specific advice for the user, such as "You have a series of consecutive meetings. We recommend you take a five-minute break."

[1100] Step 17:

[1101] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[1102] Step 18:

[1103] Users can adjust their privacy settings to disable constant camera and microphone monitoring, and can manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[1104] ---

[1105] Following this step, the system can effectively monitor changes in the user's physical and mental state and emotions and suggest appropriate measures.

[1106] Example 2

[1107] 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."

[1108] Conventional systems face the challenge of effectively monitoring a user's physical and mental state and providing appropriate measures based on that information. In particular, there is a lack of means to accurately assess a user's stress and fatigue by collecting and analyzing facial expression and tone of voice data in real time. Furthermore, there is a need for a method to collect the necessary data while ensuring user privacy.

[1109] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via a photographing device and a voice input device of the user's electronic device, means for acquiring the frequency and duration of communication, and means for acquiring the amount and content of the user's communication. This makes it possible to recognize changes in the user's mental and physical state in real time and provide appropriate countermeasures. In addition, the server is equipped with a data collection means for evaluating emotions and a means for evaluating workload, making it possible to accurately recognize the user's accurate emotional state and workload. Combining these means makes it possible to effectively manage the user's mental health and prevent excessive stress and fatigue.

[1110] "User's Electronic Device" refers to electronic devices used by a User, such as a computer, smartphone, or tablet.

[1111] "Photography device" refers to a video input device such as a camera or webcam installed in an electronic device.

[1112] "Audio input device" refers to a microphone or audio collection device installed in an electronic device.

[1113] "Facial expression data" refers to digital information obtained from key facial features of a user and is used to assess emotions and stress levels.

[1114] "Voice data" refers to digital information derived from the tone, pitch, rate and emotional nuances of a user's voice, which is used to assess emotions and stress levels.

[1115] "Frequency of communication" refers to the number of communications a user makes using an electronic device.

[1116] "Communication time" refers to the total time a user communicates using an electronic device.

[1117] "Volume of communication" refers to the amount of data a user sends and receives via electronic devices.

[1118] "Content of communication" refers to the specific content and nature of the communication a user makes through an electronic device.

[1119] "Preprocessing" refers to the process of converting collected raw data into an analyzable format, including feature extraction and data shaping.

[1120] "Preprocessed data" refers to data that has been converted into an analyzable format by preprocessing.

[1121] "User's physical and mental state" refers to the user's mental and physical health, including emotions, stress, fatigue, etc.

[1122] "Measures" refers to advice and guidelines provided to improve a user's physical or mental condition.

[1123] A "pop-up notification" refers to a message window that suddenly appears on the screen of an electronic device.

[1124] "Audio output device" refers to an audio output device such as a speaker or a headphone that is installed in an electronic device.

[1125] "Means for assessing emotions" refers to algorithms or processes that use facial expression data and tone of voice data to recognize and assess a user's emotional state.

[1126] "Means for assessing workload" refers to the process of analyzing data such as a user's work history and the frequency, time, and content of communications to assess the workload level.

[1127]

[1128] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[1129] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[1130] Next, data is collected using the user's camera and voice input devices. While the user is working using a PC or smartphone, facial expression data is collected through the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected through the voice input device. This voice tone data includes the user's voice tone, pitch, speed, and emotional nuances.

[1131] The collected facial expression and tone data are pre-processed on the device. During pre-processing, the video data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib) to extract facial expression features, and the audio data is passed through an emotion analysis algorithm (e.g., Google Speech API, Azure Cognitive Services) to extract emotional features.

[1132] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in the frequency, time, volume, and content of communication. This is where the emotion engine plays an important role.

[1133] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[1134] As a concrete example, consider the case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as whether the user's facial expression indicates fatigue through a camera device and whether the tone of their voice is declining through a voice input device is collected. Based on this data, the emotion engine recognizes the user's fatigue and stress with high accuracy.

[1135] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen and an audio output device.

[1136] Furthermore, if users value privacy, they can disable the continuous monitoring of the camera and audio input devices and switch to a setting where they can manually report their condition by entering their current mood and fatigue level in a pop-up that appears periodically.

[1137] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[1138] Examples of prompts for generative AI models include:

[1139] "Please explain in detail how the system detects user fatigue and suggests appropriate breaks when the user is participating in long, continuous online meetings. Please also include the collection method for facial expression and tone of voice data, pre-processing steps, real-time analysis process, and specific notification methods."

[1140] Based on this prompt, a more detailed understanding can be gained by referring to the explanation provided by the generative AI model.

[1141] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1142] Step 1:

[1143] A user installs an application on an electronic device (e.g., a computer, a smartphone, a tablet, etc.).

[1144] Input: Application installer

[1145] Output: Installed applications

[1146] What happens: A user runs an application installer and follows the installation wizard to complete the installation.

[1147] Step 2:

[1148] When a user launches the application for the first time, they fill out a questionnaire form with information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves.

[1149] Input: Survey form

[1150] Output: Baseline data

[1151] Specific operation: The user fills in each item on the questionnaire form and presses the "Submit" button. The device saves the input data and generates baseline data.

[1152] Step 3:

[1153] The user turns on the photographing device and the audio input device of the electronic device.

[1154] Input: Camera and audio input devices

[1155] Output: Devices ready for use

[1156] Specific behavior: The user checks the camera and microphone settings and turns them on.

[1157] Step 4:

[1158] The device collects the user's facial expression data through a camera, and uses a facial recognition algorithm (e.g., OpenCV) to detect key facial features (e.g., eye movements, mouth corners, etc.).

[1159] Input: Camera image

[1160] Output: Facial expression data

[1161] Specific operation: The device processes camera footage in real time, applies a facial recognition algorithm to extract facial features, and generates facial expression data.

[1162] Step 5:

[1163] The device collects the user's voice data through the voice input device and uses a speech recognition algorithm (e.g., Google Speech API) to detect the tone, pitch, rate, and emotional nuances of the voice.

[1164] Input: Voice input

[1165] Output: Voice tone data

[1166] Specific operation: The device processes the voice data collected from the microphone in real time, applies a voice recognition algorithm to extract voice characteristics, and generates voice data.

[1167] Step 6:

[1168] The collected facial expression and vocal tone data are preprocessed: the facial expression data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib), and the vocal data is passed through a sentiment analysis algorithm (e.g., Google Speech API, Azure Cognitive Services).

[1169] Input: Facial expression data, voice data

[1170] Output: Preprocessed data

[1171] Specific operation: The device passes the facial expression data through a facial recognition algorithm to extract facial expression features, and passes the voice data through an emotion analysis algorithm to extract emotional features.

[1172] Step 7:

[1173] The preprocessed data is sent to the server.

[1174] Input: Preprocessed data

[1175] Output: Data sent to the server

[1176] Specific operation: The device sends the preprocessed data to the server over the network, where a secure data transfer protocol (e.g., HTTPS) is used.

[1177] Step 8:

[1178] The server analyzes the received data in real time, and uses an emotion engine to detect the user's stress level and emotional fluctuations from changes in facial expressions and tone of voice.

[1179] Input: Received data

[1180] Output: Emotion and stress level assessment results

[1181] How it works: The server uses an emotion engine to analyze the received data and evaluate the user's emotions and stress level.

[1182] Step 9:

[1183] To assess workload, the server analyzes data on the frequency, time, volume, and content of communications, and compares it with historical data on work to determine the user's workload.

