System

Abstract

A system is provided.SOLUTION: A system comprising means for sentimentally analyzing input data from a user using an artificial intelligence model generated, means for evaluating a stress level based on the input data of the user, means for providing customized support according to the evaluated stress level, means for monitoring the input data and the stress level of the user in real time, and means for notifying an alert when a fluctuation of the stress level exceeds a certain standard.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] Volunteer activities during large-scale disasters pose problems such as high stress levels and psychological burdens for participants. This makes it difficult for volunteers to continue their activities efficiently and sustainably, and also has a negative impact on the volunteers' own mental health. Accumulating stress and fatigue can lead to impaired judgment and behavior, making real-time mental health management essential to addressing these issues. However, current systems make it difficult to effectively grasp the emotions and stress levels of individual volunteers and provide appropriate support. The problem this invention aims to solve is to improve this situation and provide efficient and effective stress management for volunteers. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a means for emotionally analyzing user input data using a generated artificial intelligence model. Specifically, the system analyzes text or voice data entered by the user, detects emotional nuances from the content, and assesses the user's stress level. It also includes a means for providing customized support based on the assessed stress level. This includes providing preventative advice for mild stress and recommending referral to a specialist or rest for severe stress. Furthermore, the system introduces a means for monitoring the user's input data and stress level in real time, and sends an alert if fluctuations in stress level exceed a certain threshold, enabling rapid response. These means enable appropriate stress management for volunteers and provide effective support.

[0006] "Generated artificial intelligence model" refers to the machine learning algorithm used to analyze input data from users and assess their emotions and stress levels.

[0007] "User input data" refers to information provided by users to the system in text or voice, such as impressions and progress reports during volunteer activities.

[0008] "Emotional analysis means" refers to processes and techniques for analyzing user-entered data and detecting emotional nuances from its content.

[0009] "Means for assessing stress level" refers to processes and techniques for quantitatively assessing a user's stress state based on the results of sentiment analysis.

[0010] "Means for providing customized support" refers to processes and techniques that provide users with individually appropriate advice and referrals based on their assessed stress level.

[0011] "Real-time monitoring measures" refers to processes and technologies for continuously monitoring user input data and stress levels and for immediately detecting anomalies or fluctuations.

[0012] "Means for notifying alerts" refers to processes and technologies for immediately notifying users of warnings and advice when fluctuations in stress levels exceed a certain standard.

[0013] "Referral to a specialist" refers to the process and techniques of recommending consultation with an appropriate specialist institution, counselor, etc. when a user is assessed to be in a state of severe stress. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a system that uses the generated artificial intelligence model to emotionally analyze input data from volunteers, evaluates stress levels based on the emotional analysis results, and provides customized support as needed. Embodiments of the invention are described in detail below.

[0036] Collecting User Input

[0037] First, the user uses a device (smartphone, tablet, PC, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, the user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0038] Data transmission

[0039] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0040] sentiment analysis

[0041] The server analyzes the received data using the generated artificial intelligence model. This model is built on machine learning algorithms and detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[0042] Stress level assessment

[0043] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, or severe.

[0044] Providing customized support

[0045] The server then offers customized support based on the assessed stress level: for mild stress, preventative advice such as "try some breathing exercises to relax" is suggested, while for severe stress, referrals to specialists or instructions such as "we strongly recommend you take some rest" are offered.

[0046] Support notification

[0047] The support content determined by the server is sent to the device and notified to the user, who can then check the notification within the application and take appropriate action.

[0048] Real-time monitoring and alerts

[0049] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0050] This allows the system to manage users' stress levels in real time and provide the necessary support, thereby maintaining volunteers' mental health and supporting effective disaster response.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0054] Step 2:

[0055] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0056] Step 3:

[0057] The server then passes the received data to the analysis module, which then begins analyzing it using the generated artificial intelligence model. This model is built on machine learning algorithms and can detect emotional nuances from the user's input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[0058] Step 4:

[0059] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, the sentiment analysis may evaluate the user as "70% stressed."

[0060] Step 5:

[0061] The server determines customized support based on the assessed stress level: for mild stress, it provides preventative advice, while for severe stress, it refers the user to a specialist or recommends rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0062] Step 6:

[0063] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0064] Step 7:

[0065] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0066] This process allows the system to manage the user's stress level in real time and provide appropriate support when needed.

[0067] Example 1

[0068] 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."

[0069] Conventional mental health management systems have had difficulty accurately grasping users' emotional states and stress levels and providing appropriate support. There is also a risk of user input data being leaked to external parties. In particular, there is a need for systems that can respond to fluctuations in stress levels in real time, so a new method was needed.

[0070] 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.

[0071] In this invention, the server includes means for performing emotional analysis using the generated artificial intelligence model, means for assessing the user's stress level based on the result of the emotional analysis, and means for providing customized support according to the assessed stress level, thereby making it possible to analyze the user's input data, appropriately assess the stress level, and provide customized support as needed.

[0072] A "generated artificial intelligence model" refers to a model of a machine learning algorithm that has been pre-trained to analyze user input data.

[0073] "Means for emotional analysis" refers to the process of using a generated artificial intelligence model to detect emotional nuances from user input data.

[0074] The "means for assessing stress level" refers to a process for quantitatively assessing the degree of stress of a user based on the results of sentiment analysis.

[0075] "Means for providing customized support" refers to a process for providing advice and support optimized for each user according to the assessed stress level.

[0076] "Means for encrypting and securely transmitting to the server" refers to the process of encrypting the user's input data and securely transmitting it to the server using a communication protocol.

[0077] "Real-time monitoring means" refers to the process of continuously monitoring user input data and stress levels to quickly detect fluctuations.

[0078] "Means for notifying an alert" refers to a process for sending a warning to a user or a relevant third party when fluctuations in stress levels exceed a set threshold.

[0079] "Means for accepting text or voice data and sending it to a server" refers to the process of receiving data entered by a user in text or voice format and transferring it to a server.

[0080] "Means for generating and sending referrals to specialists" refers to the process of generating referrals or consultation requests to specialists based on the results of stress assessments, as needed, and sending them through appropriate channels.

[0081] The present invention is a system that uses a generated artificial intelligence model to emotionally analyze input data from a user, evaluates the stress level based on the emotion analysis results, and provides customized support as needed. An embodiment of the present invention will be described in detail below.

[0082] Collecting User Input

[0083] Users can use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done either by text or voice, for example, by typing something like "Today's activities were very busy. I was especially tired from working in the morning," or by recording something using the voice input function.

[0084] Data transmission

[0085] The device encrypts the input data and sends it securely to the server. This transmission uses the HTTPS protocol. For example, when a user inputs text data or voice data, the device encrypts it and sends it to the server.

[0086] sentiment analysis

[0087] The server analyzes the received data using the generated artificial intelligence model. Specifically, the model is built on machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch. This model detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" or "stress" from the expression "very tired."

[0088] Stress level assessment

[0089] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, severe, etc. The evaluation is performed using statistical methods and the output of machine learning models.

[0090] Providing customized support

[0091] The server then provides customized support based on the assessed stress level. For example, for mild stress, preventative advice such as "Try some breathing exercises to relax" is suggested. For severe stress, the server may refer the user to a specialist or provide instructions such as "We strongly recommend you take some rest." This support is determined based on pre-defined rules and algorithms.

[0092] Support notification

[0093] The support content determined by the server is sent to the device and notified to the user. For example, a push notification is sent to a smartphone app. The user can check the notification and take appropriate action.

[0094] Real-time monitoring and alerts

[0095] The server monitors the user's situation in real time. Every time new data is entered, it performs emotion analysis and stress assessment, and if fluctuations in stress levels exceed a certain threshold, an alert is sent. For example, if a user frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0096] This allows the system to emotionally analyze user input data, monitor stress levels in real time, and provide appropriate support.

[0097] Specific examples

[0098] Example 1

[0099] A user uses a smartphone to voice input, "Work today was very stressful." The voice data is sent from the device to a server, which analyzes the data using the BERT model and determines the user's emotion as "stress." The server then sends a message to the device notifying the user, such as, "Your current stress level is medium. Please take an early rest today."

[0100] Example 2

[0101] A user uses a PC to input the text "I've been overwhelmed with work lately and I'm very tired." The text data is encrypted and sent to a server using the HTTPS protocol. The server uses a sentiment analysis model built with TensorFlow to evaluate the user's stress level as "severe" based on the expression "I'm very tired." The server then generates a message such as "I strongly recommend that you consult a specialist immediately" and sends it to the user's device.

[0102] Prompt Sentence Examples

[0103] "Design an algorithm that emotionally analyzes a user's input text and assesses their stress level. Then combine it with a model that generates a customized support message based on the assessment results."

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1: Collecting User Input

[0106] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done by text or voice. The input data is written in a text box in the application or recorded using the voice input function. Specifically, the user enters the text "I was very tired at work today" into the input form on the device and presses the send button.

[0107] Input: User impressions and activity reports (text or audio data)

[0108] Output: Input data in the terminal

[0109] Step 2: Send data

[0110] The terminal encrypts the data entered by the user and sends it to the server. This transmission uses the HTTPS protocol. Specifically, the terminal encrypts the input data and sends it to the server's API endpoint using HTTPS.

[0111] Input: Input data in the terminal

[0112] Data processing: Data encryption

[0113] Data calculation: Transmission using HTTPS protocol

[0114] Output: Encrypted data sent to the server

[0115] Step 3: Sentiment analysis

[0116] The server decrypts the received encrypted data and performs emotional analysis using the generated artificial intelligence model. Specific software used is TensorFlow and PyTorch. This allows emotions to be detected from the user's input data. Specifically, the server inputs emotions such as "tired" into the machine learning model, and detects "stress" and "fatigue."

[0117] Input: Encrypted data sent to the server

[0118] Data processing: Deciphering the data

[0119] Data Computing: Sentiment Analysis Using AI Models

[0120] Output: Sentiment analysis results (type and intensity of emotion)

[0121] Step 4: Assess your stress levels

[0122] The server uses the results of the emotion analysis to evaluate the user's stress level. The stress level is expressed as a quantitative indicator (such as a percentage) and is classified as mild, moderate, or severe. Specifically, the server analyzes the emotion analysis results and determines that the user's current stress level is 60% (moderate).

[0123] Input: Sentiment analysis results

[0124] Data calculation: Stress level evaluation

[0125] Output: Stress level (numerical and classification)

[0126] Step 5: Providing customized support

[0127] The server provides customized support based on the assessed stress level. For mild stress, advice such as "Try breathing exercises to relax" is provided. For severe stress, a referral to a specialist or instructions such as "We recommend you take immediate rest" are provided. Specifically, the server generates a message based on the assessment results and determines the type of support to provide.

[0128] Input: Stress level (number and classification)

[0129] Data Calculation: Support Content Generation

[0130] Output: Customized support message

[0131] Step 6: Notification of support details

[0132] The server sends the determined support content to the device and notifies the user. Notifications are sent via push notification or email. Specifically, the server sends a push notification to the device saying, "Try some breathing exercises to relax."

[0133] Input:Customized support message

[0134] Data calculation: Sending support messages

[0135] Output: Notification to terminal

[0136] Step 7: Real-time monitoring and alerting

[0137] The server monitors the user's input data and stress level in real time. Every time the user makes a new input, it performs an emotion analysis and stress assessment, and if the fluctuation in the stress level exceeds the set standard, it sends an alert. Specifically, if the server detects an input such as "I can't do it anymore," it will issue an emergency notification such as "We strongly recommend that you seek professional counseling."

[0138] Input: New user-entered data

[0139] Data calculation: Sentiment analysis, stress assessment, alert judgment

[0140] Output: Emergency notification message

[0141] These steps enable the system to analyze and monitor the user's emotional state in real time and provide tailored support accordingly.

[0142] (Application example 1)

[0143] 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."

[0144] Maintenance workers in factories often experience mental stress due to their hectic work schedules and high sense of responsibility. This stress can lead to reduced work efficiency and health problems. It is also difficult to objectively measure stress levels and provide appropriate support, making it an urgent task to address this issue.

[0145] 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.

[0146] In this invention, the server includes means for emotionally analyzing input data from a user using the generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, means for monitoring the user's input data and stress level in real time, means for issuing an alert when fluctuations in the stress level exceed a certain standard, and means for analyzing the input data of factory workers and providing mental health support according to their stress levels. This makes it possible to efficiently manage stress among factory workers and provide appropriate mental health care.

[0147] An "artificial intelligence model" is a data processing mechanism built on machine learning algorithms to analyze user input data and identify emotions and other patterns.

[0148] "User" refers to an individual or worker who utilizes the system of the present invention to provide input data and receive stress level assessment and customized support.

[0149] "Stress level" is an index that quantitatively represents the degree of emotional or mental stress of a user, and is evaluated by emotion analysis.

[0150] "Customized support" refers to advice and mental health care provided individually based on the user's stress level.

[0151] "Real-time monitoring" refers to the process of constantly monitoring fluctuations in user input data and stress levels and responding immediately if necessary.

[0152] An "alert" is a warning notification that the system automatically issues when the stress level exceeds a certain threshold.

[0153] "Factory workers" refers to workers engaged in production and maintenance activities within a factory.

[0154] "Mental health support" refers to support activities including advice, consultation, referrals, and other measures aimed at reducing stress and maintaining mental health.

[0155] This invention is a system for supporting the mental health of maintenance personnel working in factories. It uses a generated artificial intelligence model to emotionally analyze user input data, assess stress levels based on the results, and provide customized support as needed.

[0156] Collecting User Input

[0157] Users can input their daily thoughts and work progress using devices such as smartphones, tablets, and PCs. Input can be by text or voice. For example, a user can type a statement such as "Today's work was very difficult" into the application's text box, or record a similar statement using the voice input function.

[0158] Data transmission

[0159] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0160] sentiment analysis

[0161] The server analyzes the received data using the generated artificial intelligence model. Specifically, it uses the Bidirectional Encoder Representations from Transformers (BERT) model to detect emotional nuances from the user's input data. For example, it identifies the emotion "negative" from the expression "it was very difficult."

[0162] Stress level assessment

[0163] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., points or percentage) and classified as mild, moderate, severe, etc.

[0164] Providing customized support

[0165] The server then offers customized support depending on the assessed stress level: for example, advice such as "take a short break and relax" is offered for mild stress, while instructions such as "we strongly recommend you seek professional counseling" are given for severe stress.

[0166] Support notification

[0167] The support content determined by the server is sent to the user's device and notified. The user can check the notification within the application and take appropriate action.

[0168] Real-time monitoring and alerts

[0169] The server monitors the user's situation in real time. New data entered by the user is also subjected to emotion analysis and stress assessment. If fluctuations in stress levels exceed a certain threshold, the server immediately sends an alert.

[0170] overview

[0171] Hardware: Servers, smartphones, tablets, PCs

[0172] software:

[0173] Server: BERT model (Transformers library), Flask

[0174] Device: Voice recognition software, text input interface

[0175] Example prompt sentences

[0176] Example: If the user types, "Working today was very difficult."

[0177] Prompt statement:

[0178] data = { 'input': 'Today's work was very difficult'}

[0179] response = requests.post('http: / / <server IP address>:5000 / analyze', json=data)

[0180] print(response.json())

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and work progress. Input can be either text or voice, and a specific input might be, "Today's work was very difficult." This is the input data for this step. They can then type it into the text box or record it using the voice input function.

[0184] Output: Text or voice data entered into the device

[0185] Step 2:

[0186] The terminal sends the entered text or voice data to the server. At this time, the data is encrypted to ensure security. The sent data is the output data of this step.

[0187] Output: Encrypted text or audio data sent to the server

[0188] Step 3:

[0189] The server analyzes the received data using the generated artificial intelligence model. This analysis uses the BERT model (Transformers library) to tokenize the text data and perform sentiment analysis. Specifically, it identifies sentiment labels such as "negative" from the expression "it was very difficult."

