system

Abstract

We provide the system. [Solution] Means for collecting data, Means for preprocessing the data and converting it into an analyzable format, A means for training the data using an artificial intelligence model, A means of receiving inquiries from users, A means for analyzing the consultation and generating appropriate support content, A system that includes means for providing the support content to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional mental health support system, a user may feel a high psychological hurdle when consulting, or it may be difficult to receive appropriate support. Therefore, there is a need for a more effective and responsive support means to prevent the user's mental disorder and maintain physical and mental health.

Means for Solving the Problems

[0005] The present invention provides a system that can receive anonymous consultations from users by collecting data, performing preprocessing, and then learning with an artificial intelligence model. This reduces the psychological burden on the user and enables the analysis of the consultation content using natural language processing technology and the automatic generation and provision of appropriate support content.

[0006] "Data" refers to information related to user consultations, past consultation cases, and reports, and is used for the analysis and learning of this system.

[0007] "Preprocessing" refers to the process of cleaning, tokenizing, and anonymizing collected data in order to convert it into an analyzable format.

[0008] An "artificial intelligence model" is a program that learns using machine learning algorithms, analyzes user inquiries, and generates appropriate support.

[0009] A "user" refers to an individual who uses this system to seek advice regarding mental health.

[0010] "Consultation" refers to the act of a user entering their anxieties or questions regarding mental health into this system.

[0011] "Analysis" refers to the process of using an artificial intelligence model to analyze the user's consultation content and evaluate their emotional state and stress level.

[0012] "Support content" refers to advice and recommendations for the user generated based on the analysis results.

[0013] "Anonymity" refers to a state in which users can seek advice without being identified, providing an environment where privacy is protected. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0018] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0019] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system that allows users to easily seek mental health consultations and provides support content generated during those consultations. The system consists of three components: a server, a terminal, and a user.

[0036] First, the server collects historical data related to mental health. This data is retrieved from an internal database, and data preprocessing is performed based on the collected information. Data preprocessing involves cleaning, anonymizing, and converting the collected data to an appropriate format. This prepares the foundational data used for analysis in the system and for training artificial intelligence models.

[0037] Next, the server trains a generative AI model using the pre-processed data. This model is built to learn patterns based on information from past case studies and reports, and to automatically determine what kind of support to provide next.

[0038] On the other hand, users seek advice through their devices. These devices provide an interface for users to easily input their mental health concerns. Users can submit information anonymously, ensuring a privacy-protected environment.

[0039] When a consultation request is submitted, the server receives the content and analyzes it using a generation AI model. Based on the analysis results, support content is generated. This support content may include specific advice on the user's problem, resource recommendations, or suggestions for relaxation.

[0040] Finally, the device provides the generated support information to the user. Specifically, it can display advice and suggestions on the device screen and, if necessary, provide links to additional resources.

[0041] For example, if a user posts a message on their device saying they are "stressed at work," the server understands the message and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's counseling service." In this way, the generating AI utilizes insights gained from past data to enable personalized responses.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects past consultation cases and reports from the company's internal database. This data includes information related to mental health and will serve as the basis for training future analytical and generative AI models.

[0045] Step 2:

[0046] The server performs preprocessing to convert the collected data into a format that can be analyzed. At this stage, unnecessary spaces and special characters are removed as part of data cleaning, and personally identifiable information is anonymized.

[0047] Step 3:

[0048] The server trains a generative AI model using pre-processed data. Utilizing natural language processing techniques, the model learns from past cases to generate answers to similar inquiries.

[0049] Step 4:

[0050] Users enter their mental health concerns into the chat interface on their device. Users can submit their concerns anonymously and are assigned a unique session ID.

[0051] Step 5:

[0052] The terminal sends user input to the server. The transmitted data is encrypted to ensure security.

[0053] Step 6:

[0054] The server uses a generative AI model to analyze the user's inquiry. It identifies the user's emotions and stress levels in relation to the inquiry and initiates a process to generate appropriate support content.

[0055] Step 7:

[0056] Based on the analysis of the consultation content, the server generates support content that provides advice and resource suggestions tailored to the individual situation. Based on past data, it generates actionable and specific suggestions.

[0057] Step 8:

[0058] The terminal displays the generated support information to the user. The user can view advice and links to resources on the screen and ask additional questions.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In modern society, the increasing number of individuals struggling with mental health issues is a growing concern. However, many people require consultations with professionals to receive appropriate support, which is often constrained by time and geographical limitations. Therefore, there is a growing need for a system that can provide convenient, rapid, and appropriate support tailored to individual needs.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for recording information, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to quickly process inquiries from users and provide appropriate support tailored to their individual needs.

[0064] "Means for recording information" refers to devices or methods that efficiently collect and store information and data within a system, such as databases and storage.

[0065] "Means for preprocessing the information and converting it into an analyzable format" refers to a method or apparatus for preparing collected data into a format suitable for machine learning and analysis through processes such as cleaning, anonymization, and format conversion.

[0066] "Means for training information using a machine learning model" refers to a method or apparatus for building a model to perform pattern recognition or prediction by applying a machine learning algorithm based on training data.

[0067] "Means for receiving inquiries from users" refers to a device or method that provides an interface for users to input questions or problems into the system and receives that data.

[0068] "Means for analyzing the inquiry and generating appropriate support content" refers to a method or apparatus for analyzing the content of a user's inquiry received and automatically devising corresponding advice or solutions.

[0069] "Means for communicating the support content to the user" refers to methods or devices that provide information in the form of screen displays, audio, etc., in order to convey the generated advice and support content to the user in an easy-to-understand manner.

[0070] This invention aims to realize a system that allows users to easily seek advice on mental health issues and receive appropriate support. The system mainly consists of a server, terminals, and users.

[0071] The server uses an internal database to collect historical mental health information and preprocesses it. This preprocessing involves cleaning, anonymizing, and formatting the data using programming languages ​​such as Python and R. This makes the data suitable for machine learning.

[0072] Subsequently, the server trains the generative AI model. Commonly used machine learning libraries include TENSORFLOW® and PyTorch. During the training process, the model learns patterns from past cases and reports, and is built to automatically determine the next level of support to provide.

[0073] Users enter their mental health consultation details via a terminal. This terminal provides a user-friendly interface, designed to allow users to easily enter their consultation details. The information transmitted is anonymous, protecting user privacy.

[0074] When the server receives a consultation request from a user, it analyzes the content using a generative AI model. Based on the analysis results, appropriate support content is generated. This support content includes specific advice and resource recommendations to address the user's concerns.

[0075] Ultimately, the device displays the generated support information to the user. For example, if a user consults the device saying, "I'm having trouble with stress at work," the server analyzes this information and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's support desk." In this way, AI can leverage insights gained from past data to provide personalized support.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server retrieves historical mental health information from its internal database using queries. This input data includes raw historical cases and feedback. The server cleans this data, imputing missing values, removing outliers, and anonymizing it. The resulting clean data is then converted into a standardized format (e.g., a CSV file) and output as an analyzable dataset.

[0079] Step 2:

[0080] The server uses pre-processed data as input to train a generative AI model. This process involves using machine learning libraries (such as TensorFlow and PyTorch) to train the model to learn patterns from large amounts of data. The server evaluates the model's accuracy at each epoch and optimizes it by adjusting hyperparameters as needed. As a result, it outputs a trained model capable of determining what support should be provided next.

[0081] Step 3:

[0082] Users input their mental health concerns into the terminal's interface. This input data includes specific worries and situations. The terminal converts the user's input into an appropriate format and sends it to the server. This transmitted data is pre-validated to ensure the user's intent is clear before transmission.

[0083] Step 4:

[0084] The server receives user consultation data sent from the terminal and inputs it into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the consultation content and generate the most suitable support for the user. In this process, based on the input consultation data, it identifies problem-solving solutions and advice that match past patterns and generates specific suggestions as output.

[0085] Step 5:

[0086] The terminal provides the user with support information received from the server. Specifically, generated advice and instructions are displayed on the terminal's screen. Furthermore, links to relevant resources are provided as needed, allowing the user to obtain additional information. This displayed content is the final output, providing intuitive and useful information for the user.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] In modern society, individuals are increasingly experiencing psychological burdens in their daily lives, at work, and at home. Effective support measures are needed to properly manage and alleviate these psychological burdens. However, conventional methods struggle to provide specific support tailored to individual circumstances. Furthermore, the development of systems capable of understanding users' psychological states based on their electronic transaction activity and providing appropriate advice is still lacking, resulting in insufficient safe and anonymous mental health support.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, means for training an artificial intelligence model on the data, and means for analyzing the electronic transaction summary and estimating psychological burden. This enables users to receive sustainable, personalized mental health support anonymously.

[0092] "Means for collecting data" refers to a system that has the function of systematically acquiring data about user information and activities.

[0093] "Means for preprocessing the data and converting it into an analyzable format" refers to techniques that clean and anonymize the collected data to prepare it for safe analysis.

[0094] "Means of training the data using an artificial intelligence model" refers to the process of running a machine learning algorithm based on collected and pre-processed data to automatically understand patterns and trends.

[0095] "A means of receiving inquiries from users" refers to an interface through which users register their worries and problems in the system, and the system receives that information.

[0096] "A means of analyzing consultations and generating appropriate support content" refers to a process that analyzes user input information and provides appropriate advice and suggestions based on pre-learned patterns.

[0097] "Methods for analyzing electronic transaction summaries and inferring psychological burden" refers to technologies for analyzing users' daily transaction patterns and evaluating the psychological state predicted therefrom.

[0098] "Means of providing support to users" refers to mechanisms for presenting generated advice and resources on the user's device, making them accessible to the user.

[0099] This invention implements a system to support a user's mental health in the following way: The server collects data such as the user's electronic transaction history and preprocesses it into an analyzable format. This preprocessing includes data cleaning, anonymization, and conversion to an appropriate format. Next, the server trains an artificial intelligence model on the preprocessed data. This model evaluates the user's psychological state based on the collected information and generates appropriate support content.

[0100] Users provide consultations and data through their devices. The devices are equipped with an interface that allows users to easily input their mental health-related concerns, and the information is transmitted anonymously. When a consultation is sent, the server receives the content, analyzes it using a generative AI model, and provides appropriate support.

[0101] The generated support content will be displayed on the user's device. This device will provide relaxation techniques, suggestions for psychological support, and links to counseling services, which the user can utilize.

[0102] For example, if a user reports an increase in their recent purchase frequency, the system might suggest stress reduction by displaying support such as, "As a long-term stress relief method, why not try some simple yoga at home?" This allows users to improve their mental health in a sustainable way.

[0103] An example of a prompt sentence input to a generative AI model is, "Please suggest stress reduction recommendations for users whose purchase frequency has recently increased." Based on this prompt sentence, the generative AI model generates optimal advice from past data.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects users' electronic transaction history and related data in real time. The input is the user's purchase history data. Based on this, the data is cleaned and anonymized, and converted into an analyzable format. This output data is an anonymized, clean transaction record.

[0107] Step 2:

[0108] The server trains a generative AI model using pre-processed data. The input is the anonymized transaction records obtained in step 1. This data is fed to the generative AI model to learn the user's psychological patterns. The model's output is an analysis of the user's stress level and purchasing patterns.

[0109] Step 3:

[0110] Users input and submit mental health-related consultations via their devices. The input includes the user's consultation topic and current emotional state. The device uses an API to collect this information and send it to the server. The output is consultation data for analysis, which is then passed to the server.

[0111] Step 4:

[0112] The server analyzes the consultation content sent from the terminal using a generation AI model. The input is the user's consultation data. The server inputs this data, along with prompts, into the model and generates appropriate support content. The output is specific support content to be provided to the user.