[1184] Input: communication data, business history data

[1185] Output: Workload evaluation results

[1186] Specific operation: The server analyzes the communication data and compares it with work history data to determine the user's workload level.

[1187] Step 10:

[1188] The server provides the user with measures based on the analysis results, such as generating a message like, "You've been in a lot of meetings lately and are feeling tired. We recommend you take a five-minute break."

[1189] Input: Evaluation result

[1190] Output: Solution message

[1191] Specific operation: The server generates an appropriate countermeasure message based on the evaluation results and sends it to the terminal.

[1192] Step 11:

[1193] The device receives the countermeasure message from the server and notifies the user using a pop-up notification or audio output device.

[1194] Input: Action message

[1195] Output: User notification

[1196] Specific actions: The device will present the countermeasure message to the user via a pop-up notification or audio output device.

[1197] Step 12:

[1198] If the user adjusts their privacy settings and disables continuous monitoring of the camera and audio input devices, they can manually switch to reporting the status.

[1199] Input: Privacy Settings Request

[1200] Output: New configuration state

[1201] What it does: The user changes the privacy settings in the app's settings menu to disable continuous camera and microphone monitoring. The device periodically displays a pop-up allowing the user to manually enter their current mood and fatigue level.

[1202] (Application example 2)

[1203] 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."

[1204] Delivery workers' long working hours and irregular working environments can damage their physical and mental health. For this reason, there is a need for a system that monitors workers' stress and fatigue in real time and encourages them to take breaks at appropriate times. However, conventional monitoring systems have limitations, making it difficult to provide effective notifications and advice. The present invention aims to solve these problems and provide a system that efficiently maintains and improves workers' mental health.

[1205] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of situations, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting means and acquiring means, means for analyzing the preprocessed data using a generative AI model to recognize changes in the user's mental and physical state, and means for providing advice to the user via prompt sentences based on the changes. This makes it possible to monitor the mental health of delivery personnel in real time and propose necessary measures at the appropriate time.

[1206] "User's physical and mental state" refers to the user's psychological and physiological health.

[1207] "Electronic devices" refers to electronic devices such as computers, smartphones, and tablets.

[1208] A "camera" refers to a device that captures images or videos and records them as data.

[1209] A "microphone" refers to a device that collects sound and records it as data.

[1210] "Facial expression data" refers to information about a user's facial expressions.

[1211] "Voice Data" refers to information about the tone, pitch, rate, and emotional nuances of a user's voice.

[1212] "Frequency and duration of a situation" refers to how often a user performs a particular activity and the amount of time spent on that activity.

[1213] "Volume and content of communication" refers to the volume and content of messages exchanged by users.

[1214] "Preprocessing" refers to the preliminary processing of collected data to convert it into a format that can be analyzed.

[1215] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and recognize the user's emotions and state.

[1216] A "prompt" refers to an instruction or advice sentence that is input into a generative AI model.

[1217] "Means for providing advice" refers to means for providing appropriate measures or notifications to users based on their physical or mental condition.

[1218] "Pop-up notification" refers to a notification message that appears on the screen.

[1219] A "voice assistant" refers to software that interacts with users through voice and responds or takes action based on instructions.

[1220] The present invention is a system that monitors the physical and mental state of delivery workers in real time and encourages them to take breaks at appropriate times. This system is composed of an application installed on the user's electronic device (such as a smartphone) and a server. A specific embodiment of this system is described below.

[1221] First, the user installs the application on their smartphone. When they first launch it, they enter information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves. This information is then saved on the server as the user's baseline data.

[1222] Next, data is collected using the smartphone's camera and microphone during delivery operations. The camera collects facial expression data, and the microphone collects voice data. Specifically, data is collected on facial features, voice tone, pitch, speed, etc.

[1223] The collected data is preprocessed on the smartphone. In preprocessing, facial recognition algorithms such as OpenCV are used to extract facial expression features. In addition, emotion analysis algorithms (usually VoiceEmotionAnalyzer, etc.) are used to extract features from the voice data.

[1224] The preprocessed data is sent to a server, which then analyzes it using a generative AI model (such as the EmotionEngine API). The generative AI model analyzes the data and recognizes changes in the user's mental and physical state and emotions. Specifically, the following prompts are used to input emotional data into the AI:

[1225] "User facial expression and voice data:

[1226] Facial expression data: {cameraData}

[1227] Voice data: {microphoneData}

[1228] Analyze your emotional state and provide appropriate suggestions for mental health management.

[1229] Based on the analysis results, the server generates appropriate advice for the user. This advice is conveyed via a smartphone pop-up notification or voice assistant. For example, a message such as "Your current stress level is high. We recommend you take a five-minute break" is displayed.

[1230] Additionally, users can set it up so they can limit camera and microphone usage for privacy reasons, and manually report their situation and self-assess their emotional state at specified intervals.

[1231] In this way, the system can monitor the user's physical and mental state in real time and provide effective advice at the appropriate time, thereby protecting the mental health of delivery workers and improving their work efficiency.

[1232] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1233] Step 1:

[1234] The user installs the application on their smartphone and, when they first start it, enters information such as their mental health status, the type and workload of their work, and how they take breaks. This information is then saved on the server as baseline data.

[1235] Input: User-entered mental health status, work information

[1236] Output: Baseline data is saved to the server

[1237] Step 2:

[1238] The terminal (smartphone) uses a camera and microphone to collect facial expression data and tone of voice data of the user during delivery work.

[1239] Input: User's face and voice data

[1240] Output: Collected facial expression data and voice data

[1241] Step 3:

[1242] The device preprocesses the collected data. Specifically, it uses OpenCV to extract facial features and VoiceEmotionAnalyzer to extract voice features.

[1243] Input: facial expression data, voice data

[1244] Output: Data converted into features

[1245] Step 4:

[1246] The terminal transmits the preprocessed data to the server.

[1247] Input: Feature data

[1248] Output: Data is sent to the server

[1249] Step 5:

[1250] The server analyzes the transmitted data using a generative AI model (such as the EmotionEngine API), inputs the user's emotional state into the AI ​​via prompt sentences, and recognizes the user's physical and mental state and emotional changes.

[1251] Input: "User's facial expression and voice data:

[1252] Facial expression data: {cameraData}

[1253] Voice data: {microphoneData}

[1254] Analyze your emotional state and provide appropriate suggestions for mental health management.

[1255] Output: Parsed user emotional state data

[1256] Step 6:

[1257] The server generates appropriate advice for the user based on the analysis results.

[1258] Input: Analysis results

[1259] Output: Advice statement

[1260] Step 7:

[1261] The device receives advice from the server and conveys it to the user via a pop-up notification or voice assistant.

[1262] Input: Advice from the server

[1263] Output: Pop-up notification or audio notification

[1264] Step 8:

[1265] If a user wants to restrict camera and microphone usage, they manually report their status to the application and self-assess their emotional state.

[1266] Input: Manually reported data by the user

[1267] Output: Manually reported data is sent to the server and updated as baseline data.

[1268] 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.

[1269] 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.

[1270] 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.

[1271] [Fourth embodiment]

[1272] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1273] 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.

[1274] 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).

[1275] 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.

[1276] 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.

[1277] 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).

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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."

[1285] ---

[1286] The present invention provides a system for monitoring a user's physical and mental state and proposing appropriate measures. This system operates on the user's electronic device (e.g., a computer, a smartphone, a tablet, etc.). Specific embodiments of this system are described in detail below.