[0190] Input: Encrypted text or voice data received by the server

[0191] Output: Parsed emotion label (e.g. "negative")

[0192] Step 4:

[0193] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The evaluation is expressed as a quantitative indicator (points or percentage) and classified into categories such as mild, moderate, and severe. For example, if the user is labeled as "negative," the stress level is evaluated as moderate or severe.

[0194] Input: Parsed emotion labels

[0195] Output: Estimated stress level (e.g., "moderate")

[0196] Step 5:

[0197] Depending on the assessed stress level, the server will provide customized support: for example, if the stress level is mild, it will generate advice such as "take a short break and relax," while if the stress level is severe, it will generate instructions such as "we strongly recommend that you seek professional counseling."

[0198] Input: Estimated stress level

[0199] Output: Customized support (e.g., "Take a short break")

[0200] Step 6:

[0201] The server sends the determined support content to the device and notifies the user, who can then check the notification within the application and take appropriate action.

[0202] Input: Customized support content

[0203] Output: Support content sent to the device

[0204] Step 7:

[0205] The server monitors the user's situation in real time, continuously analyzing emotions and assessing stress even when new data is entered. If fluctuations in stress levels exceed a certain threshold, the server will issue an alert. For example, if the user enters "it was very difficult" multiple times in a row, an emergency alert will be issued.

[0206] Input: New data arriving in real time

[0207] Output: Alert notification as needed (e.g., "Consultation with a specialist is strongly recommended")

[0208] 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.

[0209] This invention is a system that combines the generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, evaluate stress levels based on the results, and provide customized support as needed. Embodiments of the invention are described in detail below.

[0210] Collecting User Input

[0211] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into a text box in the application, or record a similar statement using the voice input function.

[0212] Data transmission

[0213] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0214] Emotion recognition by emotion engine

[0215] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[0216] Sentiment analysis and stress level assessment

[0217] The server further analyzes the emotional information recognized by the emotion engine using the generated artificial intelligence model. Based on the analysis results, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, it may be evaluated as "70% stress."

[0218] Providing customized support

[0219] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0220] Support notification

[0221] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0222] Real-time monitoring and alerts

[0223] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and an artificial intelligence model to evaluate the user's stress level. If fluctuations in the user's stress level exceed a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0224] Through this series of processes, the system can manage the user's stress level in real time and provide appropriate support as needed. The introduction of an emotion engine enables more accurate emotion recognition, helping to maintain the user's mental health and streamlining disaster response.

[0225] The processing flow will be explained below.

[0226] Step 1:

[0227] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0228] Step 2:

[0229] The device sends the entered text and voice data to the server. The data is encrypted and sent securely. For example, the entered text "Today's activities were very busy. I was especially tired from working this morning" is sent to the server.

[0230] Step 3:

[0231] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" and "stress" from the text, "Today's activities were very busy. I was especially tired from working this morning."

[0232] Step 4:

[0233] Based on the emotional information recognized by the emotion engine, the server performs further analysis using the generated artificial intelligence model. This model is built on machine learning algorithms and evaluates the user's stress level. For example, if the emotion engine extracts "fatigue," the server will use it to evaluate the user's stress level as "70% stress."

[0234] Step 5:

[0235] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0236] Step 6:

[0237] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0238] Step 7:

[0239] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and artificial intelligence model and reevaluates the stress level. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0240] Through this process, the system can manage the user's emotions and stress levels in real time and provide appropriate support as needed. By combining the emotion engine, the system can more accurately recognize the user's emotions and quickly provide individually customized support, contributing to maintaining the user's mental health and improving the efficiency of disaster response.

[0241] Example 2

[0242] 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."

[0243] In modern society, managing personal mental health has become an important issue. However, many people often lack the time or means to properly assess their emotions and stress levels due to their busy lives. Furthermore, conventional systems have difficulty accurately analyzing emotions and stress in real time and providing appropriate support. Therefore, there is a need for a system that allows users to effectively manage their own mental health and receive prompt support when needed.

[0244] 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 a means for a user to input daily impressions and activity reports using a terminal, a means for encrypting the input text and voice data and transmitting the data to the server, a means for emotionally analyzing the input data from the user using a generated artificial intelligence model, a means for evaluating a stress level based on the user's input data, a means for providing customized support according to the evaluated stress level, a means for monitoring the user's input data and stress level in real time, and a means for issuing an alert when fluctuations in the stress level exceed a certain standard. This makes it possible to accurately analyze the user's emotions and stress level in real time and quickly provide customized support as needed.

[0245] "User" refers to an individual who uses this system and enters daily impressions and activity reports.

[0246] "Terminal" refers to an electronic device used by a user, such as a smartphone, tablet, or PC.

[0247] "Server" refers to a central control device that receives and processes data sent by users.

[0248] "Input data" refers to text and voice data that a user inputs through a terminal.

[0249] "Emotion engine" refers to a software component that analyzes input data and recognizes a user's emotions.

[0250] "Generated artificial intelligence model" refers to a trained AI model that analyzes user input data and assesses stress levels.

[0251] "Stress level" refers to the result of a quantitative assessment of the user's emotional state.

[0252] "Customized support" refers to personalized advice and recommended actions provided based on assessed stress levels.

[0253] "Real-time monitoring" refers to the process of continuously monitoring user input data and stress levels, and immediately evaluating and analyzing them.

[0254] An "alert" refers to an emergency message that is sent to the user when fluctuations in stress level exceed a certain threshold.

[0255] The present invention is a system that combines a generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, assess stress levels based on the results, and provide customized support as needed.

[0256] overview

[0257] The present invention begins with the user (using a smartphone, tablet, PC, etc.) entering their daily thoughts and activity reports. The user can enter data using text or voice, for example, "Today's activities were very busy. I was especially tired from working in the morning."

[0258] Data Transmission and Encryption

[0259] The entered data is sent by the terminal to the server, where it is guaranteed to be transmitted securely using encryption technology such as SSL / TLS.

[0260] Analysis by emotion engine

[0261] The server passes the received data to the emotion engine, which uses natural language processing (NLP) and speech analysis technology to recognize emotions from the input data. Specifically, it extracts emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[0262] Stress level assessment

[0263] The server then further analyzes the emotion information recognized by the emotion engine using an artificial intelligence model generated based on the information. The server inputs the emotion information into the model and evaluates the user's stress level in percentage format. For example, the stress level may be evaluated as 80%.

[0264] Providing customized support

[0265] Based on the assessed stress level and emotional information, the server provides customized support, such as advice such as "Try some breathing exercises to relax" for mild stress, or "We strongly recommend you seek professional counseling" for severe stress.

[0266] Support notification

[0267] The support content determined by the server is sent to the device. The user can check the notification and take action. For example, a message such as "Try some breathing exercises to relax" will be displayed on the device.

[0268] Real-time monitoring and alerts

[0269] The server monitors the user's situation in real time. Each time new data is input, it is analyzed using an emotion engine and an artificial intelligence model and the stress level is reassessed. If fluctuations in stress levels exceed a certain threshold, the server immediately generates an alert and sends an emergency notification to the device. For example, if the user frequently inputs "I can't take it anymore," the server will send a notification saying, "We strongly recommend that you seek professional counseling."

[0270] Examples of concrete examples and prompts

[0271] Example 1

[0272] A user types, "Work today was very stressful." The device sends this information to a server, which uses an emotion engine to recognize "stress." The AI ​​model evaluates the stress level at 80% and generates a notification to the user saying, "Take a deep breath and refresh yourself."

[0273] Prompt Sentence Examples

[0274] "Analyze the user's daily thoughts and activity reports to assess their stress level. Then, based on the results, suggest and notify them of appropriate support."

[0275] This system enables real-time management of the user's mental health and highly accurate recognition of subjective emotions.

[0276] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0277] Step 1:

[0278] The user uses the device to input their daily thoughts and activity reports. The user opens the application and types "Today's activities were very busy. I was especially tired from working in the morning" into the text box, or records a similar statement using the voice input function. This input data starts the system's processing (input: text and voice data, output: data temporarily stored on the device).

[0279] Step 2:

[0280] The device sends the entered data to the server. The data is protected and transferred securely using encryption protocols such as SSL / TLS (input: text and voice data stored on the device, output: transfer packets containing encrypted data).

[0281] Step 3:

[0282] The server decrypts the received data and performs preprocessing before passing it to the emotion engine. Specifically, it converts the data format and performs preprocessing (input: encrypted data, output: decrypted and format-converted data).

[0283] Step 4:

[0284] The server then passes the converted data to the emotion engine for emotion recognition. The emotion engine uses natural language processing (NLP) and speech analysis technology to extract emotions from the input data (input: preprocessed text or voice data, output: emotional information, such as "fatigue" or "stress").

[0285] Step 5:

[0286] The server inputs the emotion information obtained from the emotion engine into the generated artificial intelligence model for further analysis. Specifically, the emotion information is used to evaluate the user's stress level (input: emotion information, output: stress level score, e.g., "70% stress").

[0287] Step 6:

[0288] The server determines the customized support content according to the assessed stress level. For example, it generates advice such as "Try breathing exercises to relax" for mild stress and "We strongly recommend that you seek professional counseling" for severe stress (input: stress level score, output: customized support content).

[0289] Step 7:

[0290] The server sends the determined support content to the device. The device receives it and notifies the user. For example, the device displays "Try breathing exercises to relax" (Input: customized support content, Output: notification content displayed on the device).

[0291] Step 8:

[0292] The server monitors the user's condition in real time. Each time new data is input, the above steps are repeated to reassess the stress level. If the fluctuation in the stress level exceeds a certain threshold, the server immediately generates an alert and sends an emergency notification to the device (Input: new input data and real-time monitoring results; Output: alert containing emergency notification).

[0293] (Application example 2)

[0294] 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."

[0295] The importance of stress management and emotion recognition is increasing in modern society. However, there are only a limited number of systems that can provide appropriate support and security alerts to individual users. In addition, there is a lack of technology that can monitor emotional states in real time and respond dynamically, making it difficult to implement effective stress management and security measures.

[0296] The identification process by the identification 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 emotionally analyzing input data from a user using a generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, and means for issuing a security alert based on the user's emotional state. This makes it possible to monitor the user's emotional state in real time and dynamically provide support and security measures as needed.

[0297] A "generated artificial intelligence model" is a model based on machine learning algorithms used to analyze user input data and assess emotions and stress levels.

[0298] The "means for emotional analysis" is a function that identifies emotions from the user's input data and evaluates the type and intensity of those emotions.

[0299] The "means for assessing stress level" is a function that uses emotionally analyzed data to quantify or categorize the user's stress level and assess it.

[0300] The "means for providing customized support" is a function that provides appropriate support and advice to individual users based on the assessed stress level.

[0301] "Real-time monitoring means" refers to a function that constantly monitors the user's input data and stress level, and instantly grasps the situation.

[0302] The "means for notifying an alert" is a function that sends an emergency notification to the user and related parties when the user's stress level exceeds a certain standard.

[0303] "Means for accepting text or voice data" refers to the function of taking text or voice data entered by a user and sending it to a server for analysis.

[0304] The "means for generating and sending referrals to specialists" is a function for creating and sending referrals to guide consultation with an appropriate specialist when the assessed stress level is high.

[0305] "Means for issuing security alerts" is a function that detects security risks based on the user's emotional state and issues an alert as necessary.

[0306] This invention is a system that monitors a user's emotional state in real time, evaluates their stress level, and provides customized support and security alerts as needed. The specific system configuration and operation are described below.

[0307] System configuration

[0308] The system mainly consists of a smartphone, a server, an artificial intelligence model (generative AI model), and an emotion engine. Specifically, it includes the following components:

[0309] Hardware

[0310] Smartphone: A terminal that acquires input data from a user.

[0311] Server: Responsible for receiving and analyzing data, assessing stress levels, and generating customized support and security alerts.

[0312] software

[0313] Smartphone app (development environment: Flutter (registered trademark) or React Native): Collects user text / voice input and sends it to the server.

[0314] Google® Cloud Natural Language API: Recognize emotions from input text / speech.

[0315] Google Cloud Speech-to-Text API: Converts voice input into text data.

[0316] GPT-4® API: Analyzes emotional data and assesses stress levels.

[0317] Firebase: Manages real-time databases and push notifications.

[0318] Operation flow

[0319] 1. Collecting User Input

[0320] Users can enter their daily emotions and activities through a smartphone app by either typing or recording their voice. For example, they can enter something like, "I can't take it anymore, I'm too busy and tired" into a text box or by recording their voice.

[0321] 2. Data Transmission and Encryption

[0322] The smartphone sends the input data to the server using AES-256 encryption technology, and the data is sent in JSON format.

[0323] 3. Emotion Recognition by Emotion Engine

[0324] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API, which extracts the user's sentiment from the text data.

[0325] 4. Sentiment analysis and stress level assessment

[0326] The recognized emotion data is passed to the GPT-4 API for more detailed emotion analysis, and the resulting analysis results are used to assess stress levels and quantify them (e.g., 70% stress) or categorize them (mild, moderate, severe).

[0327] 5. Providing customized support

[0328] Depending on the stress level, it will determine customized support, for example, generating advice such as "Try some breathing exercises to relax" for mild stress, or recommending a referral to a specialist for severe stress.

[0329] 6. Notification of support details

[0330] The server will then send a push notification of the determined support details to the smartphone via Firebase, allowing the user to check the notification and take appropriate action.

[0331] 7. Real-time monitoring and security alerts

[0332] The server periodically analyzes the user's input data and monitors the stress level in real time. If the stress level exceeds a certain threshold, a security alert is generated and the user is notified.

[0333] Examples of concrete examples and prompts

[0334] For example, if a user types "I'm so stressed at work I can't take it anymore," the app's emotion engine will recognize emotions such as "sadness" and "tiredness," and the GPT-4 API will evaluate the user's level of stress as "90%." As a result, a security alert will be generated stating, "We strongly recommend that you seek professional counseling."

[0335] Example prompt for a generative AI model:

[0336] User input: "I'm so stressed at work I can't take it anymore"

[0337] Recognized emotion data: "Sadness", "Tired", "Irritation"

[0338] Stress level rating: "90%"

[0339] Customized support: "We strongly recommend that you seek professional counseling."

[0340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0341] Step 1:

[0342] Users use a smartphone app to input their emotions and activities using text or voice. For example, they can type "I can't take it anymore, I'm too busy and tired" into a text box or record their voice. This input data is temporarily stored within the app.

[0343] Step 2:

[0344] The device sends the entered text and voice data to the server using AES-256 encryption, and the input data is converted to JSON format and securely transferred to the server.

[0345] Step 3:

[0346] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API. In the case of voice data, it is first converted to text data using the Speech-to-Text API. This text data is then passed to the Natural Language API for emotion recognition. The input in this step is voice or text data, and the output is emotion information (e.g., "fatigue" or "stress").

[0347] Step 4:

[0348] The server sends the emotion information extracted by the emotion engine to the GPT-4 API for more detailed emotion analysis. At this stage, the server uses the emotion information to evaluate the stress level. The input is emotion information, and the output is the stress level (e.g., "70% stress").

[0349] Step 5:

[0350] The server determines customized support based on the assessed stress level and emotional information. For example, if the stress level is mild, the server generates advice such as "Try breathing exercises to relax," and if the stress level is severe, the server generates a referral such as "We recommend consulting a specialist." The input is the stress level and emotional information, and the output is customized support content.

[0351] Step 6:

[0352] The server then pushes the determined support content to the smartphone via Firebase. The user can check this notification and take appropriate action. The input is the customized support content, and the output is the push notification message.

[0353] Step 7:

[0354] The server analyzes the data in real time every time the user inputs new data and evaluates the stress level. If the stress level exceeds the threshold, the server immediately generates a security alert and notifies the user and, if necessary, an expert. The input in this step is the new input data, and the output is a security alert.

[0355] This makes it possible to monitor a user's emotional state in real time and provide appropriate support and security measures as needed.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] [Second embodiment]

[0360] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0361] 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.

[0362] 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).

[0363] 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.

[0364] 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.

[0365] 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).

[0366] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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."