[0113] Step 5:

[0114] The terminal displays the support information provided by the server to the user. The input is the support information generated in step 4. Advice and resource links are presented through the screen interface. The user can use this to improve their mental health. The output is support information visually presented to the user.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] This invention relates to a system that combines emotional recognition with the mental health consultation process of a user. The system consists of four components: a server, a terminal, an emotion engine, and the user.

[0117] First, the server collects past consultation cases and reports from the company's database. The collected data is preprocessed, cleaned, and anonymized to be converted into an analyzable format. This data is also used as training data for the emotion engine.

[0118] Next, the server uses the pre-processed data to train the generative AI model and the emotion engine. The generative AI model utilizes natural language processing techniques to analyze the content of the consultation. The emotion engine analyzes the linguistic and non-linguistic features contained in the consultation content to recognize the user's emotions.

[0119] Users can anonymously seek advice on mental health issues using the terminal's interface. User input is sent to the server in a secure manner.

[0120] The submitted consultation content is analyzed by a server using a generative AI model and an emotion engine. The generative AI model understands the user's consultation and generates appropriate support content based on past cases. Meanwhile, the emotion engine identifies the user's emotional state and adjusts the support content accordingly.

[0121] For example, if a user posts a message on their device saying, "I've been feeling really down lately," the server can use an emotion engine to recognize the degree of the user's depression and provide specific support such as, "Try journaling to process your feelings, or we recommend counseling with a professional."

[0122] Finally, the terminal displays the generated support content to the user. In this way, the system can not only provide information but also offer personalized advice that takes into account the user's emotional state.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server automatically collects past consultation cases and reports from the database. This data forms the foundation for the system's learning process, organizing necessary information and preparing it for future analysis.

[0126] Step 2:

[0127] The server preprocesses the collected data. This preprocessing includes cleaning and anonymizing the data, and converting it into the format necessary for analysis and sentiment recognition.

[0128] Step 3:

[0129] The server uses pre-processed data to train a generative AI model and an emotion engine. The generative AI model uses natural language processing to analyze the content of the consultation, and the emotion engine is trained to recognize emotions from linguistic and non-linguistic features.

[0130] Step 4:

[0131] Users can use their devices to input and anonymously submit their mental health-related consultations. During this process, users can utilize the device's interface to ensure their privacy is protected while conducting their consultations.

[0132] Step 5:

[0133] The terminal sends the user's inputted consultation details to the server. For security reasons, the consultation details are encrypted before transmission.

[0134] Step 6:

[0135] The server analyzes the consultation content using a generative AI model and an emotion engine. The generative AI model understands the meaning of the consultation content and generates appropriate support from past data. The emotion engine recognizes and analyzes the user's emotional state.

[0136] Step 7:

[0137] The server adjusts the support content based on the emotional information recognized by the emotion engine. For example, if a user is experiencing high levels of stress, the server generates support content that includes specific advice and resources to alleviate that stress.

[0138] Step 8:

[0139] The terminal displays the support information received from the server to the user. The user can review the support information on the screen and ask additional questions if necessary. In this way, the system provides personalized support that takes the user's emotional state into consideration.

[0140] (Example 2)

[0141] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0142] In modern society, many people suffer from mental health issues, but often feel hesitant to consult a professional directly. Furthermore, systems that accurately understand emotions and provide personalized support quickly and anonymously are not yet fully established. This leads to challenges such as users being unable to access appropriate resources and methods for support, resulting in delays in improving their mental health.

[0143] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0144] In this invention, the server includes means for collecting information from a data set, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to recognize the user's emotions and provide appropriate support anonymously.

[0145] A "data set" is a collection of data selected as the target of information collection, and is used for training and analyzing machine learning models.

[0146] An "information input device" is a device used by users to anonymously provide information about their consultations, and includes devices such as computers and smartphones.

[0147] An "information display device" is a device for displaying analyzed results and generated support content to the user, and includes devices that perform screen display and audio output.

[0148] A "machine learning model" refers to an algorithm that analyzes consultation content based on collected data and generates appropriate support plans.

[0149] "Linguistic features" refer to the linguistic characteristics included in the consultation content, such as word choice, sentence structure, and emotional expression.

[0150] "Non-verbal characteristics" refer to information other than language, such as tone of voice, speed, and context, and are used to evaluate the user's emotions and intentions.

[0151] "Emotional state" is an assessment that indicates the user's mental and emotional condition, and is identified through the analysis of the consultation content.

[0152] This invention is a system for providing mental health consultations to users. The system mainly consists of a server, a terminal, an emotion processing engine, and the user.

[0153] The server is connected to multiple databases, from which it collects past consultation cases and reports. Here, data cleansing techniques are used to clean the data, and further anonymization is applied to convert it into an analyzable format while protecting personal information. This data is later used as a dataset for training an emotion processing engine.

[0154] The emotion processing engine is built using a generative AI model, which applies natural language processing technology. The server uses this AI model to analyze the natural language inquiries provided by the user and generates appropriate support content based on the results. It also understands the user's emotional state by analyzing the linguistic and nonverbal characteristics of the inquiry content.

[0155] Users can anonymously submit mental health consultations using their own devices. The devices transmit the submitted consultation content to the server based on advanced security protocols.

[0156] The server analyzes the consultation content it receives using a generative AI model and an emotion processing engine. The server generates support content based on past cases and can also adjust this content according to the user's emotional state.

[0157] The terminal serves to notify the user of the support provided by the server. For example, if a user provides a prompt message through the terminal such as "I've been feeling really down lately," the server will identify the emotional state and then offer specific advice such as "Try journaling to help you process your feelings."

[0158] This system is unique in that it not only provides information but also offers personalized support that takes into account the user's emotional state.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The server collects past consultation cases and reports from the company's database. It receives a large amount of raw data as input and generates cleaned, anonymized data as output. This process involves specific actions to transform the data into a usable format by removing unnecessary information using data cleansing techniques and anonymizing personal information.

[0162] Step 2:

[0163] The server trains a generative AI model using pre-processed data. Pre-processed, anonymized data is used as input, and a language model is learned as output. At this stage, machine learning algorithms are used to add natural language processing skills to the model. Specific actions include dataset splitting and setting up the training process.

[0164] Step 3:

[0165] The server trains an emotion processing engine. It uses data containing linguistic and non-linguistic features as input and generates an engine capable of recognizing emotional states as output. This involves specific actions to train the engine to understand the user's emotions by utilizing emotion analysis algorithms.

[0166] Step 4:

[0167] The user anonymously enters a question about mental health using the device. The input is prompted, and the information is sent to the server as output. This stage involves the user entering the question in natural language, and the device securely transferring it to the server.

[0168] Step 5:

[0169] The server analyzes the consultation content using a generative AI model. It receives prompt text from the user as input and generates analysis results and support content as output. Specifically, its operations include understanding the context of the consultation content using a language model and referencing similar cases.

[0170] Step 6:

[0171] The server analyzes the user's emotional state using an emotion processing engine and adjusts the support accordingly. It takes analyzed consultation content and emotional data as input and generates personalized advice as output. This includes taking into account the user's emotional state to provide appropriate responses.

[0172] Step 7:

[0173] The terminal presents the generated personalized advice to the user. It receives support information from the server as input and displays the information to the user as output. This process includes specific actions such as displaying information and collecting feedback via the user interface.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0176] It is necessary to provide a system that allows users to confidently seek advice on mental health issues and receive appropriate support tailored to their emotional state. Furthermore, a safe environment where users can seek advice anonymously is also essential.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, and means for training the data using an artificial intelligence model. This enables the provision of personalized support tailored to the user's emotional state and allows for secure, anonymous consultations.

[0179] "Means for collecting data" refers to technologies that systematically gather necessary information for analysis and learning by obtaining input and related information from users.

[0180] "Means of preprocessing and converting into an analyzable format" refers to techniques that include the process of cleaning and organizing collected data to optimize it so that artificial intelligence models can learn and analyze efficiently.

[0181] "Methods for training using artificial intelligence models" refers to the process of training AI algorithms to perform pattern recognition and inference by utilizing pre-processed data.

[0182] "Methods for receiving consultations from users using electronic devices" refers to technologies that use electronic devices such as smartphones and computers to receive consultations from users regarding their mental health through an interface.

[0183] "Means for analyzing consultations and generating appropriate support content" refers to technologies that analyze the content of users' consultations and generate optimal support and advice, utilizing natural language processing and AI technologies.

[0184] "Means for identifying emotional states and adjusting support accordingly" refers to technology that analyzes a user's emotions, determines the optimal support content based on those emotions, and provides it.

[0185] "Means of providing support content to users" refers to technologies that present the analyzed and generated support content to users in an easily understandable way, and are implemented through a user interface.

[0186] "Means to enable anonymous consultations" refer to technologies that allow users to consult with peace of mind while protecting their personal information, and include mechanisms to protect privacy.

[0187] This invention provides a system that combines emotion recognition with mental health consultations for users. This system is centered around a server, a terminal, and a user, each playing a specific role.

[0188] The server first cleans and preprocesses past consultation cases collected from the database into an analyzable format. The preprocessed data is used to train the generative AI model and the emotion engine. The generative AI model analyzes the consultation content using natural language processing techniques, and the emotion engine recognizes the user's emotional state by analyzing linguistic and nonverbal features.

[0189] The terminal serves to receive inquiries from users and securely transmits the information entered by the user to the server. Electronic devices are used in this process, and users can also submit inquiries anonymously.

[0190] The server analyzes the received consultation content and generates appropriate support content based on past cases using a generative AI model. Furthermore, an emotion engine identifies the user's emotional state and adjusts the support content accordingly.

[0191] Ultimately, the terminal presents the user with support content generated and adjusted by the server. This system allows users to receive information and advice optimized for their own emotional state.

[0192] For example, if a user inputs "I've been feeling stressed and worried lately," the AI ​​model can suggest relaxation music based on past examples. It can also recommend meditation techniques or counseling services depending on the user's emotional state.

[0193] An example of a prompt message might be: "User input: 'I've been feeling stressed and worried lately.' Please generate appropriate support suggestions."

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] Users input mental health-related consultations using their devices. The entered data is provided in text format and securely transmitted from the device to the server. This input represents the user's consultation content and serves as basic information for subsequent analysis.

[0197] Step 2:

[0198] The server first stores the received consultation details in a database. The stored data is then preprocessed to serve as input for the emotion engine and generative AI model. Preprocessing includes text cleaning and tokenization, which converts the data into a parseable format.

[0199] Step 3:

[0200] The server passes the pre-processed consultation content to the generative AI model. The generative AI model utilizes natural language processing technology to analyze the input text. During the analysis process, it searches for similar past cases and generates appropriate support suggestions based on them.

[0201] Step 4:

[0202] The server uses an emotion engine to identify the user's emotional state from their inquiry. This process analyzes both linguistic and non-linguistic features (e.g., emotional vocabulary in the text) to reveal the user's emotional state.

[0203] Step 5:

[0204] The server integrates the results of the generative AI model and the emotion engine, and adjusts the support content according to the user's emotional state. Specifically, the generated support suggestions are optimized for the user's identified emotional state.

[0205] Step 6:

[0206] The support information, adjusted on the server, is sent back to the terminal and presented to the user. The user can then view the generated personalized advice and information on their terminal. This allows the user to obtain specific techniques for stress reduction.

[0207] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0208] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0209] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0213] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0214] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0215] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0216] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0217] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0218] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0219] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0220] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0221] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0222] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0223] This invention relates to a system that allows users to easily seek mental health consultations and provides support content generated during those consultations. The system consists of three components: a server, a terminal, and a user.

[0224] First, the server collects historical data related to mental health. This data is retrieved from an internal database, and data preprocessing is performed based on the collected information. Data preprocessing involves cleaning, anonymizing, and converting the collected data to an appropriate format. This prepares the foundational data used for analysis in the system and for training artificial intelligence models.

