system

Abstract

Provide a system. [Solution] A conversational AI character installed on a device for children, means for having daily conversations with a child on the terminal and collecting conversation data; A means for analyzing the conversation data collected in the terminal or server and evaluating mental health status; A means for identifying a cause of stress based on the evaluation results; The system includes a means for notifying a parent or interested party of the results of the assessment and the stressors.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] While the importance of checking children's mental health status on devices is increasing, existing systems have difficulty properly identifying and addressing stress and anxiety in children. Furthermore, if children have difficulty communicating their mental worries to their parents or teachers, these issues can become prolonged and develop into serious problems. Furthermore, there is a lack of tools for parents to properly manage their children's mental health and address them in a timely manner. To address these issues, there is a need for a system that uses AI characters that children can easily converse with to check children's mental health status, identify stressors, and promptly notify parents or other relevant parties. [Means for solving the problem]

[0005] This invention provides a system that equips a device for children with a conversational AI character and collects conversation data through daily conversations with the child. The conversation data is analyzed using natural language processing technology within the device or server, and the child's emotional state is scored to assess their mental health. Next, stress factors are identified based on the analysis results, and this information is notified to parents or other relevant parties, enabling early and appropriate countermeasures. This system can quickly detect stress and anxiety that children experience on a daily basis and provide appropriate support.

[0006] "Devices" refers to electronic devices used by children, specifically including smartphones and tablets.

[0007] "Conversational AI character" refers to an AI program that can converse with a user using natural language.

[0008] "Conversation data" refers to text data and audio data that records the content of the conversation between a child and a conversational AI character.

[0009] "Collection means" refers to a system that has the function of having a conversation with a child and recording the content of that conversation as data.

[0010] "Analysis means" refers to a system that uses natural language processing technology to analyze collected conversation data and evaluate children's emotional state and stress factors.

[0011] "Mental health" refers to a child's mental and emotional health, including the presence or absence of stress and anxiety.

[0012] "Stressors" refer to the reasons or causes that make children feel stressed or anxious.

[0013] "Means of notifying parents or relevant parties" refers to a system that has the function of informing parents or relevant parties of analysis results and stress factors via email or notification message.

[0014] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language.

[0015] "Scoring" refers to the process of quantifying emotional states based on information obtained through text data analysis. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system of the present invention is a device for children equipped with a conversational AI character that checks the mental health of children through daily conversations, identifies stressors, and notifies parents or other relevant parties of the results. An embodiment of the system is described in detail below.

[0038] Overall system overview

[0039] The main components of this system are a device for children, a conversational AI character, data collection means, analysis means, and notification means. These allow for regular assessment of children's mental health and prompt notification to parents or other relevant parties when problems arise.

[0040] Explanation of program processing

[0041] Initial Setup

[0042] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[0043] Starting everyday conversations

[0044] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, how was school today?"

[0045] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[0046] Conversation data collection

[0047] Terminal: Uses a voice recognition system to collect user speech, converts the speech data into text, and then stores the collected text data in a database.

[0048] Mental health and stress checks

[0049] Device: The collected conversational text data is processed by a dedicated analysis module. Natural language processing (NLP) technology is used to analyze the text data and score the emotional state. For example, emotions such as "happy," "sad," and "stressed" are identified.

[0050] Identifying stress factors

[0051] Device: Identify stress factors from the analysis results. Analyze the frequency of co-occurrence of keywords in the collected text data to determine what causes stress for children. Examples include "a lot of homework" and "relationships with friends."

[0052] Sending check results

[0053] Terminal: Compile the analysis results and identified stress factors into a report.

[0054] Terminal: Sends the compiled report to the server.

[0055] Server: Based on the received data, the server uses the contact information of the parent or other relevant person to generate and send a notification message containing the analysis results and stress factors. For example, an email stating, "Your child is feeling stressed about their homework recently."

[0056] Specific examples

[0057] If the user is a 10-year-old child

[0058] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[0059] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[0060] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[0061] Mental health and stress check: Using natural language processing technology, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[0062] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[0063] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[0064] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[0065] The processing flow will be explained below.

[0066] Program processing details

[0067] Step 1: Initial Setup

[0068] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[0069] User (Parent): Enter your contact information (email address, phone number).

[0070] Terminal: Saves the entered information to the internal database. Displays a message that the setup is complete.