[0372] This invention is a system that uses the generated artificial intelligence model to emotionally analyze input data from volunteers, evaluates stress levels based on the emotional analysis results, and provides customized support as needed. Embodiments of the invention are described in detail below.

[0373] Collecting User Input

[0374] First, the user uses a device (smartphone, tablet, PC, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, the user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0375] Data transmission

[0376] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0377] sentiment analysis

[0378] The server analyzes the received data using the generated artificial intelligence model. This model is built on machine learning algorithms and detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[0379] Stress level assessment

[0380] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, or severe.

[0381] Providing customized support

[0382] The server then offers customized support based on the assessed stress level: for mild stress, preventative advice such as "try some breathing exercises to relax" is suggested, while for severe stress, referrals to specialists or instructions such as "we strongly recommend you take some rest" are offered.

[0383] Support notification

[0384] The support content determined by the server is sent to the device and notified to the user, who can then check the notification within the application and take appropriate action.

[0385] Real-time monitoring and alerts

[0386] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0387] This allows the system to manage users' stress levels in real time and provide the necessary support, thereby maintaining volunteers' mental health and supporting effective disaster response.

[0388] The processing flow will be explained below.

[0389] Step 1:

[0390] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0391] Step 2:

[0392] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0393] Step 3:

[0394] The server then passes the received data to the analysis module, which then begins analyzing it using the generated artificial intelligence model. This model is built on machine learning algorithms and can detect emotional nuances from the user's input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[0395] Step 4:

[0396] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, the sentiment analysis may evaluate the user as "70% stressed."

[0397] Step 5:

[0398] The server determines customized support based on the assessed stress level: for mild stress, it provides preventative advice, while for severe stress, it refers the user to a specialist or recommends rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0399] Step 6:

[0400] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0401] Step 7:

[0402] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0403] This process allows the system to manage the user's stress level in real time and provide appropriate support when needed.

[0404] Example 1

[0405] 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."

[0406] Conventional mental health management systems have had difficulty accurately grasping users' emotional states and stress levels and providing appropriate support. There is also a risk of user input data being leaked to external parties. In particular, there is a need for systems that can respond to fluctuations in stress levels in real time, so a new method was needed.

[0407] 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.

[0408] In this invention, the server includes means for performing emotional analysis using the generated artificial intelligence model, means for assessing the user's stress level based on the result of the emotional analysis, and means for providing customized support according to the assessed stress level, thereby making it possible to analyze the user's input data, appropriately assess the stress level, and provide customized support as needed.

[0409] A "generated artificial intelligence model" refers to a model of a machine learning algorithm that has been pre-trained to analyze user input data.

[0410] "Means for emotional analysis" refers to the process of using a generated artificial intelligence model to detect emotional nuances from user input data.

[0411] The "means for assessing stress level" refers to a process for quantitatively assessing the degree of stress of a user based on the results of sentiment analysis.

[0412] "Means for providing customized support" refers to a process for providing advice and support optimized for each user according to the assessed stress level.

[0413] "Means for encrypting and securely transmitting to the server" refers to the process of encrypting the user's input data and securely transmitting it to the server using a communication protocol.

[0414] "Real-time monitoring means" refers to the process of continuously monitoring user input data and stress levels to quickly detect fluctuations.

[0415] "Means for notifying an alert" refers to a process for sending a warning to a user or a relevant third party when fluctuations in stress levels exceed a set threshold.

[0416] "Means for accepting text or voice data and sending it to a server" refers to the process of receiving data entered by a user in text or voice format and transferring it to a server.

[0417] "Means for generating and sending referrals to specialists" refers to the process of generating referrals or consultation requests to specialists based on the results of stress assessments, as needed, and sending them through appropriate channels.

[0418] The present invention is a system that uses a generated artificial intelligence model to emotionally analyze input data from a user, evaluates the stress level based on the emotion analysis results, and provides customized support as needed. An embodiment of the present invention will be described in detail below.

[0419] Collecting User Input

[0420] Users can use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done either by text or voice, for example, by typing something like "Today's activities were very busy. I was especially tired from working in the morning," or by recording something using the voice input function.

[0421] Data transmission

[0422] The device encrypts the input data and sends it securely to the server. This transmission uses the HTTPS protocol. For example, when a user inputs text data or voice data, the device encrypts it and sends it to the server.

[0423] sentiment analysis

[0424] The server analyzes the received data using the generated artificial intelligence model. Specifically, it uses a model built on machine learning frameworks such as TensorFlow and PyTorch. This model detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" or "stress" from the expression "very tired."

[0425] Stress level assessment

[0426] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, severe, etc. The evaluation is performed using statistical methods and the output of machine learning models.

[0427] Providing customized support

[0428] The server then provides customized support based on the assessed stress level. For example, for mild stress, preventative advice such as "Try some breathing exercises to relax" is suggested. For severe stress, the server may refer the user to a specialist or provide instructions such as "We strongly recommend you take some rest." This support is determined based on pre-defined rules and algorithms.

[0429] Support notification

[0430] The support content determined by the server is sent to the device and notified to the user. For example, a push notification is sent to a smartphone app. The user can check the notification and take appropriate action.

[0431] Real-time monitoring and alerts

[0432] The server monitors the user's situation in real time. Every time new data is entered, it performs emotion analysis and stress assessment, and if fluctuations in stress levels exceed a certain threshold, an alert is sent. For example, if a user frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0433] This allows the system to emotionally analyze user input data, monitor stress levels in real time, and provide appropriate support.

[0434] Specific examples

[0435] Example 1

[0436] A user uses a smartphone to voice input, "Work today was very stressful." The voice data is sent from the device to a server, which analyzes the data using the BERT model and determines the user's emotion as "stress." The server then sends a message to the device notifying the user, such as, "Your current stress level is medium. Please take an early rest today."

[0437] Example 2

[0438] A user uses a PC to input the text "I've been overwhelmed with work lately and I'm very tired." The text data is encrypted and sent to a server using the HTTPS protocol. The server uses a sentiment analysis model built with TensorFlow to evaluate the user's stress level as "severe" based on the expression "I'm very tired." The server then generates a message such as "I strongly recommend that you consult a specialist immediately" and sends it to the user's device.

[0439] Prompt Sentence Examples

[0440] "Design an algorithm that emotionally analyzes a user's input text and assesses their stress level. Then combine it with a model that generates a customized support message based on the assessment results."

[0441] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0442] Step 1: Collecting User Input

[0443] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done by text or voice. The input data is written in a text box in the application or recorded using the voice input function. Specifically, the user enters the text "I was very tired at work today" into the input form on the device and presses the send button.

[0444] Input: User impressions and activity reports (text or audio data)

[0445] Output: Input data in the terminal

[0446] Step 2: Send data

[0447] The terminal encrypts the data entered by the user and sends it to the server. This transmission uses the HTTPS protocol. Specifically, the terminal encrypts the input data and sends it to the server's API endpoint using HTTPS.

[0448] Input: Input data in the terminal

[0449] Data processing: Data encryption

[0450] Data calculation: Transmission using HTTPS protocol

[0451] Output: Encrypted data sent to the server

[0452] Step 3: Sentiment analysis

[0453] The server decrypts the received encrypted data and performs emotional analysis using the generated artificial intelligence model. Specific software used is TensorFlow and PyTorch. This allows emotions to be detected from the user's input data. Specifically, the server inputs emotions such as "tired" into the machine learning model, and detects "stress" and "fatigue."

[0454] Input: Encrypted data sent to the server

[0455] Data processing: Deciphering the data

[0456] Data Computing: Sentiment Analysis Using AI Models

[0457] Output: Sentiment analysis results (type and intensity of emotion)

[0458] Step 4: Assess your stress levels

[0459] The server uses the results of the emotion analysis to evaluate the user's stress level. The stress level is expressed as a quantitative indicator (such as a percentage) and is classified as mild, moderate, or severe. Specifically, the server analyzes the emotion analysis results and determines that the user's current stress level is 60% (moderate).

[0460] Input: Sentiment analysis results

[0461] Data calculation: Stress level evaluation

[0462] Output: Stress level (numerical and classification)

[0463] Step 5: Providing customized support

[0464] The server provides customized support based on the assessed stress level. For mild stress, advice such as "Try breathing exercises to relax" is provided. For severe stress, a referral to a specialist or instructions such as "We recommend you take immediate rest" are provided. Specifically, the server generates a message based on the assessment results and determines the type of support to provide.

[0465] Input: Stress level (number and classification)

[0466] Data Calculation: Support Content Generation

[0467] Output: Customized support message

[0468] Step 6: Notification of support details

[0469] The server sends the determined support content to the device and notifies the user. Notifications are sent via push notification or email. Specifically, the server sends a push notification to the device saying, "Try some breathing exercises to relax."

[0470] Input:Customized support message

[0471] Data calculation: Sending support messages

[0472] Output: Notification to terminal

[0473] Step 7: Real-time monitoring and alerting

[0474] The server monitors the user's input data and stress level in real time. Every time the user makes a new input, it performs an emotion analysis and stress assessment, and if the fluctuation in the stress level exceeds the set standard, it sends an alert. Specifically, if the server detects an input such as "I can't do it anymore," it will issue an emergency notification such as "We strongly recommend that you seek professional counseling."

[0475] Input: New user-entered data

[0476] Data calculation: Sentiment analysis, stress assessment, alert judgment

[0477] Output: Emergency notification message

[0478] These steps enable the system to analyze and monitor the user's emotional state in real time and provide tailored support accordingly.

[0479] (Application example 1)

[0480] 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."

[0481] Maintenance workers in factories often experience mental stress due to their hectic work schedules and high sense of responsibility. This stress can lead to reduced work efficiency and health problems. It is also difficult to objectively measure stress levels and provide appropriate support, making it an urgent task to address this issue.

[0482] 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.

[0483] In this invention, the server includes means for emotionally analyzing input data from a user using the generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, means for monitoring the user's input data and stress level in real time, means for issuing an alert when fluctuations in the stress level exceed a certain standard, and means for analyzing the input data of factory workers and providing mental health support according to their stress levels. This makes it possible to efficiently manage stress among factory workers and provide appropriate mental health care.

[0484] An "artificial intelligence model" is a data processing mechanism built on machine learning algorithms to analyze user input data and identify emotions and other patterns.

[0485] "User" refers to an individual or worker who utilizes the system of the present invention to provide input data and receive stress level assessment and customized support.

[0486] "Stress level" is an index that quantitatively represents the degree of emotional or mental stress of a user, and is evaluated by emotion analysis.

[0487] "Customized support" refers to advice and mental health care provided individually based on the user's stress level.

[0488] "Real-time monitoring" refers to the process of constantly monitoring fluctuations in user input data and stress levels and responding immediately if necessary.

[0489] An "alert" is a warning notification that the system automatically issues when the stress level exceeds a certain threshold.

[0490] "Factory workers" refers to workers engaged in production and maintenance activities within a factory.

[0491] "Mental health support" refers to support activities including advice, consultation, referrals, and other measures aimed at reducing stress and maintaining mental health.

[0492] This invention is a system for supporting the mental health of maintenance personnel working in factories. It uses a generated artificial intelligence model to emotionally analyze user input data, assess stress levels based on the results, and provide customized support as needed.

[0493] Collecting User Input

[0494] Users can input their daily thoughts and work progress using devices such as smartphones, tablets, and PCs. Input can be by text or voice. For example, a user can type a statement such as "Today's work was very difficult" into the application's text box, or record a similar statement using the voice input function.

[0495] Data transmission

[0496] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0497] sentiment analysis

[0498] The server analyzes the received data using the generated artificial intelligence model. Specifically, it uses the Bidirectional Encoder Representations from Transformers (BERT) model to detect emotional nuances from the user's input data. For example, it identifies the emotion "negative" from the expression "it was very difficult."

[0499] Stress level assessment

[0500] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., points or percentage) and classified as mild, moderate, severe, etc.

[0501] Providing customized support

[0502] The server then offers customized support depending on the assessed stress level: for example, advice such as "take a short break and relax" is offered for mild stress, while instructions such as "we strongly recommend you seek professional counseling" are given for severe stress.

[0503] Support notification

[0504] The support content determined by the server is sent to the user's device and notified. The user can check the notification within the application and take appropriate action.

[0505] Real-time monitoring and alerts

[0506] The server monitors the user's situation in real time. New data entered by the user is also subjected to emotion analysis and stress assessment. If fluctuations in stress levels exceed a certain threshold, the server immediately sends an alert.

[0507] overview

[0508] Hardware: Servers, smartphones, tablets, PCs

[0509] software:

[0510] Server: BERT model (Transformers library), Flask

[0511] Device: Voice recognition software, text input interface

[0512] Example prompt sentences

[0513] Example: If the user types, "Working today was very difficult."

[0514] Prompt statement:

[0515] data = { 'input': 'Today's work was very difficult'}

[0516] response = requests.post('http: / / <server IP address>:5000 / analyze', json=data)

[0517] print(response.json())

[0518] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0519] Step 1:

[0520] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and work progress. Input can be either text or voice, and a specific input might be, "Today's work was very difficult." This is the input data for this step. They can then type it into the text box or record it using the voice input function.

[0521] Output: Text or voice data entered into the device

[0522] Step 2:

[0523] The terminal sends the entered text or voice data to the server. At this time, the data is encrypted to ensure security. The sent data is the output data of this step.

[0524] Output: Encrypted text or audio data sent to the server

[0525] Step 3:

[0526] The server analyzes the received data using the generated artificial intelligence model. This analysis uses the BERT model (Transformers library) to tokenize the text data and perform sentiment analysis. Specifically, it identifies sentiment labels such as "negative" from the expression "it was very difficult."

[0527] Input: Encrypted text or voice data received by the server

[0528] Output: Parsed emotion label (e.g. "negative")

[0529] Step 4:

[0530] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The evaluation is expressed as a quantitative indicator (points or percentage) and classified into categories such as mild, moderate, and severe. For example, if the user is labeled as "negative," the stress level is evaluated as moderate or severe.

[0531] Input: Parsed emotion labels

[0532] Output: Estimated stress level (e.g., "moderate")

[0533] Step 5:

[0534] Depending on the assessed stress level, the server will provide customized support: for example, if the stress level is mild, it will generate advice such as "take a short break and relax," while if the stress level is severe, it will generate instructions such as "we strongly recommend that you seek professional counseling."

[0535] Input: Estimated stress level

[0536] Output: Customized support (e.g., "Take a short break")

[0537] Step 6:

[0538] The server sends the determined support content to the device and notifies the user, who can then check the notification within the application and take appropriate action.

[0539] Input: Customized support content

[0540] Output: Support content sent to the device

[0541] Step 7:

[0542] The server monitors the user's situation in real time, continuously analyzing emotions and assessing stress even when new data is entered. If fluctuations in stress levels exceed a certain threshold, the server will issue an alert. For example, if the user enters "it was very difficult" multiple times in a row, an emergency alert will be issued.

[0543] Input: New data arriving in real time

[0544] Output: Alert notification as needed (e.g., "Consultation with a specialist is strongly recommended")

[0545] 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.

[0546] This invention is a system that combines the generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, evaluate stress levels based on the results, and provide customized support as needed. Embodiments of the invention are described in detail below.

[0547] Collecting User Input

[0548] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into a text box in the application, or record a similar statement using the voice input function.

[0549] Data transmission

[0550] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0551] Emotion recognition by emotion engine

[0552] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[0553] Sentiment analysis and stress level assessment

[0554] The server further analyzes the emotional information recognized by the emotion engine using the generated artificial intelligence model. Based on the analysis results, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, it may be evaluated as "70% stress."

[0555] Providing customized support

[0556] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0557] Support notification

[0558] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0559] Real-time monitoring and alerts

[0560] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and an artificial intelligence model to evaluate the user's stress level. If fluctuations in the user's stress level exceed a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0561] Through this series of processes, the system can manage the user's stress level in real time and provide appropriate support as needed. The introduction of an emotion engine enables more accurate emotion recognition, helping to maintain the user's mental health and streamlining disaster response.

