System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting user input; means for analyzing emotions and stress levels based on the collected user input; and means for providing appropriate mental support based on the analysis.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] Individuals and their families in litigation often experience psychological strain and stress due to the uncertainty and protracted nature of the legal process. While specific and effective mental health support is needed to alleviate this psychological strain, many current methods lack real-time response and individualization. Furthermore, the lack of integration between legal advice and mental support results in inadequate support for users. This invention aims to solve these issues and provide a system that effectively protects the mental health of individuals in litigation. [Means for solving the problem]

[0005] The present invention provides a system that solves the above-mentioned problems by including the following means. First, it includes means for collecting user input. This means collects information on the user's emotional state and stress level as text or voice data. Next, it provides means for analyzing the emotions and stress level based on the collected user input data. This means analyzes the data using natural language processing (NLP) technology or an emotion analysis algorithm. It also includes means for providing appropriate mental support based on the analysis results. This means provides personalized mental support to the user in real time. It also includes means for collecting user feedback on the mental support provided and re-training the system based on that feedback. A system configured in this way realizes continuous and effective mental health support for individuals undergoing litigation.

[0006] "User input" refers to information about emotional state and stress level that a user provides to the system.

[0007] "Means for collecting" refers to the totality of hardware and software for capturing user input as text or voice data.

[0008] "Means for analyzing" refers to the process of utilizing natural language processing (NLP) techniques and / or sentiment analysis algorithms to determine emotions and stress levels based on collected user input.

[0009] "Mental support" refers to assistance provided to reduce the user's psychological burden, and includes meditation guidance, relaxation exercises, counseling, etc.

[0010] "Means for providing" refers to the totality of hardware and software for presenting the mental support selected based on the analysis results to the user and for enabling them to execute it.

[0011] "Feedback" refers to information about the user's impressions and effectiveness of the mental support provided after the user has received it.

[0012] "Retraining" refers to the process of updating and improving the AI ​​model based on collected feedback to improve the quality of the next mental support session. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[0035] 1. Collecting User Input

[0036] User:

[0037] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data will be collected.

[0038] Device:

[0039] The device collects text and voice data from the user and transmits it to the server in real time.

[0040] 2. Emotion and stress level analysis

[0041] server:

[0042] The server receives text and voice data from the device. The AI ​​model then analyzes the data using natural language processing (NLP) techniques and sentiment analysis algorithms. For example, it can identify keywords such as "stress" and "feel" and determine that the user's stress level is high.

[0043] 3. Providing appropriate mental support

[0044] server:

[0045] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, psychological counseling, etc. The selected mental support program is then proposed to the user.

[0046] Device:

[0047] The device will notify the user of suggested mental support and execute the program selected by the user. For example, if a user has a high stress level, "Meditation Guidance" will be suggested, and the device will play a meditation guidance video.

[0048] 4. Gather feedback and retrain

[0049] User:

[0050] After participating in the provided mental support program, the user provides feedback, such as, "After receiving the meditation guidance, I felt relaxed."

[0051] Device:

[0052] The terminal collects user feedback and sends it to the server.

[0053] server:

[0054] The server receives feedback data from users, updates and improves the AI ​​model based on that feedback, and reflects it in the next support proposal.

[0055] This system can provide continuous and effective mental health support to individuals undergoing litigation. As a specific example, if a user inputs "I'm feeling very stressed because of a recent trial," the server analyzes the data and determines that the stress level is high. A meditation guidance video is then delivered to the device, providing the user with guidance on how to relax. After the session, if the user provides feedback such as "Meditation helped me relax a little," this information will be reflected in the next support suggestion.

[0056] In this way, optimal mental support can be provided according to the individual circumstances of each user, thereby reducing the psychological burden during litigation.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user logs into a mental health support app on a device such as a smartphone or tablet, and inputs their emotional state and stress level by text or voice.

[0060] Step 2:

[0061] The device collects user input data (text or voice) and transmits the data to the server in real time.

[0062] Step 3:

[0063] The server receives the data sent from the device and passes it to the AI ​​model for analysis.

[0064] Step 4:

[0065] The server's AI model analyzes the data, using natural language processing (NLP) to interpret the text or voice data and determine the user's emotions and stress levels.

[0066] Step 5:

[0067] The server selects appropriate mental support based on the analysis results. For example, if the stress level is determined to be high, it will suggest meditation guidance.

[0068] Step 6:

[0069] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[0070] Step 7:

[0071] The device receives the notification sent from the server and displays and executes the mental support program (e.g., meditation guidance) suggested to the user. The user then starts the suggested program.

[0072] Step 8:

[0073] After the user completes the mental support program, they provide feedback, such as, "I was able to relax a little after meditating."

[0074] Step 9:

[0075] The device collects user feedback and sends the data to the server.

[0076] Step 10:

[0077] The server receives the feedback data and passes it to the AI ​​model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[0078] Example 1

[0079] 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."

[0080] Conventional mental health support systems often fail to adequately manage stress or provide appropriate mental support to individuals during litigation. Furthermore, they lack the ability to accurately provide feedback on the effectiveness of the support provided and to retrain the system. This makes it difficult to provide personalized support. Furthermore, in many cases, analysis of emotions and stress levels using natural language processing technology is not performed, making it difficult to provide optimal support tailored to the user's situation.

[0081] 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.

[0082] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for collecting user feedback on the provided mental support and retraining the system based on the feedback, means for analyzing the user's emotions and stress levels using natural language processing technology, means for determining the user's emotions and stress levels based on the analysis prompts using the generated artificial intelligence model, means for providing meditation guidance, relaxation exercises, and psychological counseling suggestions based on the analysis results, and means for retraining the artificial intelligence model based on the user's feedback data to improve the next support suggestion. This makes it possible to provide personalized mental support in real time and reduce the psychological burden during litigation.

[0083] "User input" refers to data including personal information, emotional state, and stress level reported by users using devices such as smartphones and tablets.

[0084] A "means for collecting" is a device or process that has the function of transmitting text or voice data entered by a user from a terminal to a server, and receiving and storing this data.

[0085] The "means for analyzing emotions and stress levels" is a system that uses natural language processing technology and emotion analysis algorithms to identify and quantify the emotional state and stress level from data entered by the user.

[0086] The "means for providing appropriate mental support" is a system that selects and provides support programs such as meditation guidance, relaxation exercises, and psychological counseling to users based on the analysis of their emotions and stress levels.

[0087] The "means for collecting feedback" refers to a device or process that collects data on the user's impressions and effects after using the mental support program and transmits this data to the server.

[0088] "Means for retraining the system" refers to the process of using collected user feedback data to update and refine the algorithm of the generative AI model and improve the next mental support proposal.

[0089] "Natural language processing technology" is a technology that allows a computer to understand and analyze text data entered by a user, and is used to identify emotions and stress levels.

[0090] A "generative AI model" is a type of machine learning, an artificial intelligence system trained to predict and determine a user's emotional state and stress level based on specific prompts.

[0091] An "analysis prompt" is an input sentence given to the generative AI model, which is used to analyze emotions and stress levels.

[0092] "Meditation Guidance" is a program that provides users with instructions and procedures for meditating to reduce stress.

[0093] "Relaxation exercises" are programs that provide a series of exercises and activities designed to help users relax.

[0094] "Psychological counseling" is the process by which a user receives professional advice and support for stress and emotional issues during litigation.

[0095] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[0096] Collecting User Input

[0097] User:

[0098] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data is collected.

[0099] Device:

[0100] The device collects text and voice data from users and transmits it to the server in real time. The technology used in this process employs encrypted communication protocols to ensure data security.

[0101] Emotion and stress level analysis

[0102] server:

[0103] The server receives text and voice data sent from the device. It then analyzes the data using AI models, natural language processing (NLP) techniques, and sentiment analysis algorithms. Specifically, it uses Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's stress level is quantified.

[0104] Generative AI models:

[0105] The generative AI model determines the user's emotional state and stress level based on analytical prompts, such as "Please assess the user's stress level from this text data: 'The trial is difficult and stressful.'"

[0106] Providing appropriate mental support

[0107] server:

[0108] Based on the analysis results, the server selects the appropriate mental support program for the user. Specifically, if the stress level is determined to be high, meditation guidance, relaxation exercises, and psychological counseling are provided. The selection is made using a rule-based engine and machine learning models.

[0109] Device:

[0110] The device receives the information sent from the server and notifies the user. If the user selects a suggested mental support program, the device executes the program. Specifically, it plays a meditation guidance video.

[0111] User:

[0112] After receiving the notification, users can select and implement the suggested mental support program, which involves watching guided meditation videos and performing relaxation exercises to reduce stress.

[0113] Gathering feedback and relearning

[0114] User:

[0115] After participating in the provided mental support program, users provide feedback on its effectiveness, such as "Thanks to the meditation guidance, I was able to relax a little."

[0116] Device:

[0117] The terminal collects feedback data from the user and transmits it to the server.

[0118] server:

[0119] The server stores the received feedback data in a database and retrains the generative AI model to improve the next mental support suggestion. This retraining process uses training data based on actual usage data.

[0120] Specifically, when a user types "I've been feeling very stressed lately because of a lawsuit" into the app, the device sends that data to the server. The server analyzes the data and determines that the user is under "high stress." Based on that result, a meditation guidance video is suggested to the user. After watching the video, the user provides feedback such as "I was able to relax a little," and the server uses this feedback to retrain the AI ​​model.

[0121] Example prompts to input to the generative AI model

[0122] "Analyze the user's emotions and stress level from the following text data: 'I am feeling very stressed about a recent court case.'"

[0123] "We use user feedback to retrain our AI model and improve the next support suggestion. Here's the feedback data: 'The meditation guidance helped me relax a bit.'"

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] Collecting User Input

[0127] input:

[0128] Text and voice data containing your personal information, emotional state, and stress levels.

[0129] Operation:

[0130] Users log in to the mental health support app using a device such as a smartphone or tablet. When they log in for the first time, they enter basic personal information such as their name, age, gender, and the type of lawsuit. After that, they periodically report their emotional state and stress level via text or voice. For example, by entering, "Preparing for trial is difficult and stressful," the data is collected.

[0131] output:

[0132] The collected text and voice data is stored on the device and sent to a server for the next step.

[0133] Step 2:

[0134] Data transmission and storage

[0135] input:

[0136] Text and voice data sent from your device.

[0137] Operation:

[0138] The terminal encrypts the user's input data in real time and sends it securely to the server. The server stores the received data in a database. During this process, transaction processing is performed to maintain data consistency.

[0139] output:

[0140] Securely stored text and audio data is stored in a database.

[0141] Step 3:

[0142] Emotion and stress level analysis

[0143] input:

[0144] User text and voice data stored in a database.

[0145] Operation:

[0146] The server analyzes the accumulated data using natural language processing (NLP) techniques, including libraries such as Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's emotional state and stress level are quantified.

[0147] output:

[0148] The analyzed emotional state and stress level are then numerically analyzed.

[0149] Step 4:

[0150] Selecting appropriate mental support

[0151] input:

[0152] Quantified emotional state and stress levels.

[0153] Operation:

[0154] Based on the analysis results, the server selects the appropriate mental support program to provide to the user. If high stress is determined, meditation guidance or relaxation exercises will be selected. This selection is made using a rule-based engine and machine learning models.

[0155] output:

[0156] Information about the selected mental support program is generated.

[0157] Step 5:

[0158] Providing mental support

[0159] input:

[0160] Information on selected mental support programs.

[0161] Operation:

[0162] The device receives the mental support information sent from the server and notifies the user. When the user selects a suggested program, the device executes the program, for example, playing a meditation guidance video.

[0163] output:

[0164] The mental support program received by the user is executed.

[0165] Step 6:

[0166] Collecting feedback

[0167] input:

[0168] Feedback data from users after implementing the mental support program.

[0169] Operation:

[0170] Users provide feedback on the effectiveness of the mental support program. For example, they can enter their impressions into the app, such as, "The meditation guidance helped me relax a little." The device collects this feedback and sends it to the server.

[0171] output:

[0172] The collected feedback data is sent to a server.

[0173] Step 7:

[0174] Re-learning and improving next suggestions

[0175] input:

[0176] User feedback data.

[0177] Operation:

[0178] The server retrains the generative AI model based on the received feedback data. During the retraining process, the collected feedback data is used as training data, improving the accuracy and suitability of the next mental support suggestion.

[0179] output:

[0180] Improved generative AI models will be reflected in the next proposal.

[0181] (Application example 1)

[0182] 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."

[0183] Conventional mental health support systems often lack the functionality to provide optimal support based on the user's emotional state. This has resulted in insufficient stress management for users and ineffective mental health care. In particular, there has been a lack of mental support provided through video content, making it difficult to provide real-time support that meets the user's specific needs. Therefore, there has been a need for a system that can suggest and deliver appropriate video content based on the user's emotional state to effectively support mental health.

[0184] 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.

[0185] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for delivering the provided mental support to the user as video content, thereby making it possible to provide optimal mental support according to the user's emotional state in the form of video content in real time.

[0186] "User input" refers to text or voice data provided by a user to the system.

[0187] "Analyzing emotions and stress levels" refers to using natural language processing and emotion analysis algorithms to identify and assess a user's emotional and stress state based on user input.

[0188] "Mental support" refers to specific programs and content to support users' mental health, including meditation guidance, relaxation exercises, and psychological counseling.

[0189] "Delivering as video content" refers to providing mental support selected based on the analysis results in video format to the user's device.

[0190] "Gathering feedback" refers to systematically collecting opinions and impressions provided by users after receiving mental support.

[0191] "Retraining" refers to the process of updating and improving a system's algorithms and models based on collected user feedback.

[0192] An "emotion label" is a classification label that indicates the user's emotional state, and includes categories such as "high stress" and "relaxed," for example.

[0193] "Proposing in real time" means instantly reflecting the analysis results and quickly presenting and providing mental support that is tailored to the user's current situation.

[0194] MODE FOR CARRYING OUT THE INVENTION

[0195] This invention is a system that includes an analysis of emotions and stress levels based on user input, provision of appropriate mental support, and a re-learning process for the system based on user feedback. How to specifically implement this system will be described below.

[0196] First, users access the mental health support app using a device such as a smartphone or tablet. They periodically input their current emotional state and stress level via text or voice. This user input is sent to the server in real time using a Python or Java program.

[0197] The server then receives the submitted user input and utilizes software such as TensorFlow and Scikit-learn to analyze the data using natural language processing (NLP) techniques and sentiment analysis algorithms. Specifically, it vectorizes the text data using TfidfVectorizer and predicts the user's sentiment label using a trained sentiment analysis model. For example, if a user enters "I've been feeling very stressed lately. I'm worried about the trial," the system will determine that the text represents a high-stress state.

[0198] Based on the analysis results, the server selects appropriate mental support for the user. Specific mental support options include meditation guidance, relaxation exercises, and psychological counseling. These options are then delivered to the user's device as video content. For example, a user who is judged to be highly stressed may be recommended a relaxation meditation video, which is then played on the device.

[0199] After watching the provided mental support video, the user enters feedback. This feedback is then sent from the device to the server and collected. The server uses this feedback information to retrain the system's AI model, so that the next mental support suggestions will better meet the user's individual needs. The retraining process involves updating the AI ​​model using Python and TensorFlow.

[0200] Using this system, optimal mental health support can be provided in real time according to the user's emotional state, effectively reducing the user's psychological burden.

[0201] As a concrete example, the following prompt sentence is input to the generative AI model:

[0202] "I'm very stressed about the recent court case. I watched a meditation video and it helped me relax a bit, but are there any others you'd recommend?"

[0203] Based on this prompt, the system will suggest mental health support tailored to the situation.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1:

[0206] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as name, age, gender, and type of lawsuit), and thereafter periodically report their emotional state and stress level via text or voice.

[0207] Input: User text or voice input

[0208] Output: Sending data from the device to the server

[0209] Step 2:

[0210] The device transmits the collected text and voice data to a server in real time.

[0211] Input: Text or audio data

[0212] Output: Data sent to the server

[0213] Step 3:

[0214] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the received data. Specifically, it vectorizes the text data using TfidfVectorizer and predicts sentiment labels using a pre-trained sentiment analysis model (powered by TensorFlow).

[0215] Input: Text or audio data

[0216] Output: Emotion label and stress level judgment result

[0217] Step 4:

[0218] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, and psychological counseling.

[0219] Input: Emotion label and stress level judgment result

[0220] Output: Selection of appropriate mental support

[0221] Step 5:

[0222] The server distributes the selected mental support as video content and notifies the user's device, where the user can watch the video content.

[0223] Input: Results of selection of appropriate mental support

[0224] Output: Video content delivered to the user's device

[0225] Step 6:

[0226] After watching the mental support video, users can enter their feedback, such as "The meditation video was helpful. It would be great if the quality was a little better."

[0227] Input: User feedback

[0228] Output: Sends feedback data from the device to the server

[0229] Step 7:

[0230] The terminal transmits the user's feedback to the server.

[0231] Input: Feedback data

[0232] Output: Feedback data sent to the server

[0233] Step 8:

[0234] The server retrains the system's AI model based on the received feedback data, allowing the next mental support suggestions to better suit individual needs. This retraining is done using software such as TensorFlow.

[0235] Input: Feedback data

[0236] Output: Updated and improved AI model

[0237] 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.