[0071] Step 2: Starting everyday conversations

[0072] Device: Periodically activates a conversational AI character that speaks to the child, asking questions such as, "Hello, what did you do at school today?"

[0073] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[0074] Step 3: Collect conversation data

[0075] Terminal: The child's answers are converted into text using a voice recognition system. This is the process of converting voice data into text data.

[0076] Terminal: The converted text data is temporarily stored in an internal database.

[0077] Step 4: Mental health and stress check

[0078] Terminal: Passes the collected text data to the analysis module, which analyzes the text data using natural language processing (NLP) techniques.

[0079] Device: Emotions are scored from text data. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[0080] Step 5: Identify the cause of stress

[0081] Device: Identify stress factors from emotion scoring results. Identify negative keywords and phrases in text data and analyze their co-occurrence frequency.

[0082] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[0083] Step 6: Submit the check results

[0084] Terminal: Generate a report containing the analysis results and identified stressors.

[0085] Terminal: Sends the generated report to the server.

[0086] Server: The server uses the received data to create a notification message using the parent's contact information.

[0087] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[0088] Step 7: Provide feedback

[0089] Server: Generates notification messages along with specific advice to the parent.

[0090] Server: Sends a message with detailed advice, for example, "Your child is stressed about a test. Give them some time to relax."

[0091] User (Parent): Receives notification messages sent and checks the status of their child.

[0092] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[0093] Example 1

[0094] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0095] Current devices for children lack systems that can properly monitor a child's mental health and immediately notify parents and other relevant parties. There are also insufficient means to analyze conversation data and identify stressors that children are experiencing. As a result, it is difficult to detect stress and anxiety that children experience on a daily basis early and deal with them appropriately.

[0096] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0097] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with the child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using voice recognition technology, means for sending the text data to a dedicated analysis module and evaluating the mental health state using natural language processing technology, means for identifying stress factors based on the evaluation results, and means for compiling the evaluation results and stress factors into a report and notifying parents or relevant parties. This makes it possible to monitor a child's mental health state through their everyday conversations, and to quickly identify stress factors and notify parents or relevant parties.

[0098] A "child-directed device" is an electronic device intended for use by children, including, for example, tablets and smartphones.

[0099] A "conversational AI character" is a software agent that uses AI technology to converse with users in natural language and can hold conversations with children.

[0100] "Speech recognition technology" is a technology for converting voice data into text data, and is used to convert a user's verbal utterances into text information.

[0101] "Natural language processing technology" is a technology for computer processing of human language, and is used to analyze text data to understand emotions and intentions.

[0102] "Means for scoring emotional states" refers to a method for quantifying and evaluating a user's emotions based on words and phrases extracted from text data.

[0103] "Keyword co-occurrence frequency" is an indicator of how often certain words or phrases appear together, allowing you to identify factors that are highly relevant.

[0104] A "report" is a document summarizing the analysis results and stress factors, and includes information for notifying parents or other relevant parties.

[0105] A "database" refers to a system that systematically stores collected data for later retrieval and analysis.

[0106] The system of the present invention is a device for children equipped with a conversational AI character that monitors the child's mental health through everyday conversations, identifies stressors, and notifies parents or other relevant parties. The components of this system include a device for children, a conversational AI character, voice recognition technology, natural language processing technology, a database, and a server.

[0107] Hardware and Software Configuration

[0108] Devices: Electronic devices such as tablets and smartphones used by children.

[0109] Conversational AI character: A software agent that can have natural conversations with children.

[0110] Speech recognition technology: Technology that converts a child's speech from voice data into text data.

[0111] Natural language processing technology: Technology that analyzes conversation data and scores emotional states.

[0112] Database: A system that stores and manages collected text data.

[0113] Server: A system that generates and sends messages to notify parents or other interested parties of the results of data analysis.

[0114] The operation of the system proceeds through the following steps.

[0115] Initial Setup

[0116] First, the parent starts up the device and enters the child's basic information (name, age, gender, interests) on the initial setup screen. The parent also enters the parent's contact information, which is then saved in a database. For example, the parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device screen, and registers their own email address.

[0117] Starting everyday conversations

[0118] When a child uses the device, a conversational AI character periodically initiates a conversation. For example, the character may display a prompt such as, "Hello, how did you do at school today?" to which the child may respond, "I had fun in gym class today."

[0119] Conversation data collection

[0120] The device uses voice recognition technology to convert the child's speech into text data, which is then stored in a database. At this time, software equipped with voice recognition technology is activated.

