system

Abstract

We provide the system. [Solution] Means for collecting user communication data, Means for preprocessing the data and converting it into an analyzable format, A means for analyzing emotional states from the aforementioned data using generative artificial intelligence, A means of determining mental health status based on analysis results, A means of providing feedback to the user based on the judgment result, A system that includes this.

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, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, stress and mental burdens are increasing, and many people are at risk of depression and other mental illnesses. In such a situation, it is required to detect early before the symptoms worsen and take appropriate measures. However, since it is difficult for users themselves to notice changes in their minds or the opportunities to consult experts are limited, effective preventive measures are often not taken. It is required to solve this problem.

Means for Solving the Problems

[0005] This invention provides a system that collects user communication data and analyzes their emotional state using generative artificial intelligence. Specifically, it preprocesses the collected data and analyzes emotional tendencies using natural language processing technology. Furthermore, based on the analysis results, it determines the user's mental health state and issues a warning and provides feedback if a certain threshold is exceeded. This enables users to recognize their own mental state early and take appropriate measures.

[0006] A "user" is someone who uses the system and provides their personal communication data.

[0007] "Communication data" refers to information such as SNS posts, voice messages, and text messages that users generate on a daily basis.

[0008] "Generative artificial intelligence" is an artificial intelligence technology that uses machine learning to understand and analyze human language and emotions.

[0009] "Preprocessing" is the process of organizing data and converting it into an analyzable format before performing analysis.

[0010] "Natural language processing technology" is a technology that enables computers to understand and interpret human language and extract useful information.

[0011] "Emotional state" refers to the psychological or emotional state inferred from the user's communication data.

[0012] "Mental health status" refers to the level of mental well-being of a user, determined based on their analyzed emotional state.

[0013] A "threshold" is a reference value set to determine a specific state.

[0014] "Feedback" refers to a means of providing users with information and advice based on analysis results.

Brief Description of the Drawings

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It 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. <H

Modes for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention provides a system that monitors the mental health status of users and provides feedback as needed. This system mainly consists of a server and terminals and performs analysis based on communication data generated in daily life.

[0037] The server first collects communication data, such as daily posts and messages, from social networking services (SNS) and messaging applications, after obtaining the user's consent. This data is stored in a secure database.

[0038] The server then preprocesses the collected data, using natural language processing techniques to extract important keywords and phrases. The audio data is converted to text using speech recognition technology and analyzed together.

[0039] Next, pre-processed data is analyzed using generative artificial intelligence to evaluate the user's emotional state. This analysis categorizes emotions as positive, negative, or neutral, and also assesses emotional trends based on time series.

[0040] The terminal provides feedback to the user based on analysis results sent from the server. The feedback will prompt specific actions regarding changes from the normal state or matters requiring attention.

[0041] For example, if a user frequently uses negative expressions such as "tired," "stressed," or "I can't do this anymore" in multiple social media posts, the server will detect this as an emotional tendency. If the risk assessment determines that there are concerns about the user's mental health, the device will send feedback to the user such as, "Your recent posts suggest you are experiencing mental stress. Please take some time to relax or consider consulting a professional."

[0042] Through this system, users will be able to recognize their own mental health status and take necessary actions early on.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server, with the user's permission, collects communication data through APIs of social networking services and messaging services. This includes text messages and voice messages.

[0046] Step 2:

[0047] The server collects data and stores it in a database. As a security measure, the data is encrypted, and a user ID is associated with a timestamp.

[0048] Step 3:

[0049] The server preprocesses the stored data. Text data is tokenized using natural language processing techniques to remove extraneous symbols and stop words. Speech data is converted to text using speech recognition techniques.

[0050] Step 4:

[0051] The server inputs the pre-processed data into a sentiment analysis algorithm. This algorithm identifies positive, negative, and neutral emotions from the data and assigns a sentiment score to each data point.

[0052] Step 5:

[0053] The server analyzes the sentiment score over time to assess recent sentiment trends. If a negative trend persists over a long period compared to past data, the risk score is increased.

[0054] Step 6:

[0055] The server compares the risk score it determines to a specific threshold and sets a warning flag if the mental health risk is high.

[0056] Step 7:

[0057] The device receives results from the server and notifies the user of mental health-related feedback. The notification includes advice and behavioral recommendations tailored to the user's condition.

[0058] Step 8:

[0059] Review the feedback received from users and select the necessary actions based on the advice provided. This may include practicing relaxation techniques or consulting with a professional.

[0060] (Example 1)

[0061] 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."

[0062] In modern society, there is a need to efficiently monitor users' mental health using data obtained from the communication methods they use daily, and to provide timely advice and warnings. However, conventional methods present challenges such as difficulty in properly analyzing collected data, understanding emotional tendencies, and providing effective feedback to users.

[0063] 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.

[0064] In this invention, the server includes means for collecting the user's communication content, means for converting the communication content into a standardized format, and means for analyzing the emotional state from the communication content using machine learning techniques. This makes it possible to efficiently monitor the user's mental health and provide advice at an appropriate time.

[0065] "Users" refer to individuals or organizations that use this system and are the subjects of analysis regarding their mental health.

[0066] "Communication content" refers to information such as posts and messages sent by users through social networking services (SNS) and messaging platforms.

[0067] "Standardized format" refers to information that has been transformed into a unified data structure for analysis.

[0068] "Machine learning techniques" refer to algorithms and methods used to analyze data and derive rules and patterns from it.

[0069] "Emotional state" refers to the feelings and mental state derived from the workings of a user's mind. It can also be classified into positive, negative, neutral, etc.

[0070] "Evaluation" refers to the process of analyzing the emotional tendencies of users obtained from the analysis results and determining their health status.

[0071] "Advice" refers to recommended actions and precautions provided to users based on their assessed mental health status.

[0072] When a user uses this system, the server first collects the user's communication content through social networking services (SNS) and messaging platforms. This collection process can be automated by utilizing APIs. Communication content may include both text and audio data. Audio data is converted to text using speech recognition software.

[0073] The server converts the collected communication content into a standardized format. This uses natural language processing techniques, specifically morphological analysis and stop word removal to extract important parts of the text. Open-source natural language processing libraries are generally used as the software for this process.

[0074] Next, the server uses machine learning techniques to analyze the user's emotional state from the aforementioned communication content. This process employs a generative AI model, which may be given a prompt such as, "Based on this text, classify the user's emotions as positive, negative, or neutral." This analysis evaluates the user's emotional state trends over time and records them in a database.

[0075] The device provides advice to the user based on evaluation results generated by the server. This advice is designed to support the user's mental health. For example, if the emotional tendencies indicate a high level of psychological stress, feedback such as, "It appears you've been experiencing increased mental stress recently. We recommend taking a break or consulting a professional," will be provided.

[0076] In this way, the present invention realizes a system that efficiently monitors a user's mental health based on their communication content and provides advice at the appropriate time. This enables users to become aware of their own mental health and take appropriate action when necessary.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server collects user communications. Specifically, it obtains text and audio data through APIs of social networking services (SNS) and messaging platforms. In this process, it securely accesses the data using authentication information obtained in advance from the user. The input is raw text and audio data provided by each platform, and the output is unstructured raw data.

[0080] Step 2:

[0081] The server converts the collected audio data into text using speech recognition technology. Specifically, it uses speech recognition software to convert audio into text data. The input for this step is audio data, and the output is the corresponding text data.

[0082] Step 3:

[0083] The server preprocesses text data using natural language processing and converts it into a standardized format. Specific operations include stop word removal, morphological analysis, and extraction of important keywords and phrases. The input for this step is text data, and the output is text converted into a parseable format.

[0084] Step 4:

[0085] The server analyzes emotional states from pre-processed text data using a generative AI model. The prompt instructs the AI ​​model to "evaluate the user's emotional state from this text and classify it as positive, negative, or neutral." The input is standardized text data, and the output is the emotional category and its evaluation result.

[0086] Step 5:

[0087] The server evaluates emotional trends over time based on the analysis results and stores the evaluation results in a database. It tracks the analyzed emotional states over time, clarifying the changes in emotions. The input for this step is the emotional evaluation results, and the output is the trend data stored in the database.

[0088] Step 6:

[0089] The device receives evaluation results sent from the server and provides advice to the user. Specifically, it notifies the user of feedback when changes in emotions or psychological burdens are detected. The input is emotional tendency data, and the output is an advice message displayed to the user.

[0090] (Application Example 1)

[0091] 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."

[0092] In recent years, with the spread of e-commerce, consumer purchasing behavior has become more susceptible to psychological factors. However, conventional electronic payment systems do not adequately support purchasing decisions while considering the user's mental health. Therefore, there is a need for a system that enables consumers to maintain their mental well-being while making purchases. The challenge is to provide a system that analyzes the user's emotional state in real time and supports the alignment of purchasing behavior with health awareness.

[0093] 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.

[0094] In this invention, the server includes means for collecting user communication information, means for preprocessing the information and converting it into an analyzable format, means for analyzing the emotional state from the information using generative artificial intelligence, means for collecting the user's purchase history and recommending product purchases based on their mental state, and means for providing spending management feedback related to purchases. This enables users to make appropriate product choices and engage in healthy consumption behavior while considering their own mental health state.

[0095] "User communication information" refers to text and audio data that users send and receive through social networking services (SNS) and messaging applications.

[0096] "Means of preprocessing and converting into an analyzable format" refers to techniques for organizing and processing raw data into a form that is easy to analyze, and includes processes such as deleting unnecessary information and converting it to text.

[0097] "Generative artificial intelligence" is a type of AI that has the ability to generate new information based on collected data, and is particularly used for pattern recognition and sentiment analysis.

[0098] "Means for analyzing emotional states" refers to the technical process of identifying emotions such as positive, negative, and neutral from users' statements and communication data using natural language processing technology, etc.

[0099] "User purchase history" refers to data about a user's past purchasing behavior, including information such as product name, purchase date and time, and price.

[0100] "Methods for recommending product purchases" refer to technologies that identify and suggest products that users should consider purchasing, based on their analyzed emotional state and purchase history.

[0101] "Purchase-related spending management feedback" is a system that provides users with feedback and advice on budget management and spending trends in relation to their purchasing behavior.

[0102] This system works by analyzing the user's mental state based on their communication information and purchase history, and then providing product purchase recommendations and spending management feedback based on that analysis. The server securely collects user communication information from social networking services (SNS) and messaging platforms.

[0103] The server preprocesses the collected information using Python and natural language processing libraries (NLTK and spaCy) to extract necessary keywords and sentiment information in text format. If audio data is included, speech recognition technology is used to convert it to text for analysis.

[0104] Next, using TENSORFLOW® as a generative artificial intelligence, the server analyzes the user's emotional state based on this pre-processed data. The emotional state is classified into categories such as positive, negative, and neutral, and the temporal fluctuations of the emotion are also evaluated.

[0105] The user's purchase history is retrieved from a database, and an algorithm is executed that recommends products to the user in combination with an analyzed emotional state. This purchase recommendation presents the most suitable products while taking the user's mental well-being into consideration. The device also provides the user with spending management feedback regarding purchases, offering guidance to help them stay within their budget.

[0106] This allows users to make purchases that align with their mental state and provides support to prevent impulse buying and overspending. For example, if a user frequently uses negative expressions such as "I'm tired" on social media, relaxation-related products will be recommended, and a notification will appear on their device saying, "Let's think about sorting out your feelings and review your budget plan again."

[0107] An example of a prompt might be, "Build purchase insights based on user sentiment analysis and recommend the most suitable products."

[0108] This system can promote healthier consumer behavior by linking users' mental health with their purchasing decisions.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server collects communication information from users' social networking services (SNS) and messaging apps. This information includes text messages and audio data. The server stores this data in secure cloud storage. The input is raw communication data, and the output is data stored securely in storage.