[0225] Next, the server trains a generative AI model using the pre-processed data. This model is built to learn patterns based on information from past case studies and reports, and to automatically determine what kind of support to provide next.

[0226] On the other hand, users seek advice through their devices. These devices provide an interface for users to easily input their mental health concerns. Users can submit information anonymously, ensuring a privacy-protected environment.

[0227] When a consultation request is submitted, the server receives the content and analyzes it using a generation AI model. Based on the analysis results, support content is generated. This support content may include specific advice on the user's problem, resource recommendations, or suggestions for relaxation.

[0228] Finally, the device provides the generated support information to the user. Specifically, it can display advice and suggestions on the device screen and, if necessary, provide links to additional resources.

[0229] For example, if a user posts a message on their device saying they are "stressed at work," the server understands the message and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's counseling service." In this way, the generating AI utilizes insights gained from past data to enable personalized responses.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server collects past consultation cases and reports from the company's internal database. This data includes information related to mental health and will serve as the basis for training future analytical and generative AI models.

[0233] Step 2:

[0234] The server performs preprocessing to convert the collected data into a format that can be analyzed. At this stage, unnecessary spaces and special characters are removed as part of data cleaning, and personally identifiable information is anonymized.

[0235] Step 3:

[0236] The server trains a generative AI model using pre-processed data. Utilizing natural language processing techniques, the model learns from past cases to generate answers to similar inquiries.

[0237] Step 4:

[0238] Users enter their mental health concerns into the chat interface on their device. Users can submit their concerns anonymously and are assigned a unique session ID.

[0239] Step 5:

[0240] The terminal sends user input to the server. The transmitted data is encrypted to ensure security.

[0241] Step 6:

[0242] The server uses a generative AI model to analyze the user's inquiry. It identifies the user's emotions and stress levels in relation to the inquiry and initiates a process to generate appropriate support content.

[0243] Step 7:

[0244] Based on the analysis of the consultation content, the server generates support content that provides advice and resource suggestions tailored to the individual situation. Based on past data, it generates actionable and specific suggestions.

[0245] Step 8:

[0246] The terminal displays the generated support information to the user. The user can view advice and links to resources on the screen and ask additional questions.

[0247] (Example 1)

[0248] Next, we will describe Example 1. 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."

[0249] In modern society, the increasing number of individuals struggling with mental health issues is a growing concern. However, many people require consultations with professionals to receive appropriate support, which is often constrained by time and geographical limitations. Therefore, there is a growing need for a system that can provide convenient, rapid, and appropriate support tailored to individual needs.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes means for recording information, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to quickly process inquiries from users and provide appropriate support tailored to their individual needs.

[0252] "Means for recording information" refers to devices or methods that efficiently collect and store information and data within a system, such as databases and storage.

[0253] "Means for preprocessing the information and converting it into an analyzable format" refers to a method or apparatus for preparing collected data into a format suitable for machine learning and analysis through processes such as cleaning, anonymization, and format conversion.

[0254] "Means for training information using a machine learning model" refers to a method or apparatus for building a model to perform pattern recognition or prediction by applying a machine learning algorithm based on training data.

[0255] "Means for receiving inquiries from users" refers to a device or method that provides an interface for users to input questions or problems into the system and receives that data.

[0256] "Means for analyzing the inquiry and generating appropriate support content" refers to a method or apparatus for analyzing the content of a user's inquiry received and automatically devising corresponding advice or solutions.

[0257] "Means for communicating the support content to the user" refers to methods or devices that provide information in the form of screen displays, audio, etc., in order to convey the generated advice and support content to the user in an easy-to-understand manner.

[0258] This invention aims to realize a system that allows users to easily seek advice on mental health issues and receive appropriate support. The system mainly consists of a server, terminals, and users.

[0259] The server uses an internal database to collect historical mental health information and preprocesses it. This preprocessing involves cleaning, anonymizing, and formatting the data using programming languages ​​such as Python and R. This makes the data suitable for machine learning.

[0260] Subsequently, the server trains the generative AI model. TensorFlow and PyTorch are commonly used as machine learning libraries. During the training process, the model learns patterns using information from past cases and reports, and is built to automatically determine what support should be provided next.

[0261] Users enter their mental health consultation details via a terminal. This terminal provides a user-friendly interface, designed to allow users to easily enter their consultation details. The information transmitted is anonymous, protecting user privacy.

[0262] When the server receives a consultation request from a user, it analyzes the content using a generative AI model. Based on the analysis results, appropriate support content is generated. This support content includes specific advice and resource recommendations to address the user's concerns.

[0263] Ultimately, the device displays the generated support information to the user. For example, if a user consults the device saying, "I'm having trouble with stress at work," the server analyzes this information and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's support desk." In this way, AI can leverage insights gained from past data to provide personalized support.

[0264] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0265] Step 1:

[0266] The server retrieves historical mental health information from its internal database using queries. This input data includes raw historical cases and feedback. The server cleans this data, imputing missing values, removing outliers, and anonymizing it. The resulting clean data is then converted into a standardized format (e.g., a CSV file) and output as an analyzable dataset.

[0267] Step 2:

[0268] The server uses pre-processed data as input to train a generative AI model. This process involves using machine learning libraries (such as TensorFlow and PyTorch) to train the model to learn patterns from large amounts of data. The server evaluates the model's accuracy at each epoch and optimizes it by adjusting hyperparameters as needed. As a result, it outputs a trained model capable of determining what support should be provided next.

[0269] Step 3:

[0270] Users input their mental health concerns into the terminal's interface. This input data includes specific worries and situations. The terminal converts the user's input into an appropriate format and sends it to the server. This transmitted data is pre-validated to ensure the user's intent is clear before transmission.

[0271] Step 4:

[0272] The server receives user consultation data sent from the terminal and inputs it into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the consultation content and generate the most suitable support for the user. In this process, based on the input consultation data, it identifies problem-solving solutions and advice that match past patterns and generates specific suggestions as output.

[0273] Step 5:

[0274] The terminal provides the user with support information received from the server. Specifically, generated advice and instructions are displayed on the terminal's screen. Furthermore, links to relevant resources are provided as needed, allowing the user to obtain additional information. This displayed content is the final output, providing intuitive and useful information for the user.

[0275] (Application Example 1)

[0276] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0277] In modern society, individuals are increasingly experiencing psychological burdens in their daily lives, at work, and at home. Effective support measures are needed to properly manage and alleviate these psychological burdens. However, conventional methods struggle to provide specific support tailored to individual circumstances. Furthermore, the development of systems capable of understanding users' psychological states based on their electronic transaction activity and providing appropriate advice is still lacking, resulting in insufficient safe and anonymous mental health support.

[0278] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0279] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, means for training an artificial intelligence model on the data, and means for analyzing the electronic transaction summary and estimating psychological burden. This enables users to receive sustainable, personalized mental health support anonymously.

[0280] "Means for collecting data" refers to a system that has the function of systematically acquiring data about user information and activities.

[0281] The means for "preprocessing the data and converting it into an analyzable form" is a technology that cleans and anonymizes the collected data to prepare it for safe analysis.

[0282] The means for "training the data using an artificial intelligence model" is a process that operates a machine learning algorithm based on the collected and preprocessed data to automatically understand patterns and trends.

[0283] The means for "receiving consultations from users" is an interface for users to register their troubles and problems with the system and for the system to receive that information.

[0284] The means for "analyzing consultations and generating appropriate support content" is a process that analyzes the input information of users and provides appropriate advice and suggestions based on pre-learned patterns.

[0285] The means for "analyzing the outline of electronic transactions and inferring the psychological burden" is a technology for analyzing the form of a user's daily transactions and evaluating the predicted psychological state.

[0286] The means for "providing support content to users" is a mechanism for presenting the generated advice and resources to the user's device so that the user can access them.

[0287] In this invention, a system for supporting a user's mental health is implemented in the following manner. The server collects data such as the user's electronic transaction history and preprocesses it into an analyzable form. This preprocessing includes data cleaning, anonymization, and conversion into an appropriate format. Next, the server trains the preprocessed data using an artificial intelligence model. This model is for evaluating the user's psychological state based on the collected information and generating appropriate support content.

[0288] Users provide consultations and data through their devices. The devices are equipped with an interface that allows users to easily input their mental health-related concerns, and the information is transmitted anonymously. When a consultation is sent, the server receives the content, analyzes it using a generative AI model, and provides appropriate support.

[0289] The generated support content will be displayed on the user's device. This device will provide relaxation techniques, suggestions for psychological support, and links to counseling services, which the user can utilize.

[0290] For example, if a user reports an increase in their recent purchase frequency, the system might suggest stress reduction by displaying support such as, "As a long-term stress relief method, why not try some simple yoga at home?" This allows users to improve their mental health in a sustainable way.

[0291] An example of a prompt sentence input to a generative AI model is, "Please suggest stress reduction recommendations for users whose purchase frequency has recently increased." Based on this prompt sentence, the generative AI model generates optimal advice from past data.

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The server collects users' electronic transaction history and related data in real time. The input is the user's purchase history data. Based on this, the data is cleaned and anonymized, and converted into an analyzable format. This output data is an anonymized, clean transaction record.

[0295] Step 2:

[0296] The server trains a generative AI model using pre-processed data. The input is the anonymized transaction records obtained in step 1. This data is fed to the generative AI model to learn the user's psychological patterns. The model's output is an analysis of the user's stress level and purchasing patterns.

[0297] Step 3:

[0298] Users input and submit mental health-related consultations via their devices. The input includes the user's consultation topic and current emotional state. The device uses an API to collect this information and send it to the server. The output is consultation data for analysis, which is then passed to the server.

[0299] Step 4:

[0300] The server analyzes the consultation content sent from the terminal using a generation AI model. The input is the user's consultation data. The server inputs this data, along with prompts, into the model and generates appropriate support content. The output is specific support content to be provided to the user.

[0301] Step 5:

[0302] The terminal displays the support information provided by the server to the user. The input is the support information generated in step 4. Advice and resource links are presented through the screen interface. The user can use this to improve their mental health. The output is support information visually presented to the user.

[0303] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0304] The present invention relates to a system that combines emotion recognition when a user consults about mental health. This system is composed of four entities: a server, a terminal, an emotion engine, and a user.

[0305] First, the server collects past consultation cases and reports from the enterprise's database. The collected data is preprocessed, cleaned, anonymized, and converted into an analyzable format. This data is also utilized as learning data for the emotion engine.

[0306] Next, the server uses the preprocessed data to train a generative AI model and an emotion engine. The generative AI model utilizes natural language processing technology to analyze the consultation content. The emotion engine analyzes the linguistic and non-linguistic features contained in the consultation content to recognize the user's emotions.

[0307] The user can anonymously conduct consultations about mental health using the terminal interface. The input from the user is sent to the server in a secure manner.

[0308] The transmitted consultation content is analyzed by the generative AI model and the emotion engine on the server. The generative AI model understands the user's consultation and generates appropriate support content based on past cases. On the other hand, the emotion engine identifies the user's emotional state and adjusts the support content according to that state.

[0309] For example, when a user consults on the terminal saying "Recently, I've been feeling extremely depressed," the server can use the emotion engine to recognize the degree of the user's depression and provide specific support such as "Try journaling to organize your thoughts or I recommend counseling with a professional."

[0310] Finally, the terminal displays the generated support content to the user. In this way, the system can not only provide information but also offer personalized advice that takes into account the user's emotional state.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The server automatically collects past consultation cases and reports from the database. This data forms the foundation for the system's learning process, organizing necessary information and preparing it for future analysis.