[0121] Mental health and stress checks

[0122] The collected text data is sent to a dedicated analysis module and analyzed using natural language processing technology. For example, emotions such as "happy," "sad," and "stressed" are identified, and the stress level is assessed based on the emotion score.

[0123] Identifying stress factors

[0124] Based on the analysis results, the device identifies the child's stressors by analyzing the frequency of co-occurrence of keywords in the conversation data, determining stressors such as "a lot of homework" and "relationships with friends."

[0125] Sending check results

[0126] The evaluation results and stress factors are compiled into a report and sent from the device to a server. The server then generates and sends a message notifying the parent or other relevant person of the analysis results using their contact information. For example, an email could be sent to the parent stating, "Your child has been feeling stressed about their homework recently."

[0127] This system allows early detection of everyday stress in children, enabling parents and other relevant parties to respond promptly. Specific examples of prompts include "Hello, what fun things did you do today?" and "Is there anything that's bothering you lately?"

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1: Initial Setup

[0130] User: The parent starts the device and accesses the initial setup screen.

[0131] Device: Displays a form for entering information such as the user's name, age, gender, interests, etc. Specifically, enter information such as "Taro," "10 years old," "boy," and "likes soccer."

[0132] User: The parent enters the required information and presses the complete button.

[0133] On the device: Display a screen to enter the parent's contact information (email address, phone number). The entered information is saved in the database.

[0134] Input: Name, Age, Gender, Interests, Parent Contact Information

[0135] Output: Child and parent information stored in a database

[0136] Step 2: Starting everyday conversations

[0137] Device: When a child turns on the device, a conversational AI character automatically launches.

[0138] Device: Periodically, such as in the morning or after school, display a prompt like "Hi, what happened at school today?"

[0139] User (child): The child replies, "I enjoyed gym class today."

[0140] Input: Child's speech

[0141] Output: Collected audio data

[0142] Step 3: Collect conversation data

[0143] Device: Activate the voice recognition system and convert the child's speech from voice data into text data.

[0144] Terminal: Save the converted text data in the database.

[0145] Input: Collected audio data

[0146] Output: Text data stored in a database

[0147] Step 4: Mental health and stress check

[0148] Terminal: The saved text data is sent to a dedicated analysis module.

[0149] Device: Analyzes text data using natural language processing (NLP) technology to score emotional states. For example, identify emotions such as "happy," "sad," or "stressed." Furthermore, evaluates stress levels based on the emotional scores.

[0150] Input: Text data stored in a database

[0151] Output: Emotional state score and stress level rating

[0152] Step 5: Identify the cause of stress

[0153] Terminal: Identify stress factors from the analysis results.

[0154] Device: Analyzes the frequency of co-occurrence of keywords in text data to determine stress factors such as "a lot of homework" and "relationships with friends."

[0155] Input: Emotional state scores and text data

[0156] Output: Identified stressors

[0157] Step 6: Submit the check results

[0158] Terminal: Compile the analysis results and identified stress factors into a report.

[0159] Terminal: Sends the compiled report to the server.

[0160] Server: Based on the received data, the server generates a notification message containing the analysis results and stress factors using the parent or interested party's contact information.

[0161] Server: Sends the generated notification message to the parent or other interested party. For example, an email stating, "Your child is feeling stressed about their homework these days."

[0162] Input: Analysis results and stress factors

[0163] Output: Notification message sent to parent or interested party

[0164] (Application example 1)

[0165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0166] In modern society, understanding children's mental health is extremely important. However, it is difficult for parents and other concerned parties to immediately understand a child's daily stress and mental burden and take appropriate measures. This can lead to mental health problems being overlooked. The present invention aims to solve this problem by providing a system that quickly and accurately assesses a child's mental health, identifies stressors, and notifies the user in a timely manner.

[0167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0168] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child on the terminal and collecting conversation data, means for analyzing the conversation data collected on the terminal or server and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying parents or relevant parties of the evaluation results and stress factors, and means for notifying if a threshold set based on the evaluation results is exceeded. This makes it possible to evaluate a child's mental health state in real time and promptly notify parents or relevant parties when a problem occurs, enabling appropriate measures to be taken.

[0169] "Children's devices" are electronic devices intended for use by children, including tablets and smartphones.

[0170] A "conversational AI character" is an AI program that can communicate with users in a dialogue format.