[0112] Step 2:

[0113] The server uses Python and natural language processing libraries (NLTK and spaCy) to preprocess the collected information into a parseable format. Audio data is converted to text using speech recognition technology. Specifically, keywords are extracted and emotional tone is analyzed. The input is the collected communication data, and the output is the analysis results of keywords and emotional tone.

[0114] Step 3:

[0115] The server utilizes a generative AI model to analyze the user's emotional state from preprocessed data. Using TensorFlow, the data is categorized into positive, negative, and neutral emotional states. The time-series fluctuations of the emotions are also evaluated. The input is preprocessed data, and the output is the user's emotional analysis result.

[0116] Step 4:

[0117] The server retrieves the user's purchase history from the database and recommends the most suitable products by combining it with the sentiment analysis results. This recommendation is based on an algorithm that takes into account past purchase data and the user's current mental state. The input is the purchase history and sentiment analysis results, and the output is a list of recommended products.

[0118] Step 5:

[0119] The device provides the user with spending management feedback related to purchases. This feedback includes points to note and advice for staying within budget. Inputs are emotional state and purchase history, and output is a feedback message.

[0120] 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.

[0121] This invention provides a system that analyzes a user's emotional state based on their communication data, determines their mental health status, and provides feedback. Furthermore, by combining this system with an emotion engine, more accurate emotion recognition can be achieved.

[0122] The server first obtains user permission and then collects text messages and voice data from social networking services (SNS) and messaging platforms. This data is stored in a secure database and used for subsequent analysis.

[0123] Next, the server preprocesses the data using natural language processing techniques. The audio data is converted to text, all data is tokenized, and unnecessary information is removed.

[0124] This preprocessed data is analyzed by an emotion engine. The emotion engine has an algorithm that classifies the data according to multiple emotion categories (e.g., joy, sadness, anger, etc.). This algorithm utilizes training data from generative artificial intelligence to understand the context of the data and determine the emotion.

[0125] Based on the analysis results obtained from the emotion engine, the server compares them with past emotion data to determine the user's mental health status. If the determined status exceeds a certain threshold, it is judged to be at risk, and countermeasures are taken promptly.

[0126] Ultimately, the device provides the user with appropriate feedback based on the information received from the server. This feedback includes specific advice regarding mental health, such as points to note and suggestions for improvement.

[0127] For example, if a user frequently posts messages expressing anger, the emotion engine will detect this and determine that negative emotions are persisting. Based on this, the device will send feedback to the user such as, "It appears you are experiencing stress. Please engage in relaxing activities or consider counseling." Through this system, the aim is to help users recognize changes in their emotions early on and choose healthy behaviors.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server collects text and audio data from social networking services (SNS) and messaging platforms based on user permission. This provides everyday communication data.

[0131] Step 2:

[0132] The server preprocesses the collected data. Audio data is transcribed using speech recognition technology, all data is tokenized to remove unnecessary information, and converted into a format suitable for sentiment analysis.

[0133] Step 3:

[0134] The server inputs pre-processed data into the emotion engine. The emotion engine uses natural language processing techniques to classify the data into multiple emotion categories. In this process, the emotion engine's algorithm understands the context and analyzes the emotions contained in the data with high accuracy.

[0135] Step 4:

[0136] The server evaluates the user's emotional state trends based on the analysis results from the emotion engine. This evaluation includes comparison with past emotional data, allowing for a time-series understanding of changes in positive, negative, and neutral emotions.

[0137] Step 5:

[0138] The server determines the user's mental health status based on their emotional state tendencies. If the determination exceeds a certain threshold, a warning flag is set, indicating a high mental health risk.

[0139] Step 6:

[0140] Based on the judgment results received by the server, the device generates and notifies the user of feedback. The feedback includes emotional tendencies and necessary improvements.

[0141] Step 7:

[0142] The user reviews the feedback they receive and considers and implements recommended actions. This includes stress-relieving activities and seeking professional help.

[0143] (Example 2)

[0144] 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".

[0145] The diversification of modern communication methods has created a need to appropriately monitor users' psychological health and provide timely feedback. Conventional methods make it difficult to perform real-time emotional analysis or quickly determine changes in psychological state, potentially causing users to miss opportunities to receive appropriate care. This invention aims to solve this problem by performing more accurate emotional analysis and health status assessment from information obtained through users' communication, and promptly notifying users.

[0146] 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.

[0147] In this invention, the server includes means for collecting user communication information, means for preprocessing the information and converting it into an analyzable format, and means for analyzing the emotional state from the information using generative artificial intelligence. This makes it possible to determine the user's psychological health state with high accuracy and speed, and to provide necessary feedback in a timely manner.

[0148] "User communication information" refers to information such as text messages and voice data that users send and receive through the digital communication platform.

[0149] "Preprocessing" refers to data cleansing, transformation, and tokenization processes performed to convert collected data into a format that is easy to analyze.

[0150] "Generative artificial intelligence" is an AI model technology that analyzes data to identify context and determine emotional states through the generation of text and data patterns.

[0151] "Means for analyzing emotional states" refer to algorithms and devices used to classify emotions such as joy, sadness, and anger from data and to evaluate the user's psychological state.

[0152] "Psychological health status" refers to the level of a user's mental and emotional well-being, and is assessed based on emotional analysis.

[0153] "Means of providing responses" refers to technical means used to present users with information and advice regarding their psychological health status and potential improvements based on analysis results.

[0154] A "digital device" is an electronic device capable of receiving and displaying digital data, such as a personal computer, smartphone, or tablet.

[0155] This invention is a system that analyzes information obtained from users' digital communications to assess their mental health and provide feedback. The server securely collects text messages and voice data from communication platforms with the user's permission. The collected data is stored in a database and subsequently used for analysis. Specifically, the system utilizes cloud-based server storage as hardware and employs API technology (e.g., a general-purpose data acquisition API) for data collection as software.

[0156] The server utilizes natural language processing techniques to preprocess the acquired data. Audio data is converted to text using speech recognition software (e.g., a speech-to-text engine), and then tokenized and denoised using a Python natural language processing library (e.g., spaCy).

[0157] This pre-processed data is analyzed by an emotion analysis engine utilizing a generative AI model. The generative AI model (e.g., an advanced text analysis AI) classifies the data according to various emotion categories and estimates the emotional state. Based on this, the server compares it with historical data to assess the psychological health status. If the risk exceeds a certain threshold, corrective action is taken immediately.

[0158] The device provides feedback to the user based on information received from the server. For example, if a user consistently posts messages indicating "sadness," the device might provide feedback such as, "It seems you've been feeling sad lately. Try incorporating some lighthearted activities to lift your spirits."

[0159] Specific examples of prompt statements are as follows:

[0160] "Please analyze the emotions expressed in messages recently sent by users. Classify them into one of three categories: joy, sadness, or anger, and indicate the degree of each emotion numerically. Also, please provide a comparison with past data."

[0161] This system will enable users to understand their emotions earlier and take appropriate health management actions.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The server, with the user's permission, collects text messages and voice data from the communication platform. It receives message data obtained via an API as input and stores it directly in the database. Specifically, the server issues API requests, encrypts the retrieved data, and stores it in cloud storage.

[0165] Step 2:

[0166] The server converts the collected audio data into text using speech recognition software. It takes audio files as input and generates corresponding text data as output. Specifically, the server uses a speech recognition API to integrate the obtained text with other text data in the database.

[0167] Step 3:

[0168] The server preprocesses the text data. It takes integrated text data as input and generates tokenized, clean data as output. This process uses Python's natural language processing library, where the server tokenizes the data and removes unwanted noise.

[0169] Step 4:

[0170] The server inputs pre-processed data into a generating AI model and performs sentiment analysis. Tokenized text data is sent to the AI ​​model along with prompts, and the output includes sentiment categories (joy, sadness, anger, etc.) and their intensity. Specifically, the server creates prompts and retrieves the analysis results through the AI ​​model.

[0171] Step 5:

[0172] The server determines the mental health status by comparing the results of sentiment analysis with historical data. It uses current sentiment analysis data and past sentiment data as input, and performs a health status assessment as output. The server uses statistical analysis techniques for pattern recognition.

[0173] Step 6:

[0174] The device provides feedback to the user based on health status assessment results received from the server. It receives assessment results as input and displays specific advice as output. Specifically, the device displays a pop-up notification to the user, prompting appropriate action.

[0175] (Application Example 2)

[0176] 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".

[0177] In modern society, busy lifestyles and information overload are leading to increased consumer stress and emotional instability. In this context, there is a need for ways to improve the consumer purchasing experience and reduce stress. Particularly in e-commerce, the challenge lies in providing a better purchasing experience by offering appropriate feedback and suggestions tailored to the individual consumer's emotional state.

[0178] 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.

[0179] In this invention, the server includes a device for collecting user information, a device for processing the information and converting it into an analyzable format, and a device for analyzing the emotional state from the information using a generative artificial intelligence model. This makes it possible to recommend relevant audio or visual content according to the emotional state of the user while they are using a product or service, and to collaborate with external information sources to provide the audio or visual content.

[0180] "User" refers to an individual or legal entity that uses the system or device.

[0181] "Information" refers to communication data and other related data related to the user, including text, audio, and visual data.

[0182] "Device" refers to hardware or software designed to perform a specific function.

[0183] "Processing" refers to a series of operations that convert collected information into a format that can be analyzed or interpreted.

[0184] A "generative artificial intelligence model" refers to artificial intelligence technology that generates new information from data or identifies patterns.

[0185] "Emotional state" refers to the user's emotional situation or psychological tendencies, and is classified into categories such as joy, sadness, and anger.

[0186] "Recommendation" means suggesting a particular action or choice to a user, and this includes feedback and advice.

[0187] "Audio or visual content" refers to media content such as audio messages, music, videos, and images.

[0188] "External information sources" refer to databases and service providers that exist outside the system, providing additional data and functionality.

[0189] This system is designed to analyze users' emotional states and provide appropriate feedback under specific conditions. The server first obtains user permission and then collects communication data from messaging platforms and other databases. The collected data is then converted into an analyzable format using a processor on the server. During this process, Google Cloud's natural language processing APIs are utilized to tokenize text data and perform sentiment analysis.

[0190] Generative artificial intelligence models use this data to analyze the user's emotional state. During the analysis, they understand the user's context and classify it into emotional categories such as joy, sadness, and anger. Based on these results, the server evaluates the emotional state and determines the user's health status. Algorithms built on specific criteria support this process.

[0191] Depending on the user's emotional state, the server collaborates with external information sources to recommend relaxing music, for example, through online music streaming services. This is effective when the server determines that the user is experiencing stress. The recommended music and visual content are provided using APIs from services such as Spotify and Apple Music.

[0192] For example, if analysis indicates that a user is experiencing stress during the online shopping process, a recommendation such as "Would you like to stream some relaxing classical music?" might be displayed. Simultaneously, coupons for health-related products and services may also be issued.

[0193] An example of a prompt for a generative AI model would be: "Show me a method for suggesting relaxing music when a user is feeling anxious. Then, generate a list of items that he might be interested in for relaxation."

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

[0195] Step 1:

[0196] The server, with the user's permission, collects communication data from messaging platforms, social networking services (SNS), and other sources. The input for this step consists of text and voice data from multiple platforms. The server then stores this data in a secure database.

[0197] Step 2:

[0198] The server preprocesses the collected data using Google Cloud's natural language processing API. The input consists of stored raw text and audio data. At this stage, the server converts the audio data to text, performs data processing such as tokenization and removal of irrelevant information, and outputs the data in a parseable format.

[0199] Step 3:

[0200] The server inputs pre-processed data into a generative artificial intelligence model to analyze emotional states. The input for this step is pre-processed text data. The generative AI model understands the context of the data, classifies it into emotional categories such as joy and sadness, and outputs the results of the emotional state analysis.

[0201] Step 4:

[0202] The server evaluates the user's health status based on the analyzed emotional state and makes a judgment based on specific criteria. The input for this step is emotional state data obtained from a generative artificial intelligence model. The server then performs an operation to assess health risks and output the judgment result.