[0238] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals in litigation. The system combines an emotion engine with a mechanism for collecting user input, analyzing emotions and stress levels, providing appropriate mental support, and relearning based on user feedback on the support provided. The emotion engine recognizes emotions based on the user's text and voice input and is used to provide more accurate mental support.

[0239] 1. Collecting User Input

[0240] User:

[0241] Users log in to a mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and then periodically report their current emotional state and stress level via text or voice. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," this data is collected.

[0242] Device:

[0243] The terminal collects text or voice data from the user and transmits it to the server in real time.

[0244] 2. Emotion and stress level analysis

[0245] server:

[0246] The server receives text and voice data sent from the device and passes it to the emotion engine. The emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data and recognize the user's emotions. For example, it identifies keywords such as "stress" and "feel" and determines that the user is feeling emotions such as "sad" or "anxious." Based on the results of this analysis, the AI ​​model determines the user's stress level.

[0247] 3. Providing appropriate mental support

[0248] server:

[0249] Based on the analysis results, the server selects the most appropriate mental support for the user. For example, if the emotion engine recognizes that the user is feeling "anxiety," it may determine that providing relaxation exercises or meditation guidance is appropriate. This selected mental support program is then proposed to the user.

[0250] Device:

[0251] The device notifies the user of the suggestions sent from the server and executes the program selected by the user. Specifically, for a user with a high stress level, "Meditation Guidance" is suggested, and the device displays a meditation guidance video.

[0252] 4. Gather feedback and retrain

[0253] User:

[0254] After completing the provided mental support program, users provide feedback through the app, such as, "After receiving the meditation guidance, I felt relaxed."

[0255] Device:

[0256] The terminal collects user feedback and sends it to the server.

[0257] server:

[0258] The server receives feedback data from users and retrains the AI ​​model based on that feedback, allowing this information to be reflected in the next mental support suggestions, making it possible to provide even more effective support.

[0259] This system provides optimal mental support tailored to each user's individual situation, reducing the psychological burden during litigation. As a specific example, if a user inputs "I'm feeling very stressed about a recent trial" and the server recognizes this emotion as "anxiety," appropriate relaxation exercises will be suggested. After the user completes this exercise, they can provide feedback, which will be reflected in future support suggestions. In this way, the system continuously provides mental support optimized for each individual user in real time.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] The user logs into a mental health support app on a device such as a smartphone or tablet. After logging in, the user enters their current emotional state and stress level by text or voice.

[0263] Step 2:

[0264] The device collects user input data (text or voice) and transmits the data to the server in real time.

[0265] Step 3:

[0266] The server receives the data sent from the device and passes it to the emotion engine.

[0267] Step 4:

[0268] The server's emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data, for example, identifying keywords such as "stress" and "feeling" to determine the user's emotional state (e.g., "anxious" or "sad").

[0269] Step 5:

[0270] The server determines the user's stress level based on the analysis results of the emotion engine. If the analysis results indicate that the user is "highly stressed," the AI ​​model considers appropriate countermeasures.

[0271] Step 6:

[0272] The server selects the most appropriate mental support (e.g., meditation guidance, relaxation exercises) based on the user's stress level and emotional state.

[0273] Step 7:

[0274] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[0275] Step 8:

[0276] The terminal receives the notification sent from the server and displays the suggested mental support program (e.g., meditation guidance) to the user. The user then starts the suggested program.

[0277] Step 9:

[0278] After the user completes the mental support program, they provide feedback, such as "I felt relaxed after meditating."

[0279] Step 10:

[0280] The device collects user feedback and sends the data to the server.

[0281] Step 11:

[0282] The server receives the feedback data and passes it to the emotion engine and AI model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[0283] This processing flow allows the system to support users' mental health in real time and continuously improve its effectiveness. For example, if a user inputs "I'm feeling very stressed because of a recent trial" and the server's emotion engine recognizes this as "anxiety," it will suggest relaxation exercises. If the user performs the exercise and provides feedback such as "I was able to relax," this will be reflected in the next suggestion.

[0284] Example 2

[0285] 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."

[0286] Mental health issues such as stress and anxiety experienced by individuals during litigation are serious, and a system that can effectively manage and support these issues is needed. Conventional mental health support systems struggle to accurately grasp users' emotions and stress levels and provide appropriate support based on those findings. Furthermore, it is difficult to fully utilize user feedback to improve and adapt the system. A new mental health support system is needed to address these challenges.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0288] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for collecting feedback from the user after implementing the provided mental support program and relearning the system. This makes it possible to accurately analyze the user's emotions and stress levels and provide appropriate mental support based on the analysis results. Furthermore, relearning the system based on user feedback enables more personalized and effective support.

[0289] "User input" is data provided by a user to a system, and is information collected in the form of text or voice.

[0290] "Means for analyzing emotions and stress levels" refers to a device or software that uses natural language processing techniques and emotion analysis algorithms to identify a user's emotions and stress levels based on user input.

[0291] The "means for providing mental support" is a device or software that proposes an appropriate mental support program to the user based on the analysis results and executes the program.

[0292] The "means for collecting feedback and retraining the system" refers to a device or software that has the function of collecting feedback provided by the user after implementing the provided mental support program and retraining the system's algorithms and models based on that data.

[0293] "Natural language processing technology" is a series of technologies that enable computers to understand, analyze, and generate human language, and is used for semantic analysis and sentiment analysis of text data.

[0294] An "emotion analysis algorithm" is a program that incorporates mathematical or statistical techniques to identify a user's emotional state from their text or voice.

[0295] A "mental support program" is a specific activity or exercise provided to support a user's mental health, such as relaxation exercises or meditation guidance.

[0296] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. Specific embodiments of this system are described in detail below.

[0297] Hardware and Software Configuration

[0298] The system mainly consists of a terminal for collecting user input, a server for analyzing and processing the input data, a server and terminal for providing appropriate mental support based on the analysis results, and a server and terminal for collecting feedback and relearning.

[0299] Device:

[0300] This refers to mobile information devices such as smartphones and tablets that users use to access mental health support apps and provide input data and feedback.

[0301] server:

[0302] This refers to a high-performance computer installed on a cloud server or a specific data center. The server receives and stores user input data, analyzes it using a natural language processing (NLP) engine and sentiment analysis algorithm, and retrains the AI ​​model based on the effectiveness of the mental support provided.

[0303] Data processing and data calculation

[0304] Collecting user input:

[0305] Users use a mental health support app to input personal information and their daily emotional state, for example, by text or voice input such as "I'm feeling very stressed about a recent court case."

[0306] Emotion and stress level analysis:

[0307] The user data sent from the device is received by the server and passed to the NLP engine. The NLP engine analyzes keywords and emotional patterns from the user's text and voice to determine their emotional state and stress level. For example, if the keyword "stress" appears frequently, it will be recognized that the user is at a high stress level.

[0308] Providing appropriate mental health support:

[0309] Based on the analysis results, the server selects an appropriate mental support program. This program is sent to the device and provided to the user. For example, a user who is feeling anxious might be offered relaxation exercises or meditation guidance.

[0310] Gathering feedback and relearning:

[0311] After the user completes the mental support program, they provide feedback. The device then sends this feedback to the server, which then uses it to retrain the AI ​​model, making future suggestions even more accurate.

[0312] Examples of concrete examples and prompts

[0313] Examples:

[0314] A user uses the app and enters, "I'm feeling very stressed because of a recent trial. I'm having trouble falling asleep and concentrating." This data is sent to the server and analyzed by the NLP engine. The server determines that the user is in an "anxious" state and suggests relaxation exercises. The user performs the exercises and then provides feedback such as, "I felt relaxed after the relaxation exercises." Based on this feedback, the AI ​​model is retrained, and the next suggestions will be even more accurate.

[0315] Example prompt sentence:

[0316] User Input: "I'm feeling very stressed about the recent court case. I'm having trouble sleeping and concentrating."

[0317] Prompt: Identify the specific emotion the user is feeling from this text and report it along with the intensity of that emotion.

[0318] This prompt enables the generative AI model to perform highly accurate emotion recognition and generate data to provide appropriate mental support.

[0319] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0320] Step 1: Collecting User Input

[0321] User:

[0322] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter their personal information, and then report their daily emotional state and stress level via text or voice. For example, they might enter, "I'm feeling very stressed because of a recent court case." This input data is sent to the app on their device.

[0323] input:

[0324] The user inputs their emotional state and stress level in text or voice format.

[0325] output:

[0326] User input data stored on the device.

[0327] Device:

[0328] The device receives the user's text and voice data and sends it to the server in real time. An app on the device then cleans up the data appropriately and converts it into a format that can be sent.

[0329] input:

[0330] Text or voice data entered by the user into the device.

[0331] output:

[0332] User input data sent to the server.

[0333] Step 2: Analyze your emotions and stress levels

[0334] server:

[0335] The server receives user data sent from the device, first stores the received data in storage, and then passes it to the natural language processing engine for processing.

[0336] input:

[0337] User input data sent from the terminal.

[0338] output:

[0339] User input data to be passed to the natural language processing engine.

[0340] server:

[0341] The natural language processing engine analyzes the user's text and voice data to identify emotions and stress levels. For example, it detects keywords such as "stress" and "feel" and determines that the user is feeling stressed. The analysis results are output as an emotional state (e.g., anxiety, sadness) and its intensity.

[0342] input:

[0343] User input data stored in storage.

[0344] output:

[0345] Analysis results identifying emotional state and stress levels.

[0346] Step 3: Providing appropriate mental health support

[0347] server:

[0348] The server selects appropriate mental support programs based on the analysis of emotions and stress levels. For example, if the user is feeling "anxious," it may determine that relaxation exercises or meditation guidance are appropriate. The server then creates links and content for these programs and sends them to the device.

[0349] input:

[0350] Emotion and stress level analysis results.

[0351] output:

[0352] A mental support program sent to your device.

[0353] Device:

[0354] The device notifies the user of the mental support program suggestions sent from the server. The suggestions are displayed in a pop-up notification or in the notification bar. When the user selects a program, the device executes the selected program, for example, playing a meditation guidance video.

[0355] input:

[0356] Mental support program suggestions sent from the server.

[0357] output:

[0358] Suggestions to be notified to the user; mental support programs to be implemented (e.g., video playback).

[0359] Step 4: Gather feedback and retrain

[0360] User:

[0361] After participating in the provided mental support program, users provide feedback about their experience, for example, by entering something like, "I felt relaxed after receiving the meditation guidance."

[0362] input:

[0363] Feedback after implementing a mental support program.

[0364] output:

[0365] Feedback data entered into the app.

[0366] Device:

[0367] The terminal collects user feedback data and transmits it to the server in real time, where data cleansing and format conversion are performed.

[0368] input:

[0369] Feedback data entered by users into the app.

[0370] output:

[0371] Feedback data sent to the server.

[0372] server:

[0373] The server passes the feedback data received from the user to the AI ​​model, which then re-learns based on that data. This updates the system's algorithms and models, improving the accuracy of the next mental support suggestion.

[0374] input:

[0375] Feedback data sent from the device.

[0376] output:

[0377] Updated data for retrained AI models.

[0378] (Application example 2)

[0379] 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."

[0380] In autonomous vehicles, there is no need to drive, so it is necessary to effectively reduce the stress and anxiety felt by passengers while riding in them and provide a comfortable riding experience. However, there are currently no systems that can analyze passengers' emotions and stress levels in real time and provide appropriate mental support. Furthermore, there is a lack of a feedback function to evaluate whether the mental support provided is actually effective and to continuously improve the system. Therefore, the objective of this invention is to develop a mental health support system for autonomous vehicles that reduces stress and anxiety while riding in them and provides a comfortable riding environment.

[0381] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0382] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for displaying and notifying the user of suggested mental support programs, and means for collecting feedback on mental support and retraining the system based on that feedback. This allows the server to analyze the user's emotions and stress levels in real time and provide appropriate mental support during the ride, enabling a comfortable riding experience. Furthermore, by retraining the system based on the feedback, the quality of the mental support provided is continuously improved.

[0383] "User input" refers to data provided by a user to a system, including data in text or voice format.

[0384] "Emotions and stress levels" are indicators that indicate the user's psychological state, where emotions refer to emotional states such as joy, sadness, and anxiety, and stress levels indicate the intensity and degree of those states.

[0385] "Means for analyzing emotions and stress levels" includes any technical elements or algorithms used to analyze and assess a user's emotional state and stress level based on user input.

[0386] "Mental support" refers to activities and programs designed to support users' mental and psychological health, including relaxation exercises and meditation guidance.

[0387] "Means for displaying and notifying the user of the proposed mental support program" includes technical elements that allow the server to visually or audibly present to the user the mental support program selected based on the analysis results.

[0388] "Feedback" refers to the act of a user reporting to the system their own experiences and opinions regarding the mental support provided.

[0389] "Retraining" refers to the process of improving the system's algorithms and models based on collected feedback to provide more accurate mental support.

[0390] "Server" refers to a computing device or network service that receives user input, analyzes it, and provides appropriate mental support.

[0391] This invention is constructed as a system that carries out a series of processes with the cooperation of a server, a terminal, and a user in order to realize mental health support during a ride.

[0392] Program Generation and Processing

[0393] The server plays a central role in collecting and analyzing user input and providing appropriate mental support. The terminal acts as an interface with the user, sending the collected data to the server and presenting feedback and support programs from the server to the user. The specific hardware and software used are as follows:

[0394] Hardware and software used

[0395] Hardware: Smartphones, tablets, and autonomous vehicle infotainment systems

[0396] Software: Python, speech_recognition, TextBlob, tensorflow, Google Speech Recognition API

[0397] Natural language processing explanation

[0398] 1. Collecting User Input

[0399] Users log into a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level in voice or text format, for example, "I'm feeling tired after a long drive."

[0400] 2. Emotion and stress level analysis

[0401] The device sends the collected user voice data to the server in real time. The server converts the data into text using speech_recognition and then performs sentiment analysis using TextBlob. The analysis results are classified as positive, negative, or neutral.

[0402] 3. Providing appropriate mental support

[0403] The server selects an appropriate mental support program based on the analysis results. For example, if the emotion is determined to be "negative," it will suggest relaxation exercises. The server then transmits the selected support program to the device, which then displays it to the user.

[0404] 4. Gather feedback and retrain

[0405] After completing the provided mental support program, the user provides feedback such as their impressions via the terminal. For example, they might say, "I felt relaxed after performing the relaxation exercises."

[0406] The device sends this feedback data to the server, which then retrains the AI ​​model based on the feedback. This retraining process allows the support program to be further optimized for the user from the next time onwards.

[0407] Specific examples and examples of prompts for generative AI models

[0408] Examples:

[0409] If a user says during a long drive, "No matter how many times I've been on this road, it's still scary. I'm worried an accident might happen," the system will analyze the user's words and determine that they are feeling anxious. It will then suggest a guidance video to support relaxation exercises and show it on the display.

[0410] Example prompt for a generative AI model:

[0411] User says: "I'm getting tired after a long drive."

[0412] AI response: "I'm going to show you some relaxation techniques. Try some deep breathing."

[0413] In this way, the present invention provides support tailored to the user's individual emotional state and stress level, enabling a comfortable and safe riding experience in an autonomous vehicle.

[0414] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0415] Step 1:

[0416] Users log in to a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level by voice or text. Input can be specific voice or sentences such as "I'm feeling tired after a long drive."

[0417] (Input) User's vocal or textual emotional report

[0418] (Output) Audio or text data

[0419] Step 2:

[0420] The device collects voice data from the user and converts the voice to text using the speech_recognition library. It takes voice data as input, analyzes it, and outputs it as text data.

[0421] (Input) Audio data

[0422] (Output) Text data

[0423] Step 3:

[0424] The server receives the text data sent from the device and performs sentiment analysis using TextBlob. The analysis detects the emotional state (positive, negative, neutral) and evaluates the stress level. For example, if a positive emotion is detected, the stress level is determined to be low.

[0425] (Input) Text data

[0426] (Output) Evaluation results of emotional state and stress level

[0427] Step 4:

[0428] The server selects an appropriate mental support program based on the analysis results. For example, if the user's emotions are determined to be "negative," it selects relaxation exercises. To select the program, it references various support programs stored in a program database in advance.

[0429] (Input) Evaluation results of emotional state and stress level

[0430] (Output) Selected mental support programs

[0431] Step 5:

[0432] The server transmits the selected mental support program to the terminal, which receives it and presents it to the user visually or audibly, for example, by showing a relaxation exercise guidance video on the display.

[0433] (Input) Selected mental support programs

[0434] (Output) Transfer of support programs to the terminal

[0435] Step 6:

[0436] The user performs the provided mental support program and provides feedback based on the experience, for example, by reporting their impression via text or voice, such as "After performing the relaxation exercises, I felt relaxed."

[0437] (Input) User feedback (voice or text)

[0438] (Output) Feedback Data

[0439] Step 7:

[0440] The device sends user feedback data to the server, which then retrains the AI ​​model based on the feedback data. Specifically, the server analyzes user feedback and updates the model to reflect this information in the selection of support programs from the next time onward.

[0441] (Input) Feedback data

[0442] (Output) Updated AI model

[0443] 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.

[0444] 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.

[0445] 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.

[0446] [Second embodiment]

[0447] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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).

[0453] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0458] 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."

[0459] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[0460] 1. Collecting User Input

[0461] User:

[0462] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data will be collected.

[0463] Device:

[0464] The device collects text and voice data from the user and transmits it to the server in real time.