[0314] Step 2:

[0315] The server preprocesses the collected data. This preprocessing includes cleaning and anonymizing the data, and converting it into the format necessary for analysis and sentiment recognition.

[0316] Step 3:

[0317] The server uses pre-processed data to train a generative AI model and an emotion engine. The generative AI model uses natural language processing to analyze the content of the consultation, and the emotion engine is trained to recognize emotions from linguistic and non-linguistic features.

[0318] Step 4:

[0319] Users can use their devices to input and anonymously submit their mental health-related consultations. During this process, users can utilize the device's interface to ensure their privacy is protected while conducting their consultations.

[0320] Step 5:

[0321] The terminal sends the user's inputted consultation details to the server. For security reasons, the consultation details are encrypted before transmission.

[0322] Step 6:

[0323] The server analyzes the consultation content using a generative AI model and an emotion engine. The generative AI model understands the meaning of the consultation content and generates appropriate support from past data. The emotion engine recognizes and analyzes the user's emotional state.

[0324] Step 7:

[0325] The server adjusts the support content based on the emotional information recognized by the emotion engine. For example, if a user is experiencing high levels of stress, the server generates support content that includes specific advice and resources to alleviate that stress.

[0326] Step 8:

[0327] The terminal displays the support information received from the server to the user. The user can review the support information on the screen and ask additional questions if necessary. In this way, the system provides personalized support that takes the user's emotional state into consideration.

[0328] (Example 2)

[0329] Next, we will describe Example 2. 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".

[0330] In modern society, many people suffer from mental health issues, but often feel hesitant to consult a professional directly. Furthermore, systems that accurately understand emotions and provide personalized support quickly and anonymously are not yet fully established. This leads to challenges such as users being unable to access appropriate resources and methods for support, resulting in delays in improving their mental health.

[0331] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0332] In this invention, the server includes means for collecting information from a data set, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to recognize the user's emotions and provide appropriate support anonymously.

[0333] A "data set" is a collection of data selected as the target of information collection, and is used for training and analyzing machine learning models.

[0334] An "information input device" is a device used by users to anonymously provide information about their consultations, and includes devices such as computers and smartphones.

[0335] An "information display device" is a device for displaying analyzed results and generated support content to the user, and includes devices that perform screen display and audio output.

[0336] A "machine learning model" refers to an algorithm that analyzes consultation content based on collected data and generates appropriate support plans.

[0337] "Linguistic features" refer to the linguistic characteristics included in the consultation content, such as word choice, sentence structure, and emotional expression.

[0338] "Non-verbal characteristics" refer to information other than language, such as tone of voice, speed, and context, and are used to evaluate the user's emotions and intentions.

[0339] "Emotional state" is an assessment that indicates the user's mental and emotional condition, and is identified through the analysis of the consultation content.

[0340] This invention is a system for providing mental health consultations to users. The system mainly consists of a server, a terminal, an emotion processing engine, and the user.

[0341] The server is connected to multiple databases, from which it collects past consultation cases and reports. Here, data cleansing techniques are used to clean the data, and further anonymization is applied to convert it into an analyzable format while protecting personal information. This data is later used as a dataset for training an emotion processing engine.

[0342] The emotion processing engine is built using a generative AI model, which applies natural language processing technology. The server uses this AI model to analyze the natural language inquiries provided by the user and generates appropriate support content based on the results. It also understands the user's emotional state by analyzing the linguistic and nonverbal characteristics of the inquiry content.

[0343] Users can anonymously submit mental health consultations using their own devices. The devices transmit the submitted consultation content to the server based on advanced security protocols.

[0344] The server analyzes the consultation content it receives using a generative AI model and an emotion processing engine. The server generates support content based on past cases and can also adjust this content according to the user's emotional state.

[0345] The terminal serves to notify the user of the support provided by the server. For example, if a user provides a prompt message through the terminal such as "I've been feeling really down lately," the server will identify the emotional state and then offer specific advice such as "Try journaling to help you process your feelings."

[0346] This system is unique in that it not only provides information but also offers personalized support that takes into account the user's emotional state.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The server collects past consultation cases and reports from the company's database. It receives a large amount of raw data as input and generates cleaned, anonymized data as output. This process involves specific actions to transform the data into a usable format by removing unnecessary information using data cleansing techniques and anonymizing personal information.

[0350] Step 2:

[0351] The server trains a generative AI model using pre-processed data. Pre-processed, anonymized data is used as input, and a language model is learned as output. At this stage, machine learning algorithms are used to add natural language processing skills to the model. Specific actions include dataset splitting and setting up the training process.

[0352] Step 3:

[0353] The server trains an emotion processing engine. It uses data containing linguistic and non-linguistic features as input and generates an engine capable of recognizing emotional states as output. This involves specific actions to train the engine to understand the user's emotions by utilizing emotion analysis algorithms.

[0354] Step 4:

[0355] The user anonymously enters a question about mental health using the device. The input is prompted, and the information is sent to the server as output. This stage involves the user entering the question in natural language, and the device securely transferring it to the server.

[0356] Step 5:

[0357] The server analyzes the consultation content using a generative AI model. It receives prompt text from the user as input and generates analysis results and support content as output. Specifically, its operations include understanding the context of the consultation content using a language model and referencing similar cases.

[0358] Step 6:

[0359] The server analyzes the user's emotional state using an emotion processing engine and adjusts the support accordingly. It takes analyzed consultation content and emotional data as input and generates personalized advice as output. This includes taking into account the user's emotional state to provide appropriate responses.

[0360] Step 7:

[0361] The terminal presents the generated personalized advice to the user. It receives support information from the server as input and displays the information to the user as output. This process includes specific actions such as displaying information and collecting feedback via the user interface.

[0362] (Application Example 2)

[0363] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0364] It is necessary to provide a system that allows users to confidently seek advice on mental health issues and receive appropriate support tailored to their emotional state. Furthermore, a safe environment where users can seek advice anonymously is also essential.

[0365] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0366] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, and means for training the data using an artificial intelligence model. This enables the provision of personalized support tailored to the user's emotional state and allows for secure, anonymous consultations.

[0367] "Means for collecting data" refers to technologies that systematically gather necessary information for analysis and learning by obtaining input and related information from users.

[0368] "Means of preprocessing and converting into an analyzable format" refers to techniques that include the process of cleaning and organizing collected data to optimize it so that artificial intelligence models can learn and analyze efficiently.

[0369] "Methods for training using artificial intelligence models" refers to the process of training AI algorithms to perform pattern recognition and inference by utilizing pre-processed data.

[0370] "Methods for receiving consultations from users using electronic devices" refers to technologies that use electronic devices such as smartphones and computers to receive consultations from users regarding their mental health through an interface.

[0371] "Means for analyzing consultations and generating appropriate support content" refers to technologies that analyze the content of users' consultations and generate optimal support and advice, utilizing natural language processing and AI technologies.

[0372] "Means for identifying emotional states and adjusting support accordingly" refers to technology that analyzes a user's emotions, determines the optimal support content based on those emotions, and provides it.

[0373] "Means of providing support content to users" refers to technologies that present the analyzed and generated support content to users in an easily understandable way, and are implemented through a user interface.

[0374] "Means to enable anonymous consultations" refer to technologies that allow users to consult with peace of mind while protecting their personal information, and include mechanisms to protect privacy.

[0375] This invention provides a system that combines emotion recognition with mental health consultations for users. This system is centered around a server, a terminal, and a user, each playing a specific role.

[0376] The server first cleans and preprocesses past consultation cases collected from the database into an analyzable format. The preprocessed data is used to train the generative AI model and the emotion engine. The generative AI model analyzes the consultation content using natural language processing techniques, and the emotion engine recognizes the user's emotional state by analyzing linguistic and nonverbal features.

[0377] The terminal serves to receive inquiries from users and securely transmits the information entered by the user to the server. Electronic devices are used in this process, and users can also submit inquiries anonymously.

[0378] The server analyzes the received consultation content and generates appropriate support content based on past cases using a generative AI model. Furthermore, an emotion engine identifies the user's emotional state and adjusts the support content accordingly.

[0379] Ultimately, the terminal presents the user with support content generated and adjusted by the server. This system allows users to receive information and advice optimized for their own emotional state.

[0380] For example, if a user inputs "I've been feeling stressed and worried lately," the AI ​​model can suggest relaxation music based on past examples. It can also recommend meditation techniques or counseling services depending on the user's emotional state.

[0381] An example of a prompt message might be: "User input: 'I've been feeling stressed and worried lately.' Please generate appropriate support suggestions."

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] Users input mental health-related consultations using their devices. The entered data is provided in text format and securely transmitted from the device to the server. This input represents the user's consultation content and serves as basic information for subsequent analysis.

[0385] Step 2:

[0386] The server first stores the received consultation details in a database. The stored data is then preprocessed to serve as input for the emotion engine and generative AI model. Preprocessing includes text cleaning and tokenization, which converts the data into a parseable format.

[0387] Step 3:

[0388] The server passes the pre-processed consultation content to the generative AI model. The generative AI model utilizes natural language processing technology to analyze the input text. During the analysis process, it searches for similar past cases and generates appropriate support suggestions based on them.

[0389] Step 4:

[0390] The server uses an emotion engine to identify the user's emotional state from their inquiry. This process analyzes both linguistic and non-linguistic features (e.g., emotional vocabulary in the text) to reveal the user's emotional state.

[0391] Step 5:

[0392] The server integrates the results of the generative AI model and the emotion engine, and adjusts the support content according to the user's emotional state. Specifically, the generated support suggestions are optimized for the user's identified emotional state.

[0393] Step 6:

[0394] The support information, adjusted on the server, is sent back to the terminal and presented to the user. The user can then view the generated personalized advice and information on their terminal. This allows the user to obtain specific techniques for stress reduction.

[0395] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0396] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0397] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0398] [Third Embodiment]

[0399] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0400] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0401] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0402] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0403] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0404] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0405] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0406] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0407] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0408] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0409] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0410] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0411] This invention relates to a system that allows users to easily seek mental health consultations and provides support content generated during those consultations. The system consists of three components: a server, a terminal, and a user.

[0412] First, the server collects historical data related to mental health. This data is retrieved from an internal database, and data preprocessing is performed based on the collected information. Data preprocessing involves cleaning, anonymizing, and converting the collected data to an appropriate format. This prepares the foundational data used for analysis in the system and for training artificial intelligence models.

[0413] Next, the server trains a generative AI model using the pre-processed data. This model is built to learn patterns based on information from past case studies and reports, and to automatically determine what kind of support to provide next.

[0414] On the other hand, users seek advice through their devices. These devices provide an interface for users to easily input their mental health concerns. Users can submit information anonymously, ensuring a privacy-protected environment.

[0415] When a consultation request is submitted, the server receives the content and analyzes it using a generation AI model. Based on the analysis results, support content is generated. This support content may include specific advice on the user's problem, resource recommendations, or suggestions for relaxation.

[0416] Finally, the device provides the generated support information to the user. Specifically, it can display advice and suggestions on the device screen and, if necessary, provide links to additional resources.

[0417] For example, if a user posts a message on their device saying they are "stressed at work," the server understands the message and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's counseling service." In this way, the generating AI utilizes insights gained from past data to enable personalized responses.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] The server collects past consultation cases and reports from the company's internal database. This data includes information related to mental health and will serve as the basis for training future analytical and generative AI models.

[0421] Step 2:

[0422] The server performs preprocessing to convert the collected data into a format that can be analyzed. At this stage, unnecessary spaces and special characters are removed as part of data cleaning, and personally identifiable information is anonymized.

[0423] Step 3:

[0424] The server trains a generative AI model using pre-processed data. Utilizing natural language processing techniques, the model learns from past cases to generate answers to similar inquiries.