[0203] Step 5:

[0204] The server provides feedback to the user based on their emotional state and recommends appropriate audio or visual content in conjunction with external information sources. The input is the result of a health status assessment. The server, for example, uses a music streaming service API to recommend relaxing music and generates output to provide.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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".

[0221] This invention provides a system that monitors the mental health status of users and provides feedback as needed. This system mainly consists of a server and terminals and performs analysis based on communication data generated in daily life.

[0222] The server first collects communication data, such as daily posts and messages, from social networking services (SNS) and messaging applications, after obtaining the user's consent. This data is stored in a secure database.

[0223] The server then preprocesses the collected data, using natural language processing techniques to extract important keywords and phrases. The audio data is converted to text using speech recognition technology and analyzed together.

[0224] Next, pre-processed data is analyzed using generative artificial intelligence to evaluate the user's emotional state. This analysis categorizes emotions as positive, negative, or neutral, and also assesses emotional trends based on time series.

[0225] The terminal provides feedback to the user based on analysis results sent from the server. The feedback will prompt specific actions regarding changes from the normal state or matters requiring attention.

[0226] For example, if a user frequently uses negative expressions such as "tired," "stressed," or "I can't do this anymore" in multiple social media posts, the server will detect this as an emotional tendency. If the risk assessment determines that there are concerns about the user's mental health, the device will send feedback to the user such as, "Your recent posts suggest you are experiencing mental stress. Please take some time to relax or consider consulting a professional."

[0227] Through this system, users will be able to recognize their own mental health status and take necessary actions early on.

[0228] The following describes the processing flow.

[0229] Step 1:

[0230] The server, with the user's permission, collects communication data through APIs of social networking services and messaging services. This includes text messages and voice messages.

[0231] Step 2:

[0232] The server collects data and stores it in a database. As a security measure, the data is encrypted, and a user ID is associated with a timestamp.

[0233] Step 3:

[0234] The server preprocesses the stored data. Text data is tokenized using natural language processing techniques to remove extraneous symbols and stop words. Speech data is converted to text using speech recognition techniques.

[0235] Step 4:

[0236] The server inputs the pre-processed data into a sentiment analysis algorithm. This algorithm identifies positive, negative, and neutral emotions from the data and assigns a sentiment score to each data point.

[0237] Step 5:

[0238] The server analyzes the sentiment score over time to assess recent sentiment trends. If a negative trend persists over a long period compared to past data, the risk score is increased.

[0239] Step 6:

[0240] The server compares the risk score it determines to a specific threshold and sets a warning flag if the mental health risk is high.

[0241] Step 7:

[0242] The device receives results from the server and notifies the user of mental health-related feedback. The notification includes advice and behavioral recommendations tailored to the user's condition.

[0243] Step 8:

[0244] Review the feedback received from users and select the necessary actions based on the advice provided. This may include practicing relaxation techniques or consulting with a professional.

[0245] (Example 1)

[0246] 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."

[0247] In modern society, there is a need to efficiently monitor users' mental health using data obtained from the communication methods they use daily, and to provide timely advice and warnings. However, conventional methods present challenges such as difficulty in properly analyzing collected data, understanding emotional tendencies, and providing effective feedback to users.

[0248] 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.

[0249] In this invention, the server includes means for collecting the user's communication content, means for converting the communication content into a standardized format, and means for analyzing the emotional state from the communication content using machine learning techniques. This makes it possible to efficiently monitor the user's mental health and provide advice at an appropriate time.

[0250] "Users" refer to individuals or organizations that use this system and are the subjects of analysis regarding their mental health.

[0251] "Communication content" refers to information such as posts and messages sent by users through social networking services (SNS) and messaging platforms.

[0252] "Standardized format" refers to information that has been transformed into a unified data structure for analysis.

[0253] "Machine learning techniques" refer to algorithms and methods used to analyze data and derive rules and patterns from it.

[0254] "Emotional state" refers to the feelings and mental state derived from the workings of a user's mind. It can also be classified into positive, negative, neutral, etc.

[0255] "Evaluation" refers to the process of analyzing the emotional tendencies of users obtained from the analysis results and determining their health status.

[0256] "Advice" refers to recommended actions and precautions provided to users based on their assessed mental health status.

[0257] When a user uses this system, the server first collects the user's communication content through social networking services (SNS) and messaging platforms. This collection process can be automated by utilizing APIs. Communication content may include both text and audio data. Audio data is converted to text using speech recognition software.

[0258] The server converts the collected communication content into a standardized format. This uses natural language processing techniques, specifically morphological analysis and stop word removal to extract important parts of the text. Open-source natural language processing libraries are generally used as the software for this process.

[0259] Next, the server uses machine learning techniques to analyze the user's emotional state from the aforementioned communication content. This process employs a generative AI model, which may be given a prompt such as, "Based on this text, classify the user's emotions as positive, negative, or neutral." This analysis evaluates the user's emotional state trends over time and records them in a database.

[0260] The device provides advice to the user based on evaluation results generated by the server. This advice is designed to support the user's mental health. For example, if the emotional tendencies indicate a high level of psychological stress, feedback such as, "It appears you've been experiencing increased mental stress recently. We recommend taking a break or consulting a professional," will be provided.

[0261] In this way, the present invention realizes a system that efficiently monitors a user's mental health based on their communication content and provides advice at the appropriate time. This enables users to become aware of their own mental health and take appropriate action when necessary.

[0262] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0263] Step 1:

[0264] The server collects user communications. Specifically, it obtains text and audio data through APIs of social networking services (SNS) and messaging platforms. In this process, it securely accesses the data using authentication information obtained in advance from the user. The input is raw text and audio data provided by each platform, and the output is unstructured raw data.

[0265] Step 2:

[0266] The server converts the collected audio data into text using speech recognition technology. Specifically, it uses speech recognition software to convert audio into text data. The input for this step is audio data, and the output is the corresponding text data.

[0267] Step 3:

[0268] The server preprocesses text data using natural language processing and converts it into a standardized format. Specific operations include stop word removal, morphological analysis, and extraction of important keywords and phrases. The input for this step is text data, and the output is text converted into a parseable format.

[0269] Step 4:

[0270] The server analyzes emotional states from pre-processed text data using a generative AI model. The prompt instructs the AI ​​model to "evaluate the user's emotional state from this text and classify it as positive, negative, or neutral." The input is standardized text data, and the output is the emotional category and its evaluation result.

[0271] Step 5:

[0272] The server evaluates emotional trends over time based on the analysis results and stores the evaluation results in a database. It tracks the analyzed emotional states over time, clarifying the changes in emotions. The input for this step is the emotional evaluation results, and the output is the trend data stored in the database.

[0273] Step 6:

[0274] The device receives evaluation results sent from the server and provides advice to the user. Specifically, it notifies the user of feedback when changes in emotions or psychological burdens are detected. The input is emotional tendency data, and the output is an advice message displayed to 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 recent years, with the spread of e-commerce, consumer purchasing behavior has become more susceptible to psychological factors. However, conventional electronic payment systems do not adequately support purchasing decisions while considering the user's mental health. Therefore, there is a need for a system that enables consumers to maintain their mental well-being while making purchases. The challenge is to provide a system that analyzes the user's emotional state in real time and supports the alignment of purchasing behavior with health awareness.

[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 user communication information, means for preprocessing the information and converting it into an analyzable format, means for analyzing the emotional state from the information using generative artificial intelligence, means for collecting the user's purchase history and recommending product purchases based on their mental state, and means for providing spending management feedback related to purchases. This enables users to make appropriate product choices and engage in healthy consumption behavior while considering their own mental health state.

[0280] "User communication information" refers to text and audio data that users send and receive through social networking services (SNS) and messaging applications.

[0281] "Means of preprocessing and converting into an analyzable format" refers to techniques for organizing and processing raw data into a form that is easy to analyze, and includes processes such as deleting unnecessary information and converting it to text.

[0282] "Generative artificial intelligence" is a type of AI that has the ability to generate new information based on collected data, and is particularly used for pattern recognition and sentiment analysis.

[0283] The "means for analyzing emotional states" refers to a technical process that uses natural language processing technology and the like to identify emotions such as positive, negative, and neutral from the user's speech and communication data.

[0284] The "user's purchase history" refers to data related to the user's past purchase actions and includes information such as product names, purchase dates and times, and amounts.

[0285] The "means for recommending product purchases" is a technology for identifying and proposing products that the user should consider purchasing based on the analyzed emotional state and purchase history of the user.

[0286] The "expenditure management feedback regarding purchases" is a mechanism that provides pointers and advice regarding budget management and spending trends for the user's purchase actions.

[0287] This system is realized by analyzing the user's mental state based on the user's communication information and purchase history and providing product purchase recommendations and expenditure management feedback based thereon. The server securely collects the user's communication information from SNS and messaging platforms.

[0288] The server preprocesses the collected information using Python and natural language processing libraries (NLTK and spaCy) and extracts necessary keywords and emotional information in text format. When voice data is included, it is converted into text using voice recognition technology and used for analysis.

[0289] Next, leveraging TensorFlow as a generative artificial intelligence, the server analyzes the user's emotional state based on this preprocessed data. The emotional state is classified into categories such as positive, negative, and neutral, and the temporal variation of the emotion is also evaluated.

[0290] The user's purchase history is retrieved from a database, and an algorithm is executed that recommends products to the user in combination with an analyzed emotional state. This purchase recommendation presents the most suitable products while taking the user's mental well-being into consideration. The device also provides the user with spending management feedback regarding purchases, offering guidance to help them stay within their budget.

[0291] This allows users to make purchases that align with their mental state and provides support to prevent impulse buying and overspending. For example, if a user frequently uses negative expressions such as "I'm tired" on social media, relaxation-related products will be recommended, and a notification will appear on their device saying, "Let's think about sorting out your feelings and review your budget plan again."

[0292] An example of a prompt might be, "Build purchase insights based on user sentiment analysis and recommend the most suitable products."

[0293] This system can promote healthier consumer behavior by linking users' mental health with their purchasing decisions.

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The server collects communication information from users' social networking services (SNS) and messaging apps. This information includes text messages and audio data. The server stores this data in secure cloud storage. The input is raw communication data, and the output is data stored securely in storage.

[0297] Step 2:

[0298] The server uses Python and natural language processing libraries (NLTK and spaCy) to preprocess the collected information into a parseable format. Audio data is converted to text using speech recognition technology. Specifically, keywords are extracted and emotional tone is analyzed. The input is the collected communication data, and the output is the analysis results of keywords and emotional tone.

[0299] Step 3:

[0300] The server utilizes a generative AI model to analyze the user's emotional state from preprocessed data. Using TensorFlow, the data is categorized into positive, negative, and neutral emotional states. The time-series fluctuations of the emotions are also evaluated. The input is preprocessed data, and the output is the user's emotional analysis result.

[0301] Step 4:

[0302] The server retrieves the user's purchase history from the database and recommends the most suitable products by combining it with the sentiment analysis results. This recommendation is based on an algorithm that takes into account past purchase data and the user's current mental state. The input is the purchase history and sentiment analysis results, and the output is a list of recommended products.

[0303] Step 5:

[0304] The device provides the user with spending management feedback related to purchases. This feedback includes points to note and advice for staying within budget. Inputs are emotional state and purchase history, and output is a feedback message.

[0305] 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.

[0306] The present invention provides a system that analyzes an emotional state based on a user's communication data, determines the mental health state, and provides feedback. Furthermore, by combining an emotion engine in this system, more accurate emotion recognition is achieved.

[0307] First, the server obtains the user's permission and collects text messages and voice data from SNSs and messaging platforms. This data is stored in a secure database and used for subsequent analysis.

[0308] Next, the server preprocesses the data using natural language processing techniques. The voice data is converted into text, all the data is tokenized, and unnecessary information is removed.