[1287] In one embodiment of this system, the user first installs the application on their electronic device. After installation, the user enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the system is first launched. This information is used as the user's baseline data.

[1288] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[1289] The collected facial expression data and vocal tone data are pre-processed on the electronic device. In the pre-processing, the video data is passed through a facial recognition algorithm to extract facial features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[1290] The preprocessed data is sent to a server, which analyzes it in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns.

[1291] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expression indicating fatigue through the camera and a decrease in the tone of their voice through the microphone are collected. The server analyzes this data and determines whether the user is excessively tired.

[1292] Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice via a pop-up notification on the PC screen or a voice assistant.

[1293] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and manually report their state of mind. A pop-up will appear periodically, prompting users to enter their current mood and fatigue level.

[1294] This allows the system to effectively monitor the user's physical and mental state and propose appropriate measures. Users can quickly recognize physical and mental stress that they may not notice themselves, and by taking appropriate measures to refresh themselves and adjust their work, they can prevent mental disorders and make it easier to maintain motivation.

[1295] ---

[1296] The processing flow will be explained below.

[1297] ---

[1298] Step 1:

[1299] The user installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves in a questionnaire form that appears when the application is first launched.

[1300] Step 2:

[1301] The device activates the user's camera and microphone. It requires the user's permission and starts operation after receiving permission.

[1302] Step 3:

[1303] The device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner positions, etc.).

[1304] Step 4:

[1305] The device collects voice data via a microphone, including the tone, pitch, speed and emotional nuances of the user's voice.

[1306] Step 5:

[1307] The device obtains the frequency and duration of meetings. It connects with the APIs of calendar and meeting apps to collect the number of meetings and the duration of each meeting.

[1308] Step 6:

[1309] The device collects data on the volume and content of user communications. Data is collected to analyze the number of chats and emails sent and received and the tone of the content.

[1310] Step 7:

[1311] The facial expression data collected by the device is preprocessed, and the video data is passed through a facial recognition algorithm to extract facial expression features.

[1312] Step 8:

[1313] The device preprocesses the collected voice data, then passes the voice data through an emotion analysis algorithm to extract emotional features.

[1314] Step 9:

[1315] The device sends the preprocessed data to the server, which includes facial expression features, vocal tone features, meeting frequency and duration, and communication volume and tone.

[1316] Step 10:

[1317] The server analyzes the received data in real time and identifies significant changes in facial expression (for example, a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[1318] Step 11:

[1319] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[1320] Step 12:

[1321] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[1322] Step 13:

[1323] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[1324] Step 14:

[1325] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[1326] Step 15:

[1327] Based on the changes the server recognizes, it generates specific advice for the user, such as "You have a series of back-to-back meetings. We recommend you take a five-minute break."

[1328] Step 16:

[1329] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[1330] Step 17:

[1331] Users can configure privacy settings, disable constant camera and microphone monitoring, and manually report their status. A pop-up periodically appears, prompting users to enter their current mood and fatigue level.

[1332] ---

[1333] Example 1

[1334] 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."

[1335] Conventional mental healthcare systems have struggled to closely monitor users' physical and mental conditions in real time and provide appropriate advice. Furthermore, they lacked mechanisms for collecting and analyzing data while respecting users' privacy. As a result, it was difficult for users to become aware of their own health conditions early and take appropriate measures.

[1336] 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.

[1337] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for transmitting the preprocessed data to the server, means for analyzing the transmitted data in real time and recognizing changes in the user's mental and physical state, and means for providing advice to the user based on the recognized changes. This makes it possible to monitor the user's mental and physical state in detail and in real time and provide appropriate advice. Furthermore, data can be collected and analyzed while respecting the user's privacy.

[1338] A "user" is an individual who uses this system.

[1339] "Physical and mental health" refers to the user's mental and physical health.

[1340] "Electronic devices" are devices used by users, such as computers, smartphones, and tablets.

[1341] "Camera and microphone" means a device that collects video and audio built into or connected to an electronic device.

[1342] "Facial expression data" is information on the user's facial movements and expressions collected using a camera.

[1343] "Voice data" refers to voice information such as the tone, pitch, and speed of a user's voice collected using a microphone.

[1344] A "means" is a device, software, algorithm, or method for achieving a particular function or purpose.

[1345] "Meeting frequency and duration" refers to the number of meetings a user participates in and the duration of each meeting.

[1346] "Amount and content of communication" refers to the number of communications a user makes and the detailed content of those communications.

[1347] "Preprocessing" is the process of shaping or transforming the raw data collected into a form suitable for analysis.

[1348] A "server" is a computer system that processes and stores data and communicates with users' electronic devices over a network.

[1349] "Real-time analysis" means processing data as soon as it is received and providing an immediate assessment of the user's situation.

[1350] "Recognizing changes" refers to comparing past data with current data to determine whether a significant change has occurred in the user's physical or mental state.

[1351] "Providing advice" means notifying the user of measures or recommendations based on the analysis results.

[1352] MODE FOR CARRYING OUT THE INVENTION

[1353] System Overview

[1354] The present invention is a system for monitoring a user's physical and mental state and proposing appropriate measures. This system is based on an application installed on the user's electronic device (e.g., computer, smartphone, tablet).

[1355] Hardware and software used

[1356] Electronic devices: computers, smartphones, tablets, etc.

[1357] Camera: an image-collecting device built into or connected to an electronic device

[1358] microphone: a sound-collecting device built into or connected to an electronic device

[1359] Face recognition library: OpenCV

[1360] Voice emotion recognition tools: Sentiment analysis algorithms (e.g. IBM Watson)

[1361] Data transmission protocol: HTTPS

[1362] Program processing flow

[1363] When a user installs the application on their device, a questionnaire form is displayed the first time they start it. This form asks questions about the user's mental health, the type and workload of their work, and how they take breaks and refresh themselves, and this information is used as baseline data.

[1364] The device uses a camera and microphone to collect data in real time as the user performs their tasks: the camera captures key facial features (e.g., eye movements, mouth corner position), and the microphone records the tone, pitch, speed, and emotional nuances of the voice.

[1365] The device preprocesses the collected facial and vocal data, specifically using the OpenCV library for facial recognition and feature extraction, and for the voice data, it uses IBM Watson's voice emotion recognition tool to calculate an emotion score (e.g., 50% joy, 10% anger).

[1366] Data transmission and processing on the server

[1367] The pre-processed data is periodically sent to a server, which analyzes the data in real time to detect changes in the user's physical and mental state. Specifically, it evaluates the following:

[1368] Detecting user stress levels and emotional fluctuations from changes in facial expressions and tone of voice

[1369] Determine workload based on meeting volume and communication patterns

[1370] Advice Generation and Notifications

[1371] The server generates appropriate advice based on the analysis results, which is then sent to the device and notified to the user via a pop-up notification or voice assistant.

[1372] Specific examples

[1373] For example, if a user is continuously participating in online meetings for a long period of time, the device will record the frequency and duration of the meetings, the camera will detect fatigue from the user's facial expressions, and the microphone will capture a drop in the tone of their voice. The server will analyze this data and generate advice such as "You've been in a lot of meetings today. We recommend you take a five-minute break," and the device will notify the user.

[1374] Example prompt sentence:

[1375] What advice will the system give if a user is in an online meeting for three consecutive hours?

[1376] How can cameras and microphones be used to gather stress indicators for long work hours?