[0425] Step 4:

[0426] Users enter their mental health concerns into the chat interface on their device. Users can submit their concerns anonymously and are assigned a unique session ID.

[0427] Step 5:

[0428] The terminal sends user input to the server. The transmitted data is encrypted to ensure security.

[0429] Step 6:

[0430] The server uses a generative AI model to analyze the user's inquiry. It identifies the user's emotions and stress levels in relation to the inquiry and initiates a process to generate appropriate support content.

[0431] Step 7:

[0432] Based on the analysis of the consultation content, the server generates support content that provides advice and resource suggestions tailored to the individual situation. Based on past data, it generates actionable and specific suggestions.

[0433] Step 8:

[0434] The terminal displays the generated support information to the user. The user can view advice and links to resources on the screen and ask additional questions.

[0435] (Example 1)

[0436] Next, we will describe Example 1. 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."

[0437] In modern society, the increasing number of individuals struggling with mental health issues is a growing concern. However, many people require consultations with professionals to receive appropriate support, which is often constrained by time and geographical limitations. Therefore, there is a growing need for a system that can provide convenient, rapid, and appropriate support tailored to individual needs.

[0438] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0439] In this invention, the server includes means for recording information, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to quickly process inquiries from users and provide appropriate support tailored to their individual needs.

[0440] "Means for recording information" refers to devices or methods that efficiently collect and store information and data within a system, such as databases and storage.

[0441] "Means for preprocessing the information and converting it into an analyzable format" refers to a method or apparatus for preparing collected data into a format suitable for machine learning and analysis through processes such as cleaning, anonymization, and format conversion.

[0442] "Means for training information using a machine learning model" refers to a method or apparatus for building a model to perform pattern recognition or prediction by applying a machine learning algorithm based on training data.

[0443] "Means for receiving inquiries from users" refers to a device or method that provides an interface for users to input questions or problems into the system and receives that data.

[0444] "Means for analyzing the inquiry and generating appropriate support content" refers to a method or apparatus for analyzing the content of a user's inquiry received and automatically devising corresponding advice or solutions.

[0445] "Means for communicating the support content to the user" refers to methods or devices that provide information in the form of screen displays, audio, etc., in order to convey the generated advice and support content to the user in an easy-to-understand manner.

[0446] This invention aims to realize a system that allows users to easily seek advice on mental health issues and receive appropriate support. The system mainly consists of a server, terminals, and users.

[0447] The server uses an internal database to collect historical mental health information and preprocesses it. This preprocessing involves cleaning, anonymizing, and formatting the data using programming languages ​​such as Python and R. This makes the data suitable for machine learning.

[0448] Subsequently, the server trains the generative AI model. TensorFlow and PyTorch are commonly used as machine learning libraries. During the training process, the model learns patterns using information from past cases and reports, and is built to automatically determine what support should be provided next.

[0449] Users enter their mental health consultation details via a terminal. This terminal provides a user-friendly interface, designed to allow users to easily enter their consultation details. The information transmitted is anonymous, protecting user privacy.

[0450] When the server receives a consultation request from a user, it analyzes the content using a generative AI model. Based on the analysis results, appropriate support content is generated. This support content includes specific advice and resource recommendations to address the user's concerns.

[0451] Ultimately, the device displays the generated support information to the user. For example, if a user consults the device saying, "I'm having trouble with stress at work," the server analyzes this information and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's support desk." In this way, AI can leverage insights gained from past data to provide personalized support.

[0452] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0453] Step 1:

[0454] The server retrieves historical mental health information from its internal database using queries. This input data includes raw historical cases and feedback. The server cleans this data, imputing missing values, removing outliers, and anonymizing it. The resulting clean data is then converted into a standardized format (e.g., a CSV file) and output as an analyzable dataset.

[0455] Step 2:

[0456] The server uses pre-processed data as input to train a generative AI model. This process involves using machine learning libraries (such as TensorFlow and PyTorch) to train the model to learn patterns from large amounts of data. The server evaluates the model's accuracy at each epoch and optimizes it by adjusting hyperparameters as needed. As a result, it outputs a trained model capable of determining what support should be provided next.

[0457] Step 3:

[0458] Users input their mental health concerns into the terminal's interface. This input data includes specific worries and situations. The terminal converts the user's input into an appropriate format and sends it to the server. This transmitted data is pre-validated to ensure the user's intent is clear before transmission.

[0459] Step 4:

[0460] The server receives user consultation data sent from the terminal and inputs it into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the consultation content and generate the most suitable support for the user. In this process, based on the input consultation data, it identifies problem-solving solutions and advice that match past patterns and generates specific suggestions as output.

[0461] Step 5:

[0462] The terminal provides the user with support information received from the server. Specifically, generated advice and instructions are displayed on the terminal's screen. Furthermore, links to relevant resources are provided as needed, allowing the user to obtain additional information. This displayed content is the final output, providing intuitive and useful information for the user.

[0463] (Application Example 1)

[0464] Next, we will explain Application Example 1. In the following explanation, 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."

[0465] In modern society, individuals are increasingly experiencing psychological burdens in their daily lives, at work, and at home. Effective support measures are needed to properly manage and alleviate these psychological burdens. However, conventional methods struggle to provide specific support tailored to individual circumstances. Furthermore, the development of systems capable of understanding users' psychological states based on their electronic transaction activity and providing appropriate advice is still lacking, resulting in insufficient safe and anonymous mental health support.

[0466] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0467] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, means for training an artificial intelligence model on the data, and means for analyzing the electronic transaction summary and estimating psychological burden. This enables users to receive sustainable, personalized mental health support anonymously.

[0468] "Means for collecting data" refers to a system that has the function of systematically acquiring data about user information and activities.

[0469] "Means for preprocessing the data and converting it into an analyzable format" refers to techniques that clean and anonymize the collected data to prepare it for safe analysis.

[0470] "Means of training the data using an artificial intelligence model" refers to the process of running a machine learning algorithm based on collected and pre-processed data to automatically understand patterns and trends.

[0471] "A means of receiving inquiries from users" refers to an interface through which users register their worries and problems in the system, and the system receives that information.

[0472] "A means of analyzing consultations and generating appropriate support content" refers to a process that analyzes user input information and provides appropriate advice and suggestions based on pre-learned patterns.

[0473] "Methods for analyzing electronic transaction summaries and inferring psychological burden" refers to technologies for analyzing users' daily transaction patterns and evaluating the psychological state predicted therefrom.

[0474] "Means of providing support to users" refers to mechanisms for presenting generated advice and resources on the user's device, making them accessible to the user.

[0475] This invention implements a system to support a user's mental health in the following way: The server collects data such as the user's electronic transaction history and preprocesses it into an analyzable format. This preprocessing includes data cleaning, anonymization, and conversion to an appropriate format. Next, the server trains an artificial intelligence model on the preprocessed data. This model evaluates the user's psychological state based on the collected information and generates appropriate support content.

[0476] Users provide consultations and data through their devices. The devices are equipped with an interface that allows users to easily input their mental health-related concerns, and the information is transmitted anonymously. When a consultation is sent, the server receives the content, analyzes it using a generative AI model, and provides appropriate support.

[0477] The generated support content will be displayed on the user's device. This device will provide relaxation techniques, suggestions for psychological support, and links to counseling services, which the user can utilize.

[0478] For example, if a user reports an increase in their recent purchase frequency, the system might suggest stress reduction by displaying support such as, "As a long-term stress relief method, why not try some simple yoga at home?" This allows users to improve their mental health in a sustainable way.

[0479] An example of a prompt sentence input to a generative AI model is, "Please suggest stress reduction recommendations for users whose purchase frequency has recently increased." Based on this prompt sentence, the generative AI model generates optimal advice from past data.

[0480] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0481] Step 1:

[0482] The server collects users' electronic transaction history and related data in real time. The input is the user's purchase history data. Based on this, the data is cleaned and anonymized, and converted into an analyzable format. This output data is an anonymized, clean transaction record.

[0483] Step 2:

[0484] The server trains a generative AI model using pre-processed data. The input is the anonymized transaction records obtained in step 1. This data is fed to the generative AI model to learn the user's psychological patterns. The model's output is an analysis of the user's stress level and purchasing patterns.

[0485] Step 3:

[0486] Users input and submit mental health-related consultations via their devices. The input includes the user's consultation topic and current emotional state. The device uses an API to collect this information and send it to the server. The output is consultation data for analysis, which is then passed to the server.

[0487] Step 4:

[0488] The server analyzes the consultation content sent from the terminal using a generation AI model. The input is the user's consultation data. The server inputs this data, along with prompts, into the model and generates appropriate support content. The output is specific support content to be provided to the user.

[0489] Step 5:

[0490] The terminal displays the support information provided by the server to the user. The input is the support information generated in step 4. Advice and resource links are presented through the screen interface. The user can use this to improve their mental health. The output is support information visually presented to the user.

[0491] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0492] This invention relates to a system that combines emotional recognition with the mental health consultation process of a user. The system consists of four components: a server, a terminal, an emotion engine, and the user.

[0493] First, the server collects past consultation cases and reports from the company's database. The collected data is preprocessed, cleaned, and anonymized to be converted into an analyzable format. This data is also used as training data for the emotion engine.

[0494] Next, the server uses the pre-processed data to train the generative AI model and the emotion engine. The generative AI model utilizes natural language processing techniques to analyze the content of the consultation. The emotion engine analyzes the linguistic and non-linguistic features contained in the consultation content to recognize the user's emotions.

[0495] Users can anonymously seek advice on mental health issues using the terminal's interface. User input is sent to the server in a secure manner.

[0496] The submitted consultation content is analyzed by a server using a generative AI model and an emotion engine. The generative AI model understands the user's consultation and generates appropriate support content based on past cases. Meanwhile, the emotion engine identifies the user's emotional state and adjusts the support content accordingly.

[0497] For example, if a user posts a message on their device saying, "I've been feeling really down lately," the server can use an emotion engine to recognize the degree of the user's depression and provide specific support such as, "Try journaling to process your feelings, or we recommend counseling with a professional."

[0498] Finally, the terminal displays the generated support content to the user. In this way, the system can not only provide information but also offer personalized advice that takes into account the user's emotional state.

[0499] The following describes the processing flow.

[0500] Step 1:

[0501] The server automatically collects past consultation cases and reports from the database. This data forms the foundation for the system's learning process, organizing necessary information and preparing it for future analysis.

[0502] Step 2:

[0503] The server preprocesses the collected data. This preprocessing includes cleaning and anonymizing the data, and converting it into the format necessary for analysis and sentiment recognition.

[0504] Step 3:

[0505] The server uses pre-processed data to train a generative AI model and an emotion engine. The generative AI model uses natural language processing to analyze the content of the consultation, and the emotion engine is trained to recognize emotions from linguistic and non-linguistic features.

[0506] Step 4:

[0507] Users can use their devices to input and anonymously submit their mental health-related consultations. During this process, users can utilize the device's interface to ensure their privacy is protected while conducting their consultations.

[0508] Step 5:

[0509] The terminal sends the user's inputted consultation details to the server. For security reasons, the consultation details are encrypted before transmission.

[0510] Step 6:

[0511] The server analyzes the consultation content using a generative AI model and an emotion engine. The generative AI model understands the meaning of the consultation content and generates appropriate support from past data. The emotion engine recognizes and analyzes the user's emotional state.

[0512] Step 7:

[0513] The server adjusts the support content based on the emotional information recognized by the emotion engine. For example, if a user is experiencing high levels of stress, the server generates support content that includes specific advice and resources to alleviate that stress.

[0514] Step 8:

[0515] The terminal displays the support information received from the server to the user. The user can review the support information on the screen and ask additional questions if necessary. In this way, the system provides personalized support that takes the user's emotional state into consideration.