[0171] The "means for collecting conversation data" is a system that has the function of recording conversations with children and storing them in a database or server.

[0172] "Means for assessing mental health" refers to algorithms or programs that analyze collected conversation data and score users' emotions and psychological state.

[0173] "Means for identifying stress factors" refers to technology that analyzes specific keywords and phrases within conversation data to determine what causes stress for users.

[0174] "Means of notification" refers to the function for communicating evaluation results and stress factors to parents or relevant parties, and includes methods such as email and app notifications.

[0175] The "means for notifying when a set threshold is exceeded" is a function that automatically sends a notification to parents or related parties when the evaluation results exceed a pre-set standard value.

[0176] "Natural language processing technology" is a computer technology that analyzes human language and understands meaning and emotions.

[0177] "Means for scoring emotional states" refers to a technology that uses emotional information extracted from conversation data to generate numerical values ​​or evaluations.

[0178] "Means for analyzing the frequency of keyword co-occurrence" is a technology that analyzes words and phrases that frequently appear together in conversation data and evaluates their relevance and importance.

[0179] The present invention is a system for monitoring children's mental health status and notifying parents and other relevant parties at appropriate times. This system includes a conversational AI character installed on a device for children, a means for collecting conversation data, a means for evaluating mental health status, a means for identifying stress factors, a means for notifying the evaluation results and stress factors, and a means for notifying when a set threshold is exceeded based on the evaluation results.

[0180] System Configuration

[0181] 1. Devices for children:

[0182] This refers to smartphones and tablet devices for everyday use by children. These devices are equipped with conversational AI characters that can hold natural conversations with users.

[0183] 2. Conversational AI Characters:

[0184] It is a specialized software program that uses natural language processing (NLP) technology to analyze everyday conversations with children and score their mental health. The character utilizes NLP services such as Google® Cloud Dialogflow.

[0185] 3. Conversation data collection methods:

[0186] All interactions between children and the conversational AI character are recorded and converted into text using voice recognition technology powered by the Google Cloud Speech-to-Text API.

[0187] 4. Mental health assessment tools:

[0188] This technology analyzes collected text data and scores emotions. It performs sentiment analysis using Google Cloud Natural Language API and other tools.

[0189] 5. Ways to identify stressors:

[0190] This technology analyzes the frequency of co-occurrence of keywords in collected data to determine what causes stress.

[0191] 6. Means of Notification:

[0192] The analysis results and stress factors are notified to parents and other relevant parties via email or SMS. This notification function uses the Twilio API.

[0193] 7. Means of notification when thresholds are exceeded:

[0194] If the mental health assessment results exceed a set threshold, a notification will be sent automatically, allowing parents to keep track of their child's condition in real time.

[0195] Program processing

[0196] The server collects voice data spoken by the child into the smartphone and converts it into text using speech recognition technology. This converted text data is then analyzed using Google Cloud Dialogflow to manage the conversation session. Based on the analysis results, sentiment analysis is performed using the Google Cloud Natural Language API to score the emotional state. If the scoring result exceeds a set threshold, parents and other relevant parties are automatically notified using the Twilio API.

[0197] Specific examples

[0198] If your child is 10 years old:

[0199] A child speaks into the device, saying, "I had a math test today, and it was a little difficult." The device collects this voice data and converts it into text using speech recognition. This text data is analyzed using natural language processing technology, and the child's emotional state is scored. Stress is identified from the keywords "test" and "difficult," and the evaluation results are notified to the parent.

[0200] Prompt Sentence Examples

[0201] "I enjoyed the gym class today, but the math test was a little difficult."

[0202] This system will enable real-time assessment of a child's mental health and promptly notify parents and other relevant parties, enabling appropriate intervention and support.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The user speaks into the smartphone or tablet device that the child uses on a daily basis, and this speech is input into the device as voice data.

[0206] Step 2:

[0207] The device converts the input voice data into text data using the Google Cloud Speech-to-Text API, which outputs the voice data as text data.

[0208] Step 3:

[0209] The device sends the converted text data to Google Cloud Dialogflow, which starts a conversation session and manages the interaction between the user and the conversational AI character. The input is text data, and the output is conversation responses and session information.

[0210] Step 4:

[0211] The server uses the Google Cloud Natural Language API to analyze the text data returned from Dialogflow and score the emotional state, outputting a numerical score for positive, negative, or other emotional states.