[0465] 2. Emotion and stress level analysis

[0466] server:

[0467] The server receives text and voice data from the device. The AI ​​model then analyzes the data using natural language processing (NLP) techniques and sentiment analysis algorithms. For example, it can identify keywords such as "stress" and "feel" and determine that the user's stress level is high.

[0468] 3. Providing appropriate mental support

[0469] server:

[0470] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, psychological counseling, etc. The selected mental support program is then proposed to the user.

[0471] Device:

[0472] The device will notify the user of suggested mental support and execute the program selected by the user. For example, if a user has a high stress level, "Meditation Guidance" will be suggested, and the device will play a meditation guidance video.

[0473] 4. Gather feedback and retrain

[0474] User:

[0475] After participating in the provided mental support program, the user provides feedback, such as, "After receiving the meditation guidance, I felt relaxed."

[0476] Device:

[0477] The terminal collects user feedback and sends it to the server.

[0478] server:

[0479] The server receives feedback data from users, updates and improves the AI ​​model based on that feedback, and reflects it in the next support proposal.

[0480] This system can provide continuous and effective mental health support to individuals undergoing litigation. As a specific example, if a user inputs "I'm feeling very stressed because of a recent trial," the server analyzes the data and determines that the stress level is high. A meditation guidance video is then delivered to the device, providing the user with guidance on how to relax. After the session, if the user provides feedback such as "Meditation helped me relax a little," this information will be reflected in the next support suggestion.

[0481] In this way, optimal mental support can be provided according to the individual circumstances of each user, thereby reducing the psychological burden during litigation.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] The user logs into a mental health support app on a device such as a smartphone or tablet, and inputs their emotional state and stress level by text or voice.

[0485] Step 2:

[0486] The device collects user input data (text or voice) and transmits the data to the server in real time.

[0487] Step 3:

[0488] The server receives the data sent from the device and passes it to the AI ​​model for analysis.

[0489] Step 4:

[0490] The server's AI model analyzes the data, using natural language processing (NLP) to interpret the text or voice data and determine the user's emotions and stress levels.

[0491] Step 5:

[0492] The server selects appropriate mental support based on the analysis results. For example, if the stress level is determined to be high, it will suggest meditation guidance.

[0493] Step 6:

[0494] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[0495] Step 7:

[0496] The device receives the notification sent from the server and displays and executes the mental support program (e.g., meditation guidance) suggested to the user. The user then starts the suggested program.

[0497] Step 8:

[0498] After the user completes the mental support program, they provide feedback, such as, "I was able to relax a little after meditating."

[0499] Step 9:

[0500] The device collects user feedback and sends the data to the server.

[0501] Step 10:

[0502] The server receives the feedback data and passes it to the AI ​​model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[0503] Example 1

[0504] 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."

[0505] Conventional mental health support systems often fail to adequately manage stress or provide appropriate mental support to individuals during litigation. Furthermore, they lack the ability to accurately provide feedback on the effectiveness of the support provided and to retrain the system. This makes it difficult to provide personalized support. Furthermore, in many cases, analysis of emotions and stress levels using natural language processing technology is not performed, making it difficult to provide optimal support tailored to the user's situation.

[0506] 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.

[0507] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for collecting user feedback on the provided mental support and retraining the system based on the feedback, means for analyzing the user's emotions and stress levels using natural language processing technology, means for determining the user's emotions and stress levels based on the analysis prompts using the generated artificial intelligence model, means for providing meditation guidance, relaxation exercises, and psychological counseling suggestions based on the analysis results, and means for retraining the artificial intelligence model based on the user's feedback data to improve the next support suggestion. This makes it possible to provide personalized mental support in real time and reduce the psychological burden during litigation.

[0508] "User input" refers to data including personal information, emotional state, and stress level reported by users using devices such as smartphones and tablets.

[0509] A "means for collecting" is a device or process that has the function of transmitting text or voice data entered by a user from a terminal to a server, and receiving and storing this data.

[0510] The "means for analyzing emotions and stress levels" is a system that uses natural language processing technology and emotion analysis algorithms to identify and quantify the emotional state and stress level from data entered by the user.

[0511] The "means for providing appropriate mental support" is a system that selects and provides support programs such as meditation guidance, relaxation exercises, and psychological counseling to users based on the analysis of their emotions and stress levels.

[0512] The "means for collecting feedback" refers to a device or process that collects data on the user's impressions and effects after using the mental support program and transmits this data to the server.

[0513] "Means for retraining the system" refers to the process of using collected user feedback data to update and refine the algorithm of the generative AI model and improve the next mental support proposal.

[0514] "Natural language processing technology" is a technology that allows a computer to understand and analyze text data entered by a user, and is used to identify emotions and stress levels.

[0515] A "generative AI model" is a type of machine learning, an artificial intelligence system trained to predict and determine a user's emotional state and stress level based on specific prompts.

[0516] An "analysis prompt" is an input sentence given to the generative AI model, which is used to analyze emotions and stress levels.

[0517] "Meditation Guidance" is a program that provides users with instructions and procedures for meditating to reduce stress.

[0518] "Relaxation exercises" are programs that provide a series of exercises and activities designed to help users relax.

[0519] "Psychological counseling" is the process by which a user receives professional advice and support for stress and emotional issues during litigation.

[0520] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[0521] Collecting User Input

[0522] User:

[0523] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data is collected.

[0524] Device:

[0525] The device collects text and voice data from users and transmits it to the server in real time. The technology used in this process employs encrypted communication protocols to ensure data security.

[0526] Emotion and stress level analysis

[0527] server:

[0528] The server receives text and voice data sent from the device. It then analyzes the data using AI models, natural language processing (NLP) techniques, and sentiment analysis algorithms. Specifically, it uses Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's stress level is quantified.

[0529] Generative AI models:

[0530] The generative AI model determines the user's emotional state and stress level based on analytical prompts, such as "Please assess the user's stress level from this text data: 'The trial is difficult and stressful.'"

[0531] Providing appropriate mental support

[0532] server:

[0533] Based on the analysis results, the server selects the appropriate mental support program for the user. Specifically, if the stress level is determined to be high, meditation guidance, relaxation exercises, and psychological counseling are provided. The selection is made using a rule-based engine and machine learning models.

[0534] Device:

[0535] The device receives the information sent from the server and notifies the user. If the user selects a suggested mental support program, the device executes the program. Specifically, it plays a meditation guidance video.

[0536] User:

[0537] After receiving the notification, users can select and implement the suggested mental support program, which involves watching guided meditation videos and performing relaxation exercises to reduce stress.

[0538] Gathering feedback and relearning

[0539] User:

[0540] After participating in the provided mental support program, users provide feedback on its effectiveness, such as "Thanks to the meditation guidance, I was able to relax a little."

[0541] Device:

[0542] The terminal collects feedback data from the user and transmits it to the server.

[0543] server:

[0544] The server stores the received feedback data in a database and retrains the generative AI model to improve the next mental support suggestion. This retraining process uses training data based on actual usage data.

[0545] Specifically, when a user types "I've been feeling very stressed lately because of a lawsuit" into the app, the device sends that data to the server. The server analyzes the data and determines that the user is under "high stress." Based on that result, a meditation guidance video is suggested to the user. After watching the video, the user provides feedback such as "I was able to relax a little," and the server uses this feedback to retrain the AI ​​model.

[0546] Example prompts to input to the generative AI model

[0547] "Analyze the user's emotions and stress level from the following text data: 'I am feeling very stressed about a recent court case.'"

[0548] "We use user feedback to retrain our AI model and improve the next support suggestion. Here's the feedback data: 'The meditation guidance helped me relax a bit.'"

[0549] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0550] Step 1:

[0551] Collecting User Input

[0552] input:

[0553] Text and voice data containing your personal information, emotional state, and stress levels.

[0554] Operation:

[0555] Users log in to the mental health support app using a device such as a smartphone or tablet. When they log in for the first time, they enter basic personal information such as their name, age, gender, and the type of lawsuit. After that, they periodically report their emotional state and stress level via text or voice. For example, by entering, "Preparing for trial is difficult and stressful," the data is collected.

[0556] output:

[0557] The collected text and voice data is stored on the device and sent to a server for the next step.

[0558] Step 2:

[0559] Data transmission and storage

[0560] input:

[0561] Text and voice data sent from your device.

[0562] Operation:

[0563] The terminal encrypts the user's input data in real time and sends it securely to the server. The server stores the received data in a database. During this process, transaction processing is performed to maintain data consistency.

[0564] output:

[0565] Securely stored text and audio data is stored in a database.

[0566] Step 3:

[0567] Emotion and stress level analysis

[0568] input:

[0569] User text and voice data stored in a database.

[0570] Operation:

[0571] The server analyzes the accumulated data using natural language processing (NLP) techniques, including libraries such as Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's emotional state and stress level are quantified.

[0572] output:

[0573] The analyzed emotional state and stress level are then numerically analyzed.

[0574] Step 4:

[0575] Selecting appropriate mental support

[0576] input:

[0577] Quantified emotional state and stress levels.

[0578] Operation:

[0579] Based on the analysis results, the server selects the appropriate mental support program to provide to the user. If high stress is determined, meditation guidance or relaxation exercises will be selected. This selection is made using a rule-based engine and machine learning models.

[0580] output:

[0581] Information about the selected mental support program is generated.

[0582] Step 5:

[0583] Providing mental support

[0584] input:

[0585] Information on selected mental support programs.

[0586] Operation:

[0587] The device receives the mental support information sent from the server and notifies the user. When the user selects a suggested program, the device executes the program, for example, playing a meditation guidance video.

[0588] output:

[0589] The mental support program received by the user is executed.

[0590] Step 6:

[0591] Collecting feedback

[0592] input:

[0593] Feedback data from users after implementing the mental support program.

[0594] Operation:

[0595] Users provide feedback on the effectiveness of the mental support program. For example, they can enter their impressions into the app, such as, "The meditation guidance helped me relax a little." The device collects this feedback and sends it to the server.

[0596] output:

[0597] The collected feedback data is sent to a server.

[0598] Step 7:

[0599] Re-learning and improving next suggestions

[0600] input:

[0601] User feedback data.

[0602] Operation:

[0603] The server retrains the generative AI model based on the received feedback data. During the retraining process, the collected feedback data is used as training data, improving the accuracy and suitability of the next mental support suggestion.

[0604] output:

[0605] Improved generative AI models will be reflected in the next proposal.

[0606] (Application example 1)

[0607] 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."

[0608] Conventional mental health support systems often lack the functionality to provide optimal support based on the user's emotional state. This has resulted in insufficient stress management for users and ineffective mental health care. In particular, there has been a lack of mental support provided through video content, making it difficult to provide real-time support that meets the user's specific needs. Therefore, there has been a need for a system that can suggest and deliver appropriate video content based on the user's emotional state to effectively support mental health.

[0609] 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.

[0610] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for delivering the provided mental support to the user as video content, thereby making it possible to provide optimal mental support according to the user's emotional state in the form of video content in real time.

[0611] "User input" refers to text or voice data provided by a user to the system.

[0612] "Analyzing emotions and stress levels" refers to using natural language processing and emotion analysis algorithms to identify and assess a user's emotional and stress state based on user input.

[0613] "Mental support" refers to specific programs and content to support users' mental health, including meditation guidance, relaxation exercises, and psychological counseling.

[0614] "Delivering as video content" refers to providing mental support selected based on the analysis results in video format to the user's device.

[0615] "Gathering feedback" refers to systematically collecting opinions and impressions provided by users after receiving mental support.

[0616] "Retraining" refers to the process of updating and improving a system's algorithms and models based on collected user feedback.

[0617] An "emotion label" is a classification label that indicates the user's emotional state, and includes categories such as "high stress" and "relaxed," for example.

[0618] "Proposing in real time" means instantly reflecting the analysis results and quickly presenting and providing mental support that is tailored to the user's current situation.

[0619] MODE FOR CARRYING OUT THE INVENTION

[0620] This invention is a system that includes an analysis of emotions and stress levels based on user input, provision of appropriate mental support, and a re-learning process for the system based on user feedback. How to specifically implement this system will be described below.

[0621] First, users access the mental health support app using a device such as a smartphone or tablet. They periodically input their current emotional state and stress level via text or voice. This user input is sent to the server in real time using a Python or Java program.

[0622] The server then receives the submitted user input and utilizes software such as TensorFlow and Scikit-learn to analyze the data using natural language processing (NLP) techniques and sentiment analysis algorithms. Specifically, it vectorizes the text data using TfidfVectorizer and predicts the user's sentiment label using a trained sentiment analysis model. For example, if a user enters "I've been feeling very stressed lately. I'm worried about the trial," the system will determine that the text represents a high-stress state.

[0623] Based on the analysis results, the server selects appropriate mental support for the user. Specific mental support options include meditation guidance, relaxation exercises, and psychological counseling. These options are then delivered to the user's device as video content. For example, a user who is judged to be highly stressed may be recommended a relaxation meditation video, which is then played on the device.

[0624] After watching the provided mental support video, the user enters feedback. This feedback is then sent from the device to the server and collected. The server uses this feedback information to retrain the system's AI model, so that the next mental support suggestions will better meet the user's individual needs. The retraining process involves updating the AI ​​model using Python and TensorFlow.

[0625] Using this system, optimal mental health support can be provided in real time according to the user's emotional state, effectively reducing the user's psychological burden.

[0626] As a concrete example, the following prompt sentence is input to the generative AI model:

[0627] "I'm very stressed about the recent court case. I watched a meditation video and it helped me relax a bit, but are there any others you'd recommend?"

[0628] Based on this prompt, the system will suggest mental health support tailored to the situation.

[0629] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0630] Step 1:

[0631] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as name, age, gender, and type of lawsuit), and thereafter periodically report their emotional state and stress level via text or voice.

[0632] Input: User text or voice input

[0633] Output: Sending data from the device to the server

[0634] Step 2:

[0635] The device transmits the collected text and voice data to a server in real time.

[0636] Input: Text or audio data

[0637] Output: Data sent to the server

[0638] Step 3:

[0639] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the received data. Specifically, it vectorizes the text data using TfidfVectorizer and predicts sentiment labels using a pre-trained sentiment analysis model (powered by TensorFlow).

[0640] Input: Text or audio data

[0641] Output: Emotion label and stress level judgment result

[0642] Step 4:

[0643] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, and psychological counseling.

[0644] Input: Emotion label and stress level judgment result

[0645] Output: Selection of appropriate mental support

[0646] Step 5:

[0647] The server distributes the selected mental support as video content and notifies the user's device, where the user can watch the video content.

[0648] Input: Results of selection of appropriate mental support

[0649] Output: Video content delivered to the user's device

[0650] Step 6:

[0651] After watching the mental support video, users can enter their feedback, such as "The meditation video was helpful. It would be great if the quality was a little better."

[0652] Input: User feedback

[0653] Output: Sends feedback data from the device to the server

[0654] Step 7:

[0655] The terminal transmits the user's feedback to the server.

[0656] Input: Feedback data

[0657] Output: Feedback data sent to the server

[0658] Step 8:

[0659] The server retrains the system's AI model based on the received feedback data, allowing the next mental support suggestions to better suit individual needs. This retraining is done using software such as TensorFlow.

[0660] Input: Feedback data

[0661] Output: Updated and improved AI model

[0662] 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.

[0663] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals in litigation. The system combines an emotion engine with a mechanism for collecting user input, analyzing emotions and stress levels, providing appropriate mental support, and relearning based on user feedback on the support provided. The emotion engine recognizes emotions based on the user's text and voice input and is used to provide more accurate mental support.

[0664] 1. Collecting User Input

[0665] User:

[0666] Users log in to a mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and then periodically report their current emotional state and stress level via text or voice. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," this data is collected.

[0667] Device:

[0668] The terminal collects text or voice data from the user and transmits it to the server in real time.

[0669] 2. Emotion and stress level analysis

[0670] server:

[0671] The server receives text and voice data sent from the device and passes it to the emotion engine. The emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data and recognize the user's emotions. For example, it identifies keywords such as "stress" and "feel" and determines that the user is feeling emotions such as "sad" or "anxious." Based on the results of this analysis, the AI ​​model determines the user's stress level.

[0672] 3. Providing appropriate mental support

[0673] server:

[0674] Based on the analysis results, the server selects the most appropriate mental support for the user. For example, if the emotion engine recognizes that the user is feeling "anxiety," it may determine that providing relaxation exercises or meditation guidance is appropriate. This selected mental support program is then proposed to the user.

[0675] Device:

[0676] The device notifies the user of the suggestions sent from the server and executes the program selected by the user. Specifically, for a user with a high stress level, "Meditation Guidance" is suggested, and the device displays a meditation guidance video.

[0677] 4. Gather feedback and retrain

[0678] User:

[0679] After completing the provided mental support program, users provide feedback through the app, such as, "After receiving the meditation guidance, I felt relaxed."

[0680] Device:

[0681] The terminal collects user feedback and sends it to the server.

[0682] server:

[0683] The server receives feedback data from users and retrains the AI ​​model based on that feedback, allowing this information to be reflected in the next mental support suggestions, making it possible to provide even more effective support.

[0684] This system provides optimal mental support tailored to each user's individual situation, reducing the psychological burden during litigation. As a specific example, if a user inputs "I'm feeling very stressed about a recent trial" and the server recognizes this emotion as "anxiety," appropriate relaxation exercises will be suggested. After the user completes this exercise, they can provide feedback, which will be reflected in future support suggestions. In this way, the system continuously provides mental support optimized for each individual user in real time.