[1377] Privacy Settings

[1378] If users value privacy, they can disable constant camera and microphone monitoring and manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[1379] This allows the system to effectively monitor the user's physical and mental state and suggest appropriate measures, making it easier for the user to maintain their health.

[1380] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1381] Step 1: User installs the application

[1382] Description: A user installs an application on their electronic device (computer, smartphone, tablet, etc.). This installation process is done through an official website or app store.

[1383] Input: User's electronic device

[1384] Output: Installed applications

[1385] Step 2: Fill out the initial survey form

[1386] Description: When a user launches the application for the first time, a questionnaire form is displayed. The user enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves. This data is used as baseline data and will be the basis for future analysis.

[1387] Input: User's own mental health status, type and workload of work, methods of rest and refreshment

[1388] Output: Baseline data

[1389] Step 3: Data Collection (Camera and Microphone)

[1390] Description: The device uses a camera and microphone to collect data in real time as the user goes about their daily tasks. The camera captures key facial features (eye movements, mouth corner position, etc.), and the microphone records the tone, pitch, speed, and emotional nuances of the user's voice.

[1391] Input: Real-time video and audio data

[1392] Output: Raw facial expression data, voice data

[1393] Step 4: Preprocessing the data

[1394] Description: The device preprocesses the collected facial expression and voice data. Specifically, it uses the OpenCV library to perform facial recognition and extract feature points. For voice data, it also uses IBM Watson's voice emotion recognition tool to extract emotional features.

[1395] Input: Raw facial expression data, voice data

[1396] Output: Preprocessed facial expression feature data, emotion feature data

[1397] Specific operation:

[1398] Using OpenCV, the positions of eyes and mouth corners are detected from video data.

[1399] Calculates emotion scores from voice data using IBM Watson

[1400] Step 5: Sending data to the server

[1401] Description: The device periodically sends pre-processed data to the server using a secure protocol (e.g. HTTPS).

[1402] Input: Preprocessed facial expression feature data, emotion feature data

[1403] Output: Data sent to the server

[1404] Step 6: Data analysis by the server

[1405] Description: The server analyzes the received data in real time and recognizes changes in the user's physical and mental state. Specifically, it detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determines workload from the number of meetings and communication patterns.

[1406] Input: Preprocessed facial expression feature data, emotion feature data

[1407] Output: Evaluation results of the user's mental and physical state

[1408] Specific operation:

[1409] Evaluate changes in stress levels by comparing with past data stored in a database

[1410] Analyze meeting duration and frequency to calculate workload

[1411] Step 7: Advice generation and notification

[1412] Description: The server generates appropriate advice based on the analysis results and sends it to the device, which then communicates this advice to the user via a pop-up notification or voice assistant.

[1413] Input: Evaluation results of the user's mental and physical state

[1414] Output: Advice notice to user

[1415] Specific operation:

[1416] Generate notification messages such as "You've had a lot of meetings today. We suggest you take a 5-minute break."

[1417] Notify users via pop-ups or voice assistants

[1418] Step 8: Change your privacy settings

[1419] Description: If the user values ​​privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting that allows the user to manually report their status. A pop-up will appear periodically, prompting the user to enter their current mood and fatigue level.

[1420] Input: User privacy settings, manually entered mood and fatigue levels

[1421] Output: Updated user data and privacy settings

[1422] Specific operation:

[1423] In the Privacy Settings menu, select "Disable camera and microphone monitoring"

[1424] A popup for manual input appears, allowing the user to enter their mood and fatigue level.

[1425] (Application example 1)

[1426] 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."

[1427] Conventional in-vehicle driver physical and mental state monitoring systems lack the technology to properly detect driver fatigue and stress and provide the driver with countermeasures in real time. Furthermore, they are unable to automatically switch the vehicle's driving mode based on the driver's physical and mental state, making it difficult to ensure the driver's safety and comfort. To solve these problems, a system is needed that precisely monitors the driver's physical and mental state and provides advice at the appropriate time.

[1428] 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.

[1429] In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of meetings, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting and acquiring means, means for analyzing the preprocessed data and recognizing changes in the user's mental and physical state, means for providing advice to the user based on the changes, means for collecting facial expression data and voice data of the driver in the vehicle and monitoring the driver's mental and physical state, and means for switching driving modes based on the driver's mental and physical state. This makes it possible to precisely monitor the driver's mental and physical state and provide appropriate advice in real time, thereby ensuring the driver's safety and comfort.

[1430] The "system for monitoring the user's mental and physical state" is a mechanism for monitoring the user's mental and physical state by collecting and analyzing the user's facial expression data and tone of voice data.

[1431] "Electronic devices" is a general term for devices capable of collecting and processing digital data, such as personal computers, tablets, smartphones, and head-mounted displays.

[1432] A "camera" is a device that captures image data or video data.

[1433] A "microphone" is a device for collecting audio data.

[1434] "Facial expression data" refers to data about the features and movements of a user's face, acquired through a camera.

[1435] "Vocal timbre data" is data obtained through a microphone regarding the tone, pitch, rate, and emotional nuances of a user's voice.

[1436] "Data preprocessing" refers to a series of processes for converting acquired data into a format that is easy to analyze.

[1437] "Analysis" is the process of using pre-processed data to evaluate the user's physical and mental state and recognize changes in it.

[1438] "Means for providing advice" refers to a mechanism for suggesting appropriate actions or breaks to users based on the analysis results.

[1439] "Driving mode" refers to a mode that indicates how a vehicle is driven, and includes an automatic driving mode and a manual driving mode.

[1440] "Means for collecting facial expression data and voice data of the driver inside the vehicle" refers to a mechanism for collecting the driver's facial expressions and voice using a camera and microphone installed in the vehicle.

[1441] The "means for switching driving modes based on the user's physical and mental state" is a mechanism for automatically changing the driving mode of a vehicle in accordance with collected data on the user's physical and mental state.

[1442] The present invention is a system for monitoring the mental and physical state of a driver, switching the driving mode of a vehicle based on the state, and providing appropriate advice. The system is configured as follows.

[1443] First, the user installs the system in the vehicle. After installation, the head-mounted display (HMD) and in-car microphone are set up, and the system is ready to collect the driver's facial expression data and voice data.

[1444] While driving, the system collects facial expression data from the driver using a camera attached to the HMD, and collects audio data through an in-car microphone. The collected facial expression data includes key facial features such as eye movements and the position of the corners of the mouth, while the audio data includes tone, pitch, speed, and emotional nuances of the voice.

[1445] Once the data is collected, the device's software preprocesses it. This includes running the video data from the camera through a facial recognition algorithm (e.g., OpenCV) to extract facial features, and it also includes running the audio data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features.

[1446] The preprocessed data is sent to a server, which then analyzes the driver's physical and mental state in real time. The server detects stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. For example, if the server's analysis determines that the driver is feeling fatigued or stressed, the system will suggest that the driver take a break.

[1447] Furthermore, if a car is equipped with an autonomous driving function, it can automatically switch to autonomous driving mode depending on the driver's physical and mental state, ensuring safe driving even when the driver is fatigued.

[1448] The notification method is to provide advice to the driver through a pop-up notification or voice assistant, for example, "The system has detected that the driver has been driving continuously for a long period of time, so it is recommended that you take a five-minute break."