[0212] Step 5:

[0213] The server performs co-occurrence analysis on the analyzed emotion scores and extracts specific keywords and phrases from the conversation data to identify stress factors. The input is text data and emotion scores, and the output is the identified stress factors.

[0214] Step 6:

[0215] The server uses the Twilio API to send a notification to parents or other relevant parties when the identified stressors and emotional score exceed a set threshold. This notification includes the emotional assessment result and the identified stressors. The input is the emotional score and stressors, and the output is a notification message to parents or other relevant parties.

[0216] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0217] The present invention relates to a system that uses a conversational AI character and emotion engine installed in a device for children to assess the mental health of children through everyday conversations, identify stress factors, and notify parents or other relevant parties of the results.

[0218] Overall system overview

[0219] The system consists of the following main parts:

[0220] 1. Devices for children

[0221] 2. Conversational AI Characters

[0222] 3. Data Collection Methods

[0223] 4. Emotion Engine

[0224] 5. Analysis method

[0225] 6. Means of notification

[0226] This makes it possible to assess a child's mental health through their everyday conversations and quickly notify parents and other relevant parties if a problem arises.

[0227] Explanation of program processing

[0228] Initial Setup

[0229] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[0230] Starting everyday conversations

[0231] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, what did you do at school today?"

[0232] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[0233] Conversation data collection

[0234] Terminal: A voice recognition system is used to collect user speech, convert the speech data into text, and then store the collected text data in a database.

[0235] Emotion recognition

[0236] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the tone of the voice and the content of the text.

[0237] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[0238] Mental health and stress checks

[0239] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[0240] Device: Evaluates overall health based on collected data and emotional scores.

[0241] Identifying stress factors

[0242] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[0243] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[0244] Sending check results

[0245] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[0246] Terminal: Sends the generated report to the server.

[0247] Server: The server uses the received data to create a notification message using the parent's contact information.

[0248] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[0249] Specific examples

[0250] If the user is a 10-year-old child

[0251] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[0252] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[0253] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[0254] Emotion recognition: The emotion engine recognizes from the text "It was a little difficult" and the tone of the voice that the user is feeling a little stressed.

[0255] Mental health and stress check: Using the results of the emotion engine, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[0256] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[0257] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[0258] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[0259] The processing flow will be explained below.

[0260] MODE FOR CARRYING OUT THE INVENTION

[0261] Step 1: Initial Setup

[0262] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[0263] User (Parent): Enter the parent's contact information (email address, phone number).

[0264] Terminal: Saves the entered information to an internal database and displays a message that the setup is complete.

[0265] Step 2: Starting everyday conversations

[0266] Terminal: A conversational AI character periodically initiates everyday conversations, such as asking questions like, "Hello, what did you do at school today?"

[0267] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[0268] Step 3: Collect conversation data

[0269] Terminal: The user's response is converted into text using a voice recognition system, which is the process of converting voice data into text data.

[0270] Terminal: The converted text data is temporarily stored in an internal database.

[0271] Step 4: Recognize emotions

[0272] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the voice tone and text content.

[0273] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[0274] Step 5: Mental health and stress check

[0275] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[0276] Device: Evaluates overall health based on collected data and emotional scores.

[0277] Step 6: Identify the source of stress

[0278] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[0279] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[0280] Step 7: Submit the check results

[0281] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[0282] Terminal: Sends the generated report to the server.

[0283] Server: The server uses the received data to create a notification message using the parent's contact information.

[0284] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[0285] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[0286] Example 2

[0287] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0288] In recent years, the mental health of children has become increasingly important, and there is a need to detect stress and mental problems early and respond appropriately. However, traditional methods make it difficult for parents and educators to accurately grasp changes and problems in children's daily lives, making it difficult to continuously and objectively evaluate children's mental health. In particular, when children have difficulty clearly expressing their emotions and stressors, there is a risk that these problems will be overlooked.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0290] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with a child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using a voice recognition system and storing it in a database, means for recognizing the child's emotions and identifying their emotional state using an emotion engine that analyzes the text data and voice data, means for evaluating and scoring the child's mental health state based on the analysis results, and means for notifying parents or other relevant parties of the evaluation results and stress factors. This enables parents and educators to understand a child's mental health state in real time through the child's everyday conversations and to identify and address stress factors early on.

[0291] A "children's device" is an electronic device designed primarily for use by minors, and is a device with functionality suitable for everyday conversation and educational activities.