[0562] The processing flow will be explained below.

[0563] Step 1:

[0564] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0565] Step 2:

[0566] The device sends the entered text and voice data to the server. The data is encrypted and sent securely. For example, the entered text "Today's activities were very busy. I was especially tired from working this morning" is sent to the server.

[0567] Step 3:

[0568] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" and "stress" from the text, "Today's activities were very busy. I was especially tired from working this morning."

[0569] Step 4:

[0570] Based on the emotional information recognized by the emotion engine, the server performs further analysis using the generated artificial intelligence model. This model is built on machine learning algorithms and evaluates the user's stress level. For example, if the emotion engine extracts "fatigue," the server will use it to evaluate the user's stress level as "70% stress."

[0571] Step 5:

[0572] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0573] Step 6:

[0574] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0575] Step 7:

[0576] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and artificial intelligence model and reevaluates the stress level. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0577] Through this process, the system can manage the user's emotions and stress levels in real time and provide appropriate support as needed. By combining the emotion engine, the system can more accurately recognize the user's emotions and quickly provide individually customized support, contributing to maintaining the user's mental health and improving the efficiency of disaster response.

[0578] Example 2

[0579] 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."

[0580] In modern society, managing personal mental health has become an important issue. However, many people often lack the time or means to properly assess their emotions and stress levels due to their busy lives. Furthermore, conventional systems have difficulty accurately analyzing emotions and stress in real time and providing appropriate support. Therefore, there is a need for a system that allows users to effectively manage their own mental health and receive prompt support when needed.

[0581] 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 a means for a user to input daily impressions and activity reports using a terminal, a means for encrypting the input text and voice data and transmitting the data to the server, a means for emotionally analyzing the input data from the user using a generated artificial intelligence model, a means for evaluating a stress level based on the user's input data, a means for providing customized support according to the evaluated stress level, a means for monitoring the user's input data and stress level in real time, and a means for issuing an alert when fluctuations in the stress level exceed a certain standard. This makes it possible to accurately analyze the user's emotions and stress level in real time and quickly provide customized support as needed.

[0582] "User" refers to an individual who uses this system and enters daily impressions and activity reports.

[0583] "Terminal" refers to an electronic device used by a user, such as a smartphone, tablet, or PC.

[0584] "Server" refers to a central control device that receives and processes data sent by users.

[0585] "Input data" refers to text and voice data that a user inputs through a terminal.

[0586] "Emotion engine" refers to a software component that analyzes input data and recognizes a user's emotions.

[0587] "Generated artificial intelligence model" refers to a trained AI model that analyzes user input data and assesses stress levels.

[0588] "Stress level" refers to the result of a quantitative assessment of the user's emotional state.

[0589] "Customized support" refers to personalized advice and recommended actions provided based on assessed stress levels.

[0590] "Real-time monitoring" refers to the process of continuously monitoring user input data and stress levels, and immediately evaluating and analyzing them.

[0591] An "alert" refers to an emergency message that is sent to the user when fluctuations in stress level exceed a certain threshold.

[0592] The present invention is a system that combines a generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, assess stress levels based on the results, and provide customized support as needed.

[0593] overview

[0594] The present invention begins with the user (using a smartphone, tablet, PC, etc.) entering their daily thoughts and activity reports. The user can enter data using text or voice, for example, "Today's activities were very busy. I was especially tired from working in the morning."

[0595] Data Transmission and Encryption

[0596] The entered data is sent by the terminal to the server, where it is guaranteed to be transmitted securely using encryption technology such as SSL / TLS.

[0597] Analysis by emotion engine

[0598] The server passes the received data to the emotion engine, which uses natural language processing (NLP) and speech analysis technology to recognize emotions from the input data. Specifically, it extracts emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[0599] Stress level assessment

[0600] The server then further analyzes the emotion information recognized by the emotion engine using an artificial intelligence model generated based on the information. The server inputs the emotion information into the model and evaluates the user's stress level in percentage format. For example, the stress level may be evaluated as 80%.

[0601] Providing customized support

[0602] Based on the assessed stress level and emotional information, the server provides customized support, such as advice such as "Try some breathing exercises to relax" for mild stress, or "We strongly recommend you seek professional counseling" for severe stress.

[0603] Support notification

[0604] The support content determined by the server is sent to the device. The user can check the notification and take action. For example, a message such as "Try some breathing exercises to relax" will be displayed on the device.

[0605] Real-time monitoring and alerts

[0606] The server monitors the user's situation in real time. Each time new data is input, it is analyzed using an emotion engine and an artificial intelligence model and the stress level is reassessed. If fluctuations in stress levels exceed a certain threshold, the server immediately generates an alert and sends an emergency notification to the device. For example, if the user frequently inputs "I can't take it anymore," the server will send a notification saying, "We strongly recommend that you seek professional counseling."

[0607] Examples of concrete examples and prompts

[0608] Example 1

[0609] A user types, "Work today was very stressful." The device sends this information to a server, which uses an emotion engine to recognize "stress." The AI ​​model evaluates the stress level at 80% and generates a notification to the user saying, "Take a deep breath and refresh yourself."

[0610] Prompt Sentence Examples

[0611] "Analyze the user's daily thoughts and activity reports to assess their stress level. Then, based on the results, suggest and notify them of appropriate support."

[0612] This system enables real-time management of the user's mental health and highly accurate recognition of subjective emotions.

[0613] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0614] Step 1:

[0615] The user uses the device to input their daily thoughts and activity reports. The user opens the application and types "Today's activities were very busy. I was especially tired from working in the morning" into the text box, or records a similar statement using the voice input function. This input data starts the system's processing (input: text and voice data, output: data temporarily stored on the device).

[0616] Step 2:

[0617] The device sends the entered data to the server. The data is protected and transferred securely using encryption protocols such as SSL / TLS (input: text and voice data stored on the device, output: transfer packets containing encrypted data).

[0618] Step 3:

[0619] The server decrypts the received data and performs preprocessing before passing it to the emotion engine. Specifically, it converts the data format and performs preprocessing (input: encrypted data, output: decrypted and format-converted data).

[0620] Step 4:

[0621] The server then passes the converted data to the emotion engine for emotion recognition. The emotion engine uses natural language processing (NLP) and speech analysis technology to extract emotions from the input data (input: preprocessed text or voice data, output: emotional information, such as "fatigue" or "stress").

[0622] Step 5:

[0623] The server inputs the emotion information obtained from the emotion engine into the generated artificial intelligence model for further analysis. Specifically, the emotion information is used to evaluate the user's stress level (input: emotion information, output: stress level score, e.g., "70% stress").

[0624] Step 6:

[0625] The server determines the customized support content according to the assessed stress level. For example, it generates advice such as "Try breathing exercises to relax" for mild stress and "We strongly recommend that you seek professional counseling" for severe stress (input: stress level score, output: customized support content).

[0626] Step 7:

[0627] The server sends the determined support content to the device. The device receives it and notifies the user. For example, the device displays "Try breathing exercises to relax" (Input: customized support content, Output: notification content displayed on the device).

[0628] Step 8:

[0629] The server monitors the user's condition in real time. Each time new data is input, the above steps are repeated to reassess the stress level. If the fluctuation in the stress level exceeds a certain threshold, the server immediately generates an alert and sends an emergency notification to the device (Input: new input data and real-time monitoring results; Output: alert containing emergency notification).

[0630] (Application example 2)

[0631] 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."

[0632] The importance of stress management and emotion recognition is increasing in modern society. However, there are only a limited number of systems that can provide appropriate support and security alerts to individual users. In addition, there is a lack of technology that can monitor emotional states in real time and respond dynamically, making it difficult to implement effective stress management and security measures.

[0633] The identification process by the identification 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 emotionally analyzing input data from a user using a generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, and means for issuing a security alert based on the user's emotional state. This makes it possible to monitor the user's emotional state in real time and dynamically provide support and security measures as needed.

[0634] A "generated artificial intelligence model" is a model based on machine learning algorithms used to analyze user input data and assess emotions and stress levels.

[0635] The "means for emotional analysis" is a function that identifies emotions from the user's input data and evaluates the type and intensity of those emotions.

[0636] The "means for assessing stress level" is a function that uses emotionally analyzed data to quantify or categorize the user's stress level and assess it.

[0637] The "means for providing customized support" is a function that provides appropriate support and advice to individual users based on the assessed stress level.

[0638] "Real-time monitoring means" refers to a function that constantly monitors the user's input data and stress level, and instantly grasps the situation.

[0639] The "means for notifying an alert" is a function that sends an emergency notification to the user and related parties when the user's stress level exceeds a certain standard.

[0640] "Means for accepting text or voice data" refers to the function of taking text or voice data entered by a user and sending it to a server for analysis.

[0641] The "means for generating and sending referrals to specialists" is a function for creating and sending referrals to guide consultation with an appropriate specialist when the assessed stress level is high.

[0642] "Means for issuing security alerts" is a function that detects security risks based on the user's emotional state and issues an alert as necessary.

[0643] This invention is a system that monitors a user's emotional state in real time, evaluates their stress level, and provides customized support and security alerts as needed. The specific system configuration and operation are described below.

[0644] System configuration

[0645] The system mainly consists of a smartphone, a server, an artificial intelligence model (generative AI model), and an emotion engine. Specifically, it includes the following components:

[0646] Hardware

[0647] Smartphone: A terminal that acquires input data from a user.

[0648] Server: Responsible for receiving and analyzing data, assessing stress levels, and generating customized support and security alerts.

[0649] software

[0650] Smartphone app (development environment: Flutter or React Native): Collects user text / voice input and sends it to the server.

[0651] Google Cloud Natural Language API: Recognize emotions from input text / speech.

[0652] Google Cloud Speech-to-Text API: Converts voice input into text data.

[0653] GPT-4 API: Analyzes emotional data and assesses stress levels.

[0654] Firebase: Manages real-time databases and push notifications.

[0655] Operation flow

[0656] 1. Collecting User Input

[0657] Users can enter their daily emotions and activities through a smartphone app by either typing or recording their voice. For example, they can enter something like, "I can't take it anymore, I'm too busy and tired" into a text box or by recording their voice.

[0658] 2. Data Transmission and Encryption

[0659] The smartphone sends the input data to the server using AES-256 encryption technology, and the data is sent in JSON format.

[0660] 3. Emotion Recognition by Emotion Engine

[0661] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API, which extracts the user's sentiment from the text data.

[0662] 4. Sentiment analysis and stress level assessment

[0663] The recognized emotion data is passed to the GPT-4 API for more detailed emotion analysis, and the resulting analysis results are used to assess stress levels and quantify them (e.g., 70% stress) or categorize them (mild, moderate, severe).

[0664] 5. Providing customized support

[0665] Depending on the stress level, it will determine customized support, for example, generating advice such as "Try some breathing exercises to relax" for mild stress, or recommending a referral to a specialist for severe stress.

[0666] 6. Notification of support details

[0667] The server will then send a push notification of the determined support details to the smartphone via Firebase, allowing the user to check the notification and take appropriate action.

[0668] 7. Real-time monitoring and security alerts

[0669] The server periodically analyzes the user's input data and monitors the stress level in real time. If the stress level exceeds a certain threshold, a security alert is generated and the user is notified.

[0670] Examples of concrete examples and prompts

[0671] For example, if a user types "I'm so stressed at work I can't take it anymore," the app's emotion engine will recognize emotions such as "sadness" and "tiredness," and the GPT-4 API will evaluate the user's level of stress as "90%." As a result, a security alert will be generated stating, "We strongly recommend that you seek professional counseling."

[0672] Example prompt for a generative AI model:

[0673] User input: "I'm so stressed at work I can't take it anymore"

[0674] Recognized emotion data: "Sadness", "Tired", "Irritation"

[0675] Stress level rating: "90%"

[0676] Customized support: "We strongly recommend that you seek professional counseling."

[0677] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0678] Step 1:

[0679] Users use a smartphone app to input their emotions and activities using text or voice. For example, they can type "I can't take it anymore, I'm too busy and tired" into a text box or record their voice. This input data is temporarily stored within the app.

[0680] Step 2:

[0681] The device sends the entered text and voice data to the server using AES-256 encryption, and the input data is converted to JSON format and securely transferred to the server.

[0682] Step 3:

[0683] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API. In the case of voice data, it is first converted to text data using the Speech-to-Text API. This text data is then passed to the Natural Language API for emotion recognition. The input in this step is voice or text data, and the output is emotion information (e.g., "fatigue" or "stress").

[0684] Step 4:

[0685] The server sends the emotion information extracted by the emotion engine to the GPT-4 API for more detailed emotion analysis. At this stage, the server uses the emotion information to evaluate the stress level. The input is emotion information, and the output is the stress level (e.g., "70% stress").

[0686] Step 5:

[0687] The server determines customized support based on the assessed stress level and emotional information. For example, if the stress level is mild, the server generates advice such as "Try breathing exercises to relax," and if the stress level is severe, the server generates a referral such as "We recommend consulting a specialist." The input is the stress level and emotional information, and the output is customized support content.

[0688] Step 6:

[0689] The server then pushes the determined support content to the smartphone via Firebase. The user can check this notification and take appropriate action. The input is the customized support content, and the output is the push notification message.

[0690] Step 7:

[0691] The server analyzes the data in real time every time the user inputs new data and evaluates the stress level. If the stress level exceeds the threshold, the server immediately generates a security alert and notifies the user and, if necessary, an expert. The input in this step is the new input data, and the output is a security alert.

[0692] This makes it possible to monitor a user's emotional state in real time and provide appropriate support and security measures as needed.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] [Third embodiment]

[0697] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0698] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0699] 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).

[0700] 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.

[0701] 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.

[0702] 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).

[0703] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] 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."

[0709] This invention is a system that uses the generated artificial intelligence model to emotionally analyze input data from volunteers, evaluates stress levels based on the emotional analysis results, and provides customized support as needed. Embodiments of the invention are described in detail below.

[0710] Collecting User Input

[0711] First, the user uses a device (smartphone, tablet, PC, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, the user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0712] Data transmission

[0713] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0714] sentiment analysis

[0715] The server analyzes the received data using the generated artificial intelligence model. This model is built on machine learning algorithms and detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[0716] Stress level assessment

[0717] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, or severe.

[0718] Providing customized support

[0719] The server then offers customized support based on the assessed stress level: for mild stress, preventative advice such as "try some breathing exercises to relax" is suggested, while for severe stress, referrals to specialists or instructions such as "we strongly recommend you take some rest" are offered.

[0720] Support notification

[0721] The support content determined by the server is sent to the device and notified to the user, who can then check the notification within the application and take appropriate action.

[0722] Real-time monitoring and alerts

[0723] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0724] This allows the system to manage users' stress levels in real time and provide the necessary support, thereby maintaining volunteers' mental health and supporting effective disaster response.

[0725] The processing flow will be explained below.

[0726] Step 1:

[0727] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0728] Step 2:

[0729] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0730] Step 3:

[0731] The server then passes the received data to the analysis module, which then begins analyzing it using the generated artificial intelligence model. This model is built on machine learning algorithms and can detect emotional nuances from the user's input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[0732] Step 4:

[0733] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, the sentiment analysis may evaluate the user as "70% stressed."

[0734] Step 5:

[0735] The server determines customized support based on the assessed stress level: for mild stress, it provides preventative advice, while for severe stress, it refers the user to a specialist or recommends rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0736] Step 6:

[0737] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0738] Step 7:

[0739] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0740] This process allows the system to manage the user's stress level in real time and provide appropriate support when needed.

[0741] Example 1

[0742] 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."

[0743] Conventional mental health management systems have had difficulty accurately grasping users' emotional states and stress levels and providing appropriate support. There is also a risk of user input data being leaked to external parties. In particular, there is a need for systems that can respond to fluctuations in stress levels in real time, so a new method was needed.

[0744] 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.

[0745] In this invention, the server includes means for performing emotional analysis using the generated artificial intelligence model, means for assessing the user's stress level based on the result of the emotional analysis, and means for providing customized support according to the assessed stress level, thereby making it possible to analyze the user's input data, appropriately assess the stress level, and provide customized support as needed.