[0685] The processing flow will be explained below.

[0686] Step 1:

[0687] The user logs into a mental health support app on a device such as a smartphone or tablet. After logging in, the user enters their current emotional state and stress level by text or voice.

[0688] Step 2:

[0689] The device collects user input data (text or voice) and transmits the data to the server in real time.

[0690] Step 3:

[0691] The server receives the data sent from the device and passes it to the emotion engine.

[0692] Step 4:

[0693] The server's emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data, for example, identifying keywords such as "stress" and "feeling" to determine the user's emotional state (e.g., "anxious" or "sad").

[0694] Step 5:

[0695] The server determines the user's stress level based on the analysis results of the emotion engine. If the analysis results indicate that the user is "highly stressed," the AI ​​model considers appropriate countermeasures.

[0696] Step 6:

[0697] The server selects the most appropriate mental support (e.g., meditation guidance, relaxation exercises) based on the user's stress level and emotional state.

[0698] Step 7:

[0699] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[0700] Step 8:

[0701] The terminal receives the notification sent from the server and displays the suggested mental support program (e.g., meditation guidance) to the user. The user then starts the suggested program.

[0702] Step 9:

[0703] After the user completes the mental support program, they provide feedback, such as "I felt relaxed after meditating."

[0704] Step 10:

[0705] The device collects user feedback and sends the data to the server.

[0706] Step 11:

[0707] The server receives the feedback data and passes it to the emotion engine and AI model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[0708] This processing flow allows the system to support users' mental health in real time and continuously improve its effectiveness. For example, if a user inputs "I'm feeling very stressed because of a recent trial" and the server's emotion engine recognizes this as "anxiety," it will suggest relaxation exercises. If the user performs the exercise and provides feedback such as "I was able to relax," this will be reflected in the next suggestion.

[0709] Example 2

[0710] 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."

[0711] Mental health issues such as stress and anxiety experienced by individuals during litigation are serious, and a system that can effectively manage and support these issues is needed. Conventional mental health support systems struggle to accurately grasp users' emotions and stress levels and provide appropriate support based on those findings. Furthermore, it is difficult to fully utilize user feedback to improve and adapt the system. A new mental health support system is needed to address these challenges.

[0712] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0713] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for collecting feedback from the user after implementing the provided mental support program and relearning the system. This makes it possible to accurately analyze the user's emotions and stress levels and provide appropriate mental support based on the analysis results. Furthermore, relearning the system based on user feedback enables more personalized and effective support.

[0714] "User input" is data provided by a user to a system, and is information collected in the form of text or voice.

[0715] "Means for analyzing emotions and stress levels" refers to a device or software that uses natural language processing techniques and emotion analysis algorithms to identify a user's emotions and stress levels based on user input.

[0716] The "means for providing mental support" is a device or software that proposes an appropriate mental support program to the user based on the analysis results and executes the program.

[0717] The "means for collecting feedback and retraining the system" refers to a device or software that has the function of collecting feedback provided by the user after implementing the provided mental support program and retraining the system's algorithms and models based on that data.

[0718] "Natural language processing technology" is a series of technologies that enable computers to understand, analyze, and generate human language, and is used for semantic analysis and sentiment analysis of text data.

[0719] An "emotion analysis algorithm" is a program that incorporates mathematical or statistical techniques to identify a user's emotional state from their text or voice.

[0720] A "mental support program" is a specific activity or exercise provided to support a user's mental health, such as relaxation exercises or meditation guidance.

[0721] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. Specific embodiments of this system are described in detail below.

[0722] Hardware and Software Configuration

[0723] The system mainly consists of a terminal for collecting user input, a server for analyzing and processing the input data, a server and terminal for providing appropriate mental support based on the analysis results, and a server and terminal for collecting feedback and relearning.

[0724] Device:

[0725] This refers to mobile information devices such as smartphones and tablets that users use to access mental health support apps and provide input data and feedback.

[0726] server:

[0727] This refers to a high-performance computer installed on a cloud server or a specific data center. The server receives and stores user input data, analyzes it using a natural language processing (NLP) engine and sentiment analysis algorithm, and retrains the AI ​​model based on the effectiveness of the mental support provided.

[0728] Data processing and data calculation

[0729] Collecting user input:

[0730] Users use a mental health support app to input personal information and their daily emotional state, for example, by text or voice input such as "I'm feeling very stressed about a recent court case."

[0731] Emotion and stress level analysis:

[0732] The user data sent from the device is received by the server and passed to the NLP engine. The NLP engine analyzes keywords and emotional patterns from the user's text and voice to determine their emotional state and stress level. For example, if the keyword "stress" appears frequently, it will be recognized that the user is at a high stress level.

[0733] Providing appropriate mental health support:

[0734] Based on the analysis results, the server selects an appropriate mental support program. This program is sent to the device and provided to the user. For example, a user who is feeling anxious might be offered relaxation exercises or meditation guidance.

[0735] Gathering feedback and relearning:

[0736] After the user completes the mental support program, they provide feedback. The device then sends this feedback to the server, which then uses it to retrain the AI ​​model, making future suggestions even more accurate.

[0737] Examples of concrete examples and prompts

[0738] Examples:

[0739] A user uses the app and enters, "I'm feeling very stressed because of a recent trial. I'm having trouble falling asleep and concentrating." This data is sent to the server and analyzed by the NLP engine. The server determines that the user is in an "anxious" state and suggests relaxation exercises. The user performs the exercises and then provides feedback such as, "I felt relaxed after the relaxation exercises." Based on this feedback, the AI ​​model is retrained, and the next suggestions will be even more accurate.

[0740] Example prompt sentence:

[0741] User Input: "I'm feeling very stressed about the recent court case. I'm having trouble sleeping and concentrating."

[0742] Prompt: Identify the specific emotion the user is feeling from this text and report it along with the intensity of that emotion.

[0743] This prompt enables the generative AI model to perform highly accurate emotion recognition and generate data to provide appropriate mental support.

[0744] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0745] Step 1: Collecting User Input

[0746] User:

[0747] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter their personal information, and then report their daily emotional state and stress level via text or voice. For example, they might enter, "I'm feeling very stressed because of a recent court case." This input data is sent to the app on their device.

[0748] input:

[0749] The user inputs their emotional state and stress level in text or voice format.

[0750] output:

[0751] User input data stored on the device.

[0752] Device:

[0753] The device receives the user's text and voice data and sends it to the server in real time. An app on the device then cleans up the data appropriately and converts it into a format that can be sent.

[0754] input:

[0755] Text or voice data entered by the user into the device.

[0756] output:

[0757] User input data sent to the server.

[0758] Step 2: Analyze your emotions and stress levels

[0759] server:

[0760] The server receives user data sent from the device, first stores the received data in storage, and then passes it to the natural language processing engine for processing.

[0761] input:

[0762] User input data sent from the terminal.

[0763] output:

[0764] User input data to be passed to the natural language processing engine.

[0765] server:

[0766] The natural language processing engine analyzes the user's text and voice data to identify emotions and stress levels. For example, it detects keywords such as "stress" and "feel" and determines that the user is feeling stressed. The analysis results are output as an emotional state (e.g., anxiety, sadness) and its intensity.

[0767] input:

[0768] User input data stored in storage.

[0769] output:

[0770] Analysis results identifying emotional state and stress levels.

[0771] Step 3: Providing appropriate mental health support

[0772] server:

[0773] The server selects appropriate mental support programs based on the analysis of emotions and stress levels. For example, if the user is feeling "anxious," it may determine that relaxation exercises or meditation guidance are appropriate. The server then creates links and content for these programs and sends them to the device.

[0774] input:

[0775] Emotion and stress level analysis results.

[0776] output:

[0777] A mental support program sent to your device.

[0778] Device:

[0779] The device notifies the user of the mental support program suggestions sent from the server. The suggestions are displayed in a pop-up notification or in the notification bar. When the user selects a program, the device executes the selected program, for example, playing a meditation guidance video.

[0780] input:

[0781] Mental support program suggestions sent from the server.

[0782] output:

[0783] Suggestions to be notified to the user; mental support programs to be implemented (e.g., video playback).

[0784] Step 4: Gather feedback and retrain

[0785] User:

[0786] After participating in the provided mental support program, users provide feedback about their experience, for example, by entering something like, "I felt relaxed after receiving the meditation guidance."

[0787] input:

[0788] Feedback after implementing a mental support program.

[0789] output:

[0790] Feedback data entered into the app.

[0791] Device:

[0792] The terminal collects user feedback data and transmits it to the server in real time, where data cleansing and format conversion are performed.

[0793] input:

[0794] Feedback data entered by users into the app.

[0795] output:

[0796] Feedback data sent to the server.

[0797] server:

[0798] The server passes the feedback data received from the user to the AI ​​model, which then re-learns based on that data. This updates the system's algorithms and models, improving the accuracy of the next mental support suggestion.

[0799] input:

[0800] Feedback data sent from the device.

[0801] output:

[0802] Updated data for retrained AI models.

[0803] (Application example 2)

[0804] 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."

[0805] In autonomous vehicles, there is no need to drive, so it is necessary to effectively reduce the stress and anxiety felt by passengers while riding in them and provide a comfortable riding experience. However, there are currently no systems that can analyze passengers' emotions and stress levels in real time and provide appropriate mental support. Furthermore, there is a lack of a feedback function to evaluate whether the mental support provided is actually effective and to continuously improve the system. Therefore, the objective of this invention is to develop a mental health support system for autonomous vehicles that reduces stress and anxiety while riding in them and provides a comfortable riding environment.

[0806] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0807] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for displaying and notifying the user of suggested mental support programs, and means for collecting feedback on mental support and retraining the system based on that feedback. This allows the server to analyze the user's emotions and stress levels in real time and provide appropriate mental support during the ride, enabling a comfortable riding experience. Furthermore, by retraining the system based on the feedback, the quality of the mental support provided is continuously improved.

[0808] "User input" refers to data provided by a user to a system, including data in text or voice format.

[0809] "Emotions and stress levels" are indicators that indicate the user's psychological state, where emotions refer to emotional states such as joy, sadness, and anxiety, and stress levels indicate the intensity and degree of those states.

[0810] "Means for analyzing emotions and stress levels" includes any technical elements or algorithms used to analyze and assess a user's emotional state and stress level based on user input.

[0811] "Mental support" refers to activities and programs designed to support users' mental and psychological health, including relaxation exercises and meditation guidance.

[0812] "Means for displaying and notifying the user of the proposed mental support program" includes technical elements that allow the server to visually or audibly present to the user the mental support program selected based on the analysis results.

[0813] "Feedback" refers to the act of a user reporting to the system their own experiences and opinions regarding the mental support provided.

[0814] "Retraining" refers to the process of improving the system's algorithms and models based on collected feedback to provide more accurate mental support.

[0815] "Server" refers to a computing device or network service that receives user input, analyzes it, and provides appropriate mental support.

[0816] This invention is constructed as a system that carries out a series of processes with the cooperation of a server, a terminal, and a user in order to realize mental health support during a ride.

[0817] Program Generation and Processing

[0818] The server plays a central role in collecting and analyzing user input and providing appropriate mental support. The terminal acts as an interface with the user, sending the collected data to the server and presenting feedback and support programs from the server to the user. The specific hardware and software used are as follows:

[0819] Hardware and software used

[0820] Hardware: Smartphones, tablets, and autonomous vehicle infotainment systems

[0821] Software: Python, speech_recognition, TextBlob, tensorflow, Google Speech Recognition API

[0822] Natural language processing explanation

[0823] 1. Collecting User Input

[0824] Users log into a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level in voice or text format, for example, "I'm feeling tired after a long drive."

[0825] 2. Emotion and stress level analysis

[0826] The device sends the collected user voice data to the server in real time. The server converts the data into text using speech_recognition and then performs sentiment analysis using TextBlob. The analysis results are classified as positive, negative, or neutral.

[0827] 3. Providing appropriate mental support

[0828] The server selects an appropriate mental support program based on the analysis results. For example, if the emotion is determined to be "negative," it will suggest relaxation exercises. The server then transmits the selected support program to the device, which then displays it to the user.

[0829] 4. Gather feedback and retrain

[0830] After completing the provided mental support program, the user provides feedback such as their impressions via the terminal. For example, they might say, "I felt relaxed after performing the relaxation exercises."

[0831] The device sends this feedback data to the server, which then retrains the AI ​​model based on the feedback. This retraining process allows the support program to be further optimized for the user from the next time onwards.

[0832] Specific examples and examples of prompts for generative AI models

[0833] Examples:

[0834] If a user says during a long drive, "No matter how many times I've been on this road, it's still scary. I'm worried an accident might happen," the system will analyze the user's words and determine that they are feeling anxious. It will then suggest a guidance video to support relaxation exercises and show it on the display.

[0835] Example prompt for a generative AI model:

[0836] User says: "I'm getting tired after a long drive."

[0837] AI response: "I'm going to show you some relaxation techniques. Try some deep breathing."

[0838] In this way, the present invention provides support tailored to the user's individual emotional state and stress level, enabling a comfortable and safe riding experience in an autonomous vehicle.

[0839] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0840] Step 1:

[0841] Users log in to a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level by voice or text. Input can be specific voice or sentences such as "I'm feeling tired after a long drive."

[0842] (Input) User's vocal or textual emotional report

[0843] (Output) Audio or text data

[0844] Step 2:

[0845] The device collects voice data from the user and converts the voice to text using the speech_recognition library. It takes voice data as input, analyzes it, and outputs it as text data.

[0846] (Input) Audio data

[0847] (Output) Text data

[0848] Step 3:

[0849] The server receives the text data sent from the device and performs sentiment analysis using TextBlob. The analysis detects the emotional state (positive, negative, neutral) and evaluates the stress level. For example, if a positive emotion is detected, the stress level is determined to be low.

[0850] (Input) Text data

[0851] (Output) Evaluation results of emotional state and stress level

[0852] Step 4:

[0853] The server selects an appropriate mental support program based on the analysis results. For example, if the user's emotions are determined to be "negative," it selects relaxation exercises. To select the program, it references various support programs stored in a program database in advance.

[0854] (Input) Evaluation results of emotional state and stress level

[0855] (Output) Selected mental support programs

[0856] Step 5:

[0857] The server transmits the selected mental support program to the terminal, which receives it and presents it to the user visually or audibly, for example, by showing a relaxation exercise guidance video on the display.

[0858] (Input) Selected mental support programs

[0859] (Output) Transfer of support programs to the terminal

[0860] Step 6:

[0861] The user performs the provided mental support program and provides feedback based on the experience, for example, by reporting their impression via text or voice, such as "After performing the relaxation exercises, I felt relaxed."

[0862] (Input) User feedback (voice or text)

[0863] (Output) Feedback Data

[0864] Step 7:

[0865] The device sends user feedback data to the server, which then retrains the AI ​​model based on the feedback data. Specifically, the server analyzes user feedback and updates the model to reflect this information in the selection of support programs from the next time onward.

[0866] (Input) Feedback data

[0867] (Output) Updated AI model

[0868] 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.

[0869] 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.

[0870] 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.

[0871] [Third embodiment]

[0872] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0873] 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.

[0874] 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).

[0875] 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.

[0876] 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.

[0877] 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).

[0878] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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."

[0884] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[0885] 1. Collecting User Input

[0886] User:

[0887] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data will be collected.

[0888] Device:

[0889] The device collects text and voice data from the user and transmits it to the server in real time.

[0890] 2. Emotion and stress level analysis

[0891] server:

[0892] The server receives text and voice data from the device. The AI ​​model then analyzes the data using natural language processing (NLP) techniques and sentiment analysis algorithms. For example, it can identify keywords such as "stress" and "feel" and determine that the user's stress level is high.

[0893] 3. Providing appropriate mental support

[0894] server:

[0895] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, psychological counseling, etc. The selected mental support program is then proposed to the user.

[0896] Device:

[0897] The device will notify the user of suggested mental support and execute the program selected by the user. For example, if a user has a high stress level, "Meditation Guidance" will be suggested, and the device will play a meditation guidance video.

[0898] 4. Gather feedback and retrain

[0899] User:

[0900] After participating in the provided mental support program, the user provides feedback, such as, "After receiving the meditation guidance, I felt relaxed."

[0901] Device:

[0902] The terminal collects user feedback and sends it to the server.

[0903] server:

[0904] The server receives feedback data from users, updates and improves the AI ​​model based on that feedback, and reflects it in the next support proposal.

[0905] This system can provide continuous and effective mental health support to individuals undergoing litigation. As a specific example, if a user inputs "I'm feeling very stressed because of a recent trial," the server analyzes the data and determines that the stress level is high. A meditation guidance video is then delivered to the device, providing the user with guidance on how to relax. After the session, if the user provides feedback such as "Meditation helped me relax a little," this information will be reflected in the next support suggestion.

[0906] In this way, optimal mental support can be provided according to the individual circumstances of each user, thereby reducing the psychological burden during litigation.

[0907] The processing flow will be explained below.

[0908] Step 1:

[0909] The user logs into a mental health support app on a device such as a smartphone or tablet, and inputs their emotional state and stress level by text or voice.

[0910] Step 2:

[0911] The device collects user input data (text or voice) and transmits the data to the server in real time.

[0912] Step 3:

[0913] The server receives the data sent from the device and passes it to the AI ​​model for analysis.