[0309] This preprocessed data is analyzed by the emotion engine. The emotion engine has an algorithm that classifies data according to multiple emotion categories (e.g., joy, sadness, anger, etc.). This algorithm utilizes the learning data of generative artificial intelligence to understand the context of the data and discriminate emotions.

[0310] Based on the analysis results obtained from the emotion engine, the server compares with past emotion data and determines the user's mental health state. If the determined state exceeds a specific threshold, it is judged that there is a risk, and prompt countermeasures are taken.

[0311] Finally, based on the information received from the server, the terminal provides appropriate feedback to the user. This feedback includes points to note regarding mental health and specific advice to encourage improvement.

[0312] For example, if a user frequently posts messages expressing anger, the emotion engine will detect this and determine that negative emotions are persisting. Based on this, the device will send feedback to the user such as, "It appears you are experiencing stress. Please engage in relaxing activities or consider counseling." Through this system, the aim is to help users recognize changes in their emotions early on and choose healthy behaviors.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The server collects text and audio data from social networking services (SNS) and messaging platforms based on user permission. This provides everyday communication data.

[0316] Step 2:

[0317] The server preprocesses the collected data. Audio data is transcribed using speech recognition technology, all data is tokenized to remove unnecessary information, and converted into a format suitable for sentiment analysis.

[0318] Step 3:

[0319] The server inputs pre-processed data into the emotion engine. The emotion engine uses natural language processing techniques to classify the data into multiple emotion categories. In this process, the emotion engine's algorithm understands the context and analyzes the emotions contained in the data with high accuracy.

[0320] Step 4:

[0321] The server evaluates the user's emotional state trends based on the analysis results from the emotion engine. This evaluation includes comparison with past emotional data, allowing for a time-series understanding of changes in positive, negative, and neutral emotions.

[0322] Step 5:

[0323] The server determines the user's mental health status based on their emotional state tendencies. If the determination exceeds a certain threshold, a warning flag is set, indicating a high mental health risk.

[0324] Step 6:

[0325] Based on the judgment results received by the server, the device generates and notifies the user of feedback. The feedback includes emotional tendencies and necessary improvements.

[0326] Step 7:

[0327] The user reviews the feedback they receive and considers and implements recommended actions. This includes stress-relieving activities and seeking professional help.

[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] The diversification of modern communication methods has created a need to appropriately monitor users' psychological health and provide timely feedback. Conventional methods make it difficult to perform real-time emotional analysis or quickly determine changes in psychological state, potentially causing users to miss opportunities to receive appropriate care. This invention aims to solve this problem by performing more accurate emotional analysis and health status assessment from information obtained through users' communication, and promptly notifying users.

[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 user communication information, means for preprocessing the information and converting it into an analyzable format, and means for analyzing the emotional state from the information using generative artificial intelligence. This makes it possible to determine the user's psychological health state with high accuracy and speed, and to provide necessary feedback in a timely manner.

[0333] "User communication information" refers to information such as text messages and voice data that users send and receive through the digital communication platform.

[0334] "Preprocessing" refers to data cleansing, transformation, and tokenization processes performed to convert collected data into a format that is easy to analyze.

[0335] "Generative artificial intelligence" is an AI model technology that analyzes data to identify context and determine emotional states through the generation of text and data patterns.

[0336] "Means for analyzing emotional states" refer to algorithms and devices used to classify emotions such as joy, sadness, and anger from data and to evaluate the user's psychological state.

[0337] "Psychological health status" refers to the level of a user's mental and emotional well-being, and is assessed based on emotional analysis.

[0338] "Means of providing responses" refers to technical means used to present users with information and advice regarding their psychological health status and potential improvements based on analysis results.

[0339] A "digital device" is an electronic device capable of receiving and displaying digital data, such as a personal computer, smartphone, or tablet.

[0340] This invention is a system that analyzes information obtained from users' digital communications to assess their mental health and provide feedback. The server securely collects text messages and voice data from communication platforms with the user's permission. The collected data is stored in a database and subsequently used for analysis. Specifically, the system utilizes cloud-based server storage as hardware and employs API technology (e.g., a general-purpose data acquisition API) for data collection as software.

[0341] The server utilizes natural language processing techniques to preprocess the acquired data. Audio data is converted to text using speech recognition software (e.g., a speech-to-text engine), and then tokenized and denoised using a Python natural language processing library (e.g., spaCy).

[0342] This pre-processed data is analyzed by an emotion analysis engine utilizing a generative AI model. The generative AI model (e.g., an advanced text analysis AI) classifies the data according to various emotion categories and estimates the emotional state. Based on this, the server compares it with historical data to assess the psychological health status. If the risk exceeds a certain threshold, corrective action is taken immediately.

[0343] The device provides feedback to the user based on information received from the server. For example, if a user consistently posts messages indicating "sadness," the device might provide feedback such as, "It seems you've been feeling sad lately. Try incorporating some lighthearted activities to lift your spirits."

[0344] Specific examples of prompt statements are as follows:

[0345] "Please analyze the emotions expressed in messages recently sent by users. Classify them into one of three categories: joy, sadness, or anger, and indicate the degree of each emotion numerically. Also, please provide a comparison with past data."

[0346] This system will enable users to understand their emotions earlier and take appropriate health management actions.

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

[0348] Step 1:

[0349] The server, with the user's permission, collects text messages and voice data from the communication platform. It receives message data obtained via an API as input and stores it directly in the database. Specifically, the server issues API requests, encrypts the retrieved data, and stores it in cloud storage.

[0350] Step 2:

[0351] The server converts the collected audio data into text using speech recognition software. It takes audio files as input and generates corresponding text data as output. Specifically, the server uses a speech recognition API to integrate the obtained text with other text data in the database.

[0352] Step 3:

[0353] The server preprocesses the text data. It takes integrated text data as input and generates tokenized, clean data as output. This process uses Python's natural language processing library, where the server tokenizes the data and removes unwanted noise.

[0354] Step 4:

[0355] The server inputs pre-processed data into a generating AI model and performs sentiment analysis. Tokenized text data is sent to the AI ​​model along with prompts, and the output includes sentiment categories (joy, sadness, anger, etc.) and their intensity. Specifically, the server creates prompts and retrieves the analysis results through the AI ​​model.

[0356] Step 5:

[0357] The server determines the mental health status by comparing the results of sentiment analysis with historical data. It uses current sentiment analysis data and past sentiment data as input, and performs a health status assessment as output. The server uses statistical analysis techniques for pattern recognition.

[0358] Step 6:

[0359] The device provides feedback to the user based on health status assessment results received from the server. It receives assessment results as input and displays specific advice as output. Specifically, the device displays a pop-up notification to the user, prompting appropriate action.

[0360] (Application Example 2)

[0361] 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."

[0362] In modern society, busy lifestyles and information overload are leading to increased consumer stress and emotional instability. In this context, there is a need for ways to improve the consumer purchasing experience and reduce stress. Particularly in e-commerce, the challenge lies in providing a better purchasing experience by offering appropriate feedback and suggestions tailored to the individual consumer's emotional state.

[0363] 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.

[0364] In this invention, the server includes a device for collecting user information, a device for processing the information and converting it into an analyzable format, and a device for analyzing the emotional state from the information using a generative artificial intelligence model. This makes it possible to recommend relevant audio or visual content according to the emotional state of the user while they are using a product or service, and to collaborate with external information sources to provide the audio or visual content.

[0365] "User" refers to an individual or legal entity that uses the system or device.

[0366] "Information" refers to communication data and other related data related to the user, including text, audio, and visual data.

[0367] "Device" refers to hardware or software designed to perform a specific function.

[0368] "Processing" refers to a series of operations that convert collected information into a format that can be analyzed or interpreted.

[0369] A "generative artificial intelligence model" refers to artificial intelligence technology that generates new information from data or identifies patterns.

[0370] "Emotional state" refers to the user's emotional situation or psychological tendencies, and is classified into categories such as joy, sadness, and anger.

[0371] "Recommendation" means suggesting a particular action or choice to a user, and this includes feedback and advice.

[0372] "Audio or visual content" refers to media content such as audio messages, music, videos, and images.

[0373] "External information sources" refer to databases and service providers that exist outside the system, providing additional data and functionality.

[0374] This system is designed to analyze users' emotional states and provide appropriate feedback under specific conditions. The server first obtains user permission to collect communication data from messaging platforms and other databases. The collected data is then converted into an analyzable format using a processor on the server. During this process, Google Cloud's natural language processing APIs are utilized for tokenizing text data and performing sentiment analysis.

[0375] Generative artificial intelligence models use this data to analyze the user's emotional state. During the analysis, they understand the user's context and classify it into emotional categories such as joy, sadness, and anger. Based on these results, the server evaluates the emotional state and determines the user's health status. Algorithms built on specific criteria support this process.

[0376] Depending on the user's emotional state, the server collaborates with external information sources to recommend relaxing music, for example, through online music streaming services. This is effective when the server determines that the user is experiencing stress. The recommended music and visual content are provided using APIs from services such as Spotify and Apple Music.

[0377] For example, if analysis indicates that a user is experiencing stress during the online shopping process, a recommendation such as "Would you like to stream some relaxing classical music?" might be displayed. Simultaneously, coupons for health-related products and services may also be issued.

[0378] An example of a prompt for a generative AI model would be: "Show me a method for suggesting relaxing music when a user is feeling anxious. Then, generate a list of items that he might be interested in for relaxation."

[0379] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0380] Step 1:

[0381] The server, with the user's permission, collects communication data from messaging platforms, social networking services (SNS), and other sources. The input for this step consists of text and voice data from multiple platforms. The server then stores this data in a secure database.

[0382] Step 2:

[0383] The server preprocesses the collected data using Google Cloud's natural language processing API. The input consists of stored raw text and audio data. At this stage, the server converts the audio data to text, performs data processing such as tokenization and removal of irrelevant information, and outputs the data in a parseable format.

[0384] Step 3:

[0385] The server inputs pre-processed data into a generative artificial intelligence model to analyze emotional states. The input for this step is pre-processed text data. The generative AI model understands the context of the data, classifies it into emotional categories such as joy and sadness, and outputs the results of the emotional state analysis.

[0386] Step 4:

[0387] The server evaluates the user's health status based on the analyzed emotional state and makes a judgment based on specific criteria. The input for this step is emotional state data obtained from a generative artificial intelligence model. The server then performs an operation to assess health risks and output the judgment result.

[0388] Step 5:

[0389] The server provides feedback to the user based on their emotional state and recommends appropriate audio or visual content in conjunction with external information sources. The input is the result of a health status assessment. The server, for example, uses a music streaming service API to recommend relaxing music and generates output to provide.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] [Third Embodiment]

[0394] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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".

[0406] This invention provides a system that monitors the mental health status of users and provides feedback as needed. This system mainly consists of a server and terminals and performs analysis based on communication data generated in daily life.

[0407] The server first collects communication data, such as daily posts and messages, from social networking services (SNS) and messaging applications, after obtaining the user's consent. This data is stored in a secure database.

[0408] The server then preprocesses the collected data, using natural language processing techniques to extract important keywords and phrases. The audio data is converted to text using speech recognition technology and analyzed together.

[0409] Next, pre-processed data is analyzed using generative artificial intelligence to evaluate the user's emotional state. This analysis categorizes emotions as positive, negative, or neutral, and also assesses emotional trends based on time series.

[0410] The terminal provides feedback to the user based on analysis results sent from the server. The feedback will prompt specific actions regarding changes from the normal state or matters requiring attention.

[0411] For example, if a user frequently uses negative expressions such as "tired," "stressed," or "I can't do this anymore" in multiple social media posts, the server will detect this as an emotional tendency. If the risk assessment determines that there are concerns about the user's mental health, the device will send feedback to the user such as, "Your recent posts suggest you are experiencing mental stress. Please take some time to relax or consider consulting a professional."

[0412] Through this system, users will be able to recognize their own mental health status and take necessary actions early on.

[0413] The following describes the processing flow.