[0516] (Example 2)

[0517] Next, we will describe Example 2. 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."

[0518] In modern society, many people suffer from mental health issues, but often feel hesitant to consult a professional directly. Furthermore, systems that accurately understand emotions and provide personalized support quickly and anonymously are not yet fully established. This leads to challenges such as users being unable to access appropriate resources and methods for support, resulting in delays in improving their mental health.

[0519] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0520] In this invention, the server includes means for collecting information from a data set, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to recognize the user's emotions and provide appropriate support anonymously.

[0521] A "data set" is a collection of data selected as the target of information collection, and is used for training and analyzing machine learning models.

[0522] An "information input device" is a device used by users to anonymously provide information about their consultations, and includes devices such as computers and smartphones.

[0523] An "information display device" is a device for displaying analyzed results and generated support content to the user, and includes devices that perform screen display and audio output.

[0524] A "machine learning model" refers to an algorithm that analyzes consultation content based on collected data and generates appropriate support plans.

[0525] "Linguistic features" refer to the linguistic characteristics included in the consultation content, such as word choice, sentence structure, and emotional expression.

[0526] "Non-verbal characteristics" refer to information other than language, such as tone of voice, speed, and context, and are used to evaluate the user's emotions and intentions.

[0527] "Emotional state" is an assessment that indicates the user's mental and emotional condition, and is identified through the analysis of the consultation content.

[0528] This invention is a system for providing mental health consultations to users. The system mainly consists of a server, a terminal, an emotion processing engine, and the user.

[0529] The server is connected to multiple databases, from which it collects past consultation cases and reports. Here, data cleansing techniques are used to clean the data, and further anonymization is applied to convert it into an analyzable format while protecting personal information. This data is later used as a dataset for training an emotion processing engine.

[0530] The emotion processing engine is built using a generative AI model, which applies natural language processing technology. The server uses this AI model to analyze the natural language inquiries provided by the user and generates appropriate support content based on the results. It also understands the user's emotional state by analyzing the linguistic and nonverbal characteristics of the inquiry content.

[0531] Users can anonymously submit mental health consultations using their own devices. The devices transmit the submitted consultation content to the server based on advanced security protocols.

[0532] The server analyzes the consultation content it receives using a generative AI model and an emotion processing engine. The server generates support content based on past cases and can also adjust this content according to the user's emotional state.

[0533] The terminal serves to notify the user of the support provided by the server. For example, if a user provides a prompt message through the terminal such as "I've been feeling really down lately," the server will identify the emotional state and then offer specific advice such as "Try journaling to help you process your feelings."

[0534] This system is unique in that it not only provides information but also offers personalized support that takes into account the user's emotional state.

[0535] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0536] Step 1:

[0537] The server collects past consultation cases and reports from the company's database. It receives a large amount of raw data as input and generates cleaned, anonymized data as output. This process involves specific actions to transform the data into a usable format by removing unnecessary information using data cleansing techniques and anonymizing personal information.

[0538] Step 2:

[0539] The server trains a generative AI model using pre-processed data. Pre-processed, anonymized data is used as input, and a language model is learned as output. At this stage, machine learning algorithms are used to add natural language processing skills to the model. Specific actions include dataset splitting and setting up the training process.

[0540] Step 3:

[0541] The server trains an emotion processing engine. It uses data containing linguistic and non-linguistic features as input and generates an engine capable of recognizing emotional states as output. This involves specific actions to train the engine to understand the user's emotions by utilizing emotion analysis algorithms.

[0542] Step 4:

[0543] The user anonymously enters a question about mental health using the device. The input is prompted, and the information is sent to the server as output. This stage involves the user entering the question in natural language, and the device securely transferring it to the server.

[0544] Step 5:

[0545] The server analyzes the consultation content using a generative AI model. It receives prompt text from the user as input and generates analysis results and support content as output. Specifically, its operations include understanding the context of the consultation content using a language model and referencing similar cases.

[0546] Step 6:

[0547] The server analyzes the user's emotional state using an emotion processing engine and adjusts the support accordingly. It takes analyzed consultation content and emotional data as input and generates personalized advice as output. This includes taking into account the user's emotional state to provide appropriate responses.

[0548] Step 7:

[0549] The terminal presents the generated personalized advice to the user. It receives support information from the server as input and displays the information to the user as output. This process includes specific actions such as displaying information and collecting feedback via the user interface.

[0550] (Application Example 2)

[0551] Next, we will explain Application Example 2. In the following explanation, 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."

[0552] It is necessary to provide a system that allows users to confidently seek advice on mental health issues and receive appropriate support tailored to their emotional state. Furthermore, a safe environment where users can seek advice anonymously is also essential.

[0553] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0554] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, and means for training the data using an artificial intelligence model. This enables the provision of personalized support tailored to the user's emotional state and allows for secure, anonymous consultations.

[0555] "Means for collecting data" refers to technologies that systematically gather necessary information for analysis and learning by obtaining input and related information from users.

[0556] "Means of preprocessing and converting into an analyzable format" refers to techniques that include the process of cleaning and organizing collected data to optimize it so that artificial intelligence models can learn and analyze efficiently.

[0557] "Methods for training using artificial intelligence models" refers to the process of training AI algorithms to perform pattern recognition and inference by utilizing pre-processed data.

[0558] "Methods for receiving consultations from users using electronic devices" refers to technologies that use electronic devices such as smartphones and computers to receive consultations from users regarding their mental health through an interface.

[0559] "Means for analyzing consultations and generating appropriate support content" refers to technologies that analyze the content of users' consultations and generate optimal support and advice, utilizing natural language processing and AI technologies.

[0560] "Means for identifying emotional states and adjusting support accordingly" refers to technology that analyzes a user's emotions, determines the optimal support content based on those emotions, and provides it.

[0561] "Means of providing support content to users" refers to technologies that present the analyzed and generated support content to users in an easily understandable way, and are implemented through a user interface.

[0562] "Means to enable anonymous consultations" refer to technologies that allow users to consult with peace of mind while protecting their personal information, and include mechanisms to protect privacy.

[0563] This invention provides a system that combines emotion recognition with mental health consultations for users. This system is centered around a server, a terminal, and a user, each playing a specific role.

[0564] The server first cleans and preprocesses past consultation cases collected from the database into an analyzable format. The preprocessed data is used to train the generative AI model and the emotion engine. The generative AI model analyzes the consultation content using natural language processing techniques, and the emotion engine recognizes the user's emotional state by analyzing linguistic and nonverbal features.

[0565] The terminal serves to receive inquiries from users and securely transmits the information entered by the user to the server. Electronic devices are used in this process, and users can also submit inquiries anonymously.

[0566] The server analyzes the received consultation content and generates appropriate support content based on past cases using a generative AI model. Furthermore, an emotion engine identifies the user's emotional state and adjusts the support content accordingly.

[0567] Ultimately, the terminal presents the user with support content generated and adjusted by the server. This system allows users to receive information and advice optimized for their own emotional state.

[0568] For example, if a user inputs "I've been feeling stressed and worried lately," the AI ​​model can suggest relaxation music based on past examples. It can also recommend meditation techniques or counseling services depending on the user's emotional state.

[0569] An example of a prompt message might be: "User input: 'I've been feeling stressed and worried lately.' Please generate appropriate support suggestions."

[0570] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0571] Step 1:

[0572] Users input mental health-related consultations using their devices. The entered data is provided in text format and securely transmitted from the device to the server. This input represents the user's consultation content and serves as basic information for subsequent analysis.

[0573] Step 2:

[0574] The server first stores the received consultation details in a database. The stored data is then preprocessed to serve as input for the emotion engine and generative AI model. Preprocessing includes text cleaning and tokenization, which converts the data into a parseable format.

[0575] Step 3:

[0576] The server passes the pre-processed consultation content to the generative AI model. The generative AI model utilizes natural language processing technology to analyze the input text. During the analysis process, it searches for similar past cases and generates appropriate support suggestions based on them.

[0577] Step 4:

[0578] The server uses an emotion engine to identify the user's emotional state from their inquiry. This process analyzes both linguistic and non-linguistic features (e.g., emotional vocabulary in the text) to reveal the user's emotional state.

[0579] Step 5:

[0580] The server integrates the results of the generative AI model and the emotion engine, and adjusts the support content according to the user's emotional state. Specifically, the generated support suggestions are optimized for the user's identified emotional state.

[0581] Step 6:

[0582] The support information, adjusted on the server, is sent back to the terminal and presented to the user. The user can then view the generated personalized advice and information on their terminal. This allows the user to obtain specific techniques for stress reduction.

[0583] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0584] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0585] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0586] [Fourth Embodiment]

[0587] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0588] As shown in Figure 7, the 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.

[0589] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0590] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0591] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0592] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0593] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0594] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0595] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0596] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0597] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0598] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0599] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0600] This invention relates to a system that allows users to easily seek mental health consultations and provides support content generated during those consultations. The system consists of three components: a server, a terminal, and a user.

[0601] First, the server collects historical data related to mental health. This data is retrieved from an internal database, and data preprocessing is performed based on the collected information. Data preprocessing involves cleaning, anonymizing, and converting the collected data to an appropriate format. This prepares the foundational data used for analysis in the system and for training artificial intelligence models.

[0602] Next, the server trains a generative AI model using the pre-processed data. This model is built to learn patterns based on information from past case studies and reports, and to automatically determine what kind of support to provide next.

[0603] On the other hand, users seek advice through their devices. These devices provide an interface for users to easily input their mental health concerns. Users can submit information anonymously, ensuring a privacy-protected environment.

[0604] When a consultation request is submitted, the server receives the content and analyzes it using a generation AI model. Based on the analysis results, support content is generated. This support content may include specific advice on the user's problem, resource recommendations, or suggestions for relaxation.

[0605] Finally, the device provides the generated support information to the user. Specifically, it can display advice and suggestions on the device screen and, if necessary, provide links to additional resources.

[0606] For example, if a user posts a message on their device saying they are "stressed at work," the server understands the message and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's counseling service." In this way, the generating AI utilizes insights gained from past data to enable personalized responses.

[0607] The following describes the processing flow.

[0608] Step 1:

[0609] The server collects past consultation cases and reports from the company's internal database. This data includes information related to mental health and will serve as the basis for training future analytical and generative AI models.

[0610] Step 2:

[0611] The server performs preprocessing to convert the collected data into a format that can be analyzed. At this stage, unnecessary spaces and special characters are removed as part of data cleaning, and personally identifiable information is anonymized.

[0612] Step 3:

[0613] The server trains a generative AI model using pre-processed data. Utilizing natural language processing techniques, the model learns from past cases to generate answers to similar inquiries.

[0614] Step 4:

[0615] Users enter their mental health concerns into the chat interface on their device. Users can submit their concerns anonymously and are assigned a unique session ID.

[0616] Step 5:

[0617] The terminal sends user input to the server. The transmitted data is encrypted to ensure security.

[0618] Step 6:

[0619] The server uses a generative AI model to analyze the user's inquiry. It identifies the user's emotions and stress levels in relation to the inquiry and initiates a process to generate appropriate support content.

[0620] Step 7:

[0621] Based on the analysis of the consultation content, the server generates support content that provides advice and resource suggestions tailored to the individual situation. Based on past data, it generates actionable and specific suggestions.

[0622] Step 8:

[0623] The terminal displays the generated support information to the user. The user can view advice and links to resources on the screen and ask additional questions.

[0624] (Example 1)

[0625] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0626] In modern society, the increasing number of individuals struggling with mental health issues is a growing concern. However, many people require consultations with professionals to receive appropriate support, which is often constrained by time and geographical limitations. Therefore, there is a growing need for a system that can provide convenient, rapid, and appropriate support tailored to individual needs.