[1449] Furthermore, if the driver is concerned about privacy, the system can disable constant monitoring of the camera and microphone and switch to a setting where the driver can manually report their condition. For example, a pop-up will appear periodically, and the driver can input their "current mood and fatigue level," and the system can provide advice based on that information.

[1450] As a concrete example, a prompt using a generative AI model could be, "If a driver has been driving for a long time and is fatigued, how can we use the autonomous driving function to suggest a break?"

[1451] In this way, the system is able to precisely monitor the driver's physical and mental state and provide appropriate advice in real time, providing a safe and comfortable driving environment.

[1452] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1453] Step 1:

[1454] The device sets up a camera and microphone on the user's electronic device and starts collecting the driver's facial expression data and voice data. The camera captures key features of the driver's face (e.g., eye movements, position of the corners of the mouth, etc.), and the microphone records the driver's voice data (tone, pitch, speed, emotional nuances). The input is the camera image and voice data, and the output is the collected facial expression data and voice data.

[1455] Step 2:

[1456] The device passes the collected facial expression data through a facial recognition algorithm (e.g., OpenCV) to extract facial expression features. It also passes the voice data through an emotion analysis algorithm (e.g., a generative AI model) to extract emotional features. The input is the facial expression data and voice data collected in step 1, and the output is the facial expression data and voice data from which features have been extracted.

[1457] Step 3:

[1458] The device sends the preprocessed data (facial expression data and voice data from which features have been extracted) to the server. The server receives this data in real time and starts analysis according to the situation. The input is the facial expression data and voice data from which features have been extracted, and the output is the preprocessed data sent to the server.

[1459] Step 4:

[1460] The server analyzes the driver's physical and mental state in real time based on the received data. Specifically, it detects the driver's stress level and emotional fluctuations from changes in facial expressions and tone of voice, and evaluates the driver's fatigue based on continuous driving time and driving behavior. The input is preprocessed data, and the output is the driver's physical and mental state and any changes therein.

[1461] Step 5:

[1462] Based on the analysis results, the server generates advice for the driver to take a break and sends it to the terminal. For example, a notification may be created in the form of, "The driver has been driving continuously for a long period of time, so we recommend that you take a five-minute break." The input is the results regarding the driver's physical and mental state and any changes therein, and the output is advice to the driver.

[1463] Step 6:

[1464] The terminal notifies the driver of the advice provided by the server. Notification methods include pop-up notifications and voice assistants. Advice such as suggestions for taking a break is displayed to the driver at appropriate times. The input is the advice sent from the server, and the output is the advice notified to the driver.

[1465] Step 7:

[1466] The terminal also has a means for automatically switching to autonomous driving mode depending on the driver's physical and mental state. If the system determines that the driver is excessively fatigued, a command to switch to autonomous driving mode is sent from the terminal to the vehicle's control device. The input is the decision to switch to autonomous driving based on the driver's physical and mental state, and the output is the vehicle being switched to autonomous driving mode.

[1467] 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.

[1468] ---

[1469] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[1470] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[1471] Next, data is collected using the user's camera and microphone. When the user is working using a PC or smartphone, facial expression data is collected via the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected via the microphone. This voice tone data includes the user's tone, pitch, speed, and emotional nuances of their voice.

[1472] The collected facial expression and tone data are pre-processed on the device. In pre-processing, the video data is passed through a facial recognition algorithm to extract facial expression features, and the audio data is passed through an emotion analysis algorithm to extract emotional features.

[1473] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in meeting volume and communication patterns. This is where the emotion engine plays an important role.

[1474] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[1475] For example, consider a case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as the user's facial expressions indicating fatigue through the camera and a decrease in the tone of their voice through the microphone is collected. Furthermore, the emotion engine uses this data to accurately recognize the user's fatigue and stress.

[1476] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen or a voice assistant.

[1477] Additionally, if users are concerned about privacy, the system allows them to disable constant camera and microphone monitoring and switch to a setting where they can manually report their state of mind: periodically, a pop-up appears, prompting the user to enter their current mood and fatigue level.

[1478] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[1479] ---

[1480] The processing flow will be explained below.

[1481] ---

[1482] Step 1:

[1483] The user installs the application on their electronic device and enters information about their mental health, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched.

[1484] Step 2:

[1485] The device will ask the user for permission to use the camera and microphone, and if the user grants permission, will activate these devices.

[1486] Step 3:

[1487] While the user is working, the device collects facial expression data via the camera, including key facial features (e.g., eye movements, mouth corner position, etc.).

[1488] Step 4:

[1489] At the same time, the device collects voice data through the microphone, including the user's voice tone, pitch, speed and emotional nuances.

[1490] Step 5:

[1491] The device connects to the API of the calendar or meeting app to obtain data on the frequency and duration of meetings.

[1492] Step 6:

[1493] The device collects the number and content of the user's chat and email communications, and collects the volume and tone of communication.

[1494] Step 7:

[1495] The facial expression data collected by the device is preprocessed and passed through a facial recognition algorithm to extract facial features.

[1496] Step 8:

[1497] The voice data collected by the device is preprocessed and passed through an emotion analysis algorithm to extract emotional features.

[1498] Step 9:

[1499] The device sends the preprocessed data to the server, which includes facial expression features, vocal tone features, meeting frequency and duration, and communication volume and tone.

[1500] Step 10:

[1501] The server analyzes the received data in real time and identifies significant changes in facial expression (e.g., a long period of neutral expression or a sad face that differs from the normal facial expression pattern).

[1502] Step 11:

[1503] The server analyzes the pre-processed voice data and evaluates any drop in voice tone or tempo.

[1504] Step 12:

[1505] The server uses an emotion engine to recognize the user's emotion from the facial expression data and tone of voice data, for example, if the emotion is classified as "sadness" or "fatigue", the server generates the data.

[1506] Step 13:

[1507] The server analyzes the data on the number of meetings and determines the user's stress level and workload. For example, if the number of meetings increases sharply, the workload will be detected.

[1508] Step 14:

[1509] The server analyzes communication patterns and recognizes any spikes in chat or email volume or changes in tone.

[1510] Step 15:

[1511] The server compares the analysis results with the user's baseline data to detect anomalies, such as a sustained, clearly fatigued tone compared to normal tone, which is then recognized as a change.

[1512] Step 16:

[1513] Based on the changes and emotion data recognized by the server, the server generates specific advice for the user, such as "You have a series of consecutive meetings. We recommend you take a five-minute break."

[1514] Step 17:

[1515] The device will notify the user of the generated advice via a pop-up notification on the PC screen or a voice assistant.

[1516] Step 18:

[1517] Users can adjust their privacy settings to disable constant camera and microphone monitoring, and can manually report their status by entering their current mood and fatigue level in a periodic pop-up.

[1518] ---

[1519] Following this step, the system can effectively monitor changes in the user's physical and mental state and emotions and suggest appropriate measures.

[1520] Example 2

[1521] 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."

[1522] Conventional systems face the challenge of effectively monitoring a user's physical and mental state and providing appropriate measures based on that information. In particular, there is a lack of means to accurately assess a user's stress and fatigue by collecting and analyzing facial expression and tone of voice data in real time. Furthermore, there is a need for a method to collect the necessary data while ensuring user privacy.

[1523] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via a photographing device and a voice input device of the user's electronic device, means for acquiring the frequency and duration of communication, and means for acquiring the amount and content of the user's communication. This makes it possible to recognize changes in the user's mental and physical state in real time and provide appropriate countermeasures. In addition, the server is equipped with a data collection means for evaluating emotions and a means for evaluating workload, making it possible to accurately recognize the user's accurate emotional state and workload. Combining these means makes it possible to effectively manage the user's mental health and prevent excessive stress and fatigue.