[0414] Step 1:

[0415] The server, with the user's permission, collects communication data through APIs of social networking services and messaging services. This includes text messages and voice messages.

[0416] Step 2:

[0417] The server collects data and stores it in a database. As a security measure, the data is encrypted, and a user ID is associated with a timestamp.

[0418] Step 3:

[0419] The server preprocesses the stored data. Text data is tokenized using natural language processing techniques to remove extraneous symbols and stop words. Speech data is converted to text using speech recognition techniques.

[0420] Step 4:

[0421] The server inputs the pre-processed data into a sentiment analysis algorithm. This algorithm identifies positive, negative, and neutral emotions from the data and assigns a sentiment score to each data point.

[0422] Step 5:

[0423] The server analyzes the sentiment score over time to assess recent sentiment trends. If a negative trend persists over a long period compared to past data, the risk score is increased.

[0424] Step 6:

[0425] The server compares the risk score it determines to a specific threshold and sets a warning flag if the mental health risk is high.

[0426] Step 7:

[0427] The device receives results from the server and notifies the user of mental health-related feedback. The notification includes advice and behavioral recommendations tailored to the user's condition.

[0428] Step 8:

[0429] Review the feedback received from users and select the necessary actions based on the advice provided. This may include practicing relaxation techniques or consulting with a professional.

[0430] (Example 1)

[0431] 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."

[0432] In modern society, there is a need to efficiently monitor users' mental health using data obtained from the communication methods they use daily, and to provide timely advice and warnings. However, conventional methods present challenges such as difficulty in properly analyzing collected data, understanding emotional tendencies, and providing effective feedback to users.

[0433] 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.

[0434] In this invention, the server includes means for collecting the user's communication content, means for converting the communication content into a standardized format, and means for analyzing the emotional state from the communication content using machine learning techniques. This makes it possible to efficiently monitor the user's mental health and provide advice at an appropriate time.

[0435] "Users" refer to individuals or organizations that use this system and are the subjects of analysis regarding their mental health.

[0436] "Communication content" refers to information such as posts and messages sent by users through social networking services (SNS) and messaging platforms.

[0437] "Standardized format" refers to information that has been transformed into a unified data structure for analysis.

[0438] "Machine learning techniques" refer to algorithms and methods used to analyze data and derive rules and patterns from it.

[0439] "Emotional state" refers to the feelings and mental state derived from the workings of a user's mind. It can also be classified into positive, negative, neutral, etc.

[0440] "Evaluation" refers to the process of analyzing the emotional tendencies of users obtained from the analysis results and determining their health status.

[0441] "Advice" refers to recommended actions and precautions provided to users based on their assessed mental health status.

[0442] When a user uses this system, the server first collects the user's communication content through social networking services (SNS) and messaging platforms. This collection process can be automated by utilizing APIs. Communication content may include both text and audio data. Audio data is converted to text using speech recognition software.

[0443] The server converts the collected communication content into a standardized format. This uses natural language processing techniques, specifically morphological analysis and stop word removal to extract important parts of the text. Open-source natural language processing libraries are generally used as the software for this process.

[0444] Next, the server uses machine learning techniques to analyze the user's emotional state from the aforementioned communication content. This process employs a generative AI model, which may be given a prompt such as, "Based on this text, classify the user's emotions as positive, negative, or neutral." This analysis evaluates the user's emotional state trends over time and records them in a database.

[0445] The device provides advice to the user based on evaluation results generated by the server. This advice is designed to support the user's mental health. For example, if the emotional tendencies indicate a high level of psychological stress, feedback such as, "It appears you've been experiencing increased mental stress recently. We recommend taking a break or consulting a professional," will be provided.

[0446] In this way, the present invention realizes a system that efficiently monitors a user's mental health based on their communication content and provides advice at the appropriate time. This enables users to become aware of their own mental health and take appropriate action when necessary.

[0447] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0448] Step 1:

[0449] The server collects user communications. Specifically, it obtains text and audio data through APIs of social networking services (SNS) and messaging platforms. In this process, it securely accesses the data using authentication information obtained in advance from the user. The input is raw text and audio data provided by each platform, and the output is unstructured raw data.

[0450] Step 2:

[0451] The server converts the collected audio data into text using speech recognition technology. Specifically, it uses speech recognition software to convert audio into text data. The input for this step is audio data, and the output is the corresponding text data.

[0452] Step 3:

[0453] The server preprocesses text data using natural language processing and converts it into a standardized format. Specific operations include stop word removal, morphological analysis, and extraction of important keywords and phrases. The input for this step is text data, and the output is text converted into a parseable format.

[0454] Step 4:

[0455] The server analyzes emotional states from pre-processed text data using a generative AI model. The prompt instructs the AI ​​model to "evaluate the user's emotional state from this text and classify it as positive, negative, or neutral." The input is standardized text data, and the output is the emotional category and its evaluation result.

[0456] Step 5:

[0457] The server evaluates emotional trends over time based on the analysis results and stores the evaluation results in a database. It tracks the analyzed emotional states over time, clarifying the changes in emotions. The input for this step is the emotional evaluation results, and the output is the trend data stored in the database.

[0458] Step 6:

[0459] The device receives evaluation results sent from the server and provides advice to the user. Specifically, it notifies the user of feedback when changes in emotions or psychological burdens are detected. The input is emotional tendency data, and the output is an advice message displayed to the user.

[0460] (Application Example 1)

[0461] 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."

[0462] In recent years, with the spread of e-commerce, consumer purchasing behavior has become more susceptible to psychological factors. However, conventional electronic payment systems do not adequately support purchasing decisions while considering the user's mental health. Therefore, there is a need for a system that enables consumers to maintain their mental well-being while making purchases. The challenge is to provide a system that analyzes the user's emotional state in real time and supports the alignment of purchasing behavior with health awareness.

[0463] 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.

[0464] In this invention, the server includes means for collecting user communication information, means for preprocessing the information and converting it into an analyzable format, means for analyzing the emotional state from the information using generative artificial intelligence, means for collecting the user's purchase history and recommending product purchases based on their mental state, and means for providing spending management feedback related to purchases. This enables users to make appropriate product choices and engage in healthy consumption behavior while considering their own mental health state.

[0465] "User communication information" refers to text and audio data that users send and receive through social networking services (SNS) and messaging applications.

[0466] "Means of preprocessing and converting into an analyzable format" refers to techniques for organizing and processing raw data into a form that is easy to analyze, and includes processes such as deleting unnecessary information and converting it to text.

[0467] "Generative artificial intelligence" is a type of AI that has the ability to generate new information based on collected data, and is particularly used for pattern recognition and sentiment analysis.

[0468] "Means for analyzing emotional states" refers to the technical process of identifying emotions such as positive, negative, and neutral from users' statements and communication data using natural language processing technology, etc.

[0469] "User purchase history" refers to data about a user's past purchasing behavior, including information such as product name, purchase date and time, and price.

[0470] "Methods for recommending product purchases" refer to technologies that identify and suggest products that users should consider purchasing, based on their analyzed emotional state and purchase history.

[0471] "Purchase-related spending management feedback" is a system that provides users with feedback and advice on budget management and spending trends in relation to their purchasing behavior.

[0472] This system works by analyzing the user's mental state based on their communication information and purchase history, and then providing product purchase recommendations and spending management feedback based on that analysis. The server securely collects user communication information from social networking services (SNS) and messaging platforms.

[0473] The server preprocesses the collected information using Python and natural language processing libraries (NLTK and spaCy) to extract necessary keywords and sentiment information in text format. If audio data is included, speech recognition technology is used to convert it to text for analysis.

[0474] Next, TensorFlow is used as a generative artificial intelligence, and the server analyzes the user's emotional state based on this pre-processed data. The emotional state is classified into categories such as positive, negative, and neutral, and the temporal fluctuations of the emotion are also evaluated.

[0475] The user's purchase history is retrieved from a database, and an algorithm is executed that recommends products to the user in combination with an analyzed emotional state. This purchase recommendation presents the most suitable products while taking the user's mental well-being into consideration. The device also provides the user with spending management feedback regarding purchases, offering guidance to help them stay within their budget.

[0476] This allows users to make purchases that align with their mental state and provides support to prevent impulse buying and overspending. For example, if a user frequently uses negative expressions such as "I'm tired" on social media, relaxation-related products will be recommended, and a notification will appear on their device saying, "Let's think about sorting out your feelings and review your budget plan again."

[0477] An example of a prompt might be, "Build purchase insights based on user sentiment analysis and recommend the most suitable products."

[0478] This system can promote healthier consumer behavior by linking users' mental health with their purchasing decisions.

[0479] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0480] Step 1:

[0481] The server collects communication information from users' social networking services (SNS) and messaging apps. This information includes text messages and audio data. The server stores this data in secure cloud storage. The input is raw communication data, and the output is data stored securely in storage.

[0482] Step 2:

[0483] The server uses Python and natural language processing libraries (NLTK and spaCy) to preprocess the collected information into a parseable format. Audio data is converted to text using speech recognition technology. Specifically, keywords are extracted and emotional tone is analyzed. The input is the collected communication data, and the output is the analysis results of keywords and emotional tone.

[0484] Step 3:

[0485] The server utilizes a generative AI model to analyze the user's emotional state from preprocessed data. Using TensorFlow, the data is categorized into positive, negative, and neutral emotional states. The time-series fluctuations of the emotions are also evaluated. The input is preprocessed data, and the output is the user's emotional analysis result.

[0486] Step 4:

[0487] The server retrieves the user's purchase history from the database and recommends the most suitable products by combining it with the sentiment analysis results. This recommendation is based on an algorithm that takes into account past purchase data and the user's current mental state. The input is the purchase history and sentiment analysis results, and the output is a list of recommended products.

[0488] Step 5:

[0489] The device provides the user with spending management feedback related to purchases. This feedback includes points to note and advice for staying within budget. Inputs are emotional state and purchase history, and output is a feedback message.

[0490] 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.

[0491] This invention provides a system that analyzes a user's emotional state based on their communication data, determines their mental health status, and provides feedback. Furthermore, by combining this system with an emotion engine, more accurate emotion recognition can be achieved.

[0492] The server first obtains user permission and then collects text messages and voice data from social networking services (SNS) and messaging platforms. This data is stored in a secure database and used for subsequent analysis.

[0493] Next, the server preprocesses the data using natural language processing techniques. The audio data is converted to text, all data is tokenized, and unnecessary information is removed.

[0494] This preprocessed data is analyzed by an emotion engine. The emotion engine has an algorithm that classifies the data according to multiple emotion categories (e.g., joy, sadness, anger, etc.). This algorithm utilizes training data from generative artificial intelligence to understand the context of the data and determine the emotion.

[0495] Based on the analysis results obtained from the emotion engine, the server compares them with past emotion data to determine the user's mental health status. If the determined status exceeds a certain threshold, it is judged to be at risk, and countermeasures are taken promptly.

[0496] Ultimately, the device provides the user with appropriate feedback based on the information received from the server. This feedback includes specific advice regarding mental health, such as points to note and suggestions for improvement.

[0497] For example, if a user frequently posts messages expressing anger, the emotion engine will detect this and determine that negative emotions are persisting. Based on this, the device will send feedback to the user such as, "It appears you are experiencing stress. Please engage in relaxing activities or consider counseling." Through this system, the aim is to help users recognize changes in their emotions early on and choose healthy behaviors.

[0498] The following describes the processing flow.

[0499] Step 1:

[0500] The server collects text and audio data from social networking services (SNS) and messaging platforms based on user permission. This provides everyday communication data.

[0501] Step 2:

[0502] The server preprocesses the collected data. Audio data is transcribed using speech recognition technology, all data is tokenized to remove unnecessary information, and converted into a format suitable for sentiment analysis.

[0503] Step 3:

[0504] The server inputs pre-processed data into the emotion engine. The emotion engine uses natural language processing techniques to classify the data into multiple emotion categories. In this process, the emotion engine's algorithm understands the context and analyzes the emotions contained in the data with high accuracy.