[0627] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0628] In this invention, the server includes means for recording information, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to quickly process inquiries from users and provide appropriate support tailored to their individual needs.

[0629] "Means for recording information" refers to devices or methods that efficiently collect and store information and data within a system, such as databases and storage.

[0630] "Means for preprocessing the information and converting it into an analyzable format" refers to a method or apparatus for preparing collected data into a format suitable for machine learning and analysis through processes such as cleaning, anonymization, and format conversion.

[0631] "Means for training information using a machine learning model" refers to a method or apparatus for building a model to perform pattern recognition or prediction by applying a machine learning algorithm based on training data.

[0632] "Means for receiving inquiries from users" refers to a device or method that provides an interface for users to input questions or problems into the system and receives that data.

[0633] "Means for analyzing the inquiry and generating appropriate support content" refers to a method or apparatus for analyzing the content of a user's inquiry received and automatically devising corresponding advice or solutions.

[0634] "Means for communicating the support content to the user" refers to methods or devices that provide information in the form of screen displays, audio, etc., in order to convey the generated advice and support content to the user in an easy-to-understand manner.

[0635] This invention aims to realize a system that allows users to easily seek advice on mental health issues and receive appropriate support. The system mainly consists of a server, terminals, and users.

[0636] The server uses an internal database to collect historical mental health information and preprocesses it. This preprocessing involves cleaning, anonymizing, and formatting the data using programming languages ​​such as Python and R. This makes the data suitable for machine learning.

[0637] Subsequently, the server trains the generative AI model. TensorFlow and PyTorch are commonly used as machine learning libraries. During the training process, the model learns patterns using information from past cases and reports, and is built to automatically determine what support should be provided next.

[0638] Users enter their mental health consultation details via a terminal. This terminal provides a user-friendly interface, designed to allow users to easily enter their consultation details. The information transmitted is anonymous, protecting user privacy.

[0639] When the server receives a consultation request from a user, it analyzes the content using a generative AI model. Based on the analysis results, appropriate support content is generated. This support content includes specific advice and resource recommendations to address the user's concerns.

[0640] Ultimately, the device displays the generated support information to the user. For example, if a user consults the device saying, "I'm having trouble with stress at work," the server analyzes this information and provides specific advice such as, "Try regular short meditation sessions. We can also help you find a way to contact your workplace's support desk." In this way, AI can leverage insights gained from past data to provide personalized support.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1:

[0643] The server retrieves historical mental health information from its internal database using queries. This input data includes raw historical cases and feedback. The server cleans this data, imputing missing values, removing outliers, and anonymizing it. The resulting clean data is then converted into a standardized format (e.g., a CSV file) and output as an analyzable dataset.

[0644] Step 2:

[0645] The server uses pre-processed data as input to train a generative AI model. This process involves using machine learning libraries (such as TensorFlow and PyTorch) to train the model to learn patterns from large amounts of data. The server evaluates the model's accuracy at each epoch and optimizes it by adjusting hyperparameters as needed. As a result, it outputs a trained model capable of determining what support should be provided next.

[0646] Step 3:

[0647] Users input their mental health concerns into the terminal's interface. This input data includes specific worries and situations. The terminal converts the user's input into an appropriate format and sends it to the server. This transmitted data is pre-validated to ensure the user's intent is clear before transmission.

[0648] Step 4:

[0649] The server receives user consultation data sent from the terminal and inputs it into the AI ​​model. The AI ​​model uses natural language processing technology to analyze the consultation content and generate the most suitable support for the user. In this process, based on the input consultation data, it identifies problem-solving solutions and advice that match past patterns and generates specific suggestions as output.

[0650] Step 5:

[0651] The terminal provides the user with support information received from the server. Specifically, generated advice and instructions are displayed on the terminal's screen. Furthermore, links to relevant resources are provided as needed, allowing the user to obtain additional information. This displayed content is the final output, providing intuitive and useful information for the user.

[0652] (Application Example 1)

[0653] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0654] In modern society, individuals are increasingly experiencing psychological burdens in their daily lives, at work, and at home. Effective support measures are needed to properly manage and alleviate these psychological burdens. However, conventional methods struggle to provide specific support tailored to individual circumstances. Furthermore, the development of systems capable of understanding users' psychological states based on their electronic transaction activity and providing appropriate advice is still lacking, resulting in insufficient safe and anonymous mental health support.

[0655] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0656] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, means for training an artificial intelligence model on the data, and means for analyzing the electronic transaction summary and estimating psychological burden. This enables users to receive sustainable, personalized mental health support anonymously.

[0657] "Means for collecting data" refers to a system that has the function of systematically acquiring data about user information and activities.

[0658] "Means for preprocessing the data and converting it into an analyzable format" refers to techniques that clean and anonymize the collected data to prepare it for safe analysis.

[0659] "Means of training the data using an artificial intelligence model" refers to the process of running a machine learning algorithm based on collected and pre-processed data to automatically understand patterns and trends.

[0660] "A means of receiving inquiries from users" refers to an interface through which users register their worries and problems in the system, and the system receives that information.

[0661] "A means of analyzing consultations and generating appropriate support content" refers to a process that analyzes user input information and provides appropriate advice and suggestions based on pre-learned patterns.

[0662] "Methods for analyzing electronic transaction summaries and inferring psychological burden" refers to technologies for analyzing users' daily transaction patterns and evaluating the psychological state predicted therefrom.

[0663] "Means of providing support to users" refers to mechanisms for presenting generated advice and resources on the user's device, making them accessible to the user.

[0664] This invention implements a system to support a user's mental health in the following way: The server collects data such as the user's electronic transaction history and preprocesses it into an analyzable format. This preprocessing includes data cleaning, anonymization, and conversion to an appropriate format. Next, the server trains an artificial intelligence model on the preprocessed data. This model evaluates the user's psychological state based on the collected information and generates appropriate support content.

[0665] Users provide consultations and data through their devices. The devices are equipped with an interface that allows users to easily input their mental health-related concerns, and the information is transmitted anonymously. When a consultation is sent, the server receives the content, analyzes it using a generative AI model, and provides appropriate support.

[0666] The generated support content will be displayed on the user's device. This device will provide relaxation techniques, suggestions for psychological support, and links to counseling services, which the user can utilize.

[0667] For example, if a user reports an increase in their recent purchase frequency, the system might suggest stress reduction by displaying support such as, "As a long-term stress relief method, why not try some simple yoga at home?" This allows users to improve their mental health in a sustainable way.

[0668] An example of a prompt sentence input to a generative AI model is, "Please suggest stress reduction recommendations for users whose purchase frequency has recently increased." Based on this prompt sentence, the generative AI model generates optimal advice from past data.

[0669] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0670] Step 1:

[0671] The server collects users' electronic transaction history and related data in real time. The input is the user's purchase history data. Based on this, the data is cleaned and anonymized, and converted into an analyzable format. This output data is an anonymized, clean transaction record.

[0672] Step 2:

[0673] The server trains a generative AI model using pre-processed data. The input is the anonymized transaction records obtained in step 1. This data is fed to the generative AI model to learn the user's psychological patterns. The model's output is an analysis of the user's stress level and purchasing patterns.

[0674] Step 3:

[0675] Users input and submit mental health-related consultations via their devices. The input includes the user's consultation topic and current emotional state. The device uses an API to collect this information and send it to the server. The output is consultation data for analysis, which is then passed to the server.

[0676] Step 4:

[0677] The server analyzes the consultation content sent from the terminal using a generation AI model. The input is the user's consultation data. The server inputs this data, along with prompts, into the model and generates appropriate support content. The output is specific support content to be provided to the user.

[0678] Step 5:

[0679] The terminal displays the support information provided by the server to the user. The input is the support information generated in step 4. Advice and resource links are presented through the screen interface. The user can use this to improve their mental health. The output is support information visually presented to the user.

[0680] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0681] This invention relates to a system that combines emotional recognition with the mental health consultation process of a user. The system consists of four components: a server, a terminal, an emotion engine, and the user.

[0682] First, the server collects past consultation cases and reports from the company's database. The collected data is preprocessed, cleaned, and anonymized to be converted into an analyzable format. This data is also used as training data for the emotion engine.

[0683] Next, the server uses the pre-processed data to train the generative AI model and the emotion engine. The generative AI model utilizes natural language processing techniques to analyze the content of the consultation. The emotion engine analyzes the linguistic and non-linguistic features contained in the consultation content to recognize the user's emotions.

[0684] Users can anonymously seek advice on mental health issues using the terminal's interface. User input is sent to the server in a secure manner.

[0685] The submitted consultation content is analyzed by a server using a generative AI model and an emotion engine. The generative AI model understands the user's consultation and generates appropriate support content based on past cases. Meanwhile, the emotion engine identifies the user's emotional state and adjusts the support content accordingly.

[0686] For example, if a user posts a message on their device saying, "I've been feeling really down lately," the server can use an emotion engine to recognize the degree of the user's depression and provide specific support such as, "Try journaling to process your feelings, or we recommend counseling with a professional."

[0687] Finally, the terminal displays the generated support content to the user. In this way, the system can not only provide information but also offer personalized advice that takes into account the user's emotional state.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The server automatically collects past consultation cases and reports from the database. This data forms the foundation for the system's learning process, organizing necessary information and preparing it for future analysis.

[0691] Step 2:

[0692] The server preprocesses the collected data. This preprocessing includes cleaning and anonymizing the data, and converting it into the format necessary for analysis and sentiment recognition.

[0693] Step 3:

[0694] The server uses pre-processed data to train a generative AI model and an emotion engine. The generative AI model uses natural language processing to analyze the content of the consultation, and the emotion engine is trained to recognize emotions from linguistic and non-linguistic features.

[0695] Step 4:

[0696] Users can use their devices to input and anonymously submit their mental health-related consultations. During this process, users can utilize the device's interface to ensure their privacy is protected while conducting their consultations.

[0697] Step 5:

[0698] The terminal sends the user's inputted consultation details to the server. For security reasons, the consultation details are encrypted before transmission.

[0699] Step 6:

[0700] The server analyzes the consultation content using a generative AI model and an emotion engine. The generative AI model understands the meaning of the consultation content and generates appropriate support from past data. The emotion engine recognizes and analyzes the user's emotional state.

[0701] Step 7:

[0702] The server adjusts the support content based on the emotional information recognized by the emotion engine. For example, if a user is experiencing high levels of stress, the server generates support content that includes specific advice and resources to alleviate that stress.

[0703] Step 8:

[0704] The terminal displays the support information received from the server to the user. The user can review the support information on the screen and ask additional questions if necessary. In this way, the system provides personalized support that takes the user's emotional state into consideration.

[0705] (Example 2)

[0706] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0707] In modern society, many people suffer from mental health issues, but often feel hesitant to consult a professional directly. Furthermore, systems that accurately understand emotions and provide personalized support quickly and anonymously are not yet fully established. This leads to challenges such as users being unable to access appropriate resources and methods for support, resulting in delays in improving their mental health.

[0708] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0709] In this invention, the server includes means for collecting information from a data set, means for preprocessing the information and converting it into an analyzable format, and means for training the information using a machine learning model. This makes it possible to recognize the user's emotions and provide appropriate support anonymously.

[0710] A "data set" is a collection of data selected as the target of information collection, and is used for training and analyzing machine learning models.

[0711] An "information input device" is a device used by users to anonymously provide information about their consultations, and includes devices such as computers and smartphones.

[0712] An "information display device" is a device for displaying analyzed results and generated support content to the user, and includes devices that perform screen display and audio output.

[0713] A "machine learning model" refers to an algorithm that analyzes consultation content based on collected data and generates appropriate support plans.

[0714] "Linguistic features" refer to the linguistic characteristics included in the consultation content, such as word choice, sentence structure, and emotional expression.