[1524] "User's Electronic Device" refers to electronic devices used by a User, such as a computer, smartphone, or tablet.

[1525] "Photography device" refers to a video input device such as a camera or webcam installed in an electronic device.

[1526] "Audio input device" refers to a microphone or audio collection device installed in an electronic device.

[1527] "Facial expression data" refers to digital information obtained from key facial features of a user and is used to assess emotions and stress levels.

[1528] "Voice data" refers to digital information derived from the tone, pitch, rate and emotional nuances of a user's voice, which is used to assess emotions and stress levels.

[1529] "Frequency of communication" refers to the number of communications a user makes using an electronic device.

[1530] "Communication time" refers to the total time a user communicates using an electronic device.

[1531] "Volume of communication" refers to the amount of data a user sends and receives via electronic devices.

[1532] "Content of communication" refers to the specific content and nature of the communication a user makes through an electronic device.

[1533] "Preprocessing" refers to the process of converting collected raw data into an analyzable format, including feature extraction and data shaping.

[1534] "Preprocessed data" refers to data that has been converted into an analyzable format by preprocessing.

[1535] "User's physical and mental state" refers to the user's mental and physical health, including emotions, stress, fatigue, etc.

[1536] "Measures" refers to advice and guidelines provided to improve a user's physical or mental condition.

[1537] A "pop-up notification" refers to a message window that suddenly appears on the screen of an electronic device.

[1538] "Audio output device" refers to an audio output device such as a speaker or a headphone that is installed in an electronic device.

[1539] "Means for assessing emotions" refers to algorithms or processes that use facial expression data and tone of voice data to recognize and assess a user's emotional state.

[1540] "Means for assessing workload" refers to the process of analyzing data such as a user's work history and the frequency, time, and content of communications to assess the workload level.

[1541]

[1542] The present invention is a system for monitoring a user's mental and physical state and emotions and proposing appropriate measures. This system runs on the user's electronic device (e.g., computer, smartphone, tablet, etc.) and is implemented in combination with an emotion engine. Specific embodiments of this system are described in detail below.

[1543] In one embodiment of this system, a user first installs the application on their electronic device and enters information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves into a questionnaire form that is displayed when the application is first launched. This information is used as the user's baseline data.

[1544] Next, data is collected using the user's camera and voice input devices. While the user is working using a PC or smartphone, facial expression data is collected through the camera. This facial expression data includes key facial features (e.g., eye movements, mouth corner position, etc.) and is used to assess the user's emotions and stress level. Voice tone data is also collected through the voice input device. This voice tone data includes the user's voice tone, pitch, speed, and emotional nuances.

[1545] The collected facial expression and tone data are pre-processed on the device. During pre-processing, the video data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib) to extract facial expression features, and the audio data is passed through an emotion analysis algorithm (e.g., Google Speech API, Azure Cognitive Services) to extract emotional features.

[1546] The preprocessed data is sent to a server, which analyzes the data in real time and evaluates the user's physical and mental state based on the following points: detecting stress levels and emotional fluctuations from changes in facial expressions and tone of voice, and determining workload from changes in the frequency, time, volume, and content of communication. This is where the emotion engine plays an important role.

[1547] The emotion engine recognizes the user's emotions using facial expression data and tone of voice data and generates emotion change data. For example, if the user's facial expression looks sadder than usual, the emotion engine recognizes the emotion as "sadness." Similarly, emotions can also be analyzed from changes in tone of voice.

[1548] As a concrete example, consider the case where a user is continuously participating in online meetings for a long period of time. The device obtains the frequency and duration of the meetings and detects that the meetings are being held continuously. Furthermore, data such as whether the user's facial expression indicates fatigue through a camera device and whether the tone of their voice is declining through a voice input device is collected. Based on this data, the emotion engine recognizes the user's fatigue and stress with high accuracy.

[1549] The server analyzes this data and determines whether the user is overly tired. Based on this data, the server generates advice such as, "You've had a lot of meetings today. We recommend you take a five-minute break." The device notifies the user of this advice. Notification methods include a pop-up notification on the PC screen and an audio output device.

[1550] Furthermore, if users value privacy, they can disable the continuous monitoring of the camera and audio input devices and switch to a setting where they can manually report their condition by entering their current mood and fatigue level in a pop-up that appears periodically.

[1551] This allows the system to effectively monitor not only the user's physical and mental state but also their emotional changes, and propose appropriate measures. By quickly recognizing physical and mental stress and emotional fluctuations that users may not notice themselves, and taking appropriate measures to refresh themselves and adjust their work, users can prevent mental disorders and maintain motivation.

[1552] Examples of prompts for generative AI models include:

[1553] "Please explain in detail how the system detects user fatigue and suggests appropriate breaks when the user is participating in long, continuous online meetings. Please also include the collection method for facial expression and tone of voice data, pre-processing steps, real-time analysis process, and specific notification methods."

[1554] Based on this prompt, a more detailed understanding can be gained by referring to the explanation provided by the generative AI model.

[1555] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1556] Step 1:

[1557] A user installs an application on an electronic device (e.g., a computer, a smartphone, a tablet, etc.).

[1558] Input: Application installer

[1559] Output: Installed applications

[1560] What happens: A user runs an application installer and follows the installation wizard to complete the installation.

[1561] Step 2:

[1562] When a user launches the application for the first time, they fill out a questionnaire form with information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves.

[1563] Input: Survey form

[1564] Output: Baseline data

[1565] Specific operation: The user fills in each item on the questionnaire form and presses the "Submit" button. The device saves the input data and generates baseline data.

[1566] Step 3:

[1567] The user turns on the photographing device and the audio input device of the electronic device.

[1568] Input: Camera and audio input devices

[1569] Output: Devices ready for use

[1570] Specific behavior: The user checks the camera and microphone settings and turns them on.

[1571] Step 4:

[1572] The device collects the user's facial expression data through a camera, and uses a facial recognition algorithm (e.g., OpenCV) to detect key facial features (e.g., eye movements, mouth corners, etc.).

[1573] Input: Camera image

[1574] Output: Facial expression data

[1575] Specific operation: The device processes camera footage in real time, applies a facial recognition algorithm to extract facial features, and generates facial expression data.

[1576] Step 5:

[1577] The device collects the user's voice data through the voice input device and uses a speech recognition algorithm (e.g., Google Speech API) to detect the tone, pitch, rate, and emotional nuances of the voice.

[1578] Input: Voice input

[1579] Output: Voice tone data

[1580] Specific operation: The device processes the voice data collected from the microphone in real time, applies a voice recognition algorithm to extract voice characteristics, and generates voice data.

[1581] Step 6:

[1582] The collected facial expression and vocal tone data are preprocessed: the facial expression data is passed through a facial recognition algorithm (e.g., OpenCV, Dlib), and the vocal data is passed through a sentiment analysis algorithm (e.g., Google Speech API, Azure Cognitive Services).

[1583] Input: Facial expression data, voice data

[1584] Output: Preprocessed data

[1585] Specific operation: The device passes the facial expression data through a facial recognition algorithm to extract facial expression features, and passes the voice data through an emotion analysis algorithm to extract emotional features.