[0505] Step 4:

[0506] The server evaluates the user's emotional state trends based on the analysis results from the emotion engine. This evaluation includes comparison with past emotional data, allowing for a time-series understanding of changes in positive, negative, and neutral emotions.

[0507] Step 5:

[0508] The server determines the user's mental health status based on their emotional state tendencies. If the determination exceeds a certain threshold, a warning flag is set, indicating a high mental health risk.

[0509] Step 6:

[0510] Based on the judgment results received by the server, the device generates and notifies the user of feedback. The feedback includes emotional tendencies and necessary improvements.

[0511] Step 7:

[0512] The user reviews the feedback they receive and considers and implements recommended actions. This includes stress-relieving activities and seeking professional help.

[0513] (Example 2)

[0514] 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."

[0515] The diversification of modern communication methods has created a need to appropriately monitor users' psychological health and provide timely feedback. Conventional methods make it difficult to perform real-time emotional analysis or quickly determine changes in psychological state, potentially causing users to miss opportunities to receive appropriate care. This invention aims to solve this problem by performing more accurate emotional analysis and health status assessment from information obtained through users' communication, and promptly notifying users.

[0516] 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.

[0517] In this invention, the server includes means for collecting user communication information, means for preprocessing the information and converting it into an analyzable format, and means for analyzing the emotional state from the information using generative artificial intelligence. This makes it possible to determine the user's psychological health state with high accuracy and speed, and to provide necessary feedback in a timely manner.

[0518] "User communication information" refers to information such as text messages and voice data that users send and receive through the digital communication platform.

[0519] "Preprocessing" refers to data cleansing, transformation, and tokenization processes performed to convert collected data into a format that is easy to analyze.

[0520] "Generative artificial intelligence" is an AI model technology that analyzes data to identify context and determine emotional states through the generation of text and data patterns.

[0521] "Means for analyzing emotional states" refer to algorithms and devices used to classify emotions such as joy, sadness, and anger from data and to evaluate the user's psychological state.

[0522] "Psychological health status" refers to the level of a user's mental and emotional well-being, and is assessed based on emotional analysis.

[0523] "Means of providing responses" refers to technical means used to present users with information and advice regarding their psychological health status and potential improvements based on analysis results.

[0524] A "digital device" is an electronic device capable of receiving and displaying digital data, such as a personal computer, smartphone, or tablet.

[0525] This invention is a system that analyzes information obtained from users' digital communications to assess their mental health and provide feedback. The server securely collects text messages and voice data from communication platforms with the user's permission. The collected data is stored in a database and subsequently used for analysis. Specifically, the system utilizes cloud-based server storage as hardware and employs API technology (e.g., a general-purpose data acquisition API) for data collection as software.

[0526] The server utilizes natural language processing techniques to preprocess the acquired data. Audio data is converted to text using speech recognition software (e.g., a speech-to-text engine), and then tokenized and denoised using a Python natural language processing library (e.g., spaCy).

[0527] This pre-processed data is analyzed by an emotion analysis engine utilizing a generative AI model. The generative AI model (e.g., an advanced text analysis AI) classifies the data according to various emotion categories and estimates the emotional state. Based on this, the server compares it with historical data to assess the psychological health status. If the risk exceeds a certain threshold, corrective action is taken immediately.

[0528] The device provides feedback to the user based on information received from the server. For example, if a user consistently posts messages indicating "sadness," the device might provide feedback such as, "It seems you've been feeling sad lately. Try incorporating some lighthearted activities to lift your spirits."

[0529] Specific examples of prompt statements are as follows:

[0530] "Please analyze the emotions expressed in messages recently sent by users. Classify them into one of three categories: joy, sadness, or anger, and indicate the degree of each emotion numerically. Also, please provide a comparison with past data."

[0531] This system will enable users to understand their emotions earlier and take appropriate health management actions.

[0532] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0533] Step 1:

[0534] The server, with the user's permission, collects text messages and voice data from the communication platform. It receives message data obtained via an API as input and stores it directly in the database. Specifically, the server issues API requests, encrypts the retrieved data, and stores it in cloud storage.

[0535] Step 2:

[0536] The server converts the collected audio data into text using speech recognition software. It takes audio files as input and generates corresponding text data as output. Specifically, the server uses a speech recognition API to integrate the obtained text with other text data in the database.

[0537] Step 3:

[0538] The server preprocesses the text data. It takes integrated text data as input and generates tokenized, clean data as output. This process uses Python's natural language processing library, where the server tokenizes the data and removes unwanted noise.

[0539] Step 4:

[0540] The server inputs pre-processed data into a generating AI model and performs sentiment analysis. Tokenized text data is sent to the AI ​​model along with prompts, and the output includes sentiment categories (joy, sadness, anger, etc.) and their intensity. Specifically, the server creates prompts and retrieves the analysis results through the AI ​​model.

[0541] Step 5:

[0542] The server determines the mental health status by comparing the results of sentiment analysis with historical data. It uses current sentiment analysis data and past sentiment data as input, and performs a health status assessment as output. The server uses statistical analysis techniques for pattern recognition.

[0543] Step 6:

[0544] The device provides feedback to the user based on health status assessment results received from the server. It receives assessment results as input and displays specific advice as output. Specifically, the device displays a pop-up notification to the user, prompting appropriate action.

[0545] (Application Example 2)

[0546] 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."

[0547] In modern society, busy lifestyles and information overload are leading to increased consumer stress and emotional instability. In this context, there is a need for ways to improve the consumer purchasing experience and reduce stress. Particularly in e-commerce, the challenge lies in providing a better purchasing experience by offering appropriate feedback and suggestions tailored to the individual consumer's emotional state.

[0548] 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.

[0549] In this invention, the server includes a device for collecting user information, a device for processing the information and converting it into an analyzable format, and a device for analyzing the emotional state from the information using a generative artificial intelligence model. This makes it possible to recommend relevant audio or visual content according to the emotional state of the user while they are using a product or service, and to collaborate with external information sources to provide the audio or visual content.

[0550] "User" refers to an individual or legal entity that uses the system or device.

[0551] "Information" refers to communication data and other related data related to the user, including text, audio, and visual data.

[0552] "Device" refers to hardware or software designed to perform a specific function.

[0553] "Processing" refers to a series of operations that convert collected information into a format that can be analyzed or interpreted.

[0554] A "generative artificial intelligence model" refers to artificial intelligence technology that generates new information from data or identifies patterns.

[0555] "Emotional state" refers to the user's emotional situation or psychological tendencies, and is classified into categories such as joy, sadness, and anger.

[0556] "Recommendation" means suggesting a particular action or choice to a user, and this includes feedback and advice.

[0557] "Audio or visual content" refers to media content such as audio messages, music, videos, and images.

[0558] "External information sources" refer to databases and service providers that exist outside the system, providing additional data and functionality.

[0559] This system is designed to analyze users' emotional states and provide appropriate feedback under specific conditions. The server first obtains user permission to collect communication data from messaging platforms and other databases. The collected data is then converted into an analyzable format using a processor on the server. During this process, Google Cloud's natural language processing APIs are utilized for tokenizing text data and performing sentiment analysis.

[0560] Generative artificial intelligence models use this data to analyze the user's emotional state. During the analysis, they understand the user's context and classify it into emotional categories such as joy, sadness, and anger. Based on these results, the server evaluates the emotional state and determines the user's health status. Algorithms built on specific criteria support this process.

[0561] Depending on the user's emotional state, the server collaborates with external information sources to recommend relaxing music, for example, through online music streaming services. This is effective when the server determines that the user is experiencing stress. The recommended music and visual content are provided using APIs from services such as Spotify and Apple Music.

[0562] For example, if analysis indicates that a user is experiencing stress during the online shopping process, a recommendation such as "Would you like to stream some relaxing classical music?" might be displayed. Simultaneously, coupons for health-related products and services may also be issued.

[0563] An example of a prompt for a generative AI model would be: "Show me a method for suggesting relaxing music when a user is feeling anxious. Then, generate a list of items that he might be interested in for relaxation."

[0564] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0565] Step 1:

[0566] The server, with the user's permission, collects communication data from messaging platforms, social networking services (SNS), and other sources. The input for this step consists of text and voice data from multiple platforms. The server then stores this data in a secure database.

[0567] Step 2:

[0568] The server preprocesses the collected data using Google Cloud's natural language processing API. The input consists of stored raw text and audio data. At this stage, the server converts the audio data to text, performs data processing such as tokenization and removal of irrelevant information, and outputs the data in a parseable format.

[0569] Step 3:

[0570] The server inputs pre-processed data into a generative artificial intelligence model to analyze emotional states. The input for this step is pre-processed text data. The generative AI model understands the context of the data, classifies it into emotional categories such as joy and sadness, and outputs the results of the emotional state analysis.

[0571] Step 4:

[0572] The server evaluates the user's health status based on the analyzed emotional state and makes a judgment based on specific criteria. The input for this step is emotional state data obtained from a generative artificial intelligence model. The server then performs an operation to assess health risks and output the judgment result.

[0573] Step 5:

[0574] The server provides feedback to the user based on their emotional state and recommends appropriate audio or visual content in conjunction with external information sources. The input is the result of a health status assessment. The server, for example, uses a music streaming service API to recommend relaxing music and generates output to provide.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] [Fourth Embodiment]

[0579] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0580] 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.

[0581] 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).

[0582] 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.

[0583] 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.

[0584] 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).

[0585] 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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".

[0592] This invention provides a system that monitors the mental health status of users and provides feedback as needed. This system mainly consists of a server and terminals and performs analysis based on communication data generated in daily life.

[0593] The server first collects communication data, such as daily posts and messages, from social networking services (SNS) and messaging applications, after obtaining the user's consent. This data is stored in a secure database.

[0594] The server then preprocesses the collected data, using natural language processing techniques to extract important keywords and phrases. The audio data is converted to text using speech recognition technology and analyzed together.

[0595] Next, pre-processed data is analyzed using generative artificial intelligence to evaluate the user's emotional state. This analysis categorizes emotions as positive, negative, or neutral, and also assesses emotional trends based on time series.

[0596] The terminal provides feedback to the user based on analysis results sent from the server. The feedback will prompt specific actions regarding changes from the normal state or matters requiring attention.

[0597] For example, if a user frequently uses negative expressions such as "tired," "stressed," or "I can't do this anymore" in multiple social media posts, the server will detect this as an emotional tendency. If the risk assessment determines that there are concerns about the user's mental health, the device will send feedback to the user such as, "Your recent posts suggest you are experiencing mental stress. Please take some time to relax or consider consulting a professional."

[0598] Through this system, users will be able to recognize their own mental health status and take necessary actions early on.

[0599] The following describes the processing flow.

[0600] Step 1:

[0601] The server, with the user's permission, collects communication data through APIs of social networking services and messaging services. This includes text messages and voice messages.

[0602] Step 2:

[0603] The server collects data and stores it in a database. As a security measure, the data is encrypted, and a user ID is associated with a timestamp.

[0604] Step 3:

[0605] The server preprocesses the stored data. Text data is tokenized using natural language processing techniques to remove extraneous symbols and stop words. Speech data is converted to text using speech recognition techniques.

[0606] Step 4:

[0607] The server inputs the pre-processed data into a sentiment analysis algorithm. This algorithm identifies positive, negative, and neutral emotions from the data and assigns a sentiment score to each data point.

[0608] Step 5:

[0609] The server analyzes the sentiment score over time to assess recent sentiment trends. If a negative trend persists over a long period compared to past data, the risk score is increased.

[0610] Step 6:

[0611] The server compares the risk score it determines to a specific threshold and sets a warning flag if the mental health risk is high.

[0612] Step 7:

[0613] The device receives results from the server and notifies the user of mental health-related feedback. The notification includes advice and behavioral recommendations tailored to the user's condition.