[0914] Step 4:

[0915] The server's AI model analyzes the data, using natural language processing (NLP) to interpret the text or voice data and determine the user's emotions and stress levels.

[0916] Step 5:

[0917] The server selects appropriate mental support based on the analysis results. For example, if the stress level is determined to be high, it will suggest meditation guidance.

[0918] Step 6:

[0919] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[0920] Step 7:

[0921] The device receives the notification sent from the server and displays and executes the mental support program (e.g., meditation guidance) suggested to the user. The user then starts the suggested program.

[0922] Step 8:

[0923] After the user completes the mental support program, they provide feedback, such as, "I was able to relax a little after meditating."

[0924] Step 9:

[0925] The device collects user feedback and sends the data to the server.

[0926] Step 10:

[0927] The server receives the feedback data and passes it to the AI ​​model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[0928] Example 1

[0929] 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."

[0930] Conventional mental health support systems often fail to adequately manage stress or provide appropriate mental support to individuals during litigation. Furthermore, they lack the ability to accurately provide feedback on the effectiveness of the support provided and to retrain the system. This makes it difficult to provide personalized support. Furthermore, in many cases, analysis of emotions and stress levels using natural language processing technology is not performed, making it difficult to provide optimal support tailored to the user's situation.

[0931] 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.

[0932] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for collecting user feedback on the provided mental support and retraining the system based on the feedback, means for analyzing the user's emotions and stress levels using natural language processing technology, means for determining the user's emotions and stress levels based on the analysis prompts using the generated artificial intelligence model, means for providing meditation guidance, relaxation exercises, and psychological counseling suggestions based on the analysis results, and means for retraining the artificial intelligence model based on the user's feedback data to improve the next support suggestion. This makes it possible to provide personalized mental support in real time and reduce the psychological burden during litigation.

[0933] "User input" refers to data including personal information, emotional state, and stress level reported by users using devices such as smartphones and tablets.

[0934] A "means for collecting" is a device or process that has the function of transmitting text or voice data entered by a user from a terminal to a server, and receiving and storing this data.

[0935] The "means for analyzing emotions and stress levels" is a system that uses natural language processing technology and emotion analysis algorithms to identify and quantify the emotional state and stress level from data entered by the user.

[0936] The "means for providing appropriate mental support" is a system that selects and provides support programs such as meditation guidance, relaxation exercises, and psychological counseling to users based on the analysis of their emotions and stress levels.

[0937] The "means for collecting feedback" refers to a device or process that collects data on the user's impressions and effects after using the mental support program and transmits this data to the server.

[0938] "Means for retraining the system" refers to the process of using collected user feedback data to update and refine the algorithm of the generative AI model and improve the next mental support proposal.

[0939] "Natural language processing technology" is a technology that allows a computer to understand and analyze text data entered by a user, and is used to identify emotions and stress levels.

[0940] A "generative AI model" is a type of machine learning, an artificial intelligence system trained to predict and determine a user's emotional state and stress level based on specific prompts.

[0941] An "analysis prompt" is an input sentence given to the generative AI model, which is used to analyze emotions and stress levels.

[0942] "Meditation Guidance" is a program that provides users with instructions and procedures for meditating to reduce stress.

[0943] "Relaxation exercises" are programs that provide a series of exercises and activities designed to help users relax.

[0944] "Psychological counseling" is the process by which a user receives professional advice and support for stress and emotional issues during litigation.

[0945] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[0946] Collecting User Input

[0947] User:

[0948] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data is collected.

[0949] Device:

[0950] The device collects text and voice data from users and transmits it to the server in real time. The technology used in this process employs encrypted communication protocols to ensure data security.

[0951] Emotion and stress level analysis

[0952] server:

[0953] The server receives text and voice data sent from the device. It then analyzes the data using AI models, natural language processing (NLP) techniques, and sentiment analysis algorithms. Specifically, it uses Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's stress level is quantified.

[0954] Generative AI models:

[0955] The generative AI model determines the user's emotional state and stress level based on analytical prompts, such as "Please assess the user's stress level from this text data: 'The trial is difficult and stressful.'"

[0956] Providing appropriate mental support

[0957] server:

[0958] Based on the analysis results, the server selects the appropriate mental support program for the user. Specifically, if the stress level is determined to be high, meditation guidance, relaxation exercises, and psychological counseling are provided. The selection is made using a rule-based engine and machine learning models.

[0959] Device:

[0960] The device receives the information sent from the server and notifies the user. If the user selects a suggested mental support program, the device executes the program. Specifically, it plays a meditation guidance video.

[0961] User:

[0962] After receiving the notification, users can select and implement the suggested mental support program, which involves watching guided meditation videos and performing relaxation exercises to reduce stress.

[0963] Gathering feedback and relearning

[0964] User:

[0965] After participating in the provided mental support program, users provide feedback on its effectiveness, such as "Thanks to the meditation guidance, I was able to relax a little."

[0966] Device:

[0967] The terminal collects feedback data from the user and transmits it to the server.

[0968] server:

[0969] The server stores the received feedback data in a database and retrains the generative AI model to improve the next mental support suggestion. This retraining process uses training data based on actual usage data.

[0970] Specifically, when a user types "I've been feeling very stressed lately because of a lawsuit" into the app, the device sends that data to the server. The server analyzes the data and determines that the user is under "high stress." Based on that result, a meditation guidance video is suggested to the user. After watching the video, the user provides feedback such as "I was able to relax a little," and the server uses this feedback to retrain the AI ​​model.

[0971] Example prompts to input to the generative AI model

[0972] "Analyze the user's emotions and stress level from the following text data: 'I am feeling very stressed about a recent court case.'"

[0973] "We use user feedback to retrain our AI model and improve the next support suggestion. Here's the feedback data: 'The meditation guidance helped me relax a bit.'"

[0974] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0975] Step 1:

[0976] Collecting User Input

[0977] input:

[0978] Text and voice data containing your personal information, emotional state, and stress levels.

[0979] Operation:

[0980] Users log in to the mental health support app using a device such as a smartphone or tablet. When they log in for the first time, they enter basic personal information such as their name, age, gender, and the type of lawsuit. After that, they periodically report their emotional state and stress level via text or voice. For example, by entering, "Preparing for trial is difficult and stressful," the data is collected.

[0981] output:

[0982] The collected text and voice data is stored on the device and sent to a server for the next step.

[0983] Step 2:

[0984] Data transmission and storage

[0985] input:

[0986] Text and voice data sent from your device.

[0987] Operation:

[0988] The terminal encrypts the user's input data in real time and sends it securely to the server. The server stores the received data in a database. During this process, transaction processing is performed to maintain data consistency.

[0989] output:

[0990] Securely stored text and audio data is stored in a database.

[0991] Step 3:

[0992] Emotion and stress level analysis

[0993] input:

[0994] User text and voice data stored in a database.

[0995] Operation:

[0996] The server analyzes the accumulated data using natural language processing (NLP) techniques, including libraries such as Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's emotional state and stress level are quantified.

[0997] output:

[0998] The analyzed emotional state and stress level are then numerically analyzed.

[0999] Step 4:

[1000] Selecting appropriate mental support

[1001] input:

[1002] Quantified emotional state and stress levels.

[1003] Operation:

[1004] Based on the analysis results, the server selects the appropriate mental support program to provide to the user. If high stress is determined, meditation guidance or relaxation exercises will be selected. This selection is made using a rule-based engine and machine learning models.

[1005] output:

[1006] Information about the selected mental support program is generated.

[1007] Step 5:

[1008] Providing mental support

[1009] input:

[1010] Information on selected mental support programs.

[1011] Operation:

[1012] The device receives the mental support information sent from the server and notifies the user. When the user selects a suggested program, the device executes the program, for example, playing a meditation guidance video.

[1013] output:

[1014] The mental support program received by the user is executed.

[1015] Step 6:

[1016] Collecting feedback

[1017] input:

[1018] Feedback data from users after implementing the mental support program.

[1019] Operation:

[1020] Users provide feedback on the effectiveness of the mental support program. For example, they can enter their impressions into the app, such as, "The meditation guidance helped me relax a little." The device collects this feedback and sends it to the server.

[1021] output:

[1022] The collected feedback data is sent to a server.

[1023] Step 7:

[1024] Re-learning and improving next suggestions

[1025] input:

[1026] User feedback data.

[1027] Operation:

[1028] The server retrains the generative AI model based on the received feedback data. During the retraining process, the collected feedback data is used as training data, improving the accuracy and suitability of the next mental support suggestion.

[1029] output:

[1030] Improved generative AI models will be reflected in the next proposal.

[1031] (Application example 1)

[1032] 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."

[1033] Conventional mental health support systems often lack the functionality to provide optimal support based on the user's emotional state. This has resulted in insufficient stress management for users and ineffective mental health care. In particular, there has been a lack of mental support provided through video content, making it difficult to provide real-time support that meets the user's specific needs. Therefore, there has been a need for a system that can suggest and deliver appropriate video content based on the user's emotional state to effectively support mental health.

[1034] 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.

[1035] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for delivering the provided mental support to the user as video content, thereby making it possible to provide optimal mental support according to the user's emotional state in the form of video content in real time.

[1036] "User input" refers to text or voice data provided by a user to the system.

[1037] "Analyzing emotions and stress levels" refers to using natural language processing and emotion analysis algorithms to identify and assess a user's emotional and stress state based on user input.

[1038] "Mental support" refers to specific programs and content to support users' mental health, including meditation guidance, relaxation exercises, and psychological counseling.

[1039] "Delivering as video content" refers to providing mental support selected based on the analysis results in video format to the user's device.

[1040] "Gathering feedback" refers to systematically collecting opinions and impressions provided by users after receiving mental support.

[1041] "Retraining" refers to the process of updating and improving a system's algorithms and models based on collected user feedback.

[1042] An "emotion label" is a classification label that indicates the user's emotional state, and includes categories such as "high stress" and "relaxed," for example.

[1043] "Proposing in real time" means instantly reflecting the analysis results and quickly presenting and providing mental support that is tailored to the user's current situation.

[1044] MODE FOR CARRYING OUT THE INVENTION

[1045] This invention is a system that includes an analysis of emotions and stress levels based on user input, provision of appropriate mental support, and a re-learning process for the system based on user feedback. How to specifically implement this system will be described below.

[1046] First, users access the mental health support app using a device such as a smartphone or tablet. They periodically input their current emotional state and stress level via text or voice. This user input is sent to the server in real time using a Python or Java program.

[1047] The server then receives the submitted user input and utilizes software such as TensorFlow and Scikit-learn to analyze the data using natural language processing (NLP) techniques and sentiment analysis algorithms. Specifically, it vectorizes the text data using TfidfVectorizer and predicts the user's sentiment label using a trained sentiment analysis model. For example, if a user enters "I've been feeling very stressed lately. I'm worried about the trial," the system will determine that the text represents a high-stress state.

[1048] Based on the analysis results, the server selects appropriate mental support for the user. Specific mental support options include meditation guidance, relaxation exercises, and psychological counseling. These options are then delivered to the user's device as video content. For example, a user who is judged to be highly stressed may be recommended a relaxation meditation video, which is then played on the device.

[1049] After watching the provided mental support video, the user enters feedback. This feedback is then sent from the device to the server and collected. The server uses this feedback information to retrain the system's AI model, so that the next mental support suggestions will better meet the user's individual needs. The retraining process involves updating the AI ​​model using Python and TensorFlow.

[1050] Using this system, optimal mental health support can be provided in real time according to the user's emotional state, effectively reducing the user's psychological burden.

[1051] As a concrete example, the following prompt sentence is input to the generative AI model:

[1052] "I'm very stressed about the recent court case. I watched a meditation video and it helped me relax a bit, but are there any others you'd recommend?"

[1053] Based on this prompt, the system will suggest mental health support tailored to the situation.

[1054] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1055] Step 1:

[1056] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as name, age, gender, and type of lawsuit), and thereafter periodically report their emotional state and stress level via text or voice.

[1057] Input: User text or voice input

[1058] Output: Sending data from the device to the server

[1059] Step 2:

[1060] The device transmits the collected text and voice data to a server in real time.

[1061] Input: Text or audio data

[1062] Output: Data sent to the server

[1063] Step 3:

[1064] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the received data. Specifically, it vectorizes the text data using TfidfVectorizer and predicts sentiment labels using a pre-trained sentiment analysis model (powered by TensorFlow).

[1065] Input: Text or audio data

[1066] Output: Emotion label and stress level judgment result

[1067] Step 4:

[1068] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, and psychological counseling.

[1069] Input: Emotion label and stress level judgment result

[1070] Output: Selection of appropriate mental support

[1071] Step 5:

[1072] The server distributes the selected mental support as video content and notifies the user's device, where the user can watch the video content.

[1073] Input: Results of selection of appropriate mental support

[1074] Output: Video content delivered to the user's device

[1075] Step 6:

[1076] After watching the mental support video, users can enter their feedback, such as "The meditation video was helpful. It would be great if the quality was a little better."

[1077] Input: User feedback

[1078] Output: Sends feedback data from the device to the server

[1079] Step 7:

[1080] The terminal transmits the user's feedback to the server.

[1081] Input: Feedback data

[1082] Output: Feedback data sent to the server

[1083] Step 8:

[1084] The server retrains the system's AI model based on the received feedback data, allowing the next mental support suggestions to better suit individual needs. This retraining is done using software such as TensorFlow.

[1085] Input: Feedback data

[1086] Output: Updated and improved AI model

[1087] 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.

[1088] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals in litigation. The system combines an emotion engine with a mechanism for collecting user input, analyzing emotions and stress levels, providing appropriate mental support, and relearning based on user feedback on the support provided. The emotion engine recognizes emotions based on the user's text and voice input and is used to provide more accurate mental support.

[1089] 1. Collecting User Input

[1090] User:

[1091] Users log in to a mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and then periodically report their current emotional state and stress level via text or voice. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," this data is collected.

[1092] Device:

[1093] The terminal collects text or voice data from the user and transmits it to the server in real time.

[1094] 2. Emotion and stress level analysis

[1095] server:

[1096] The server receives text and voice data sent from the device and passes it to the emotion engine. The emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data and recognize the user's emotions. For example, it identifies keywords such as "stress" and "feel" and determines that the user is feeling emotions such as "sad" or "anxious." Based on the results of this analysis, the AI ​​model determines the user's stress level.

[1097] 3. Providing appropriate mental support

[1098] server:

[1099] Based on the analysis results, the server selects the most appropriate mental support for the user. For example, if the emotion engine recognizes that the user is feeling "anxiety," it may determine that providing relaxation exercises or meditation guidance is appropriate. This selected mental support program is then proposed to the user.

[1100] Device:

[1101] The device notifies the user of the suggestions sent from the server and executes the program selected by the user. Specifically, for a user with a high stress level, "Meditation Guidance" is suggested, and the device displays a meditation guidance video.

[1102] 4. Gather feedback and retrain

[1103] User:

[1104] After completing the provided mental support program, users provide feedback through the app, such as, "After receiving the meditation guidance, I felt relaxed."

[1105] Device:

[1106] The terminal collects user feedback and sends it to the server.

[1107] server:

[1108] The server receives feedback data from users and retrains the AI ​​model based on that feedback, allowing this information to be reflected in the next mental support suggestions, making it possible to provide even more effective support.

[1109] This system provides optimal mental support tailored to each user's individual situation, reducing the psychological burden during litigation. As a specific example, if a user inputs "I'm feeling very stressed about a recent trial" and the server recognizes this emotion as "anxiety," appropriate relaxation exercises will be suggested. After the user completes this exercise, they can provide feedback, which will be reflected in future support suggestions. In this way, the system continuously provides mental support optimized for each individual user in real time.

[1110] The processing flow will be explained below.

[1111] Step 1:

[1112] The user logs into a mental health support app on a device such as a smartphone or tablet. After logging in, the user enters their current emotional state and stress level by text or voice.

[1113] Step 2:

[1114] The device collects user input data (text or voice) and transmits the data to the server in real time.

[1115] Step 3:

[1116] The server receives the data sent from the device and passes it to the emotion engine.

[1117] Step 4:

[1118] The server's emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data, for example, identifying keywords such as "stress" and "feeling" to determine the user's emotional state (e.g., "anxious" or "sad").

[1119] Step 5:

[1120] The server determines the user's stress level based on the analysis results of the emotion engine. If the analysis results indicate that the user is "highly stressed," the AI ​​model considers appropriate countermeasures.

[1121] Step 6:

[1122] The server selects the most appropriate mental support (e.g., meditation guidance, relaxation exercises) based on the user's stress level and emotional state.

[1123] Step 7:

[1124] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[1125] Step 8:

[1126] The terminal receives the notification sent from the server and displays the suggested mental support program (e.g., meditation guidance) to the user. The user then starts the suggested program.

[1127] Step 9:

[1128] After the user completes the mental support program, they provide feedback, such as "I felt relaxed after meditating."

[1129] Step 10:

[1130] The device collects user feedback and sends the data to the server.

[1131] Step 11:

[1132] The server receives the feedback data and passes it to the emotion engine and AI model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[1133] This processing flow allows the system to support users' mental health in real time and continuously improve its effectiveness. For example, if a user inputs "I'm feeling very stressed because of a recent trial" and the server's emotion engine recognizes this as "anxiety," it will suggest relaxation exercises. If the user performs the exercise and provides feedback such as "I was able to relax," this will be reflected in the next suggestion.