[1586] Step 7:

[1587] The preprocessed data is sent to the server.

[1588] Input: Preprocessed data

[1589] Output: Data sent to the server

[1590] Specific operation: The device sends the preprocessed data to the server over the network, where a secure data transfer protocol (e.g., HTTPS) is used.

[1591] Step 8:

[1592] The server analyzes the received data in real time, and uses an emotion engine to detect the user's stress level and emotional fluctuations from changes in facial expressions and tone of voice.

[1593] Input: Received data

[1594] Output: Emotion and stress level assessment results

[1595] How it works: The server uses an emotion engine to analyze the received data and evaluate the user's emotions and stress level.

[1596] Step 9:

[1597] To assess workload, the server analyzes data on the frequency, time, volume, and content of communications, and compares it with historical data on work to determine the user's workload.

[1598] Input: communication data, business history data

[1599] Output: Workload evaluation results

[1600] Specific operation: The server analyzes the communication data and compares it with work history data to determine the user's workload level.

[1601] Step 10:

[1602] The server provides the user with measures based on the analysis results, such as generating a message like, "You've been in a lot of meetings lately and are feeling tired. We recommend you take a five-minute break."

[1603] Input: Evaluation result

[1604] Output: Solution message

[1605] Specific operation: The server generates an appropriate countermeasure message based on the evaluation results and sends it to the terminal.

[1606] Step 11:

[1607] The device receives the countermeasure message from the server and notifies the user using a pop-up notification or audio output device.

[1608] Input: Action message

[1609] Output: User notification

[1610] Specific actions: The device will present the countermeasure message to the user via a pop-up notification or audio output device.

[1611] Step 12:

[1612] If the user adjusts their privacy settings and disables continuous monitoring of the camera and audio input devices, they can manually switch to reporting the status.

[1613] Input: Privacy Settings Request

[1614] Output: New configuration state

[1615] What it does: The user changes the privacy settings in the app's settings menu to disable continuous camera and microphone monitoring. The device periodically displays a pop-up allowing the user to manually enter their current mood and fatigue level.

[1616] (Application example 2)

[1617] 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."

[1618] Delivery workers' long working hours and irregular working environments can damage their physical and mental health. For this reason, there is a need for a system that monitors workers' stress and fatigue in real time and encourages them to take breaks at appropriate times. However, conventional monitoring systems have limitations, making it difficult to provide effective notifications and advice. The present invention aims to solve these problems and provide a system that efficiently maintains and improves workers' mental health.

[1619] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting facial expression data and tone of voice data via the camera and microphone of the user's electronic device, means for acquiring the frequency and duration of situations, means for acquiring the amount and content of the user's communication, means for preprocessing the data acquired by the collecting means and acquiring means, means for analyzing the preprocessed data using a generative AI model to recognize changes in the user's mental and physical state, and means for providing advice to the user via prompt sentences based on the changes. This makes it possible to monitor the mental health of delivery personnel in real time and propose necessary measures at the appropriate time.

[1620] "User's physical and mental state" refers to the user's psychological and physiological health.

[1621] "Electronic devices" refers to electronic devices such as computers, smartphones, and tablets.

[1622] A "camera" refers to a device that captures images or videos and records them as data.

[1623] A "microphone" refers to a device that collects sound and records it as data.

[1624] "Facial expression data" refers to information about a user's facial expressions.

[1625] "Voice Data" refers to information about the tone, pitch, rate, and emotional nuances of a user's voice.

[1626] "Frequency and duration of a situation" refers to how often a user performs a particular activity and the amount of time spent on that activity.

[1627] "Volume and content of communication" refers to the volume and content of messages exchanged by users.

[1628] "Preprocessing" refers to the preliminary processing of collected data to convert it into a format that can be analyzed.

[1629] A "generative AI model" refers to a model that uses artificial intelligence to analyze data and recognize the user's emotions and state.

[1630] A "prompt" refers to an instruction or advice sentence that is input into a generative AI model.

[1631] "Means for providing advice" refers to means for providing appropriate measures or notifications to users based on their physical or mental condition.

[1632] "Pop-up notification" refers to a notification message that appears on the screen.

[1633] A "voice assistant" refers to software that interacts with users through voice and responds or takes action based on instructions.

[1634] The present invention is a system that monitors the physical and mental state of delivery workers in real time and encourages them to take breaks at appropriate times. This system is composed of an application installed on the user's electronic device (such as a smartphone) and a server. A specific embodiment of this system is described below.

[1635] First, the user installs the application on their smartphone. When they first launch it, they enter information about their mental health status, the type and workload of their work, and how they take breaks and refresh themselves. This information is then saved on the server as the user's baseline data.

[1636] Next, data is collected using the smartphone's camera and microphone during delivery operations. The camera collects facial expression data, and the microphone collects voice data. Specifically, data is collected on facial features, voice tone, pitch, speed, etc.

[1637] The collected data is preprocessed on the smartphone. In preprocessing, facial recognition algorithms such as OpenCV are used to extract facial expression features. In addition, emotion analysis algorithms (usually VoiceEmotionAnalyzer, etc.) are used to extract features from the voice data.

[1638] The preprocessed data is sent to a server, which then analyzes it using a generative AI model (such as the EmotionEngine API). The generative AI model analyzes the data and recognizes changes in the user's mental and physical state and emotions. Specifically, the following prompts are used to input emotional data into the AI:

[1639] "User facial expression and voice data:

[1640] Facial expression data: {cameraData}

[1641] Voice data: {microphoneData}

[1642] Analyze your emotional state and provide appropriate suggestions for mental health management.

[1643] Based on the analysis results, the server generates appropriate advice for the user. This advice is conveyed via a smartphone pop-up notification or voice assistant. For example, a message such as "Your current stress level is high. We recommend you take a five-minute break" is displayed.

[1644] Additionally, users can set it up so they can limit camera and microphone usage for privacy reasons, and manually report their situation and self-assess their emotional state at specified intervals.

[1645] In this way, the system can monitor the user's physical and mental state in real time and provide effective advice at the appropriate time, thereby protecting the mental health of delivery workers and improving their work efficiency.

[1646] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1647] Step 1:

[1648] The user installs the application on their smartphone and, when they first start it, enters information such as their mental health status, the type and workload of their work, and how they take breaks. This information is then saved on the server as baseline data.

[1649] Input: User-entered mental health status, work information

[1650] Output: Baseline data is saved to the server

[1651] Step 2:

[1652] The terminal (smartphone) uses a camera and microphone to collect facial expression data and tone of voice data of the user during delivery work.

[1653] Input: User's face and voice data

[1654] Output: Collected facial expression data and voice data

[1655] Step 3:

[1656] The device preprocesses the collected data. Specifically, it uses OpenCV to extract facial features and VoiceEmotionAnalyzer to extract voice features.

[1657] Input: facial expression data, voice data

[1658] Output: Data converted into features

[1659] Step 4:

[1660] The terminal transmits the preprocessed data to the server.

[1661] Input: Feature data

[1662] Output: Data is sent to the server

[1663] Step 5:

[1664] The server analyzes the transmitted data using a generative AI model (such as the EmotionEngine API), inputs the user's emotional state into the AI ​​via prompt sentences, and recognizes the user's physical and mental state and emotional changes.

[1665] Input: "User's facial expression and voice data:

[1666] Facial expression data: {cameraData}

[1667] Voice data: {microphoneData}

[1668] Analyze your emotional state and provide appropriate suggestions for mental health management.