[0614] Step 8:

[0615] Review the feedback received from users and select the necessary actions based on the advice provided. This may include practicing relaxation techniques or consulting with a professional.

[0616] (Example 1)

[0617] 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".

[0618] In modern society, there is a need to efficiently monitor users' mental health using data obtained from the communication methods they use daily, and to provide timely advice and warnings. However, conventional methods present challenges such as difficulty in properly analyzing collected data, understanding emotional tendencies, and providing effective feedback to users.

[0619] 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.

[0620] In this invention, the server includes means for collecting the user's communication content, means for converting the communication content into a standardized format, and means for analyzing the emotional state from the communication content using machine learning techniques. This makes it possible to efficiently monitor the user's mental health and provide advice at an appropriate time.

[0621] "Users" refer to individuals or organizations that use this system and are the subjects of analysis regarding their mental health.

[0622] "Communication content" refers to information such as posts and messages sent by users through social networking services (SNS) and messaging platforms.

[0623] "Standardized format" refers to information that has been transformed into a unified data structure for analysis.

[0624] "Machine learning techniques" refer to algorithms and methods used to analyze data and derive rules and patterns from it.

[0625] "Emotional state" refers to the feelings and mental state derived from the workings of a user's mind. It can also be classified into positive, negative, neutral, etc.

[0626] "Evaluation" refers to the process of analyzing the emotional tendencies of users obtained from the analysis results and determining their health status.

[0627] "Advice" refers to recommended actions and precautions provided to users based on their assessed mental health status.

[0628] When a user uses this system, the server first collects the user's communication content through social networking services (SNS) and messaging platforms. This collection process can be automated by utilizing APIs. Communication content may include both text and audio data. Audio data is converted to text using speech recognition software.

[0629] The server converts the collected communication content into a standardized format. This uses natural language processing techniques, specifically morphological analysis and stop word removal to extract important parts of the text. Open-source natural language processing libraries are generally used as the software for this process.

[0630] Next, the server uses machine learning techniques to analyze the user's emotional state from the aforementioned communication content. This process employs a generative AI model, which may be given a prompt such as, "Based on this text, classify the user's emotions as positive, negative, or neutral." This analysis evaluates the user's emotional state trends over time and records them in a database.

[0631] The device provides advice to the user based on evaluation results generated by the server. This advice is designed to support the user's mental health. For example, if the emotional tendencies indicate a high level of psychological stress, feedback such as, "It appears you've been experiencing increased mental stress recently. We recommend taking a break or consulting a professional," will be provided.

[0632] In this way, the present invention realizes a system that efficiently monitors a user's mental health based on their communication content and provides advice at the appropriate time. This enables users to become aware of their own mental health and take appropriate action when necessary.

[0633] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0634] Step 1:

[0635] The server collects user communications. Specifically, it obtains text and audio data through APIs of social networking services (SNS) and messaging platforms. In this process, it securely accesses the data using authentication information obtained in advance from the user. The input is raw text and audio data provided by each platform, and the output is unstructured raw data.

[0636] Step 2:

[0637] The server converts the collected audio data into text using speech recognition technology. Specifically, it uses speech recognition software to convert audio into text data. The input for this step is audio data, and the output is the corresponding text data.

[0638] Step 3:

[0639] The server preprocesses text data using natural language processing and converts it into a standardized format. Specific operations include stop word removal, morphological analysis, and extraction of important keywords and phrases. The input for this step is text data, and the output is text converted into a parseable format.

[0640] Step 4:

[0641] The server analyzes emotional states from pre-processed text data using a generative AI model. The prompt instructs the AI ​​model to "evaluate the user's emotional state from this text and classify it as positive, negative, or neutral." The input is standardized text data, and the output is the emotional category and its evaluation result.

[0642] Step 5:

[0643] The server evaluates emotional trends over time based on the analysis results and stores the evaluation results in a database. It tracks the analyzed emotional states over time, clarifying the changes in emotions. The input for this step is the emotional evaluation results, and the output is the trend data stored in the database.

[0644] Step 6:

[0645] The device receives evaluation results sent from the server and provides advice to the user. Specifically, it notifies the user of feedback when changes in emotions or psychological burdens are detected. The input is emotional tendency data, and the output is an advice message displayed to the user.

[0646] (Application Example 1)

[0647] 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".

[0648] In recent years, with the spread of e-commerce, consumer purchasing behavior has become more susceptible to psychological factors. However, conventional electronic payment systems do not adequately support purchasing decisions while considering the user's mental health. Therefore, there is a need for a system that enables consumers to maintain their mental well-being while making purchases. The challenge is to provide a system that analyzes the user's emotional state in real time and supports the alignment of purchasing behavior with health awareness.

[0649] 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.

[0650] In this invention, the server includes means for collecting user communication information, means for preprocessing the information and converting it into an analyzable format, means for analyzing the emotional state from the information using generative artificial intelligence, means for collecting the user's purchase history and recommending product purchases based on their mental state, and means for providing spending management feedback related to purchases. This enables users to make appropriate product choices and engage in healthy consumption behavior while considering their own mental health state.

[0651] "User communication information" refers to text and audio data that users send and receive through social networking services (SNS) and messaging applications.

[0652] "Means of preprocessing and converting into an analyzable format" refers to techniques for organizing and processing raw data into a form that is easy to analyze, and includes processes such as deleting unnecessary information and converting it to text.

[0653] "Generative artificial intelligence" is a type of AI that has the ability to generate new information based on collected data, and is particularly used for pattern recognition and sentiment analysis.

[0654] "Means for analyzing emotional states" refers to the technical process of identifying emotions such as positive, negative, and neutral from users' statements and communication data using natural language processing technology, etc.

[0655] "User purchase history" refers to data about a user's past purchasing behavior, including information such as product name, purchase date and time, and price.

[0656] "Methods for recommending product purchases" refer to technologies that identify and suggest products that users should consider purchasing, based on their analyzed emotional state and purchase history.

[0657] "Purchase-related spending management feedback" is a system that provides users with feedback and advice on budget management and spending trends in relation to their purchasing behavior.

[0658] This system works by analyzing the user's mental state based on their communication information and purchase history, and then providing product purchase recommendations and spending management feedback based on that analysis. The server securely collects user communication information from social networking services (SNS) and messaging platforms.

[0659] The server preprocesses the collected information using Python and natural language processing libraries (NLTK and spaCy) to extract necessary keywords and sentiment information in text format. If audio data is included, speech recognition technology is used to convert it to text for analysis.

[0660] Next, TensorFlow is used as a generative artificial intelligence, and the server analyzes the user's emotional state based on this pre-processed data. The emotional state is classified into categories such as positive, negative, and neutral, and the temporal fluctuations of the emotion are also evaluated.

[0661] The user's purchase history is retrieved from a database, and an algorithm is executed that recommends products to the user in combination with an analyzed emotional state. This purchase recommendation presents the most suitable products while taking the user's mental well-being into consideration. The device also provides the user with spending management feedback regarding purchases, offering guidance to help them stay within their budget.

[0662] This allows users to make purchases that align with their mental state and provides support to prevent impulse buying and overspending. For example, if a user frequently uses negative expressions such as "I'm tired" on social media, relaxation-related products will be recommended, and a notification will appear on their device saying, "Let's think about sorting out your feelings and review your budget plan again."

[0663] An example of a prompt might be, "Build purchase insights based on user sentiment analysis and recommend the most suitable products."

[0664] This system can promote healthier consumer behavior by linking users' mental health with their purchasing decisions.

[0665] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0666] Step 1:

[0667] The server collects communication information from users' social networking services (SNS) and messaging apps. This information includes text messages and audio data. The server stores this data in secure cloud storage. The input is raw communication data, and the output is data stored securely in storage.

[0668] Step 2:

[0669] The server uses Python and natural language processing libraries (NLTK and spaCy) to preprocess the collected information into a parseable format. Audio data is converted to text using speech recognition technology. Specifically, keywords are extracted and emotional tone is analyzed. The input is the collected communication data, and the output is the analysis results of keywords and emotional tone.

[0670] Step 3:

[0671] The server utilizes a generative AI model to analyze the user's emotional state from preprocessed data. Using TensorFlow, the data is categorized into positive, negative, and neutral emotional states. The time-series fluctuations of the emotions are also evaluated. The input is preprocessed data, and the output is the user's emotional analysis result.

[0672] Step 4:

[0673] The server retrieves the user's purchase history from the database and recommends the most suitable products by combining it with the sentiment analysis results. This recommendation is based on an algorithm that takes into account past purchase data and the user's current mental state. The input is the purchase history and sentiment analysis results, and the output is a list of recommended products.

[0674] Step 5:

[0675] The device provides the user with spending management feedback related to purchases. This feedback includes points to note and advice for staying within budget. Inputs are emotional state and purchase history, and output is a feedback message.

[0676] 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.

[0677] This invention provides a system that analyzes a user's emotional state based on their communication data, determines their mental health status, and provides feedback. Furthermore, by combining this system with an emotion engine, more accurate emotion recognition can be achieved.

[0678] The server first obtains user permission and then collects text messages and voice data from social networking services (SNS) and messaging platforms. This data is stored in a secure database and used for subsequent analysis.

[0679] Next, the server preprocesses the data using natural language processing techniques. The audio data is converted to text, all data is tokenized, and unnecessary information is removed.

[0680] This preprocessed data is analyzed by an emotion engine. The emotion engine has an algorithm that classifies the data according to multiple emotion categories (e.g., joy, sadness, anger, etc.). This algorithm utilizes training data from generative artificial intelligence to understand the context of the data and determine the emotion.

[0681] Based on the analysis results obtained from the emotion engine, the server compares them with past emotion data to determine the user's mental health status. If the determined status exceeds a certain threshold, it is judged to be at risk, and countermeasures are taken promptly.

[0682] Ultimately, the device provides the user with appropriate feedback based on the information received from the server. This feedback includes specific advice regarding mental health, such as points to note and suggestions for improvement.

[0683] For example, if a user frequently posts messages expressing anger, the emotion engine will detect this and determine that negative emotions are persisting. Based on this, the device will send feedback to the user such as, "It appears you are experiencing stress. Please engage in relaxing activities or consider counseling." Through this system, the aim is to help users recognize changes in their emotions early on and choose healthy behaviors.

[0684] The following describes the processing flow.

[0685] Step 1:

[0686] The server collects text and audio data from social networking services (SNS) and messaging platforms based on user permission. This provides everyday communication data.

[0687] Step 2:

[0688] The server preprocesses the collected data. Audio data is transcribed using speech recognition technology, all data is tokenized to remove unnecessary information, and converted into a format suitable for sentiment analysis.

[0689] Step 3:

[0690] The server inputs pre-processed data into the emotion engine. The emotion engine uses natural language processing techniques to classify the data into multiple emotion categories. In this process, the emotion engine's algorithm understands the context and analyzes the emotions contained in the data with high accuracy.

[0691] Step 4:

[0692] The server evaluates the user's emotional state trends based on the analysis results from the emotion engine. This evaluation includes comparison with past emotional data, allowing for a time-series understanding of changes in positive, negative, and neutral emotions.

[0693] Step 5:

[0694] The server determines the user's mental health status based on their emotional state tendencies. If the determination exceeds a certain threshold, a warning flag is set, indicating a high mental health risk.

[0695] Step 6:

[0696] Based on the judgment results received by the server, the device generates and notifies the user of feedback. The feedback includes emotional tendencies and necessary improvements.

[0697] Step 7:

[0698] The user reviews the feedback they receive and considers and implements recommended actions. This includes stress-relieving activities and seeking professional help.

[0699] (Example 2)

[0700] 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".

[0701] The diversification of modern communication methods has created a need to appropriately monitor users' psychological health and provide timely feedback. Conventional methods make it difficult to perform real-time emotional analysis or quickly determine changes in psychological state, potentially causing users to miss opportunities to receive appropriate care. This invention aims to solve this problem by performing more accurate emotional analysis and health status assessment from information obtained through users' communication, and promptly notifying users.