[1134] Example 2

[1135] 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."

[1136] Mental health issues such as stress and anxiety experienced by individuals during litigation are serious, and a system that can effectively manage and support these issues is needed. Conventional mental health support systems struggle to accurately grasp users' emotions and stress levels and provide appropriate support based on those findings. Furthermore, it is difficult to fully utilize user feedback to improve and adapt the system. A new mental health support system is needed to address these challenges.

[1137] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1138] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for collecting feedback from the user after implementing the provided mental support program and relearning the system. This makes it possible to accurately analyze the user's emotions and stress levels and provide appropriate mental support based on the analysis results. Furthermore, relearning the system based on user feedback enables more personalized and effective support.

[1139] "User input" is data provided by a user to a system, and is information collected in the form of text or voice.

[1140] "Means for analyzing emotions and stress levels" refers to a device or software that uses natural language processing techniques and emotion analysis algorithms to identify a user's emotions and stress levels based on user input.

[1141] The "means for providing mental support" is a device or software that proposes an appropriate mental support program to the user based on the analysis results and executes the program.

[1142] The "means for collecting feedback and retraining the system" refers to a device or software that has the function of collecting feedback provided by the user after implementing the provided mental support program and retraining the system's algorithms and models based on that data.

[1143] "Natural language processing technology" is a series of technologies that enable computers to understand, analyze, and generate human language, and is used for semantic analysis and sentiment analysis of text data.

[1144] An "emotion analysis algorithm" is a program that incorporates mathematical or statistical techniques to identify a user's emotional state from their text or voice.

[1145] A "mental support program" is a specific activity or exercise provided to support a user's mental health, such as relaxation exercises or meditation guidance.

[1146] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. Specific embodiments of this system are described in detail below.

[1147] Hardware and Software Configuration

[1148] The system mainly consists of a terminal for collecting user input, a server for analyzing and processing the input data, a server and terminal for providing appropriate mental support based on the analysis results, and a server and terminal for collecting feedback and relearning.

[1149] Device:

[1150] This refers to mobile information devices such as smartphones and tablets that users use to access mental health support apps and provide input data and feedback.

[1151] server:

[1152] This refers to a high-performance computer installed on a cloud server or a specific data center. The server receives and stores user input data, analyzes it using a natural language processing (NLP) engine and sentiment analysis algorithm, and retrains the AI ​​model based on the effectiveness of the mental support provided.

[1153] Data processing and data calculation

[1154] Collecting user input:

[1155] Users use a mental health support app to input personal information and their daily emotional state, for example, by text or voice input such as "I'm feeling very stressed about a recent court case."

[1156] Emotion and stress level analysis:

[1157] The user data sent from the device is received by the server and passed to the NLP engine. The NLP engine analyzes keywords and emotional patterns from the user's text and voice to determine their emotional state and stress level. For example, if the keyword "stress" appears frequently, it will be recognized that the user is at a high stress level.

[1158] Providing appropriate mental health support:

[1159] Based on the analysis results, the server selects an appropriate mental support program. This program is sent to the device and provided to the user. For example, a user who is feeling anxious might be offered relaxation exercises or meditation guidance.

[1160] Gathering feedback and relearning:

[1161] After the user completes the mental support program, they provide feedback. The device then sends this feedback to the server, which then uses it to retrain the AI ​​model, making future suggestions even more accurate.

[1162] Examples of concrete examples and prompts

[1163] Examples:

[1164] A user uses the app and enters, "I'm feeling very stressed because of a recent trial. I'm having trouble falling asleep and concentrating." This data is sent to the server and analyzed by the NLP engine. The server determines that the user is in an "anxious" state and suggests relaxation exercises. The user performs the exercises and then provides feedback such as, "I felt relaxed after the relaxation exercises." Based on this feedback, the AI ​​model is retrained, and the next suggestions will be even more accurate.

[1165] Example prompt sentence:

[1166] User Input: "I'm feeling very stressed about the recent court case. I'm having trouble sleeping and concentrating."

[1167] Prompt: Identify the specific emotion the user is feeling from this text and report it along with the intensity of that emotion.

[1168] This prompt enables the generative AI model to perform highly accurate emotion recognition and generate data to provide appropriate mental support.

[1169] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1170] Step 1: Collecting User Input

[1171] User:

[1172] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter their personal information, and then report their daily emotional state and stress level via text or voice. For example, they might enter, "I'm feeling very stressed because of a recent court case." This input data is sent to the app on their device.

[1173] input:

[1174] The user inputs their emotional state and stress level in text or voice format.

[1175] output:

[1176] User input data stored on the device.

[1177] Device:

[1178] The device receives the user's text and voice data and sends it to the server in real time. An app on the device then cleans up the data appropriately and converts it into a format that can be sent.

[1179] input:

[1180] Text or voice data entered by the user into the device.

[1181] output:

[1182] User input data sent to the server.

[1183] Step 2: Analyze your emotions and stress levels

[1184] server:

[1185] The server receives user data sent from the device, first stores the received data in storage, and then passes it to the natural language processing engine for processing.

[1186] input:

[1187] User input data sent from the terminal.

[1188] output:

[1189] User input data to be passed to the natural language processing engine.

[1190] server:

[1191] The natural language processing engine analyzes the user's text and voice data to identify emotions and stress levels. For example, it detects keywords such as "stress" and "feel" and determines that the user is feeling stressed. The analysis results are output as an emotional state (e.g., anxiety, sadness) and its intensity.

[1192] input:

[1193] User input data stored in storage.

[1194] output:

[1195] Analysis results identifying emotional state and stress levels.

[1196] Step 3: Providing appropriate mental health support

[1197] server:

[1198] The server selects appropriate mental support programs based on the analysis of emotions and stress levels. For example, if the user is feeling "anxious," it may determine that relaxation exercises or meditation guidance are appropriate. The server then creates links and content for these programs and sends them to the device.

[1199] input:

[1200] Emotion and stress level analysis results.

[1201] output:

[1202] A mental support program sent to your device.

[1203] Device:

[1204] The device notifies the user of the mental support program suggestions sent from the server. The suggestions are displayed in a pop-up notification or in the notification bar. When the user selects a program, the device executes the selected program, for example, playing a meditation guidance video.

[1205] input:

[1206] Mental support program suggestions sent from the server.

[1207] output:

[1208] Suggestions to be notified to the user; mental support programs to be implemented (e.g., video playback).

[1209] Step 4: Gather feedback and retrain

[1210] User:

[1211] After participating in the provided mental support program, users provide feedback about their experience, for example, by entering something like, "I felt relaxed after receiving the meditation guidance."

[1212] input:

[1213] Feedback after implementing a mental support program.

[1214] output:

[1215] Feedback data entered into the app.

[1216] Device:

[1217] The terminal collects user feedback data and transmits it to the server in real time, where data cleansing and format conversion are performed.

[1218] input:

[1219] Feedback data entered by users into the app.

[1220] output:

[1221] Feedback data sent to the server.

[1222] server:

[1223] The server passes the feedback data received from the user to the AI ​​model, which then re-learns based on that data. This updates the system's algorithms and models, improving the accuracy of the next mental support suggestion.

[1224] input:

[1225] Feedback data sent from the device.

[1226] output:

[1227] Updated data for retrained AI models.

[1228] (Application example 2)

[1229] 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."

[1230] In autonomous vehicles, there is no need to drive, so it is necessary to effectively reduce the stress and anxiety felt by passengers while riding in them and provide a comfortable riding experience. However, there are currently no systems that can analyze passengers' emotions and stress levels in real time and provide appropriate mental support. Furthermore, there is a lack of a feedback function to evaluate whether the mental support provided is actually effective and to continuously improve the system. Therefore, the objective of this invention is to develop a mental health support system for autonomous vehicles that reduces stress and anxiety while riding in them and provides a comfortable riding environment.

[1231] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1232] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for displaying and notifying the user of suggested mental support programs, and means for collecting feedback on mental support and retraining the system based on that feedback. This allows the server to analyze the user's emotions and stress levels in real time and provide appropriate mental support during the ride, enabling a comfortable riding experience. Furthermore, by retraining the system based on the feedback, the quality of the mental support provided is continuously improved.

[1233] "User input" refers to data provided by a user to a system, including data in text or voice format.

[1234] "Emotions and stress levels" are indicators that indicate the user's psychological state, where emotions refer to emotional states such as joy, sadness, and anxiety, and stress levels indicate the intensity and degree of those states.

[1235] "Means for analyzing emotions and stress levels" includes any technical elements or algorithms used to analyze and assess a user's emotional state and stress level based on user input.

[1236] "Mental support" refers to activities and programs designed to support users' mental and psychological health, including relaxation exercises and meditation guidance.

[1237] "Means for displaying and notifying the user of the proposed mental support program" includes technical elements that allow the server to visually or audibly present to the user the mental support program selected based on the analysis results.

[1238] "Feedback" refers to the act of a user reporting to the system their own experiences and opinions regarding the mental support provided.

[1239] "Retraining" refers to the process of improving the system's algorithms and models based on collected feedback to provide more accurate mental support.

[1240] "Server" refers to a computing device or network service that receives user input, analyzes it, and provides appropriate mental support.

[1241] This invention is constructed as a system that carries out a series of processes with the cooperation of a server, a terminal, and a user in order to realize mental health support during a ride.

[1242] Program Generation and Processing

[1243] The server plays a central role in collecting and analyzing user input and providing appropriate mental support. The terminal acts as an interface with the user, sending the collected data to the server and presenting feedback and support programs from the server to the user. The specific hardware and software used are as follows:

[1244] Hardware and software used

[1245] Hardware: Smartphones, tablets, and autonomous vehicle infotainment systems

[1246] Software: Python, speech_recognition, TextBlob, tensorflow, Google Speech Recognition API

[1247] Natural language processing explanation

[1248] 1. Collecting User Input

[1249] Users log into a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level in voice or text format, for example, "I'm feeling tired after a long drive."

[1250] 2. Emotion and stress level analysis

[1251] The device sends the collected user voice data to the server in real time. The server converts the data into text using speech_recognition and then performs sentiment analysis using TextBlob. The analysis results are classified as positive, negative, or neutral.

[1252] 3. Providing appropriate mental support

[1253] The server selects an appropriate mental support program based on the analysis results. For example, if the emotion is determined to be "negative," it will suggest relaxation exercises. The server then transmits the selected support program to the device, which then displays it to the user.

[1254] 4. Gather feedback and retrain

[1255] After completing the provided mental support program, the user provides feedback such as their impressions via the terminal. For example, they might say, "I felt relaxed after performing the relaxation exercises."

[1256] The device sends this feedback data to the server, which then retrains the AI ​​model based on the feedback. This retraining process allows the support program to be further optimized for the user from the next time onwards.

[1257] Specific examples and examples of prompts for generative AI models

[1258] Examples:

[1259] If a user says during a long drive, "No matter how many times I've been on this road, it's still scary. I'm worried an accident might happen," the system will analyze the user's words and determine that they are feeling anxious. It will then suggest a guidance video to support relaxation exercises and show it on the display.

[1260] Example prompt for a generative AI model:

[1261] User says: "I'm getting tired after a long drive."

[1262] AI response: "I'm going to show you some relaxation techniques. Try some deep breathing."

[1263] In this way, the present invention provides support tailored to the user's individual emotional state and stress level, enabling a comfortable and safe riding experience in an autonomous vehicle.

[1264] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1265] Step 1:

[1266] Users log in to a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level by voice or text. Input can be specific voice or sentences such as "I'm feeling tired after a long drive."

[1267] (Input) User's vocal or textual emotional report

[1268] (Output) Audio or text data

[1269] Step 2:

[1270] The device collects voice data from the user and converts the voice to text using the speech_recognition library. It takes voice data as input, analyzes it, and outputs it as text data.

[1271] (Input) Audio data

[1272] (Output) Text data

[1273] Step 3:

[1274] The server receives the text data sent from the device and performs sentiment analysis using TextBlob. The analysis detects the emotional state (positive, negative, neutral) and evaluates the stress level. For example, if a positive emotion is detected, the stress level is determined to be low.

[1275] (Input) Text data

[1276] (Output) Evaluation results of emotional state and stress level

[1277] Step 4:

[1278] The server selects an appropriate mental support program based on the analysis results. For example, if the user's emotions are determined to be "negative," it selects relaxation exercises. To select the program, it references various support programs stored in a program database in advance.

[1279] (Input) Evaluation results of emotional state and stress level

[1280] (Output) Selected mental support programs

[1281] Step 5:

[1282] The server transmits the selected mental support program to the terminal, which receives it and presents it to the user visually or audibly, for example, by showing a relaxation exercise guidance video on the display.

[1283] (Input) Selected mental support programs

[1284] (Output) Transfer of support programs to the terminal

[1285] Step 6:

[1286] The user performs the provided mental support program and provides feedback based on the experience, for example, by reporting their impression via text or voice, such as "After performing the relaxation exercises, I felt relaxed."

[1287] (Input) User feedback (voice or text)

[1288] (Output) Feedback Data

[1289] Step 7:

[1290] The device sends user feedback data to the server, which then retrains the AI ​​model based on the feedback data. Specifically, the server analyzes user feedback and updates the model to reflect this information in the selection of support programs from the next time onward.

[1291] (Input) Feedback data

[1292] (Output) Updated AI model

[1293] 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.

[1294] 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.

[1295] 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.

[1296] [Fourth embodiment]

[1297] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1298] 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.

[1299] 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).

[1300] 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.

[1301] 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.

[1302] 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).

[1303] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] 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.

[1309] 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."

[1310] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[1311] 1. Collecting User Input

[1312] User:

[1313] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data will be collected.

[1314] Device:

[1315] The device collects text and voice data from the user and transmits it to the server in real time.

[1316] 2. Emotion and stress level analysis

[1317] server:

[1318] The server receives text and voice data from the device. The AI ​​model then analyzes the data using natural language processing (NLP) techniques and sentiment analysis algorithms. For example, it can identify keywords such as "stress" and "feel" and determine that the user's stress level is high.

[1319] 3. Providing appropriate mental support

[1320] server:

[1321] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, psychological counseling, etc. The selected mental support program is then proposed to the user.

[1322] Device:

[1323] The device will notify the user of suggested mental support and execute the program selected by the user. For example, if a user has a high stress level, "Meditation Guidance" will be suggested, and the device will play a meditation guidance video.

[1324] 4. Gather feedback and retrain

[1325] User:

[1326] After participating in the provided mental support program, the user provides feedback, such as, "After receiving the meditation guidance, I felt relaxed."

[1327] Device:

[1328] The terminal collects user feedback and sends it to the server.

[1329] server:

[1330] The server receives feedback data from users, updates and improves the AI ​​model based on that feedback, and reflects it in the next support proposal.

[1331] This system can provide continuous and effective mental health support to individuals undergoing litigation. As a specific example, if a user inputs "I'm feeling very stressed because of a recent trial," the server analyzes the data and determines that the stress level is high. A meditation guidance video is then delivered to the device, providing the user with guidance on how to relax. After the session, if the user provides feedback such as "Meditation helped me relax a little," this information will be reflected in the next support suggestion.

[1332] In this way, optimal mental support can be provided according to the individual circumstances of each user, thereby reducing the psychological burden during litigation.

[1333] The processing flow will be explained below.

[1334] Step 1:

[1335] The user logs into a mental health support app on a device such as a smartphone or tablet, and inputs their emotional state and stress level by text or voice.

[1336] Step 2:

[1337] The device collects user input data (text or voice) and transmits the data to the server in real time.

[1338] Step 3:

[1339] The server receives the data sent from the device and passes it to the AI ​​model for analysis.

[1340] Step 4:

[1341] The server's AI model analyzes the data, using natural language processing (NLP) to interpret the text or voice data and determine the user's emotions and stress levels.

[1342] Step 5:

[1343] The server selects appropriate mental support based on the analysis results. For example, if the stress level is determined to be high, it will suggest meditation guidance.

[1344] Step 6:

[1345] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[1346] Step 7:

[1347] The device receives the notification sent from the server and displays and executes the mental support program (e.g., meditation guidance) suggested to the user. The user then starts the suggested program.

[1348] Step 8:

[1349] After the user completes the mental support program, they provide feedback, such as, "I was able to relax a little after meditating."

[1350] Step 9:

[1351] The device collects user feedback and sends the data to the server.

[1352] Step 10:

[1353] The server receives the feedback data and passes it to the AI ​​model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[1354] Example 1

[1355] 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."

[1356] Conventional mental health support systems often fail to adequately manage stress or provide appropriate mental support to individuals during litigation. Furthermore, they lack the ability to accurately provide feedback on the effectiveness of the support provided and to retrain the system. This makes it difficult to provide personalized support. Furthermore, in many cases, analysis of emotions and stress levels using natural language processing technology is not performed, making it difficult to provide optimal support tailored to the user's situation.

[1357] 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.

[1358] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for collecting user feedback on the provided mental support and retraining the system based on the feedback, means for analyzing the user's emotions and stress levels using natural language processing technology, means for determining the user's emotions and stress levels based on the analysis prompts using the generated artificial intelligence model, means for providing meditation guidance, relaxation exercises, and psychological counseling suggestions based on the analysis results, and means for retraining the artificial intelligence model based on the user's feedback data to improve the next support suggestion. This makes it possible to provide personalized mental support in real time and reduce the psychological burden during litigation.