[0292] A "conversational AI character" is a software program that can hold natural conversations with users, and is a virtual character that responds to user utterances using voice recognition and natural language processing technology.

[0293] The "data collection means" is a system component that has the function of collecting input data from a user, and is a device or software that acquires voice data or text data.

[0294] A "voice recognition system" is a technology or software that automatically converts voice data into text data.

[0295] A "database" is a digital storage system that stores collected information in an organized manner and facilitates retrieval and analysis as needed.

[0296] An "emotion engine" is software that includes algorithms and machine learning models to analyze voice and text data and identify a user's emotions.

[0297] The "means for assessing mental health status" is a function that scores the user's psychological state based on collected data and evaluates the user's health status numerically or qualitatively.

[0298] The "means for identifying stress factors" is a function that analyzes the collected data and emotion determination results to identify the specific causes and situations that cause the user to feel stressed.

[0299] "Notification means" is a system component that communicates identified stressors and mental health assessment results to parents or other relevant parties, and is a device or software that sends email or message notifications.

[0300] A "generative AI model" is a machine learning model that learns from large amounts of data and generates natural conversational prompts.

[0301] A "prompt sentence" is a question or statement presented by a conversational AI character to initiate a conversation with the user, and is a guidance sentence to elicit a response from the user.

[0302] This invention relates to a system that uses a conversational AI character installed on a device for children, and the device and a server to collect and analyze data on children's everyday conversations, evaluate their mental health, identify stress factors, and notify parents or other relevant parties of the results.

[0303] Hardware and software used

[0304] Device:

[0305] Portable electronic devices (e.g., tablets, smartphones) used by children are used.

[0306] The device is equipped with basic audio and video collection devices such as a microphone, camera, and speaker.

[0307] Conversational AI Character:

[0308] Conversational AI characters incorporate voice recognition software (e.g., Google Speech-to-Text) and natural language processing engines (e.g., NVIDIA Riva).

[0309] A generative AI model creates prompts, enabling natural conversations with users.

[0310] Database:

[0311] A cloud-based database is used to store the collected data (voice data, text data, emotion recognition results, etc.).

[0312] Emotion Engine:

[0313] The emotion engine utilizes emotion recognition algorithms (e.g., IBM Watson® Tone Analyzer) to analyze voice tone, facial expressions, and text content to identify the user's emotional state.

[0314] server:

[0315] A central server is used to analyze the collected data and notify parents or other relevant parties via email, push notifications, or other methods.

[0316] System Operation

[0317] Initial Settings:

[0318] When the device is first started, parents are prompted to enter basic information about their child (such as name, age, gender, and interests) as well as their own contact information, which is then securely stored in a database.

[0319] Starting everyday conversations:

[0320] The device will talk to the child through a conversational AI character based on a pre-set schedule, for example, using a generative AI model to generate and display prompts such as "Hello, what did you do at school today?"

[0321] Conversation data collection:

[0322] The device collects the child's speech through a microphone and converts it into text data using a voice recognition system. The converted text data and the original voice data are stored in a database.

[0323] Emotion Recognition:

[0324] The device uses an emotion engine to analyze the collected voice and text data, for example, to identify the user's emotions (happy, sad, angry, etc.) based on the tone of the voice, the content of the text, and even facial expression data collected by the camera.

[0325] Mental health assessment:

[0326] The device evaluates and quantifies the state of mental health based on the analysis results of the emotion engine, and accumulates daily data to monitor long-term health.

[0327] Identifying stressors:

[0328] The device analyzes negative keywords (e.g., "test" and "fight") in the text data based on their frequency and co-occurrence, and identifies stress factors.

[0329] Notification of results:

[0330] The device and server then compile the analysis results into a report and notify parents and other relevant parties. An example of the content of the report might be a message such as, "Taro is feeling stressed about today's math test."

[0331] Examples of prompts:

[0332] "Hello, what did you do at school today?"

[0333] "What fun things happened today?"

[0334] "Tell me what you've been enjoying lately."

[0335] This will enable early detection of mental changes and stress that children experience on a daily basis, allowing parents and educators to respond quickly and effectively manage and support children's mental health.

[0336] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0337] Step 1: Initial Setup

[0338] Input: Parents enter their child's basic information (such as name, age, gender, interests) and their own contact information into the device.

[0339] Data processing: The device stores this information securely in a database.