[0702] 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.

[0703] In this invention, the server includes means for collecting user communication information, means for preprocessing the information and converting it into an analyzable format, and means for analyzing the emotional state from the information using generative artificial intelligence. This makes it possible to determine the user's psychological health state with high accuracy and speed, and to provide necessary feedback in a timely manner.

[0704] "User communication information" refers to information such as text messages and voice data that users send and receive through the digital communication platform.

[0705] "Preprocessing" refers to data cleansing, transformation, and tokenization processes performed to convert collected data into a format that is easy to analyze.

[0706] "Generative artificial intelligence" is an AI model technology that analyzes data to identify context and determine emotional states through the generation of text and data patterns.

[0707] "Means for analyzing emotional states" refer to algorithms and devices used to classify emotions such as joy, sadness, and anger from data and to evaluate the user's psychological state.

[0708] "Psychological health status" refers to the level of a user's mental and emotional well-being, and is assessed based on emotional analysis.

[0709] "Means of providing responses" refers to technical means used to present users with information and advice regarding their psychological health status and potential improvements based on analysis results.

[0710] A "digital device" is an electronic device capable of receiving and displaying digital data, such as a personal computer, smartphone, or tablet.

[0711] This invention is a system that analyzes information obtained from users' digital communications to assess their mental health and provide feedback. The server securely collects text messages and voice data from communication platforms with the user's permission. The collected data is stored in a database and subsequently used for analysis. Specifically, the system utilizes cloud-based server storage as hardware and employs API technology (e.g., a general-purpose data acquisition API) for data collection as software.

[0712] The server utilizes natural language processing techniques to preprocess the acquired data. Audio data is converted to text using speech recognition software (e.g., a speech-to-text engine), and then tokenized and denoised using a Python natural language processing library (e.g., spaCy).

[0713] This pre-processed data is analyzed by an emotion analysis engine utilizing a generative AI model. The generative AI model (e.g., an advanced text analysis AI) classifies the data according to various emotion categories and estimates the emotional state. Based on this, the server compares it with historical data to assess the psychological health status. If the risk exceeds a certain threshold, corrective action is taken immediately.

[0714] The device provides feedback to the user based on information received from the server. For example, if a user consistently posts messages indicating "sadness," the device might provide feedback such as, "It seems you've been feeling sad lately. Try incorporating some lighthearted activities to lift your spirits."

[0715] Specific examples of prompt statements are as follows:

[0716] "Please analyze the emotions expressed in messages recently sent by users. Classify them into one of three categories: joy, sadness, or anger, and indicate the degree of each emotion numerically. Also, please provide a comparison with past data."

[0717] This system will enable users to understand their emotions earlier and take appropriate health management actions.

[0718] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0719] Step 1:

[0720] The server, with the user's permission, collects text messages and voice data from the communication platform. It receives message data obtained via an API as input and stores it directly in the database. Specifically, the server issues API requests, encrypts the retrieved data, and stores it in cloud storage.

[0721] Step 2:

[0722] The server converts the collected audio data into text using speech recognition software. It takes audio files as input and generates corresponding text data as output. Specifically, the server uses a speech recognition API to integrate the obtained text with other text data in the database.

[0723] Step 3:

[0724] The server preprocesses the text data. It takes integrated text data as input and generates tokenized, clean data as output. This process uses Python's natural language processing library, where the server tokenizes the data and removes unwanted noise.

[0725] Step 4:

[0726] The server inputs pre-processed data into a generating AI model and performs sentiment analysis. Tokenized text data is sent to the AI ​​model along with prompts, and the output includes sentiment categories (joy, sadness, anger, etc.) and their intensity. Specifically, the server creates prompts and retrieves the analysis results through the AI ​​model.

[0727] Step 5:

[0728] The server determines the mental health status by comparing the results of sentiment analysis with historical data. It uses current sentiment analysis data and past sentiment data as input, and performs a health status assessment as output. The server uses statistical analysis techniques for pattern recognition.

[0729] Step 6:

[0730] The device provides feedback to the user based on health status assessment results received from the server. It receives assessment results as input and displays specific advice as output. Specifically, the device displays a pop-up notification to the user, prompting appropriate action.

[0731] (Application Example 2)

[0732] 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".

[0733] In modern society, busy lifestyles and information overload are leading to increased consumer stress and emotional instability. In this context, there is a need for ways to improve the consumer purchasing experience and reduce stress. Particularly in e-commerce, the challenge lies in providing a better purchasing experience by offering appropriate feedback and suggestions tailored to the individual consumer's emotional state.

[0734] 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.

[0735] In this invention, the server includes a device for collecting user information, a device for processing the information and converting it into an analyzable format, and a device for analyzing the emotional state from the information using a generative artificial intelligence model. This makes it possible to recommend relevant audio or visual content according to the emotional state of the user while they are using a product or service, and to collaborate with external information sources to provide the audio or visual content.

[0736] "User" refers to an individual or legal entity that uses the system or device.

[0737] "Information" refers to communication data and other related data related to the user, including text, audio, and visual data.

[0738] "Device" refers to hardware or software designed to perform a specific function.

[0739] "Processing" refers to a series of operations that convert collected information into a format that can be analyzed or interpreted.

[0740] A "generative artificial intelligence model" refers to artificial intelligence technology that generates new information from data or identifies patterns.

[0741] "Emotional state" refers to the user's emotional situation or psychological tendencies, and is classified into categories such as joy, sadness, and anger.

[0742] "Recommendation" means suggesting a particular action or choice to a user, and this includes feedback and advice.

[0743] "Audio or visual content" refers to media content such as audio messages, music, videos, and images.

[0744] "External information sources" refer to databases and service providers that exist outside the system, providing additional data and functionality.

[0745] This system is designed to analyze users' emotional states and provide appropriate feedback under specific conditions. The server first obtains user permission to collect communication data from messaging platforms and other databases. The collected data is then converted into an analyzable format using a processor on the server. During this process, Google Cloud's natural language processing APIs are utilized for tokenizing text data and performing sentiment analysis.

[0746] Generative artificial intelligence models use this data to analyze the user's emotional state. During the analysis, they understand the user's context and classify it into emotional categories such as joy, sadness, and anger. Based on these results, the server evaluates the emotional state and determines the user's health status. Algorithms built on specific criteria support this process.

[0747] Depending on the user's emotional state, the server collaborates with external information sources to recommend relaxing music, for example, through online music streaming services. This is effective when the server determines that the user is experiencing stress. The recommended music and visual content are provided using APIs from services such as Spotify and Apple Music.

[0748] For example, if analysis indicates that a user is experiencing stress during the online shopping process, a recommendation such as "Would you like to stream some relaxing classical music?" might be displayed. Simultaneously, coupons for health-related products and services may also be issued.

[0749] An example of a prompt for a generative AI model would be: "Show me a method for suggesting relaxing music when a user is feeling anxious. Then, generate a list of items that he might be interested in for relaxation."

[0750] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0751] Step 1:

[0752] The server, with the user's permission, collects communication data from messaging platforms, social networking services (SNS), and other sources. The input for this step consists of text and voice data from multiple platforms. The server then stores this data in a secure database.

[0753] Step 2:

[0754] The server preprocesses the collected data using Google Cloud's natural language processing API. The input consists of stored raw text and audio data. At this stage, the server converts the audio data to text, performs data processing such as tokenization and removal of irrelevant information, and outputs the data in a parseable format.

[0755] Step 3:

[0756] The server inputs pre-processed data into a generative artificial intelligence model to analyze emotional states. The input for this step is pre-processed text data. The generative AI model understands the context of the data, classifies it into emotional categories such as joy and sadness, and outputs the results of the emotional state analysis.

[0757] Step 4:

[0758] The server evaluates the user's health status based on the analyzed emotional state and makes a judgment based on specific criteria. The input for this step is emotional state data obtained from a generative artificial intelligence model. The server then performs an operation to assess health risks and output the judgment result.

[0759] Step 5:

[0760] The server provides feedback to the user based on their emotional state and recommends appropriate audio or visual content in conjunction with external information sources. The input is the result of a health status assessment. The server, for example, uses a music streaming service API to recommend relaxing music and generates output to provide.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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."

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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 to be incorporated by reference.

[0782] The following is further disclosed regarding the embodiments described above.

[0783] (Claim 1)

[0784] Means for collecting user communication data,

[0785] Means for preprocessing the data and converting it into an analyzable format,

[0786] A means for analyzing emotional states from the aforementioned data using generative artificial intelligence,

[0787] A means of determining mental health status based on analysis results,

[0788] A means of providing feedback to the user based on the judgment result,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, which utilizes natural language processing technology for analyzing emotional states.

[0792] (Claim 3)

[0793] The system according to claim 1, comprising means for issuing a warning when a user's mental health risk exceeds a certain threshold.

[0794] "Example 1"

[0795] (Claim 1)

[0796] Means for collecting the content of users' communications,

[0797] Means for converting the communication content into a standardized format,

[0798] A means for analyzing emotional states from the communication content using machine learning technology,

[0799] A method for evaluating emotional tendencies based on the passage of time using the analysis results,

[0800] A means of providing advice on mental health based on evaluation results,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, which utilizes natural language processing technology for analyzing emotional states.

[0804] (Claim 3)

[0805] The system according to claim 1, including means for alerting the user if their mental state exceeds a predetermined standard.

[0806] "Application Example 1"

[0807] (Claim 1)

[0808] Means for collecting user communication information,

[0809] Means for preprocessing the information and converting it into an analyzable format,

[0810] A means for analyzing emotional states from the aforementioned information using generative artificial intelligence,

[0811] A means of determining mental health status based on analysis results,

[0812] A means of providing feedback to the user based on the judgment result,

[0813] A means of collecting users' purchase history and recommending product purchases based on their mental state,

[0814] A means of providing spending management feedback related to purchasing,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, which utilizes natural language processing technology for analyzing emotional states.

[0818] (Claim 3)

[0819] The system according to claim 1, comprising means for issuing a warning when a user's mental health risk exceeds a certain threshold.

[0820] "Example 2 of combining an emotion engine"

[0821] (Claim 1)

[0822] Means for collecting user communication information,

[0823] Means for preprocessing the information and converting it into an analyzable format,

[0824] A means for analyzing emotional states from the aforementioned information using generative artificial intelligence,

[0825] A means of determining the state of mental health based on the analysis results,

[0826] A means of providing a response to the user based on the determination result,

[0827] A means for displaying a response on a digital device,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, which utilizes natural language processing technology for analyzing emotional states.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising means for issuing a warning when a user's mental health risk exceeds a certain threshold.

[0833] "Application example 2 when combining with an emotional engine"

[0834] (Claim 1)

[0835] A device for collecting user information,

[0836] A device that processes the information and converts it into an analyzable format,

[0837] A device that analyzes emotional states from the aforementioned information using a generative artificial intelligence model,

[0838] A device that determines health status based on analysis results,

[0839] A device that provides feedback to the user based on the determination result,

[0840] A device that recommends relevant audio or visual content to users based on their emotional state while they are using a product or service,

[0841] A device that interacts with external information sources to provide audio or visual content,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, which utilizes language processing technology to analyze emotional states and uses a generative AI model to create relevant prompt sentences.

[0845] (Claim 3)

[0846] The system according to claim 1, comprising a device that issues a warning when the user's health risk exceeds a specific threshold value. [Explanation of Symbols]

[0847] 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 user communication data, Means for preprocessing the data and converting it into an analyzable format, A means for analyzing emotional states from the aforementioned data using generative artificial intelligence, A means of determining mental health status based on analysis results, A means of providing feedback to the user based on the judgment result, A system that includes this.

2. The system according to claim 1, which utilizes natural language processing technology for analyzing emotional states.

3. The system according to claim 1, comprising means for issuing a warning when a user's mental health risk exceeds a specific threshold.

Images