[0746] A "generated artificial intelligence model" refers to a model of a machine learning algorithm that has been pre-trained to analyze user input data.

[0747] "Means for emotional analysis" refers to the process of using a generated artificial intelligence model to detect emotional nuances from user input data.

[0748] The "means for assessing stress level" refers to a process for quantitatively assessing the degree of stress of a user based on the results of sentiment analysis.

[0749] "Means for providing customized support" refers to a process for providing advice and support optimized for each user according to the assessed stress level.

[0750] "Means for encrypting and securely transmitting to the server" refers to the process of encrypting the user's input data and securely transmitting it to the server using a communication protocol.

[0751] "Real-time monitoring means" refers to the process of continuously monitoring user input data and stress levels to quickly detect fluctuations.

[0752] "Means for notifying an alert" refers to a process for sending a warning to a user or a relevant third party when fluctuations in stress levels exceed a set threshold.

[0753] "Means for accepting text or voice data and sending it to a server" refers to the process of receiving data entered by a user in text or voice format and transferring it to a server.

[0754] "Means for generating and sending referrals to specialists" refers to the process of generating referrals or consultation requests to specialists based on the results of stress assessments, as needed, and sending them through appropriate channels.

[0755] The present invention is a system that uses a generated artificial intelligence model to emotionally analyze input data from a user, evaluates the stress level based on the emotion analysis results, and provides customized support as needed. An embodiment of the present invention will be described in detail below.

[0756] Collecting User Input

[0757] Users can use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done either by text or voice, for example, by typing something like "Today's activities were very busy. I was especially tired from working in the morning," or by recording something using the voice input function.

[0758] Data transmission

[0759] The device encrypts the input data and sends it securely to the server. This transmission uses the HTTPS protocol. For example, when a user inputs text data or voice data, the device encrypts it and sends it to the server.

[0760] sentiment analysis

[0761] The server analyzes the received data using the generated artificial intelligence model. Specifically, it uses a model built on machine learning frameworks such as TensorFlow and PyTorch. This model detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" or "stress" from the expression "very tired."

[0762] Stress level assessment

[0763] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, severe, etc. The evaluation is performed using statistical methods and the output of machine learning models.

[0764] Providing customized support

[0765] The server then provides customized support based on the assessed stress level. For example, for mild stress, preventative advice such as "Try some breathing exercises to relax" is suggested. For severe stress, the server may refer the user to a specialist or provide instructions such as "We strongly recommend you take some rest." This support is determined based on pre-defined rules and algorithms.

[0766] Support notification

[0767] The support content determined by the server is sent to the device and notified to the user. For example, a push notification is sent to a smartphone app. The user can check the notification and take appropriate action.

[0768] Real-time monitoring and alerts

[0769] The server monitors the user's situation in real time. Every time new data is entered, it performs emotion analysis and stress assessment, and if fluctuations in stress levels exceed a certain threshold, an alert is sent. For example, if a user frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0770] This allows the system to emotionally analyze user input data, monitor stress levels in real time, and provide appropriate support.

[0771] Specific examples

[0772] Example 1

[0773] A user uses a smartphone to voice input, "Work today was very stressful." The voice data is sent from the device to a server, which analyzes the data using the BERT model and determines the user's emotion as "stress." The server then sends a message to the device notifying the user, such as, "Your current stress level is medium. Please take an early rest today."

[0774] Example 2

[0775] A user uses a PC to input the text "I've been overwhelmed with work lately and I'm very tired." The text data is encrypted and sent to a server using the HTTPS protocol. The server uses a sentiment analysis model built with TensorFlow to evaluate the user's stress level as "severe" based on the expression "I'm very tired." The server then generates a message such as "I strongly recommend that you consult a specialist immediately" and sends it to the user's device.

[0776] Prompt Sentence Examples

[0777] "Design an algorithm that emotionally analyzes a user's input text and assesses their stress level. Then combine it with a model that generates a customized support message based on the assessment results."

[0778] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0779] Step 1: Collecting User Input

[0780] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done by text or voice. The input data is written in a text box in the application or recorded using the voice input function. Specifically, the user enters the text "I was very tired at work today" into the input form on the device and presses the send button.

[0781] Input: User impressions and activity reports (text or audio data)

[0782] Output: Input data in the terminal

[0783] Step 2: Send data

[0784] The terminal encrypts the data entered by the user and sends it to the server. This transmission uses the HTTPS protocol. Specifically, the terminal encrypts the input data and sends it to the server's API endpoint using HTTPS.

[0785] Input: Input data in the terminal

[0786] Data processing: Data encryption

[0787] Data calculation: Transmission using HTTPS protocol

[0788] Output: Encrypted data sent to the server

[0789] Step 3: Sentiment analysis

[0790] The server decrypts the received encrypted data and performs emotional analysis using the generated artificial intelligence model. Specific software used is TensorFlow and PyTorch. This allows emotions to be detected from the user's input data. Specifically, the server inputs emotions such as "tired" into the machine learning model, and detects "stress" and "fatigue."

[0791] Input: Encrypted data sent to the server

[0792] Data processing: Deciphering the data

[0793] Data Computing: Sentiment Analysis Using AI Models

[0794] Output: Sentiment analysis results (type and intensity of emotion)

[0795] Step 4: Assess your stress levels

[0796] The server uses the results of the emotion analysis to evaluate the user's stress level. The stress level is expressed as a quantitative indicator (such as a percentage) and is classified as mild, moderate, or severe. Specifically, the server analyzes the emotion analysis results and determines that the user's current stress level is 60% (moderate).

[0797] Input: Sentiment analysis results

[0798] Data calculation: Stress level evaluation

[0799] Output: Stress level (numerical and classification)

[0800] Step 5: Providing customized support

[0801] The server provides customized support based on the assessed stress level. For mild stress, advice such as "Try breathing exercises to relax" is provided. For severe stress, a referral to a specialist or instructions such as "We recommend you take immediate rest" are provided. Specifically, the server generates a message based on the assessment results and determines the type of support to provide.

[0802] Input: Stress level (number and classification)

[0803] Data Calculation: Support Content Generation

[0804] Output: Customized support message

[0805] Step 6: Notification of support details

[0806] The server sends the determined support content to the device and notifies the user. Notifications are sent via push notification or email. Specifically, the server sends a push notification to the device saying, "Try some breathing exercises to relax."

[0807] Input:Customized support message

[0808] Data calculation: Sending support messages

[0809] Output: Notification to terminal

[0810] Step 7: Real-time monitoring and alerting

[0811] The server monitors the user's input data and stress level in real time. Every time the user makes a new input, it performs an emotion analysis and stress assessment, and if the fluctuation in the stress level exceeds the set standard, it sends an alert. Specifically, if the server detects an input such as "I can't do it anymore," it will issue an emergency notification such as "We strongly recommend that you seek professional counseling."

[0812] Input: New user-entered data

[0813] Data calculation: Sentiment analysis, stress assessment, alert judgment

[0814] Output: Emergency notification message

[0815] These steps enable the system to analyze and monitor the user's emotional state in real time and provide tailored support accordingly.

[0816] (Application example 1)

[0817] 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."

[0818] Maintenance workers in factories often experience mental stress due to their hectic work schedules and high sense of responsibility. This stress can lead to reduced work efficiency and health problems. It is also difficult to objectively measure stress levels and provide appropriate support, making it an urgent task to address this issue.

[0819] 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.

[0820] In this invention, the server includes means for emotionally analyzing input data from a user using the generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, means for monitoring the user's input data and stress level in real time, means for issuing an alert when fluctuations in the stress level exceed a certain standard, and means for analyzing the input data of factory workers and providing mental health support according to their stress levels. This makes it possible to efficiently manage stress among factory workers and provide appropriate mental health care.

[0821] An "artificial intelligence model" is a data processing mechanism built on machine learning algorithms to analyze user input data and identify emotions and other patterns.

[0822] "User" refers to an individual or worker who utilizes the system of the present invention to provide input data and receive stress level assessment and customized support.

[0823] "Stress level" is an index that quantitatively represents the degree of emotional or mental stress of a user, and is evaluated by emotion analysis.

[0824] "Customized support" refers to advice and mental health care provided individually based on the user's stress level.

[0825] "Real-time monitoring" refers to the process of constantly monitoring fluctuations in user input data and stress levels and responding immediately if necessary.

[0826] An "alert" is a warning notification that the system automatically issues when the stress level exceeds a certain threshold.

[0827] "Factory workers" refers to workers engaged in production and maintenance activities within a factory.

[0828] "Mental health support" refers to support activities including advice, consultation, referrals, and other measures aimed at reducing stress and maintaining mental health.

[0829] This invention is a system for supporting the mental health of maintenance personnel working in factories. It uses a generated artificial intelligence model to emotionally analyze user input data, assess stress levels based on the results, and provide customized support as needed.

[0830] Collecting User Input

[0831] Users can input their daily thoughts and work progress using devices such as smartphones, tablets, and PCs. Input can be by text or voice. For example, a user can type a statement such as "Today's work was very difficult" into the application's text box, or record a similar statement using the voice input function.

[0832] Data transmission

[0833] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0834] sentiment analysis

[0835] The server analyzes the received data using the generated artificial intelligence model. Specifically, it uses the Bidirectional Encoder Representations from Transformers (BERT) model to detect emotional nuances from the user's input data. For example, it identifies the emotion "negative" from the expression "it was very difficult."

[0836] Stress level assessment

[0837] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., points or percentage) and classified as mild, moderate, severe, etc.

[0838] Providing customized support

[0839] The server then offers customized support depending on the assessed stress level: for example, advice such as "take a short break and relax" is offered for mild stress, while instructions such as "we strongly recommend you seek professional counseling" are given for severe stress.

[0840] Support notification

[0841] The support content determined by the server is sent to the user's device and notified. The user can check the notification within the application and take appropriate action.

[0842] Real-time monitoring and alerts

[0843] The server monitors the user's situation in real time. New data entered by the user is also subjected to emotion analysis and stress assessment. If fluctuations in stress levels exceed a certain threshold, the server immediately sends an alert.

[0844] overview

[0845] Hardware: Servers, smartphones, tablets, PCs

[0846] software:

[0847] Server: BERT model (Transformers library), Flask

[0848] Device: Voice recognition software, text input interface

[0849] Example prompt sentences

[0850] Example: If the user types, "Working today was very difficult."

[0851] Prompt statement:

[0852] data = { 'input': 'Today's work was very difficult'}

[0853] response = requests.post('http: / / <server IP address>:5000 / analyze', json=data)

[0854] print(response.json())

[0855] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0856] Step 1:

[0857] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and work progress. Input can be either text or voice, and a specific input might be, "Today's work was very difficult." This is the input data for this step. They can then type it into the text box or record it using the voice input function.

[0858] Output: Text or voice data entered into the device

[0859] Step 2:

[0860] The terminal sends the entered text or voice data to the server. At this time, the data is encrypted to ensure security. The sent data is the output data of this step.

[0861] Output: Encrypted text or audio data sent to the server

[0862] Step 3:

[0863] The server analyzes the received data using the generated artificial intelligence model. This analysis uses the BERT model (Transformers library) to tokenize the text data and perform sentiment analysis. Specifically, it identifies sentiment labels such as "negative" from the expression "it was very difficult."

[0864] Input: Encrypted text or voice data received by the server

[0865] Output: Parsed emotion label (e.g. "negative")

[0866] Step 4:

[0867] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The evaluation is expressed as a quantitative indicator (points or percentage) and classified into categories such as mild, moderate, and severe. For example, if the user is labeled as "negative," the stress level is evaluated as moderate or severe.

[0868] Input: Parsed emotion labels

[0869] Output: Estimated stress level (e.g., "moderate")

[0870] Step 5:

[0871] Depending on the assessed stress level, the server will provide customized support: for example, if the stress level is mild, it will generate advice such as "take a short break and relax," while if the stress level is severe, it will generate instructions such as "we strongly recommend that you seek professional counseling."

[0872] Input: Estimated stress level

[0873] Output: Customized support (e.g., "Take a short break")

[0874] Step 6:

[0875] The server sends the determined support content to the device and notifies the user, who can then check the notification within the application and take appropriate action.

[0876] Input: Customized support content

[0877] Output: Support content sent to the device

[0878] Step 7:

[0879] The server monitors the user's situation in real time, continuously analyzing emotions and assessing stress even when new data is entered. If fluctuations in stress levels exceed a certain threshold, the server will issue an alert. For example, if the user enters "it was very difficult" multiple times in a row, an emergency alert will be issued.

[0880] Input: New data arriving in real time

[0881] Output: Alert notification as needed (e.g., "Consultation with a specialist is strongly recommended")

[0882] 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.

[0883] This invention is a system that combines the generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, evaluate stress levels based on the results, and provide customized support as needed. Embodiments of the invention are described in detail below.

[0884] Collecting User Input

[0885] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into a text box in the application, or record a similar statement using the voice input function.

[0886] Data transmission

[0887] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[0888] Emotion recognition by emotion engine

[0889] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[0890] Sentiment analysis and stress level assessment

[0891] The server further analyzes the emotional information recognized by the emotion engine using the generated artificial intelligence model. Based on the analysis results, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, it may be evaluated as "70% stress."

[0892] Providing customized support

[0893] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0894] Support notification

[0895] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0896] Real-time monitoring and alerts

[0897] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and an artificial intelligence model to evaluate the user's stress level. If fluctuations in the user's stress level exceed a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0898] Through this series of processes, the system can manage the user's stress level in real time and provide appropriate support as needed. The introduction of an emotion engine enables more accurate emotion recognition, helping to maintain the user's mental health and streamlining disaster response.

[0899] The processing flow will be explained below.

[0900] Step 1:

[0901] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[0902] Step 2:

[0903] The device sends the entered text and voice data to the server. The data is encrypted and sent securely. For example, the entered text "Today's activities were very busy. I was especially tired from working this morning" is sent to the server.

[0904] Step 3:

[0905] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" and "stress" from the text, "Today's activities were very busy. I was especially tired from working this morning."

[0906] Step 4:

[0907] Based on the emotional information recognized by the emotion engine, the server performs further analysis using the generated artificial intelligence model. This model is built on machine learning algorithms and evaluates the user's stress level. For example, if the emotion engine extracts "fatigue," the server will use it to evaluate the user's stress level as "70% stress."

[0908] Step 5:

[0909] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[0910] Step 6:

[0911] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[0912] Step 7:

[0913] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and artificial intelligence model and reevaluates the stress level. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[0914] Through this process, the system can manage the user's emotions and stress levels in real time and provide appropriate support as needed. By combining the emotion engine, the system can more accurately recognize the user's emotions and quickly provide individually customized support, contributing to maintaining the user's mental health and improving the efficiency of disaster response.

[0915] Example 2

[0916] 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."

[0917] In modern society, managing personal mental health has become an important issue. However, many people often lack the time or means to properly assess their emotions and stress levels due to their busy lives. Furthermore, conventional systems have difficulty accurately analyzing emotions and stress in real time and providing appropriate support. Therefore, there is a need for a system that allows users to effectively manage their own mental health and receive prompt support when needed.

[0918] 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 a means for a user to input daily impressions and activity reports using a terminal, a means for encrypting the input text and voice data and transmitting the data to the server, a means for emotionally analyzing the input data from the user using a generated artificial intelligence model, a means for evaluating a stress level based on the user's input data, a means for providing customized support according to the evaluated stress level, a means for monitoring the user's input data and stress level in real time, and a means for issuing an alert when fluctuations in the stress level exceed a certain standard. This makes it possible to accurately analyze the user's emotions and stress level in real time and quickly provide customized support as needed.

[0919] "User" refers to an individual who uses this system and enters daily impressions and activity reports.

[0920] "Terminal" refers to an electronic device used by a user, such as a smartphone, tablet, or PC.

[0921] "Server" refers to a central control device that receives and processes data sent by users.