[1359] "User input" refers to data including personal information, emotional state, and stress level reported by users using devices such as smartphones and tablets.

[1360] A "means for collecting" is a device or process that has the function of transmitting text or voice data entered by a user from a terminal to a server, and receiving and storing this data.

[1361] The "means for analyzing emotions and stress levels" is a system that uses natural language processing technology and emotion analysis algorithms to identify and quantify the emotional state and stress level from data entered by the user.

[1362] The "means for providing appropriate mental support" is a system that selects and provides support programs such as meditation guidance, relaxation exercises, and psychological counseling to users based on the analysis of their emotions and stress levels.

[1363] The "means for collecting feedback" refers to a device or process that collects data on the user's impressions and effects after using the mental support program and transmits this data to the server.

[1364] "Means for retraining the system" refers to the process of using collected user feedback data to update and refine the algorithm of the generative AI model and improve the next mental support proposal.

[1365] "Natural language processing technology" is a technology that allows a computer to understand and analyze text data entered by a user, and is used to identify emotions and stress levels.

[1366] A "generative AI model" is a type of machine learning, an artificial intelligence system trained to predict and determine a user's emotional state and stress level based on specific prompts.

[1367] An "analysis prompt" is an input sentence given to the generative AI model, which is used to analyze emotions and stress levels.

[1368] "Meditation Guidance" is a program that provides users with instructions and procedures for meditating to reduce stress.

[1369] "Relaxation exercises" are programs that provide a series of exercises and activities designed to help users relax.

[1370] "Psychological counseling" is the process by which a user receives professional advice and support for stress and emotional issues during litigation.

[1371] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. The system collects user input, analyzes emotions and stress levels, and provides appropriate mental support. In addition, it collects user feedback on the mental support provided and retrains the system based on that feedback. In this way, it is possible to continuously provide personalized mental support in real time.

[1372] Collecting User Input

[1373] User:

[1374] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and thereafter periodically report their current emotional state and stress level via text or voice data. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," that data is collected.

[1375] Device:

[1376] The device collects text and voice data from users and transmits it to the server in real time. The technology used in this process employs encrypted communication protocols to ensure data security.

[1377] Emotion and stress level analysis

[1378] server:

[1379] The server receives text and voice data sent from the device. It then analyzes the data using AI models, natural language processing (NLP) techniques, and sentiment analysis algorithms. Specifically, it uses Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's stress level is quantified.

[1380] Generative AI models:

[1381] The generative AI model determines the user's emotional state and stress level based on analytical prompts, such as "Please assess the user's stress level from this text data: 'The trial is difficult and stressful.'"

[1382] Providing appropriate mental support

[1383] server:

[1384] Based on the analysis results, the server selects the appropriate mental support program for the user. Specifically, if the stress level is determined to be high, meditation guidance, relaxation exercises, and psychological counseling are provided. The selection is made using a rule-based engine and machine learning models.

[1385] Device:

[1386] The device receives the information sent from the server and notifies the user. If the user selects a suggested mental support program, the device executes the program. Specifically, it plays a meditation guidance video.

[1387] User:

[1388] After receiving the notification, users can select and implement the suggested mental support program, which involves watching guided meditation videos and performing relaxation exercises to reduce stress.

[1389] Gathering feedback and relearning

[1390] User:

[1391] After participating in the provided mental support program, users provide feedback on its effectiveness, such as "Thanks to the meditation guidance, I was able to relax a little."

[1392] Device:

[1393] The terminal collects feedback data from the user and transmits it to the server.

[1394] server:

[1395] The server stores the received feedback data in a database and retrains the generative AI model to improve the next mental support suggestion. This retraining process uses training data based on actual usage data.

[1396] Specifically, when a user types "I've been feeling very stressed lately because of a lawsuit" into the app, the device sends that data to the server. The server analyzes the data and determines that the user is under "high stress." Based on that result, a meditation guidance video is suggested to the user. After watching the video, the user provides feedback such as "I was able to relax a little," and the server uses this feedback to retrain the AI ​​model.

[1397] Example prompts to input to the generative AI model

[1398] "Analyze the user's emotions and stress level from the following text data: 'I am feeling very stressed about a recent court case.'"

[1399] "We use user feedback to retrain our AI model and improve the next support suggestion. Here's the feedback data: 'The meditation guidance helped me relax a bit.'"

[1400] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1401] Step 1:

[1402] Collecting User Input

[1403] input:

[1404] Text and voice data containing your personal information, emotional state, and stress levels.

[1405] Operation:

[1406] Users log in to the mental health support app using a device such as a smartphone or tablet. When they log in for the first time, they enter basic personal information such as their name, age, gender, and the type of lawsuit. After that, they periodically report their emotional state and stress level via text or voice. For example, by entering, "Preparing for trial is difficult and stressful," the data is collected.

[1407] output:

[1408] The collected text and voice data is stored on the device and sent to a server for the next step.

[1409] Step 2:

[1410] Data transmission and storage

[1411] input:

[1412] Text and voice data sent from your device.

[1413] Operation:

[1414] The terminal encrypts the user's input data in real time and sends it securely to the server. The server stores the received data in a database. During this process, transaction processing is performed to maintain data consistency.

[1415] output:

[1416] Securely stored text and audio data is stored in a database.

[1417] Step 3:

[1418] Emotion and stress level analysis

[1419] input:

[1420] User text and voice data stored in a database.

[1421] Operation:

[1422] The server analyzes the accumulated data using natural language processing (NLP) techniques, including libraries such as Python's NLTK, spaCy, and Hugging Face's Transformers. Keywords such as "stress" and "tough" are identified during the analysis process, and the user's emotional state and stress level are quantified.

[1423] output:

[1424] The analyzed emotional state and stress level are then numerically analyzed.

[1425] Step 4:

[1426] Selecting appropriate mental support

[1427] input:

[1428] Quantified emotional state and stress levels.

[1429] Operation:

[1430] Based on the analysis results, the server selects the appropriate mental support program to provide to the user. If high stress is determined, meditation guidance or relaxation exercises will be selected. This selection is made using a rule-based engine and machine learning models.

[1431] output:

[1432] Information about the selected mental support program is generated.

[1433] Step 5:

[1434] Providing mental support

[1435] input:

[1436] Information on selected mental support programs.

[1437] Operation:

[1438] The device receives the mental support information sent from the server and notifies the user. When the user selects a suggested program, the device executes the program, for example, playing a meditation guidance video.

[1439] output:

[1440] The mental support program received by the user is executed.

[1441] Step 6:

[1442] Collecting feedback

[1443] input:

[1444] Feedback data from users after implementing the mental support program.

[1445] Operation:

[1446] Users provide feedback on the effectiveness of the mental support program. For example, they can enter their impressions into the app, such as, "The meditation guidance helped me relax a little." The device collects this feedback and sends it to the server.

[1447] output:

[1448] The collected feedback data is sent to a server.

[1449] Step 7:

[1450] Re-learning and improving next suggestions

[1451] input:

[1452] User feedback data.

[1453] Operation:

[1454] The server retrains the generative AI model based on the received feedback data. During the retraining process, the collected feedback data is used as training data, improving the accuracy and suitability of the next mental support suggestion.

[1455] output:

[1456] Improved generative AI models will be reflected in the next proposal.

[1457] (Application example 1)

[1458] 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."

[1459] Conventional mental health support systems often lack the functionality to provide optimal support based on the user's emotional state. This has resulted in insufficient stress management for users and ineffective mental health care. In particular, there has been a lack of mental support provided through video content, making it difficult to provide real-time support that meets the user's specific needs. Therefore, there has been a need for a system that can suggest and deliver appropriate video content based on the user's emotional state to effectively support mental health.

[1460] 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.

[1461] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for delivering the provided mental support to the user as video content, thereby making it possible to provide optimal mental support according to the user's emotional state in the form of video content in real time.

[1462] "User input" refers to text or voice data provided by a user to the system.

[1463] "Analyzing emotions and stress levels" refers to using natural language processing and emotion analysis algorithms to identify and assess a user's emotional and stress state based on user input.

[1464] "Mental support" refers to specific programs and content to support users' mental health, including meditation guidance, relaxation exercises, and psychological counseling.

[1465] "Delivering as video content" refers to providing mental support selected based on the analysis results in video format to the user's device.

[1466] "Gathering feedback" refers to systematically collecting opinions and impressions provided by users after receiving mental support.

[1467] "Retraining" refers to the process of updating and improving a system's algorithms and models based on collected user feedback.

[1468] An "emotion label" is a classification label that indicates the user's emotional state, and includes categories such as "high stress" and "relaxed," for example.

[1469] "Proposing in real time" means instantly reflecting the analysis results and quickly presenting and providing mental support that is tailored to the user's current situation.

[1470] MODE FOR CARRYING OUT THE INVENTION

[1471] This invention is a system that includes an analysis of emotions and stress levels based on user input, provision of appropriate mental support, and a re-learning process for the system based on user feedback. How to specifically implement this system will be described below.

[1472] First, users access the mental health support app using a device such as a smartphone or tablet. They periodically input their current emotional state and stress level via text or voice. This user input is sent to the server in real time using a Python or Java program.

[1473] The server then receives the submitted user input and utilizes software such as TensorFlow and Scikit-learn to analyze the data using natural language processing (NLP) techniques and sentiment analysis algorithms. Specifically, it vectorizes the text data using TfidfVectorizer and predicts the user's sentiment label using a trained sentiment analysis model. For example, if a user enters "I've been feeling very stressed lately. I'm worried about the trial," the system will determine that the text represents a high-stress state.

[1474] Based on the analysis results, the server selects appropriate mental support for the user. Specific mental support options include meditation guidance, relaxation exercises, and psychological counseling. These options are then delivered to the user's device as video content. For example, a user who is judged to be highly stressed may be recommended a relaxation meditation video, which is then played on the device.

[1475] After watching the provided mental support video, the user enters feedback. This feedback is then sent from the device to the server and collected. The server uses this feedback information to retrain the system's AI model, so that the next mental support suggestions will better meet the user's individual needs. The retraining process involves updating the AI ​​model using Python and TensorFlow.

[1476] Using this system, optimal mental health support can be provided in real time according to the user's emotional state, effectively reducing the user's psychological burden.

[1477] As a concrete example, the following prompt sentence is input to the generative AI model:

[1478] "I'm very stressed about the recent court case. I watched a meditation video and it helped me relax a bit, but are there any others you'd recommend?"

[1479] Based on this prompt, the system will suggest mental health support tailored to the situation.

[1480] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1481] Step 1:

[1482] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as name, age, gender, and type of lawsuit), and thereafter periodically report their emotional state and stress level via text or voice.

[1483] Input: User text or voice input

[1484] Output: Sending data from the device to the server

[1485] Step 2:

[1486] The device transmits the collected text and voice data to a server in real time.

[1487] Input: Text or audio data

[1488] Output: Data sent to the server

[1489] Step 3:

[1490] The server uses natural language processing (NLP) techniques and sentiment analysis algorithms to analyze the received data. Specifically, it vectorizes the text data using TfidfVectorizer and predicts sentiment labels using a pre-trained sentiment analysis model (powered by TensorFlow).

[1491] Input: Text or audio data

[1492] Output: Emotion label and stress level judgment result

[1493] Step 4:

[1494] Based on the analysis results, the server selects appropriate mental support for the user, such as meditation guidance, relaxation exercises, and psychological counseling.

[1495] Input: Emotion label and stress level judgment result

[1496] Output: Selection of appropriate mental support

[1497] Step 5:

[1498] The server distributes the selected mental support as video content and notifies the user's device, where the user can watch the video content.

[1499] Input: Results of selection of appropriate mental support

[1500] Output: Video content delivered to the user's device

[1501] Step 6:

[1502] After watching the mental support video, users can enter their feedback, such as "The meditation video was helpful. It would be great if the quality was a little better."

[1503] Input: User feedback

[1504] Output: Sends feedback data from the device to the server

[1505] Step 7:

[1506] The terminal transmits the user's feedback to the server.

[1507] Input: Feedback data

[1508] Output: Feedback data sent to the server

[1509] Step 8:

[1510] The server retrains the system's AI model based on the received feedback data, allowing the next mental support suggestions to better suit individual needs. This retraining is done using software such as TensorFlow.

[1511] Input: Feedback data

[1512] Output: Updated and improved AI model

[1513] 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.

[1514] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals in litigation. The system combines an emotion engine with a mechanism for collecting user input, analyzing emotions and stress levels, providing appropriate mental support, and relearning based on user feedback on the support provided. The emotion engine recognizes emotions based on the user's text and voice input and is used to provide more accurate mental support.

[1515] 1. Collecting User Input

[1516] User:

[1517] Users log in to a mental health support app using a device such as a smartphone or tablet. When they first log in, they enter basic personal information (such as their name, age, gender, and type of lawsuit), and then periodically report their current emotional state and stress level via text or voice. For example, if a user enters, "I'm feeling very stressed because of a recent lawsuit," this data is collected.

[1518] Device:

[1519] The terminal collects text or voice data from the user and transmits it to the server in real time.

[1520] 2. Emotion and stress level analysis

[1521] server:

[1522] The server receives text and voice data sent from the device and passes it to the emotion engine. The emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data and recognize the user's emotions. For example, it identifies keywords such as "stress" and "feel" and determines that the user is feeling emotions such as "sad" or "anxious." Based on the results of this analysis, the AI ​​model determines the user's stress level.

[1523] 3. Providing appropriate mental support

[1524] server:

[1525] Based on the analysis results, the server selects the most appropriate mental support for the user. For example, if the emotion engine recognizes that the user is feeling "anxiety," it may determine that providing relaxation exercises or meditation guidance is appropriate. This selected mental support program is then proposed to the user.

[1526] Device:

[1527] The device notifies the user of the suggestions sent from the server and executes the program selected by the user. Specifically, for a user with a high stress level, "Meditation Guidance" is suggested, and the device displays a meditation guidance video.

[1528] 4. Gather feedback and retrain

[1529] User:

[1530] After completing the provided mental support program, users provide feedback through the app, such as, "After receiving the meditation guidance, I felt relaxed."

[1531] Device:

[1532] The terminal collects user feedback and sends it to the server.

[1533] server:

[1534] The server receives feedback data from users and retrains the AI ​​model based on that feedback, allowing this information to be reflected in the next mental support suggestions, making it possible to provide even more effective support.

[1535] This system provides optimal mental support tailored to each user's individual situation, reducing the psychological burden during litigation. As a specific example, if a user inputs "I'm feeling very stressed about a recent trial" and the server recognizes this emotion as "anxiety," appropriate relaxation exercises will be suggested. After the user completes this exercise, they can provide feedback, which will be reflected in future support suggestions. In this way, the system continuously provides mental support optimized for each individual user in real time.

[1536] The processing flow will be explained below.

[1537] Step 1:

[1538] The user logs into a mental health support app on a device such as a smartphone or tablet. After logging in, the user enters their current emotional state and stress level by text or voice.

[1539] Step 2:

[1540] The device collects user input data (text or voice) and transmits the data to the server in real time.

[1541] Step 3:

[1542] The server receives the data sent from the device and passes it to the emotion engine.

[1543] Step 4:

[1544] The server's emotion engine uses natural language processing (NLP) and emotion analysis algorithms to analyze the data, for example, identifying keywords such as "stress" and "feeling" to determine the user's emotional state (e.g., "anxious" or "sad").

[1545] Step 5:

[1546] The server determines the user's stress level based on the analysis results of the emotion engine. If the analysis results indicate that the user is "highly stressed," the AI ​​model considers appropriate countermeasures.

[1547] Step 6:

[1548] The server selects the most appropriate mental support (e.g., meditation guidance, relaxation exercises) based on the user's stress level and emotional state.

[1549] Step 7:

[1550] The server generates a notification to suggest the selected mental support program to the user, and transmits the notification to the terminal.

[1551] Step 8:

[1552] The terminal receives the notification sent from the server and displays the suggested mental support program (e.g., meditation guidance) to the user. The user then starts the suggested program.

[1553] Step 9:

[1554] After the user completes the mental support program, they provide feedback, such as "I felt relaxed after meditating."

[1555] Step 10:

[1556] The device collects user feedback and sends the data to the server.

[1557] Step 11:

[1558] The server receives the feedback data and passes it to the emotion engine and AI model, which then retrains the model based on the feedback and incorporates it into the next support proposal.

[1559] This processing flow allows the system to support users' mental health in real time and continuously improve its effectiveness. For example, if a user inputs "I'm feeling very stressed because of a recent trial" and the server's emotion engine recognizes this as "anxiety," it will suggest relaxation exercises. If the user performs the exercise and provides feedback such as "I was able to relax," this will be reflected in the next suggestion.

[1560] Example 2

[1561] 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."

[1562] Mental health issues such as stress and anxiety experienced by individuals during litigation are serious, and a system that can effectively manage and support these issues is needed. Conventional mental health support systems struggle to accurately grasp users' emotions and stress levels and provide appropriate support based on those findings. Furthermore, it is difficult to fully utilize user feedback to improve and adapt the system. A new mental health support system is needed to address these challenges.

[1563] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1564] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, and means for collecting feedback from the user after implementing the provided mental support program and relearning the system. This makes it possible to accurately analyze the user's emotions and stress levels and provide appropriate mental support based on the analysis results. Furthermore, relearning the system based on user feedback enables more personalized and effective support.