[1669] Output: Parsed user emotional state data

[1670] Step 6:

[1671] The server generates appropriate advice for the user based on the analysis results.

[1672] Input: Analysis results

[1673] Output: Advice statement

[1674] Step 7:

[1675] The device receives advice from the server and conveys it to the user via a pop-up notification or voice assistant.

[1676] Input: Advice from the server

[1677] Output: Pop-up notification or audio notification

[1678] Step 8:

[1679] If a user wants to restrict camera and microphone usage, they manually report their status to the application and self-assess their emotional state.

[1680] Input: Manually reported data by the user

[1681] Output: Manually reported data is sent to the server and updated as baseline data.

[1682] 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.

[1683] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1684] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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).

[1689] 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.

[1690] 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."

[1691] 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.

[1692] 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).

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] 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.

[1701] 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.

[1702] 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.

[1703] The following is further disclosed regarding the above embodiment.

[1704] ---

[1705] (Claim 1)

[1706] A system for monitoring the mental and physical state of a user, comprising:

[1707] means for collecting facial expression data and tone of voice data via a camera and a microphone of a user's electronic device;

[1708] A means for obtaining the frequency and duration of meetings;

[1709] A means for acquiring the amount and content of user communications;

[1710] means for pre-processing the data obtained by the collecting means and the acquiring means;

[1711] means for analyzing the pre-processed data and recognizing changes related to the user's physical and mental state;

[1712] means for providing advice to the user based on said changes;

[1713] A system including:

[1714] (Claim 2)

[1715] The system of claim 1 further comprising means for enabling the use of the camera and microphone to be configured based on user permission.

[1716] (Claim 3)

[1717] The system of claim 1 , further comprising means for communicating the advice to the user through a pop-up notification or a voice assistant.

[1718] (Claim 4)

[1719] 10. The system of claim 1, further comprising: means for providing a user with an input means for manually reporting the physical and mental state.

[1720] (Claim 5)

[1721] 10. The system of claim 1, further comprising means for collecting and analyzing said facial expression data and vocal tone data in real time.

[1722] (Claim 6)

[1723] The system of claim 1 , further comprising means for analyzing the amount and content of said communication and assessing a stress level of the user.

[1724] ---

[1725] The draft claims clearly outline the essential functions and features of the system.

[1726] "Example 1"

[1727] (Claim 1)

[1728] A system for monitoring the mental and physical state of a user, comprising:

[1729] means for collecting facial expression data and tone of voice data via a camera and a microphone of a user's electronic device;

[1730] A means for obtaining the frequency and duration of meetings;

[1731] A means for acquiring the amount and content of user communications;

[1732] means for pre-processing the data obtained by the collecting means and the acquiring means;

[1733] means for transmitting the preprocessed data to a server;

[1734] a means for analyzing the transmitted data in real time in the server and recognizing changes in the user's mental and physical state;

[1735] means for providing advice to the user based on the recognized changes;

[1736] A system including:

[1737] (Claim 2)

[1738] The system of claim 1 , further comprising means for enabling the use of the camera and microphone to be configured based on user permission.

[1739] (Claim 3)

[1740] The system of claim 1 , further comprising means for communicating the advice to the user through a pop-up notification or a voice assistant.

[1741] "Application Example 1"

[1742] (Claim 1)

[1743] A system for monitoring the mental and physical state of a user, comprising:

[1744] means for collecting facial expression data and tone of voice data via a camera and a microphone of a user's electronic device;

[1745] A means for obtaining the frequency and duration of meetings;

[1746] A means for acquiring the amount and content of user communications;

[1747] means for pre-processing the data obtained by the collecting means and the acquiring means;

[1748] means for analyzing the pre-processed data and recognizing changes related to the user's physical and mental state;

[1749] means for providing advice to the user based on said changes;

[1750] a means for collecting facial expression data and voice data of the driver in the vehicle and monitoring the mental and physical state of the driver;

[1751] A means for switching driving modes based on the mental and physical state of the driver;

[1752] A system including:

[1753] (Claim 2)

[1754] The system of claim 1 further comprising means for enabling the use of the camera and microphone to be configured based on user permission.

[1755] (Claim 3)

[1756] The system of claim 1 , further comprising means for communicating the advice to the user through a pop-up notification or a voice assistant.

[1757] "Example 2: Combining Emotion Engines"

[1758] (Claim 1)

[1759] A system for monitoring the mental and physical state of a user, comprising:

[1760] means for collecting facial expression data and voice tone data via a photographing device and a voice input device of a user's electronic device;

[1761] means for acquiring the frequency and duration of communication;

[1762] A means for acquiring the volume and content of user communications;

[1763] means for pre-processing the data obtained by the collecting means and the acquiring means;

[1764] means for analyzing the pre-processed data and recognizing changes related to the user's physical and mental state;

[1765] means for providing a user with a measure based on said change;

[1766] A means for learning facial expression data and tone of voice data of a user and evaluating emotions;

[1767] a means for assessing user workload;

[1768] A system including:

[1769] (Claim 2)

[1770] 10. The system according to claim 1, further comprising means for enabling setting of use of the photographing device and the audio input device based on user permission.

[1771] (Claim 3)

[1772] 10. The system of claim 1, further comprising means for communicating said countermeasure to a user through a pop-up notification or an audio output device.

[1773] The above is the rewritten scope of the patent claims by combining new parts from the description of the processing of the program of this system. Proper nouns, proper names, people's names, and company names have been converted to generic terms, and nouns have been converted to superordinate expressions.

[1774] "Application example 2 when combining emotion engines"

[1775] (Claim 1)

[1776] A system for monitoring the mental and physical state of a user, comprising:

[1777] means for collecting facial expression data and tone of voice data via a camera and a microphone of a user's electronic device;

[1778] means for acquiring the frequency and duration of the event;

[1779] A means for acquiring the amount and content of user communications;

[1780] means for pre-processing the data obtained by the collecting means and the acquiring means;

[1781] A means for analyzing the pre-processed data using a generative AI model to recognize changes in the user's mental and physical state;

[1782] means for providing advice to the user via prompt sentences based on said changes;

[1783] A system including:

[1784] (Claim 2)

[1785] The system of claim 1 further comprising means for enabling the use of the camera and microphone to be configured based on user permission.

[1786] (Claim 3)

[1787] The system of claim 1 , further comprising means for communicating the advice to the user through a pop-up notification or a voice assistant. [Explanation of symbols]

[1788] 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 system for monitoring the mental and physical state of a user, comprising: means for collecting facial expression data and tone of voice data via a camera and a microphone of a user's electronic device; A means for obtaining the frequency and duration of meetings; A means for acquiring the amount and content of user communications; means for pre-processing the data obtained by the collecting means and the acquiring means; means for analyzing the pre-processed data and recognizing changes related to the user's physical and mental state; means for providing advice to the user based on said changes; A system including:

2. The system of claim 1 , further comprising means for enabling the use of the camera and microphone to be configured based on user permission.

3. The system of claim 1 , further comprising means for communicating the advice to the user through a pop-up notification or a voice assistant.

4. 10. The system of claim 1, further comprising means for providing a user with an input means for manually reporting the physical and mental state.

5. The system of claim 1 further comprising means for collecting and analyzing said facial expression data and vocal tone data in real time.

6. The system of claim 1 , further comprising means for analyzing the amount and content of said communications and assessing a stress level of the user.

Images