[0922] "Input data" refers to text and voice data that a user inputs through a terminal.

[0923] "Emotion engine" refers to a software component that analyzes input data and recognizes a user's emotions.

[0924] "Generated artificial intelligence model" refers to a trained AI model that analyzes user input data and assesses stress levels.

[0925] "Stress level" refers to the result of a quantitative assessment of the user's emotional state.

[0926] "Customized support" refers to personalized advice and recommended actions provided based on assessed stress levels.

[0927] "Real-time monitoring" refers to the process of continuously monitoring user input data and stress levels, and immediately evaluating and analyzing them.

[0928] An "alert" refers to an emergency message that is sent to the user when fluctuations in stress level exceed a certain threshold.

[0929] The present invention is a system that combines a generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, assess stress levels based on the results, and provide customized support as needed.

[0930] overview

[0931] The present invention begins with the user (using a smartphone, tablet, PC, etc.) entering their daily thoughts and activity reports. The user can enter data using text or voice, for example, "Today's activities were very busy. I was especially tired from working in the morning."

[0932] Data Transmission and Encryption

[0933] The entered data is sent by the terminal to the server, where it is guaranteed to be transmitted securely using encryption technology such as SSL / TLS.

[0934] Analysis by emotion engine

[0935] The server passes the received data to the emotion engine, which uses natural language processing (NLP) and speech analysis technology to recognize emotions from the input data. Specifically, it extracts emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[0936] Stress level assessment

[0937] The server then further analyzes the emotion information recognized by the emotion engine using an artificial intelligence model generated based on the information. The server inputs the emotion information into the model and evaluates the user's stress level in percentage format. For example, the stress level may be evaluated as 80%.

[0938] Providing customized support

[0939] Based on the assessed stress level and emotional information, the server provides customized support, such as advice such as "Try some breathing exercises to relax" for mild stress, or "We strongly recommend you seek professional counseling" for severe stress.

[0940] Support notification

[0941] The support content determined by the server is sent to the device. The user can check the notification and take action. For example, a message such as "Try some breathing exercises to relax" will be displayed on the device.

[0942] Real-time monitoring and alerts

[0943] The server monitors the user's situation in real time. Each time new data is input, it is analyzed using an emotion engine and an artificial intelligence model and the stress level is reassessed. If fluctuations in stress levels exceed a certain threshold, the server immediately generates an alert and sends an emergency notification to the device. For example, if the user frequently inputs "I can't take it anymore," the server will send a notification saying, "We strongly recommend that you seek professional counseling."

[0944] Examples of concrete examples and prompts

[0945] Example 1

[0946] A user types, "Work today was very stressful." The device sends this information to a server, which uses an emotion engine to recognize "stress." The AI ​​model evaluates the stress level at 80% and generates a notification to the user saying, "Take a deep breath and refresh yourself."

[0947] Prompt Sentence Examples

[0948] "Analyze the user's daily thoughts and activity reports to assess their stress level. Then, based on the results, suggest and notify them of appropriate support."

[0949] This system enables real-time management of the user's mental health and highly accurate recognition of subjective emotions.

[0950] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0951] Step 1:

[0952] The user uses the device to input their daily thoughts and activity reports. The user opens the application and types "Today's activities were very busy. I was especially tired from working in the morning" into the text box, or records a similar statement using the voice input function. This input data starts the system's processing (input: text and voice data, output: data temporarily stored on the device).

[0953] Step 2:

[0954] The device sends the entered data to the server. The data is protected and transferred securely using encryption protocols such as SSL / TLS (input: text and voice data stored on the device, output: transfer packets containing encrypted data).

[0955] Step 3:

[0956] The server decrypts the received data and performs preprocessing before passing it to the emotion engine. Specifically, it converts the data format and performs preprocessing (input: encrypted data, output: decrypted and format-converted data).

[0957] Step 4:

[0958] The server then passes the converted data to the emotion engine for emotion recognition. The emotion engine uses natural language processing (NLP) and speech analysis technology to extract emotions from the input data (input: preprocessed text or voice data, output: emotional information, such as "fatigue" or "stress").

[0959] Step 5:

[0960] The server inputs the emotion information obtained from the emotion engine into the generated artificial intelligence model for further analysis. Specifically, the emotion information is used to evaluate the user's stress level (input: emotion information, output: stress level score, e.g., "70% stress").

[0961] Step 6:

[0962] The server determines the customized support content according to the assessed stress level. For example, it generates advice such as "Try breathing exercises to relax" for mild stress and "We strongly recommend that you seek professional counseling" for severe stress (input: stress level score, output: customized support content).

[0963] Step 7:

[0964] The server sends the determined support content to the device. The device receives it and notifies the user. For example, the device displays "Try breathing exercises to relax" (Input: customized support content, Output: notification content displayed on the device).

[0965] Step 8:

[0966] The server monitors the user's condition in real time. Each time new data is input, the above steps are repeated to reassess the stress level. If the fluctuation in the stress level exceeds a certain threshold, the server immediately generates an alert and sends an emergency notification to the device (Input: new input data and real-time monitoring results; Output: alert containing emergency notification).

[0967] (Application example 2)

[0968] 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."

[0969] The importance of stress management and emotion recognition is increasing in modern society. However, there are only a limited number of systems that can provide appropriate support and security alerts to individual users. In addition, there is a lack of technology that can monitor emotional states in real time and respond dynamically, making it difficult to implement effective stress management and security measures.

[0970] The identification process by the identification 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 emotionally analyzing input data from a user using a generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, and means for issuing a security alert based on the user's emotional state. This makes it possible to monitor the user's emotional state in real time and dynamically provide support and security measures as needed.

[0971] A "generated artificial intelligence model" is a model based on machine learning algorithms used to analyze user input data and assess emotions and stress levels.

[0972] The "means for emotional analysis" is a function that identifies emotions from the user's input data and evaluates the type and intensity of those emotions.

[0973] The "means for assessing stress level" is a function that uses emotionally analyzed data to quantify or categorize the user's stress level and assess it.

[0974] The "means for providing customized support" is a function that provides appropriate support and advice to individual users based on the assessed stress level.

[0975] "Real-time monitoring means" refers to a function that constantly monitors the user's input data and stress level, and instantly grasps the situation.

[0976] The "means for notifying an alert" is a function that sends an emergency notification to the user and related parties when the user's stress level exceeds a certain standard.

[0977] "Means for accepting text or voice data" refers to the function of taking text or voice data entered by a user and sending it to a server for analysis.

[0978] The "means for generating and sending referrals to specialists" is a function for creating and sending referrals to guide consultation with an appropriate specialist when the assessed stress level is high.

[0979] "Means for issuing security alerts" is a function that detects security risks based on the user's emotional state and issues an alert as necessary.

[0980] This invention is a system that monitors a user's emotional state in real time, evaluates their stress level, and provides customized support and security alerts as needed. The specific system configuration and operation are described below.

[0981] System configuration

[0982] The system mainly consists of a smartphone, a server, an artificial intelligence model (generative AI model), and an emotion engine. Specifically, it includes the following components:

[0983] Hardware

[0984] Smartphone: A terminal that acquires input data from a user.

[0985] Server: Responsible for receiving and analyzing data, assessing stress levels, and generating customized support and security alerts.

[0986] software

[0987] Smartphone app (development environment: Flutter or React Native): Collects user text / voice input and sends it to the server.

[0988] Google Cloud Natural Language API: Recognize emotions from input text / speech.

[0989] Google Cloud Speech-to-Text API: Converts voice input into text data.

[0990] GPT-4 API: Analyzes emotional data and assesses stress levels.

[0991] Firebase: Manages real-time databases and push notifications.

[0992] Operation flow

[0993] 1. Collecting User Input

[0994] Users can enter their daily emotions and activities through a smartphone app by either typing or recording their voice. For example, they can enter something like, "I can't take it anymore, I'm too busy and tired" into a text box or by recording their voice.

[0995] 2. Data Transmission and Encryption

[0996] The smartphone sends the input data to the server using AES-256 encryption technology, and the data is sent in JSON format.

[0997] 3. Emotion Recognition by Emotion Engine

[0998] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API, which extracts the user's sentiment from the text data.

[0999] 4. Sentiment analysis and stress level assessment

[1000] The recognized emotion data is passed to the GPT-4 API for more detailed emotion analysis, and the resulting analysis results are used to assess stress levels and quantify them (e.g., 70% stress) or categorize them (mild, moderate, severe).

[1001] 5. Providing customized support

[1002] Depending on the stress level, it will determine customized support, for example, generating advice such as "Try some breathing exercises to relax" for mild stress, or recommending a referral to a specialist for severe stress.

[1003] 6. Notification of support details

[1004] The server will then send a push notification of the determined support details to the smartphone via Firebase, allowing the user to check the notification and take appropriate action.

[1005] 7. Real-time monitoring and security alerts

[1006] The server periodically analyzes the user's input data and monitors the stress level in real time. If the stress level exceeds a certain threshold, a security alert is generated and the user is notified.

[1007] Examples of concrete examples and prompts

[1008] For example, if a user types "I'm so stressed at work I can't take it anymore," the app's emotion engine will recognize emotions such as "sadness" and "tiredness," and the GPT-4 API will evaluate the user's level of stress as "90%." As a result, a security alert will be generated stating, "We strongly recommend that you seek professional counseling."

[1009] Example prompt for a generative AI model:

[1010] User input: "I'm so stressed at work I can't take it anymore"

[1011] Recognized emotion data: "Sadness", "Tired", "Irritation"

[1012] Stress level rating: "90%"

[1013] Customized support: "We strongly recommend that you seek professional counseling."

[1014] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1015] Step 1:

[1016] Users use a smartphone app to input their emotions and activities using text or voice. For example, they can type "I can't take it anymore, I'm too busy and tired" into a text box or record their voice. This input data is temporarily stored within the app.

[1017] Step 2:

[1018] The device sends the entered text and voice data to the server using AES-256 encryption, and the input data is converted to JSON format and securely transferred to the server.

[1019] Step 3:

[1020] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API. In the case of voice data, it is first converted to text data using the Speech-to-Text API. This text data is then passed to the Natural Language API for emotion recognition. The input in this step is voice or text data, and the output is emotion information (e.g., "fatigue" or "stress").

[1021] Step 4:

[1022] The server sends the emotion information extracted by the emotion engine to the GPT-4 API for more detailed emotion analysis. At this stage, the server uses the emotion information to evaluate the stress level. The input is emotion information, and the output is the stress level (e.g., "70% stress").

[1023] Step 5:

[1024] The server determines customized support based on the assessed stress level and emotional information. For example, if the stress level is mild, the server generates advice such as "Try breathing exercises to relax," and if the stress level is severe, the server generates a referral such as "We recommend consulting a specialist." The input is the stress level and emotional information, and the output is customized support content.

[1025] Step 6:

[1026] The server then pushes the determined support content to the smartphone via Firebase. The user can check this notification and take appropriate action. The input is the customized support content, and the output is the push notification message.

[1027] Step 7:

[1028] The server analyzes the data in real time every time the user inputs new data and evaluates the stress level. If the stress level exceeds the threshold, the server immediately generates a security alert and notifies the user and, if necessary, an expert. The input in this step is the new input data, and the output is a security alert.

[1029] This makes it possible to monitor a user's emotional state in real time and provide appropriate support and security measures as needed.

[1030] 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.

[1031] 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.

[1032] 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.

[1033] [Fourth embodiment]

[1034] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1035] 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.

[1036] 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).

[1037] 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.

[1038] 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.

[1039] 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).

[1040] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1041] 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.

[1042] 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.

[1043] 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.

[1044] 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.

[1045] 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.

[1046] 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."

[1047] This invention is a system that uses the generated artificial intelligence model to emotionally analyze input data from volunteers, evaluates stress levels based on the emotional analysis results, and provides customized support as needed. Embodiments of the invention are described in detail below.

[1048] Collecting User Input

[1049] First, the user uses a device (smartphone, tablet, PC, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, the user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[1050] Data transmission

[1051] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[1052] sentiment analysis

[1053] The server analyzes the received data using the generated artificial intelligence model. This model is built on machine learning algorithms and detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[1054] Stress level assessment

[1055] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, or severe.

[1056] Providing customized support

[1057] The server then offers customized support based on the assessed stress level: for mild stress, preventative advice such as "try some breathing exercises to relax" is suggested, while for severe stress, referrals to specialists or instructions such as "we strongly recommend you take some rest" are offered.

[1058] Support notification

[1059] The support content determined by the server is sent to the device and notified to the user, who can then check the notification within the application and take appropriate action.

[1060] Real-time monitoring and alerts

[1061] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[1062] This allows the system to manage users' stress levels in real time and provide the necessary support, thereby maintaining volunteers' mental health and supporting effective disaster response.

[1063] The processing flow will be explained below.

[1064] Step 1:

[1065] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[1066] Step 2:

[1067] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[1068] Step 3:

[1069] The server then passes the received data to the analysis module, which then begins analyzing it using the generated artificial intelligence model. This model is built on machine learning algorithms and can detect emotional nuances from the user's input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[1070] Step 4:

[1071] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, the sentiment analysis may evaluate the user as "70% stressed."

[1072] Step 5:

[1073] The server determines customized support based on the assessed stress level: for mild stress, it provides preventative advice, while for severe stress, it refers the user to a specialist or recommends rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[1074] Step 6:

[1075] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[1076] Step 7:

[1077] The server monitors the user's situation in real time. Every time the user enters new data, the server performs emotional analysis and stress assessment. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[1078] This process allows the system to manage the user's stress level in real time and provide appropriate support when needed.

[1079] Example 1

[1080] 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."

[1081] Conventional mental health management systems have had difficulty accurately grasping users' emotional states and stress levels and providing appropriate support. There is also a risk of user input data being leaked to external parties. In particular, there is a need for systems that can respond to fluctuations in stress levels in real time, so a new method was needed.

[1082] 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.

[1083] In this invention, the server includes means for performing emotional analysis using the generated artificial intelligence model, means for assessing the user's stress level based on the result of the emotional analysis, and means for providing customized support according to the assessed stress level, thereby making it possible to analyze the user's input data, appropriately assess the stress level, and provide customized support as needed.

[1084] A "generated artificial intelligence model" refers to a model of a machine learning algorithm that has been pre-trained to analyze user input data.

[1085] "Means for emotional analysis" refers to the process of using a generated artificial intelligence model to detect emotional nuances from user input data.

[1086] The "means for assessing stress level" refers to a process for quantitatively assessing the degree of stress of a user based on the results of sentiment analysis.

[1087] "Means for providing customized support" refers to a process for providing advice and support optimized for each user according to the assessed stress level.

[1088] "Means for encrypting and securely transmitting to the server" refers to the process of encrypting the user's input data and securely transmitting it to the server using a communication protocol.

[1089] "Real-time monitoring means" refers to the process of continuously monitoring user input data and stress levels to quickly detect fluctuations.

[1090] "Means for notifying an alert" refers to a process for sending a warning to a user or a relevant third party when fluctuations in stress levels exceed a set threshold.

[1091] "Means for accepting text or voice data and sending it to a server" refers to the process of receiving data entered by a user in text or voice format and transferring it to a server.

[1092] "Means for generating and sending referrals to specialists" refers to the process of generating referrals or consultation requests to specialists based on the results of stress assessments, as needed, and sending them through appropriate channels.

[1093] The present invention is a system that uses a generated artificial intelligence model to emotionally analyze input data from a user, evaluates the stress level based on the emotion analysis results, and provides customized support as needed. An embodiment of the present invention will be described in detail below.

[1094] Collecting User Input

[1095] Users can use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done either by text or voice, for example, by typing something like "Today's activities were very busy. I was especially tired from working in the morning," or by recording something using the voice input function.

[1096] Data transmission

[1097] The device encrypts the input data and sends it securely to the server. This transmission uses the HTTPS protocol. For example, when a user inputs text data or voice data, the device encrypts it and sends it to the server.