[1565] "User input" is data provided by a user to a system, and is information collected in the form of text or voice.

[1566] "Means for analyzing emotions and stress levels" refers to a device or software that uses natural language processing techniques and emotion analysis algorithms to identify a user's emotions and stress levels based on user input.

[1567] The "means for providing mental support" is a device or software that proposes an appropriate mental support program to the user based on the analysis results and executes the program.

[1568] The "means for collecting feedback and retraining the system" refers to a device or software that has the function of collecting feedback provided by the user after implementing the provided mental support program and retraining the system's algorithms and models based on that data.

[1569] "Natural language processing technology" is a series of technologies that enable computers to understand, analyze, and generate human language, and is used for semantic analysis and sentiment analysis of text data.

[1570] An "emotion analysis algorithm" is a program that incorporates mathematical or statistical techniques to identify a user's emotional state from their text or voice.

[1571] A "mental support program" is a specific activity or exercise provided to support a user's mental health, such as relaxation exercises or meditation guidance.

[1572] This invention is an AI-driven mental health support system for protecting the mental health and managing stress of individuals during litigation. Specific embodiments of this system are described in detail below.

[1573] Hardware and Software Configuration

[1574] The system mainly consists of a terminal for collecting user input, a server for analyzing and processing the input data, a server and terminal for providing appropriate mental support based on the analysis results, and a server and terminal for collecting feedback and relearning.

[1575] Device:

[1576] This refers to mobile information devices such as smartphones and tablets that users use to access mental health support apps and provide input data and feedback.

[1577] server:

[1578] This refers to a high-performance computer installed on a cloud server or a specific data center. The server receives and stores user input data, analyzes it using a natural language processing (NLP) engine and sentiment analysis algorithm, and retrains the AI ​​model based on the effectiveness of the mental support provided.

[1579] Data processing and data calculation

[1580] Collecting user input:

[1581] Users use a mental health support app to input personal information and their daily emotional state, for example, by text or voice input such as "I'm feeling very stressed about a recent court case."

[1582] Emotion and stress level analysis:

[1583] The user data sent from the device is received by the server and passed to the NLP engine. The NLP engine analyzes keywords and emotional patterns from the user's text and voice to determine their emotional state and stress level. For example, if the keyword "stress" appears frequently, it will be recognized that the user is at a high stress level.

[1584] Providing appropriate mental health support:

[1585] Based on the analysis results, the server selects an appropriate mental support program. This program is sent to the device and provided to the user. For example, a user who is feeling anxious might be offered relaxation exercises or meditation guidance.

[1586] Gathering feedback and relearning:

[1587] After the user completes the mental support program, they provide feedback. The device then sends this feedback to the server, which then uses it to retrain the AI ​​model, making future suggestions even more accurate.

[1588] Examples of concrete examples and prompts

[1589] Examples:

[1590] A user uses the app and enters, "I'm feeling very stressed because of a recent trial. I'm having trouble falling asleep and concentrating." This data is sent to the server and analyzed by the NLP engine. The server determines that the user is in an "anxious" state and suggests relaxation exercises. The user performs the exercises and then provides feedback such as, "I felt relaxed after the relaxation exercises." Based on this feedback, the AI ​​model is retrained, and the next suggestions will be even more accurate.

[1591] Example prompt sentence:

[1592] User Input: "I'm feeling very stressed about the recent court case. I'm having trouble sleeping and concentrating."

[1593] Prompt: Identify the specific emotion the user is feeling from this text and report it along with the intensity of that emotion.

[1594] This prompt enables the generative AI model to perform highly accurate emotion recognition and generate data to provide appropriate mental support.

[1595] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1596] Step 1: Collecting User Input

[1597] User:

[1598] Users log in to the mental health support app using a device such as a smartphone or tablet. When they first log in, they enter their personal information, and then report their daily emotional state and stress level via text or voice. For example, they might enter, "I'm feeling very stressed because of a recent court case." This input data is sent to the app on their device.

[1599] input:

[1600] The user inputs their emotional state and stress level in text or voice format.

[1601] output:

[1602] User input data stored on the device.

[1603] Device:

[1604] The device receives the user's text and voice data and sends it to the server in real time. An app on the device then cleans up the data appropriately and converts it into a format that can be sent.

[1605] input:

[1606] Text or voice data entered by the user into the device.

[1607] output:

[1608] User input data sent to the server.

[1609] Step 2: Analyze your emotions and stress levels

[1610] server:

[1611] The server receives user data sent from the device, first stores the received data in storage, and then passes it to the natural language processing engine for processing.

[1612] input:

[1613] User input data sent from the terminal.

[1614] output:

[1615] User input data to be passed to the natural language processing engine.

[1616] server:

[1617] The natural language processing engine analyzes the user's text and voice data to identify emotions and stress levels. For example, it detects keywords such as "stress" and "feel" and determines that the user is feeling stressed. The analysis results are output as an emotional state (e.g., anxiety, sadness) and its intensity.

[1618] input:

[1619] User input data stored in storage.

[1620] output:

[1621] Analysis results identifying emotional state and stress levels.

[1622] Step 3: Providing appropriate mental health support

[1623] server:

[1624] The server selects appropriate mental support programs based on the analysis of emotions and stress levels. For example, if the user is feeling "anxious," it may determine that relaxation exercises or meditation guidance are appropriate. The server then creates links and content for these programs and sends them to the device.

[1625] input:

[1626] Emotion and stress level analysis results.

[1627] output:

[1628] A mental support program sent to your device.

[1629] Device:

[1630] The device notifies the user of the mental support program suggestions sent from the server. The suggestions are displayed in a pop-up notification or in the notification bar. When the user selects a program, the device executes the selected program, for example, playing a meditation guidance video.

[1631] input:

[1632] Mental support program suggestions sent from the server.

[1633] output:

[1634] Suggestions to be notified to the user; mental support programs to be implemented (e.g., video playback).

[1635] Step 4: Gather feedback and retrain

[1636] User:

[1637] After participating in the provided mental support program, users provide feedback about their experience, for example, by entering something like, "I felt relaxed after receiving the meditation guidance."

[1638] input:

[1639] Feedback after implementing a mental support program.

[1640] output:

[1641] Feedback data entered into the app.

[1642] Device:

[1643] The terminal collects user feedback data and transmits it to the server in real time, where data cleansing and format conversion are performed.

[1644] input:

[1645] Feedback data entered by users into the app.

[1646] output:

[1647] Feedback data sent to the server.

[1648] server:

[1649] The server passes the feedback data received from the user to the AI ​​model, which then re-learns based on that data. This updates the system's algorithms and models, improving the accuracy of the next mental support suggestion.

[1650] input:

[1651] Feedback data sent from the device.

[1652] output:

[1653] Updated data for retrained AI models.

[1654] (Application example 2)

[1655] 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."

[1656] In autonomous vehicles, there is no need to drive, so it is necessary to effectively reduce the stress and anxiety felt by passengers while riding in them and provide a comfortable riding experience. However, there are currently no systems that can analyze passengers' emotions and stress levels in real time and provide appropriate mental support. Furthermore, there is a lack of a feedback function to evaluate whether the mental support provided is actually effective and to continuously improve the system. Therefore, the objective of this invention is to develop a mental health support system for autonomous vehicles that reduces stress and anxiety while riding in them and provides a comfortable riding environment.

[1657] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1658] In this invention, the server includes means for collecting user input, means for analyzing emotions and stress levels based on the collected user input, means for providing appropriate mental support based on the analysis results, means for displaying and notifying the user of suggested mental support programs, and means for collecting feedback on mental support and retraining the system based on that feedback. This allows the server to analyze the user's emotions and stress levels in real time and provide appropriate mental support during the ride, enabling a comfortable riding experience. Furthermore, by retraining the system based on the feedback, the quality of the mental support provided is continuously improved.

[1659] "User input" refers to data provided by a user to a system, including data in text or voice format.

[1660] "Emotions and stress levels" are indicators that indicate the user's psychological state, where emotions refer to emotional states such as joy, sadness, and anxiety, and stress levels indicate the intensity and degree of those states.

[1661] "Means for analyzing emotions and stress levels" includes any technical elements or algorithms used to analyze and assess a user's emotional state and stress level based on user input.

[1662] "Mental support" refers to activities and programs designed to support users' mental and psychological health, including relaxation exercises and meditation guidance.

[1663] "Means for displaying and notifying the user of the proposed mental support program" includes technical elements that allow the server to visually or audibly present to the user the mental support program selected based on the analysis results.

[1664] "Feedback" refers to the act of a user reporting to the system their own experiences and opinions regarding the mental support provided.

[1665] "Retraining" refers to the process of improving the system's algorithms and models based on collected feedback to provide more accurate mental support.

[1666] "Server" refers to a computing device or network service that receives user input, analyzes it, and provides appropriate mental support.

[1667] This invention is constructed as a system that carries out a series of processes with the cooperation of a server, a terminal, and a user in order to realize mental health support during a ride.

[1668] Program Generation and Processing

[1669] The server plays a central role in collecting and analyzing user input and providing appropriate mental support. The terminal acts as an interface with the user, sending the collected data to the server and presenting feedback and support programs from the server to the user. The specific hardware and software used are as follows:

[1670] Hardware and software used

[1671] Hardware: Smartphones, tablets, and autonomous vehicle infotainment systems

[1672] Software: Python, speech_recognition, TextBlob, tensorflow, Google Speech Recognition API

[1673] Natural language processing explanation

[1674] 1. Collecting User Input

[1675] Users log into a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level in voice or text format, for example, "I'm feeling tired after a long drive."

[1676] 2. Emotion and stress level analysis

[1677] The device sends the collected user voice data to the server in real time. The server converts the data into text using speech_recognition and then performs sentiment analysis using TextBlob. The analysis results are classified as positive, negative, or neutral.

[1678] 3. Providing appropriate mental support

[1679] The server selects an appropriate mental support program based on the analysis results. For example, if the emotion is determined to be "negative," it will suggest relaxation exercises. The server then transmits the selected support program to the device, which then displays it to the user.

[1680] 4. Gather feedback and retrain

[1681] After completing the provided mental support program, the user provides feedback such as their impressions via the terminal. For example, they might say, "I felt relaxed after performing the relaxation exercises."

[1682] The device sends this feedback data to the server, which then retrains the AI ​​model based on the feedback. This retraining process allows the support program to be further optimized for the user from the next time onwards.

[1683] Specific examples and examples of prompts for generative AI models

[1684] Examples:

[1685] If a user says during a long drive, "No matter how many times I've been on this road, it's still scary. I'm worried an accident might happen," the system will analyze the user's words and determine that they are feeling anxious. It will then suggest a guidance video to support relaxation exercises and show it on the display.

[1686] Example prompt for a generative AI model:

[1687] User says: "I'm getting tired after a long drive."

[1688] AI response: "I'm going to show you some relaxation techniques. Try some deep breathing."

[1689] In this way, the present invention provides support tailored to the user's individual emotional state and stress level, enabling a comfortable and safe riding experience in an autonomous vehicle.

[1690] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1691] Step 1:

[1692] Users log in to a mental health support app using the infotainment system of the autonomous vehicle or their smartphone and report their emotional state and stress level by voice or text. Input can be specific voice or sentences such as "I'm feeling tired after a long drive."

[1693] (Input) User's vocal or textual emotional report

[1694] (Output) Audio or text data

[1695] Step 2:

[1696] The device collects voice data from the user and converts the voice to text using the speech_recognition library. It takes voice data as input, analyzes it, and outputs it as text data.

[1697] (Input) Audio data

[1698] (Output) Text data

[1699] Step 3:

[1700] The server receives the text data sent from the device and performs sentiment analysis using TextBlob. The analysis detects the emotional state (positive, negative, neutral) and evaluates the stress level. For example, if a positive emotion is detected, the stress level is determined to be low.

[1701] (Input) Text data

[1702] (Output) Evaluation results of emotional state and stress level

[1703] Step 4:

[1704] The server selects an appropriate mental support program based on the analysis results. For example, if the user's emotions are determined to be "negative," it selects relaxation exercises. To select the program, it references various support programs stored in a program database in advance.

[1705] (Input) Evaluation results of emotional state and stress level

[1706] (Output) Selected mental support programs

[1707] Step 5:

[1708] The server transmits the selected mental support program to the terminal, which receives it and presents it to the user visually or audibly, for example, by showing a relaxation exercise guidance video on the display.

[1709] (Input) Selected mental support programs

[1710] (Output) Transfer of support programs to the terminal

[1711] Step 6:

[1712] The user performs the provided mental support program and provides feedback based on the experience, for example, by reporting their impression via text or voice, such as "After performing the relaxation exercises, I felt relaxed."

[1713] (Input) User feedback (voice or text)

[1714] (Output) Feedback Data

[1715] Step 7:

[1716] The device sends user feedback data to the server, which then retrains the AI ​​model based on the feedback data. Specifically, the server analyzes user feedback and updates the model to reflect this information in the selection of support programs from the next time onward.

[1717] (Input) Feedback data

[1718] (Output) Updated AI model

[1719] 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.

[1720] 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.

[1721] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1722] 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.

[1723] 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.

[1724] 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.

[1725] 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).

[1726] 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.

[1727] 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."

[1728] 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.

[1729] 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).

[1730] 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.

[1731] 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.

[1732] 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.

[1733] 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.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] 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, in order to avoid confusion and to 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.

[1739] 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.

[1740] The following is further disclosed regarding the above embodiment.

[1741] (Claim 1)

[1742] means for collecting user input;

[1743] means for analyzing emotions and stress levels based on the collected user input;

[1744] A means of providing appropriate mental support based on the analysis results;

[1745] A system including:

[1746] (Claim 2)

[1747] 10. The system of claim 1, wherein the user input is collected as text or voice data.

[1748] (Claim 3)

[1749] 10. The system of claim 1, further comprising means for collecting user feedback on the mental support provided and retraining the system based on the feedback.

[1750] "Example 1"

[1751] (Claim 1)

[1752] means for collecting user input;

[1753] means for analyzing emotions and stress levels based on the collected user input;

[1754] A means of providing appropriate mental support based on the analysis results;

[1755] a means for collecting user feedback on the mental support provided and retraining the system based on the feedback;

[1756] A system including:

[1757] (Claim 2)

[1758] 10. The system of claim 1, wherein the user input is collected as text or voice data.

[1759] (Claim 3)

[1760] 10. The system of claim 1, wherein natural language processing techniques are used to analyze the user's emotions and stress levels.

[1761] (Claim 4)

[1762] 10. The system of claim 1, further comprising means for determining the user's emotions and stress level based on the analytical prompts using the generated artificial intelligence model.

[1763] (Claim 5)

[1764] 10. The system of claim 1, further comprising means for providing meditation guidance, relaxation exercises, and psychological counseling suggestions based on the analysis results.

[1765] (Claim 6)

[1766] 10. The system of claim 1, further comprising means for retraining the artificial intelligence model based on user feedback data to improve subsequent support suggestions.

[1767] "Application Example 1"

[1768] (Claim 1)

[1769] means for collecting user input;

[1770] means for analyzing emotions and stress levels based on the collected user input;

[1771] A means of providing appropriate mental support based on the analysis results;

[1772] A means for distributing the provided mental support to users as video content;

[1773] A system including:

[1774] (Claim 2)

[1775] 10. The system of claim 1, wherein the user input is collected as text or voice data.

[1776] (Claim 3)

[1777] 10. The system of claim 1, further comprising means for collecting user feedback on the mental support provided and retraining the system based on the feedback.

[1778] (Claim 4)

[1779] 10. The system of claim 1, further comprising means for predicting emotion labels and suggesting optimal video content in real time based on user input.

[1780] (Claim 5)

[1781] 10. The system of claim 1, further comprising means for storing user-provided feedback and using it as retraining data.

[1782] "Example 2: Combining Emotion Engines"

[1783] (Claim 1)

[1784] means for collecting user input;

[1785] means for analyzing emotions and stress levels based on the collected user input;

[1786] A means of providing appropriate mental support based on the analysis results;

[1787] A means for collecting feedback from users after they have implemented the provided mental support program and for retraining the system;

[1788] A system including:

[1789] (Claim 2)

[1790] 10. The system of claim 1, wherein the user input is collected as text or voice data.

[1791] (Claim 3)

[1792] 10. The system of claim 1, further comprising means for analyzing emotions based on the generated data using natural language processing techniques.

[1793] "Application example 2 when combining emotion engines"

[1794] (Claim 1)

[1795] means for collecting user input;

[1796] means for analyzing emotions and stress levels based on the collected user input;

[1797] A means of providing appropriate mental support based on the analysis results;

[1798] A means for displaying and notifying the proposed mental support program;

[1799] A means of collecting mental support feedback and retraining the system based on that feedback; and

[1800] A system including:

[1801] (Claim 2)

[1802] 10. The system of claim 1, wherein the user input is collected as text or voice data.

[1803] (Claim 3)

[1804] 10. The system of claim 1, wherein the system performs feedback relearning to dynamically update the mental support provided in response to newly determined emotions and stress levels. [Explanation of symbols]

[1805] 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. means for collecting user input; means for analyzing emotions and stress levels based on the collected user input; A means of providing appropriate mental support based on the analysis results; A system including:

2. The system of claim 1 , wherein the user input is collected as text or voice data.

3. 2. The system of claim 1, further comprising means for collecting user feedback on the mental support provided and retraining the system based on the feedback.

Images