[0340] Output: Basic information of parents and children saved is available.

[0341] Specific actions: Parents enter information through the user interface and press the registration button to submit the data.

[0342] Step 2: Starting everyday conversations

[0343] Enter: Your child starts or begins using the device.

[0344] Data processing: The device uses a generative AI model to create prompts based on pre-set schedules and conditions.

[0345] Output: Display a prompt sentence on the screen, such as "Hello, what did you do at school today?"

[0346] Specific actions: The conversational AI character reads out the displayed prompt aloud and asks the child a question.

[0347] Step 3: Collect conversation data

[0348] Input: The child speaks in response to the prompt.

[0349] Data processing: Voice data is collected through the device's microphone and converted into text data using a voice recognition system. The converted text data is then stored in a database.

[0350] Output: The audio data and its converted text are stored in a database for later analysis.

[0351] How it works: Your child's responses are collected by a microphone and converted into text in real time by speech recognition software.

[0352] Step 4: Recognize emotions

[0353] Input: Stored text and audio data.

[0354] Data processing: The device uses an emotion engine to analyze text and voice, recognizing emotions from voice tone and text content to identify emotional states such as happy, sad, or angry.

[0355] Output: Emotion recognition results are generated and stored in a database.

[0356] Specific operation: The emotion engine determines the emotion from the tone of the voice and the content of the text, and assigns a label such as "fun."

[0357] Step 5: Mental health assessment

[0358] Input: Emotion recognition results and text data.

[0359] Data processing: The device quantifies the emotion recognition results and assigns a score to the user's mental health. The score is evaluated as a positive or negative number and stored in a database.

[0360] Output: A mental health assessment score is generated and used for daily health monitoring.

[0361] What it does: A scoring algorithm calculates a number based on emotion data and updates your overall health score.

[0362] Step 6: Identify the stressors

[0363] Input: Scoring results and text data.

[0364] Data processing: The device analyzes negative keywords in the text data based on frequency and co-occurrence relationships to identify stress factors.

[0365] Output: Specific stressors (e.g., "test" or "fight") are identified and stored in a database.

[0366] What it does: A keyword extraction algorithm extracts important negative phrases from the text and performs a frequency analysis.

[0367] Step 7: Notification of results

[0368] Input: Mental health assessment scores and stressors.

[0369] Data processing: The device and server compile the analysis results into a report and notify parents and other relevant parties via email or push notification.

[0370] Output: A specific notification message (e.g., "Taro is stressed about today's math test") is sent to the parent.

[0371] What happens: The report generation module creates a report based on the data, and the notification system sends it to the parent's email address or other contact.

[0372] This will allow children's mental health to be monitored on a daily basis, and parents and other relevant parties to respond quickly if a problem arises.

[0373] (Application example 2)

[0374] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0375] Currently, there is no fully developed system that can assess the mental health of children or agents from everyday conversations, identify stress factors, and quickly notify relevant parties of the results. As a result, it is difficult to detect changes in mental health early and take appropriate action. There is a need to provide a system that can solve this problem and monitor mental health more quickly and accurately.

[0376] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0377] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child and the agent and collecting conversation data, means for analyzing the collected conversation data and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying the parent, manager, or relevant person of the evaluation results and stress factors, and means for installing a program for evaluating the agent's mental health state, identifying stress factors, and notifying the manager or relevant person of the results. This makes it possible to detect changes in mental health state early and take appropriate measures.

[0378] A "children's device" is an electronic device intended for use by children that includes a conversational artificial intelligence character.

[0379] A "conversational AI character" is an AI-based character that can converse with users using natural language processing technology.

[0380] "Conversational Data" means data in the form of voice or text exchanged between a user and a conversational AI character.

[0381] "Emotional state" refers to the user's psychological or emotional state analyzed from conversation data.

[0382] "Means of collection" includes the technical means by which a terminal or associated device captures a user's voice or text data.

[0383] "Means for analyzing and assessing mental health status" refers to technology or programs that use collected conversation data to assess a user's psychological health status.

[0384] A "stressor" is a specific event or situation that may have a negative impact on a user's mental well-being.

[0385] "Means of notification" includes techniques or methods for informing parents, administrators, and other stakeholders about assessment results and stressors.

[0386] "Assessment Results" refers to information about a user's health and emotional state obtained based on collected and analyzed data.