[1098] sentiment analysis

[1099] The server analyzes the received data using the generated artificial intelligence model. Specifically, it uses a model built on machine learning frameworks such as TensorFlow and PyTorch. This model detects emotional nuances from the user's input data. For example, it identifies emotions such as "fatigue" or "stress" from the expression "very tired."

[1100] Stress level assessment

[1101] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., a percentage) and categorized as mild, moderate, severe, etc. The evaluation is performed using statistical methods and the output of machine learning models.

[1102] Providing customized support

[1103] The server then provides customized support based on the assessed stress level. For example, for mild stress, preventative advice such as "Try some breathing exercises to relax" is suggested. For severe stress, the server may refer the user to a specialist or provide instructions such as "We strongly recommend you take some rest." This support is determined based on pre-defined rules and algorithms.

[1104] Support notification

[1105] The support content determined by the server is sent to the device and notified to the user. For example, a push notification is sent to a smartphone app. The user can check the notification and take appropriate action.

[1106] Real-time monitoring and alerts

[1107] The server monitors the user's situation in real time. Every time new data is entered, it performs emotion analysis and stress assessment, and if fluctuations in stress levels exceed a certain threshold, an alert is sent. For example, if a user frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[1108] This allows the system to emotionally analyze user input data, monitor stress levels in real time, and provide appropriate support.

[1109] Specific examples

[1110] Example 1

[1111] A user uses a smartphone to voice input, "Work today was very stressful." The voice data is sent from the device to a server, which analyzes the data using the BERT model and determines the user's emotion as "stress." The server then sends a message to the device notifying the user, such as, "Your current stress level is medium. Please take an early rest today."

[1112] Example 2

[1113] A user uses a PC to input the text "I've been overwhelmed with work lately and I'm very tired." The text data is encrypted and sent to a server using the HTTPS protocol. The server uses a sentiment analysis model built with TensorFlow to evaluate the user's stress level as "severe" based on the expression "I'm very tired." The server then generates a message such as "I strongly recommend that you consult a specialist immediately" and sends it to the user's device.

[1114] Prompt Sentence Examples

[1115] "Design an algorithm that emotionally analyzes a user's input text and assesses their stress level. Then combine it with a model that generates a customized support message based on the assessment results."

[1116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1117] Step 1: Collecting User Input

[1118] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and progress reports. Input can be done by text or voice. The input data is written in a text box in the application or recorded using the voice input function. Specifically, the user enters the text "I was very tired at work today" into the input form on the device and presses the send button.

[1119] Input: User impressions and activity reports (text or audio data)

[1120] Output: Input data in the terminal

[1121] Step 2: Send data

[1122] The terminal encrypts the data entered by the user and sends it to the server. This transmission uses the HTTPS protocol. Specifically, the terminal encrypts the input data and sends it to the server's API endpoint using HTTPS.

[1123] Input: Input data in the terminal

[1124] Data processing: Data encryption

[1125] Data calculation: Transmission using HTTPS protocol

[1126] Output: Encrypted data sent to the server

[1127] Step 3: Sentiment analysis

[1128] The server decrypts the received encrypted data and performs emotional analysis using the generated artificial intelligence model. Specific software used is TensorFlow and PyTorch. This allows emotions to be detected from the user's input data. Specifically, the server inputs emotions such as "tired" into the machine learning model, and detects "stress" and "fatigue."

[1129] Input: Encrypted data sent to the server

[1130] Data processing: Deciphering the data

[1131] Data Computing: Sentiment Analysis Using AI Models

[1132] Output: Sentiment analysis results (type and intensity of emotion)

[1133] Step 4: Assess your stress levels

[1134] The server uses the results of the emotion analysis to evaluate the user's stress level. The stress level is expressed as a quantitative indicator (such as a percentage) and is classified as mild, moderate, or severe. Specifically, the server analyzes the emotion analysis results and determines that the user's current stress level is 60% (moderate).

[1135] Input: Sentiment analysis results

[1136] Data calculation: Stress level evaluation

[1137] Output: Stress level (numerical and classification)

[1138] Step 5: Providing customized support

[1139] The server provides customized support based on the assessed stress level. For mild stress, advice such as "Try breathing exercises to relax" is provided. For severe stress, a referral to a specialist or instructions such as "We recommend you take immediate rest" are provided. Specifically, the server generates a message based on the assessment results and determines the type of support to provide.

[1140] Input: Stress level (number and classification)

[1141] Data Calculation: Support Content Generation

[1142] Output: Customized support message

[1143] Step 6: Notification of support details

[1144] The server sends the determined support content to the device and notifies the user. Notifications are sent via push notification or email. Specifically, the server sends a push notification to the device saying, "Try some breathing exercises to relax."

[1145] Input:Customized support message

[1146] Data calculation: Sending support messages

[1147] Output: Notification to terminal

[1148] Step 7: Real-time monitoring and alerting

[1149] The server monitors the user's input data and stress level in real time. Every time the user makes a new input, it performs an emotion analysis and stress assessment, and if the fluctuation in the stress level exceeds the set standard, it sends an alert. Specifically, if the server detects an input such as "I can't do it anymore," it will issue an emergency notification such as "We strongly recommend that you seek professional counseling."

[1150] Input: New user-entered data

[1151] Data calculation: Sentiment analysis, stress assessment, alert judgment

[1152] Output: Emergency notification message

[1153] These steps enable the system to analyze and monitor the user's emotional state in real time and provide tailored support accordingly.

[1154] (Application example 1)

[1155] 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."

[1156] Maintenance workers in factories often experience mental stress due to their hectic work schedules and high sense of responsibility. This stress can lead to reduced work efficiency and health problems. It is also difficult to objectively measure stress levels and provide appropriate support, making it an urgent task to address this issue.

[1157] 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.

[1158] In this invention, the server includes means for emotionally analyzing input data from a user using the generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, means for monitoring the user's input data and stress level in real time, means for issuing an alert when fluctuations in the stress level exceed a certain standard, and means for analyzing the input data of factory workers and providing mental health support according to their stress levels. This makes it possible to efficiently manage stress among factory workers and provide appropriate mental health care.

[1159] An "artificial intelligence model" is a data processing mechanism built on machine learning algorithms to analyze user input data and identify emotions and other patterns.

[1160] "User" refers to an individual or worker who utilizes the system of the present invention to provide input data and receive stress level assessment and customized support.

[1161] "Stress level" is an index that quantitatively represents the degree of emotional or mental stress of a user, and is evaluated by emotion analysis.

[1162] "Customized support" refers to advice and mental health care provided individually based on the user's stress level.

[1163] "Real-time monitoring" refers to the process of constantly monitoring fluctuations in user input data and stress levels and responding immediately if necessary.

[1164] An "alert" is a warning notification that the system automatically issues when the stress level exceeds a certain threshold.

[1165] "Factory workers" refers to workers engaged in production and maintenance activities within a factory.

[1166] "Mental health support" refers to support activities including advice, consultation, referrals, and other measures aimed at reducing stress and maintaining mental health.

[1167] This invention is a system for supporting the mental health of maintenance personnel working in factories. It uses a generated artificial intelligence model to emotionally analyze user input data, assess stress levels based on the results, and provide customized support as needed.

[1168] Collecting User Input

[1169] Users can input their daily thoughts and work progress using devices such as smartphones, tablets, and PCs. Input can be by text or voice. For example, a user can type a statement such as "Today's work was very difficult" into the application's text box, or record a similar statement using the voice input function.

[1170] Data transmission

[1171] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[1172] sentiment analysis

[1173] The server analyzes the received data using the generated artificial intelligence model. Specifically, it uses the Bidirectional Encoder Representations from Transformers (BERT) model to detect emotional nuances from the user's input data. For example, it identifies the emotion "negative" from the expression "it was very difficult."

[1174] Stress level assessment

[1175] Based on the results of the sentiment analysis, the server evaluates the user's stress level, which is expressed as a quantitative indicator (e.g., points or percentage) and classified as mild, moderate, severe, etc.

[1176] Providing customized support

[1177] The server then offers customized support depending on the assessed stress level: for example, advice such as "take a short break and relax" is offered for mild stress, while instructions such as "we strongly recommend you seek professional counseling" are given for severe stress.

[1178] Support notification

[1179] The support content determined by the server is sent to the user's device and notified. The user can check the notification within the application and take appropriate action.

[1180] Real-time monitoring and alerts

[1181] The server monitors the user's situation in real time. New data entered by the user is also subjected to emotion analysis and stress assessment. If fluctuations in stress levels exceed a certain threshold, the server immediately sends an alert.

[1182] overview

[1183] Hardware: Servers, smartphones, tablets, PCs

[1184] software:

[1185] Server: BERT model (Transformers library), Flask

[1186] Device: Voice recognition software, text input interface

[1187] Example prompt sentences

[1188] Example: If the user types, "Working today was very difficult."

[1189] Prompt statement:

[1190] data = { 'input': 'Today's work was very difficult'}

[1191] response = requests.post('http: / / <server IP address>:5000 / analyze', json=data)

[1192] print(response.json())

[1193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1194] Step 1:

[1195] Users use devices such as smartphones, tablets, and PCs to input their daily thoughts and work progress. Input can be either text or voice, and a specific input might be, "Today's work was very difficult." This is the input data for this step. They can then type it into the text box or record it using the voice input function.

[1196] Output: Text or voice data entered into the device

[1197] Step 2:

[1198] The terminal sends the entered text or voice data to the server. At this time, the data is encrypted to ensure security. The sent data is the output data of this step.

[1199] Output: Encrypted text or audio data sent to the server

[1200] Step 3:

[1201] The server analyzes the received data using the generated artificial intelligence model. This analysis uses the BERT model (Transformers library) to tokenize the text data and perform sentiment analysis. Specifically, it identifies sentiment labels such as "negative" from the expression "it was very difficult."

[1202] Input: Encrypted text or voice data received by the server

[1203] Output: Parsed emotion label (e.g. "negative")

[1204] Step 4:

[1205] Based on the results of the sentiment analysis, the server evaluates the user's stress level. The evaluation is expressed as a quantitative indicator (points or percentage) and classified into categories such as mild, moderate, and severe. For example, if the user is labeled as "negative," the stress level is evaluated as moderate or severe.

[1206] Input: Parsed emotion labels

[1207] Output: Estimated stress level (e.g., "moderate")

[1208] Step 5:

[1209] Depending on the assessed stress level, the server will provide customized support: for example, if the stress level is mild, it will generate advice such as "take a short break and relax," while if the stress level is severe, it will generate instructions such as "we strongly recommend that you seek professional counseling."

[1210] Input: Estimated stress level

[1211] Output: Customized support (e.g., "Take a short break")

[1212] Step 6:

[1213] The server sends the determined support content to the device and notifies the user, who can then check the notification within the application and take appropriate action.

[1214] Input: Customized support content

[1215] Output: Support content sent to the device

[1216] Step 7:

[1217] The server monitors the user's situation in real time, continuously analyzing emotions and assessing stress even when new data is entered. If fluctuations in stress levels exceed a certain threshold, the server will issue an alert. For example, if the user enters "it was very difficult" multiple times in a row, an emergency alert will be issued.

[1218] Input: New data arriving in real time

[1219] Output: Alert notification as needed (e.g., "Consultation with a specialist is strongly recommended")

[1220] 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.

[1221] This invention is a system that combines the generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, evaluate stress levels based on the results, and provide customized support as needed. Embodiments of the invention are described in detail below.

[1222] Collecting User Input

[1223] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into a text box in the application, or record a similar statement using the voice input function.

[1224] Data transmission

[1225] The device sends the entered text and voice data to the server, where the data is encrypted and sent securely.

[1226] Emotion recognition by emotion engine

[1227] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" or "stress" from the expression "I'm very tired."

[1228] Sentiment analysis and stress level assessment

[1229] The server further analyzes the emotional information recognized by the emotion engine using the generated artificial intelligence model. Based on the analysis results, the server evaluates the user's stress level. The stress level is expressed as a quantitative indicator (e.g., a percentage) and classified as mild, moderate, severe, etc. For example, it may be evaluated as "70% stress."

[1230] Providing customized support

[1231] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[1232] Support notification

[1233] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[1234] Real-time monitoring and alerts

[1235] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and an artificial intelligence model to evaluate the user's stress level. If fluctuations in the user's stress level exceed a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[1236] Through this series of processes, the system can manage the user's stress level in real time and provide appropriate support as needed. The introduction of an emotion engine enables more accurate emotion recognition, helping to maintain the user's mental health and streamlining disaster response.

[1237] The processing flow will be explained below.

[1238] Step 1:

[1239] Users use devices (smartphones, tablets, PCs, etc.) to input their daily thoughts and progress reports. Input can be done either by text or voice. For example, a user can type a statement such as "Today's activities were very busy. I was especially tired from working in the morning" into the application's text box, or record similar content using the voice input function.

[1240] Step 2:

[1241] The device sends the entered text and voice data to the server. The data is encrypted and sent securely. For example, the entered text "Today's activities were very busy. I was especially tired from working this morning" is sent to the server.

[1242] Step 3:

[1243] The server passes the received data to the emotion engine, which recognizes emotions from the user's input data. This emotion engine uses natural language processing and speech analysis techniques to extract emotional nuances from the input data. For example, it can identify emotions such as "fatigue" and "stress" from the text, "Today's activities were very busy. I was especially tired from working this morning."

[1244] Step 4:

[1245] Based on the emotional information recognized by the emotion engine, the server performs further analysis using the generated artificial intelligence model. This model is built on machine learning algorithms and evaluates the user's stress level. For example, if the emotion engine extracts "fatigue," the server will use it to evaluate the user's stress level as "70% stress."

[1246] Step 5:

[1247] The server determines customized support based on the assessed stress level and emotional information. For mild stress, it provides preventative advice, while for severe stress, it recommends referral to a specialist or rest. For example, for mild stress, it generates advice such as "Try some breathing exercises to relax."

[1248] Step 6:

[1249] The support content determined by the server is sent to the device and notified to the user. The user can check the notification in the application and take appropriate action. For example, the device may display a message saying, "Try some breathing exercises to relax."

[1250] Step 7:

[1251] The server monitors the user's situation in real time. Every time the user enters new data, the server analyzes it using an emotion engine and artificial intelligence model and reevaluates the stress level. If the stress level fluctuation exceeds a certain threshold, the server immediately sends an alert. For example, if a volunteer frequently enters "I can't do this anymore," the server will send an urgent notification saying, "We strongly recommend that you seek professional counseling."

[1252] Through this process, the system can manage the user's emotions and stress levels in real time and provide appropriate support as needed. By combining the emotion engine, the system can more accurately recognize the user's emotions and quickly provide individually customized support, contributing to maintaining the user's mental health and improving the efficiency of disaster response.

[1253] Example 2

[1254] 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."

[1255] In modern society, managing personal mental health has become an important issue. However, many people often lack the time or means to properly assess their emotions and stress levels due to their busy lives. Furthermore, conventional systems have difficulty accurately analyzing emotions and stress in real time and providing appropriate support. Therefore, there is a need for a system that allows users to effectively manage their own mental health and receive prompt support when needed.

[1256] 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 a means for a user to input daily impressions and activity reports using a terminal, a means for encrypting the input text and voice data and transmitting the data to the server, a means for emotionally analyzing the input data from the user using a generated artificial intelligence model, a means for evaluating a stress level based on the user's input data, a means for providing customized support according to the evaluated stress level, a means for monitoring the user's input data and stress level in real time, and a means for issuing an alert when fluctuations in the stress level exceed a certain standard. This makes it possible to accurately analyze the user's emotions and stress level in real time and quickly provide customized support as needed.

[1257] "User" refers to an individual who uses this system and enters daily impressions and activity reports.

[1258] "Terminal" refers to an electronic device used by a user, such as a smartphone, tablet, or PC.

[1259] "Server" refers to a central control device that receives and processes data sent by users.

[1260] "Input data" refers to text and voice data that a user inputs through a terminal.

[1261] "Emotion engine" refers to a software component that analyzes input data and recognizes a user's emotions.