[0715] "Non-verbal characteristics" refer to information other than language, such as tone of voice, speed, and context, and are used to evaluate the user's emotions and intentions.

[0716] "Emotional state" is an assessment that indicates the user's mental and emotional condition, and is identified through the analysis of the consultation content.

[0717] This invention is a system for providing mental health consultations to users. The system mainly consists of a server, a terminal, an emotion processing engine, and the user.

[0718] The server is connected to multiple databases, from which it collects past consultation cases and reports. Here, data cleansing techniques are used to clean the data, and further anonymization is applied to convert it into an analyzable format while protecting personal information. This data is later used as a dataset for training an emotion processing engine.

[0719] The emotion processing engine is built using a generative AI model, which applies natural language processing technology. The server uses this AI model to analyze the natural language inquiries provided by the user and generates appropriate support content based on the results. It also understands the user's emotional state by analyzing the linguistic and nonverbal characteristics of the inquiry content.

[0720] Users can anonymously submit mental health consultations using their own devices. The devices transmit the submitted consultation content to the server based on advanced security protocols.

[0721] The server analyzes the consultation content it receives using a generative AI model and an emotion processing engine. The server generates support content based on past cases and can also adjust this content according to the user's emotional state.

[0722] The terminal serves to notify the user of the support provided by the server. For example, if a user provides a prompt message through the terminal such as "I've been feeling really down lately," the server will identify the emotional state and then offer specific advice such as "Try journaling to help you process your feelings."

[0723] This system is unique in that it not only provides information but also offers personalized support that takes into account the user's emotional state.

[0724] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0725] Step 1:

[0726] The server collects past consultation cases and reports from the company's database. It receives a large amount of raw data as input and generates cleaned, anonymized data as output. This process involves specific actions to transform the data into a usable format by removing unnecessary information using data cleansing techniques and anonymizing personal information.

[0727] Step 2:

[0728] The server trains a generative AI model using pre-processed data. Pre-processed, anonymized data is used as input, and a language model is learned as output. At this stage, machine learning algorithms are used to add natural language processing skills to the model. Specific actions include dataset splitting and setting up the training process.

[0729] Step 3:

[0730] The server trains an emotion processing engine. It uses data containing linguistic and non-linguistic features as input and generates an engine capable of recognizing emotional states as output. This involves specific actions to train the engine to understand the user's emotions by utilizing emotion analysis algorithms.

[0731] Step 4:

[0732] The user anonymously enters a question about mental health using the device. The input is prompted, and the information is sent to the server as output. This stage involves the user entering the question in natural language, and the device securely transferring it to the server.

[0733] Step 5:

[0734] The server analyzes the consultation content using a generative AI model. It receives prompt text from the user as input and generates analysis results and support content as output. Specifically, its operations include understanding the context of the consultation content using a language model and referencing similar cases.

[0735] Step 6:

[0736] The server analyzes the user's emotional state using an emotion processing engine and adjusts the support accordingly. It takes analyzed consultation content and emotional data as input and generates personalized advice as output. This includes taking into account the user's emotional state to provide appropriate responses.

[0737] Step 7:

[0738] The terminal presents the generated personalized advice to the user. It receives support information from the server as input and displays the information to the user as output. This process includes specific actions such as displaying information and collecting feedback via the user interface.

[0739] (Application Example 2)

[0740] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0741] It is necessary to provide a system that allows users to confidently seek advice on mental health issues and receive appropriate support tailored to their emotional state. Furthermore, a safe environment where users can seek advice anonymously is also essential.

[0742] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0743] In this invention, the server includes means for collecting data, means for preprocessing the data and converting it into an analyzable format, and means for training the data using an artificial intelligence model. This enables the provision of personalized support tailored to the user's emotional state and allows for secure, anonymous consultations.

[0744] "Means for collecting data" refers to technologies that systematically gather necessary information for analysis and learning by obtaining input and related information from users.

[0745] "Means of preprocessing and converting into an analyzable format" refers to techniques that include the process of cleaning and organizing collected data to optimize it so that artificial intelligence models can learn and analyze efficiently.

[0746] "Methods for training using artificial intelligence models" refers to the process of training AI algorithms to perform pattern recognition and inference by utilizing pre-processed data.

[0747] "Methods for receiving consultations from users using electronic devices" refers to technologies that use electronic devices such as smartphones and computers to receive consultations from users regarding their mental health through an interface.

[0748] "Means for analyzing consultations and generating appropriate support content" refers to technologies that analyze the content of users' consultations and generate optimal support and advice, utilizing natural language processing and AI technologies.

[0749] "Means for identifying emotional states and adjusting support accordingly" refers to technology that analyzes a user's emotions, determines the optimal support content based on those emotions, and provides it.

[0750] "Means of providing support content to users" refers to technologies that present the analyzed and generated support content to users in an easily understandable way, and are implemented through a user interface.

[0751] "Means to enable anonymous consultations" refer to technologies that allow users to consult with peace of mind while protecting their personal information, and include mechanisms to protect privacy.

[0752] This invention provides a system that combines emotion recognition with mental health consultations for users. This system is centered around a server, a terminal, and a user, each playing a specific role.

[0753] The server first cleans and preprocesses past consultation cases collected from the database into an analyzable format. The preprocessed data is used to train the generative AI model and the emotion engine. The generative AI model analyzes the consultation content using natural language processing techniques, and the emotion engine recognizes the user's emotional state by analyzing linguistic and nonverbal features.

[0754] The terminal serves to receive inquiries from users and securely transmits the information entered by the user to the server. Electronic devices are used in this process, and users can also submit inquiries anonymously.

[0755] The server analyzes the received consultation content and generates appropriate support content based on past cases using a generative AI model. Furthermore, an emotion engine identifies the user's emotional state and adjusts the support content accordingly.

[0756] Ultimately, the terminal presents the user with support content generated and adjusted by the server. This system allows users to receive information and advice optimized for their own emotional state.

[0757] For example, if a user inputs "I've been feeling stressed and worried lately," the AI ​​model can suggest relaxation music based on past examples. It can also recommend meditation techniques or counseling services depending on the user's emotional state.

[0758] An example of a prompt message might be: "User input: 'I've been feeling stressed and worried lately.' Please generate appropriate support suggestions."

[0759] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0760] Step 1:

[0761] Users input mental health-related consultations using their devices. The entered data is provided in text format and securely transmitted from the device to the server. This input represents the user's consultation content and serves as basic information for subsequent analysis.

[0762] Step 2:

[0763] The server first stores the received consultation details in a database. The stored data is then preprocessed to serve as input for the emotion engine and generative AI model. Preprocessing includes text cleaning and tokenization, which converts the data into a parseable format.

[0764] Step 3:

[0765] The server passes the pre-processed consultation content to the generative AI model. The generative AI model utilizes natural language processing technology to analyze the input text. During the analysis process, it searches for similar past cases and generates appropriate support suggestions based on them.

[0766] Step 4:

[0767] The server uses an emotion engine to identify the user's emotional state from their inquiry. This process analyzes both linguistic and non-linguistic features (e.g., emotional vocabulary in the text) to reveal the user's emotional state.

[0768] Step 5:

[0769] The server integrates the results of the generative AI model and the emotion engine, and adjusts the support content according to the user's emotional state. Specifically, the generated support suggestions are optimized for the user's identified emotional state.

[0770] Step 6:

[0771] The support information, adjusted on the server, is sent back to the terminal and presented to the user. The user can then view the generated personalized advice and information on their terminal. This allows the user to obtain specific techniques for stress reduction.

[0772] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0773] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0774] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0775] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0776] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0777] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0778] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0779] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0780] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0781] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0782] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0783] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0784] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0785] 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.

[0786] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0787] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0788] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0789] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0790] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0791] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0792] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0793] The following is further disclosed regarding the embodiments described above.

[0794] (Claim 1)

[0795] Means for collecting data,

[0796] Means for preprocessing the data and converting it into an analyzable format,

[0797] A means for training the data using an artificial intelligence model,

[0798] A means of receiving inquiries from users,

[0799] A means for analyzing the consultation and generating appropriate support content,

[0800] A system that includes means for providing the support content to the user.

[0801] (Claim 2)

[0802] The system according to claim 1, wherein the artificial intelligence model utilizes natural language processing technology for analyzing the content of the consultation.

[0803] (Claim 3)

[0804] The system according to claim 1, further comprising means for enabling the user to make inquiries anonymously.

[0805] "Example 1"

[0806] (Claim 1)

[0807] Means for recording information,

[0808] Means for preprocessing the information and converting it into an analyzable format,

[0809] A means for training the information using a machine learning model,

[0810] A means of receiving inquiries from users,

[0811] A means for analyzing the inquiry and generating appropriate support content,

[0812] An information processing system that includes means for communicating the details of the support to the user.

[0813] (Claim 2)

[0814] The information processing system according to claim 1, wherein the machine learning model utilizes natural language processing technology for analyzing the content of the inquiry.

[0815] (Claim 3)

[0816] The information processing system according to claim 1, further comprising means for enabling inquiries from the user to be made anonymously.

[0817] "Application Example 1"

[0818] (Claim 1)

[0819] Means for collecting data,

[0820] Means for preprocessing the data and converting it into an analyzable format,

[0821] A means for training the data using an artificial intelligence model,

[0822] A means of receiving inquiries from users,

[0823] A means for analyzing the consultation and generating appropriate support content,

[0824] Analyzing the details of electronic transactions and using methods to estimate psychological burden,

[0825] A system that includes means for providing the support content to the user.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the artificial intelligence model utilizes natural language processing technology for analyzing the content of the consultation.

[0828] (Claim 3)

[0829] The system according to claim 1, further comprising means for enabling the user to make inquiries anonymously.

[0830] "Example 2 of combining an emotion engine"

[0831] (Claim 1)

[0832] Means of collecting information from a data set,

[0833] Means for preprocessing the information and converting it into an analyzable format,

[0834] A means for training the information using a machine learning model,

[0835] A means of receiving inquiries from information input devices,

[0836] A means for analyzing the content of the consultation and generating appropriate support content,

[0837] Means for providing the support content to an information display device,

[0838] A system that includes means for analyzing linguistic and nonverbal features contained in the consultation content and recognizing the emotional state.

[0839] (Claim 2)

[0840] The system according to claim 1, wherein the machine learning model utilizes natural language processing technology to analyze the content of the consultation and generates a language model.

[0841] (Claim 3)

[0842] The system according to claim 1, further comprising means for enabling consultations from the information input device to be conducted anonymously.

[0843] "Application example 2 when combining with an emotional engine"

[0844] (Claim 1)

[0845] Means for collecting data,

[0846] Means for preprocessing the data and converting it into an analyzable format,

[0847] A means for training the data using an artificial intelligence model,

[0848] A means of receiving inquiries from users using electronic devices,

[0849] A means for analyzing the consultation and generating appropriate support content,

[0850] A means for identifying the emotional state of the user and adjusting the support provided according to that state,

[0851] A system including means for providing the support content to the user.

[0852] (Claim 2)

[0853] The system according to claim 1, wherein the artificial intelligence model utilizes natural language processing technology for analyzing the content of the consultation.

[0854] (Claim 3)

[0855] The system according to claim 1, further comprising means for enabling the user to make inquiries anonymously. [Explanation of symbols]

[0856] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting data, Means for preprocessing the data and converting it into an analyzable format, A means for training the data using an artificial intelligence model, A means of receiving inquiries from users, A means for analyzing the consultation and generating appropriate support content, A system that includes means for providing the support content to the user.

2. The system according to claim 1, wherein the artificial intelligence model utilizes natural language processing technology for analyzing the content of the consultation.

3. The system according to claim 1, further comprising means for enabling the user to make inquiries anonymously.

Images