[1262] "Generated artificial intelligence model" refers to a trained AI model that analyzes user input data and assesses stress levels.

[1263] "Stress level" refers to the result of a quantitative assessment of the user's emotional state.

[1264] "Customized support" refers to personalized advice and recommended actions provided based on assessed stress levels.

[1265] "Real-time monitoring" refers to the process of continuously monitoring user input data and stress levels, and immediately evaluating and analyzing them.

[1266] An "alert" refers to an emergency message that is sent to the user when fluctuations in stress level exceed a certain threshold.

[1267] The present invention is a system that combines a generated artificial intelligence model and an emotion engine that recognizes the user's emotions to emotionally analyze input data from volunteers, assess stress levels based on the results, and provide customized support as needed.

[1268] overview

[1269] The present invention begins with the user (using a smartphone, tablet, PC, etc.) entering their daily thoughts and activity reports. The user can enter data using text or voice, for example, "Today's activities were very busy. I was especially tired from working in the morning."

[1270] Data Transmission and Encryption

[1271] The entered data is sent by the terminal to the server, where it is guaranteed to be transmitted securely using encryption technology such as SSL / TLS.

[1272] Analysis by emotion engine

[1273] The server passes the received data to the emotion engine, which uses natural language processing (NLP) and speech analysis technology to recognize emotions from the input data. Specifically, it extracts emotions such as "fatigue" and "stress" from the expression "I'm very tired."

[1274] Stress level assessment

[1275] The server then further analyzes the emotion information recognized by the emotion engine using an artificial intelligence model generated based on the information. The server inputs the emotion information into the model and evaluates the user's stress level in percentage format. For example, the stress level may be evaluated as 80%.

[1276] Providing customized support

[1277] Based on the assessed stress level and emotional information, the server provides customized support, such as advice such as "Try some breathing exercises to relax" for mild stress, or "We strongly recommend you seek professional counseling" for severe stress.

[1278] Support notification

[1279] The support content determined by the server is sent to the device. The user can check the notification and take action. For example, a message such as "Try some breathing exercises to relax" will be displayed on the device.

[1280] Real-time monitoring and alerts

[1281] The server monitors the user's situation in real time. Each time new data is input, it is analyzed using an emotion engine and an artificial intelligence model and the stress level is reassessed. If fluctuations in stress levels exceed a certain threshold, the server immediately generates an alert and sends an emergency notification to the device. For example, if the user frequently inputs "I can't take it anymore," the server will send a notification saying, "We strongly recommend that you seek professional counseling."

[1282] Examples of concrete examples and prompts

[1283] Example 1

[1284] A user types, "Work today was very stressful." The device sends this information to a server, which uses an emotion engine to recognize "stress." The AI ​​model evaluates the stress level at 80% and generates a notification to the user saying, "Take a deep breath and refresh yourself."

[1285] Prompt Sentence Examples

[1286] "Analyze the user's daily thoughts and activity reports to assess their stress level. Then, based on the results, suggest and notify them of appropriate support."

[1287] This system enables real-time management of the user's mental health and highly accurate recognition of subjective emotions.

[1288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1289] Step 1:

[1290] The user uses the device to input their daily thoughts and activity reports. The user opens the application and types "Today's activities were very busy. I was especially tired from working in the morning" into the text box, or records a similar statement using the voice input function. This input data starts the system's processing (input: text and voice data, output: data temporarily stored on the device).

[1291] Step 2:

[1292] The device sends the entered data to the server. The data is protected and transferred securely using encryption protocols such as SSL / TLS (input: text and voice data stored on the device, output: transfer packets containing encrypted data).

[1293] Step 3:

[1294] The server decrypts the received data and performs preprocessing before passing it to the emotion engine. Specifically, it converts the data format and performs preprocessing (input: encrypted data, output: decrypted and format-converted data).

[1295] Step 4:

[1296] The server then passes the converted data to the emotion engine for emotion recognition. The emotion engine uses natural language processing (NLP) and speech analysis technology to extract emotions from the input data (input: preprocessed text or voice data, output: emotional information, such as "fatigue" or "stress").

[1297] Step 5:

[1298] The server inputs the emotion information obtained from the emotion engine into the generated artificial intelligence model for further analysis. Specifically, the emotion information is used to evaluate the user's stress level (input: emotion information, output: stress level score, e.g., "70% stress").

[1299] Step 6:

[1300] The server determines the customized support content according to the assessed stress level. For example, it generates advice such as "Try breathing exercises to relax" for mild stress and "We strongly recommend that you seek professional counseling" for severe stress (input: stress level score, output: customized support content).

[1301] Step 7:

[1302] The server sends the determined support content to the device. The device receives it and notifies the user. For example, the device displays "Try breathing exercises to relax" (Input: customized support content, Output: notification content displayed on the device).

[1303] Step 8:

[1304] The server monitors the user's condition in real time. Each time new data is input, the above steps are repeated to reassess the stress level. If the fluctuation in the stress level exceeds a certain threshold, the server immediately generates an alert and sends an emergency notification to the device (Input: new input data and real-time monitoring results; Output: alert containing emergency notification).

[1305] (Application example 2)

[1306] 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."

[1307] The importance of stress management and emotion recognition is increasing in modern society. However, there are only a limited number of systems that can provide appropriate support and security alerts to individual users. In addition, there is a lack of technology that can monitor emotional states in real time and respond dynamically, making it difficult to implement effective stress management and security measures.

[1308] The identification process by the identification 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 emotionally analyzing input data from a user using a generated artificial intelligence model, means for assessing a stress level based on the user's input data, means for providing customized support according to the assessed stress level, and means for issuing a security alert based on the user's emotional state. This makes it possible to monitor the user's emotional state in real time and dynamically provide support and security measures as needed.

[1309] A "generated artificial intelligence model" is a model based on machine learning algorithms used to analyze user input data and assess emotions and stress levels.

[1310] The "means for emotional analysis" is a function that identifies emotions from the user's input data and evaluates the type and intensity of those emotions.

[1311] The "means for assessing stress level" is a function that uses emotionally analyzed data to quantify or categorize the user's stress level and assess it.

[1312] The "means for providing customized support" is a function that provides appropriate support and advice to individual users based on the assessed stress level.

[1313] "Real-time monitoring means" refers to a function that constantly monitors the user's input data and stress level, and instantly grasps the situation.

[1314] The "means for notifying an alert" is a function that sends an emergency notification to the user and related parties when the user's stress level exceeds a certain standard.

[1315] "Means for accepting text or voice data" refers to the function of taking text or voice data entered by a user and sending it to a server for analysis.

[1316] The "means for generating and sending referrals to specialists" is a function for creating and sending referrals to guide consultation with an appropriate specialist when the assessed stress level is high.

[1317] "Means for issuing security alerts" is a function that detects security risks based on the user's emotional state and issues an alert as necessary.

[1318] This invention is a system that monitors a user's emotional state in real time, evaluates their stress level, and provides customized support and security alerts as needed. The specific system configuration and operation are described below.

[1319] System configuration

[1320] The system mainly consists of a smartphone, a server, an artificial intelligence model (generative AI model), and an emotion engine. Specifically, it includes the following components:

[1321] Hardware

[1322] Smartphone: A terminal that acquires input data from a user.

[1323] Server: Responsible for receiving and analyzing data, assessing stress levels, and generating customized support and security alerts.

[1324] software

[1325] Smartphone app (development environment: Flutter or React Native): Collects user text / voice input and sends it to the server.

[1326] Google Cloud Natural Language API: Recognize emotions from input text / speech.

[1327] Google Cloud Speech-to-Text API: Converts voice input into text data.

[1328] GPT-4 API: Analyzes emotional data and assesses stress levels.

[1329] Firebase: Manages real-time databases and push notifications.

[1330] Operation flow

[1331] 1. Collecting User Input

[1332] Users can enter their daily emotions and activities through a smartphone app by either typing or recording their voice. For example, they can enter something like, "I can't take it anymore, I'm too busy and tired" into a text box or by recording their voice.

[1333] 2. Data Transmission and Encryption

[1334] The smartphone sends the input data to the server using AES-256 encryption technology, and the data is sent in JSON format.

[1335] 3. Emotion Recognition by Emotion Engine

[1336] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API, which extracts the user's sentiment from the text data.

[1337] 4. Sentiment analysis and stress level assessment

[1338] The recognized emotion data is passed to the GPT-4 API for more detailed emotion analysis, and the resulting analysis results are used to assess stress levels and quantify them (e.g., 70% stress) or categorize them (mild, moderate, severe).

[1339] 5. Providing customized support

[1340] Depending on the stress level, it will determine customized support, for example, generating advice such as "Try some breathing exercises to relax" for mild stress, or recommending a referral to a specialist for severe stress.

[1341] 6. Notification of support details

[1342] The server will then send a push notification of the determined support details to the smartphone via Firebase, allowing the user to check the notification and take appropriate action.

[1343] 7. Real-time monitoring and security alerts

[1344] The server periodically analyzes the user's input data and monitors the stress level in real time. If the stress level exceeds a certain threshold, a security alert is generated and the user is notified.

[1345] Examples of concrete examples and prompts

[1346] For example, if a user types "I'm so stressed at work I can't take it anymore," the app's emotion engine will recognize emotions such as "sadness" and "tiredness," and the GPT-4 API will evaluate the user's level of stress as "90%." As a result, a security alert will be generated stating, "We strongly recommend that you seek professional counseling."

[1347] Example prompt for a generative AI model:

[1348] User input: "I'm so stressed at work I can't take it anymore"

[1349] Recognized emotion data: "Sadness", "Tired", "Irritation"

[1350] Stress level rating: "90%"

[1351] Customized support: "We strongly recommend that you seek professional counseling."

[1352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1353] Step 1:

[1354] Users use a smartphone app to input their emotions and activities using text or voice. For example, they can type "I can't take it anymore, I'm too busy and tired" into a text box or record their voice. This input data is temporarily stored within the app.

[1355] Step 2:

[1356] The device sends the entered text and voice data to the server using AES-256 encryption, and the input data is converted to JSON format and securely transferred to the server.

[1357] Step 3:

[1358] The server provides the received data to the Google Cloud Natural Language API and Google Cloud Speech-to-Text API. In the case of voice data, it is first converted to text data using the Speech-to-Text API. This text data is then passed to the Natural Language API for emotion recognition. The input in this step is voice or text data, and the output is emotion information (e.g., "fatigue" or "stress").

[1359] Step 4:

[1360] The server sends the emotion information extracted by the emotion engine to the GPT-4 API for more detailed emotion analysis. At this stage, the server uses the emotion information to evaluate the stress level. The input is emotion information, and the output is the stress level (e.g., "70% stress").

[1361] Step 5:

[1362] The server determines customized support based on the assessed stress level and emotional information. For example, if the stress level is mild, the server generates advice such as "Try breathing exercises to relax," and if the stress level is severe, the server generates a referral such as "We recommend consulting a specialist." The input is the stress level and emotional information, and the output is customized support content.

[1363] Step 6:

[1364] The server then pushes the determined support content to the smartphone via Firebase. The user can check this notification and take appropriate action. The input is the customized support content, and the output is the push notification message.

[1365] Step 7:

[1366] The server analyzes the data in real time every time the user inputs new data and evaluates the stress level. If the stress level exceeds the threshold, the server immediately generates a security alert and notifies the user and, if necessary, an expert. The input in this step is the new input data, and the output is a security alert.

[1367] This makes it possible to monitor a user's emotional state in real time and provide appropriate support and security measures as needed.

[1368] 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.

[1369] 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.

[1370] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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).

[1375] 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.

[1376] 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."

[1377] 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.

[1378] 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).

[1379] 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.

[1380] 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.

[1381] 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.

[1382] 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.

[1383] 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.

[1384] 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.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] The following is further disclosed regarding the above embodiment.

[1390] (Claim 1)

[1391] A means for emotionally analyzing input data from a user using the generated artificial intelligence model;

[1392] means for assessing a stress level based on user input data;

[1393] a means of providing customized support according to assessed stress levels;

[1394] means for monitoring user input data and stress levels in real time;

[1395] The system includes a means for issuing an alert when fluctuations in stress levels exceed a certain standard.

[1396] (Claim 2)

[1397] 10. The system of claim 1, further comprising means for accepting user input data as text or voice data and transmitting it to the server.

[1398] (Claim 3)

[1399] 10. The system of claim 1, further comprising means for generating and sending referrals to specialists according to stress levels.

[1400] "Example 1"

[1401] (Claim 1)

[1402] A means for emotionally analyzing input data from a user using the generated artificial intelligence model;

[1403] means for assessing a stress level of the user based on the results of the sentiment analysis;

[1404] a means of providing customized support according to assessed stress levels;

[1405] A means for encrypting user input data and transmitting it securely to a server;

[1406] means for monitoring user input data and stress levels in real time;

[1407] A means of sending an alert when fluctuations in stress levels exceed a certain standard;

[1408] The system includes a means for the server to process the results of the emotion analysis and stress assessment using a generative AI model.

[1409] (Claim 2)

[1410] 10. The system of claim 1, further comprising means for accepting user input data as text or voice data and transmitting it to the server.

[1411] (Claim 3)

[1412] 10. The system of claim 1, further comprising means for generating and sending referrals to specialists according to stress levels.

[1413] "Application Example 1"

[1414] (Claim 1)

[1415] A means for emotionally analyzing input data from a user using the generated artificial intelligence model;

[1416] means for assessing a stress level based on user input data;

[1417] a means of providing customized support according to assessed stress levels;

[1418] means for monitoring user input data and stress levels in real time;

[1419] A means of sending an alert when fluctuations in stress levels exceed a certain standard;

[1420] A system that includes a means for analyzing input data from factory workers and providing mental health support according to their stress levels.

[1421] (Claim 2)

[1422] 10. The system of claim 1, further comprising means for accepting user input data as text or voice data and transmitting it to the server.

[1423] (Claim 3)

[1424] 10. The system of claim 1, further comprising means for generating and sending referrals to specialists according to stress levels.

[1425] "Example 2: Combining Emotion Engines"

[1426] (Claim 1)

[1427] A means for users to input their daily thoughts and activity reports using a terminal;

[1428] A means for encrypting input text and voice data and sending it to a server;

[1429] A means for emotionally analyzing input data from a user using the generated artificial intelligence model;

[1430] means for assessing a stress level based on user input data;

[1431] a means of providing customized support according to assessed stress levels;

[1432] means for monitoring user input data and stress levels in real time;

[1433] The system includes a means for issuing an alert when fluctuations in stress levels exceed a certain standard.

[1434] (Claim 2)

[1435] 10. The system of claim 1, further comprising means for accepting user input data as text or voice data and transmitting it to the server.

[1436] (Claim 3)

[1437] 10. The system of claim 1, further comprising means for generating and sending referrals to specialists according to stress levels.

[1438] "Application example 2 when combining emotion engines"

[1439] (Claim 1)

[1440] A means for emotionally analyzing input data from a user using the generated artificial intelligence model;

[1441] means for assessing a stress level based on user input data;

[1442] a means of providing customized support according to assessed stress levels;

[1443] means for monitoring user input data and stress levels in real time;

[1444] A means of sending an alert when fluctuations in stress levels exceed a certain standard;

[1445] A system including means for generating security alerts based on a user's emotional state.

[1446] (Claim 2)

[1447] 10. The system of claim 1, further comprising means for accepting user input data as text or voice data and transmitting it to the server.

[1448] (Claim 3)

[1449] 10. The system of claim 1, further comprising means for generating and sending referrals to specialists according to stress levels. [Explanation of symbols]

[1450] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for emotionally analyzing input data from a user using the generated artificial intelligence model; means for assessing a stress level based on user input data; a means of providing customized support according to assessed stress levels; means for monitoring user input data and stress levels in real time; The system includes a means for issuing an alert when fluctuations in stress levels exceed a certain standard.

2. 2. The system of claim 1, further comprising means for accepting user input data as text or voice data and transmitting the data to the server.

3. The system of claim 1 , further comprising means for generating and sending referrals to specialists according to stress levels.

Images