[0387] "Controller" means a person who is responsible for the supervision and management of an Agent's or Child's well-being.

[0388] "Means for installing a program" refers to the methods and technologies for installing software with specific functions onto a terminal or server.

[0389] MODE FOR CARRYING OUT THE INVENTION

[0390] This invention relates to a system for assessing the mental health of children and agents and identifying stress factors. This system mainly comprises a device for children, a conversational AI character, a data collection means, an emotion engine, an analysis means, and a notification means. It also includes a means for installing a program for assessing the mental health of the agent.

[0391] Overall system overview

[0392] The system consists of the following main parts:

[0393] 1. Devices for children

[0394] The device is equipped with a conversational artificial intelligence character that can hold everyday conversations with children.

[0395] 2. Conversational AI Characters

[0396] The conversational AI character uses natural language processing technology to collect conversational data through conversations with users and score their emotions.

[0397] 3. Data Collection Methods

[0398] The device uses a speech recognition system (e.g., Google Speech Recognition API) to collect the user's voice and text data, which is then converted into text.

[0399] 4. Emotion engine and analysis methods

[0400] The collected data is subjected to sentiment analysis by an emotion engine (e.g., TextBlob). Based on the sentiment scoring, the user's mental health is evaluated.

[0401] 5. Evaluation results and identification of stress factors

[0402] Stress factors are identified based on the results of the emotion engine and keyword analysis in the conversation data. For example, negative keywords such as "tired" and "tough" are detected by analyzing the frequency of co-occurrence of keywords.

[0403] 6. Means of notification

[0404] A report is generated based on the assessment results and identified stressors, and parents and administrators are notified via email or other means using SMTP.

[0405] 7. Installing the program

[0406] A program to assess the agent's mental health will be installed on the device or server, and will comprehensively perform voice recognition, emotion analysis, stress assessment, and notifications.

[0407] Specific examples

[0408] For example, if Agent Taro says to the conversation system after a delivery, "I'm tired because there were a lot of orders today," this voice data is collected and converted into text. The emotion engine detects negative emotions from the expression "tired" and evaluates the mental health state as "high stress." The detected stress factors are "many orders" and "tired." Based on this, a notification is sent to the manager via email stating, "There were a lot of orders today, and the agent is feeling tired."

[0409] Prompt example

[0410] The agent and child are presented with the following prompt:

[0411] "It's been tough with so many orders. How can I make deliveries easier?"

[0412] "I'm tired after a long drive today. How can I relieve this fatigue?"

[0413] In this way, the system assesses the mental health of children and agents through everyday conversations, quickly and accurately identifies stressors, and notifies relevant parties, enabling early response.

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

[0415] Step 1:

[0416] Initial Setup

[0417] The server saves the initial information of the agent (such as name, age, contact details, etc.) and the administrator's contact details in a database. This operation is performed based on the information entered by the user (agent or administrator) and saved in a database (e.g., a JSON file or SQL database).

[0418] Step 2:

[0419] Starting everyday conversations

[0420] The terminal starts a conversational AI character and displays a prompt to the user (agent). An example of a prompt is "How was your day?". The input is the agent's voice.

[0421] Step 3:

[0422] Conversation data collection

[0423] The terminal uses a speech recognition system to convert the agent's speech into text data (e.g., Google Speech Recognition API). The collected text data is stored in a database. The input is speech data, and the output is text data.

[0424] Step 4:

[0425] Emotion recognition

[0426] Based on the collected text data, the server performs sentiment analysis using an emotion engine (e.g., TextBlob). It performs sentiment scoring and quantifies the user's mental health. The input is text data, and the output is a sentiment score.

[0427] Step 5:

[0428] Mental health assessment

[0429] The server evaluates the agent's mental health state based on the emotion score. Depending on the range of the score, the state is classified as "high stress," "mild stress," "normal," etc. The input is the emotion score, and the output is the health state evaluation result.

[0430] Step 6:

[0431] Identifying stressors

[0432] The server detects negative keywords (e.g., "tired" or "tough") from the collected text data and identifies stress factors by analyzing their co-occurrence frequency. The input is text data, and the output is stress factors.

[0433] Step 7:

[0434] Generating check results

[0435] Based on the assessment results and stressors, the server generates a report that includes the agent's health status and identified stressors. The inputs are the assessment results and stressors, and the output is the report.

[0436] Step 8:

[0437] Notification of check results

[0438] The server notifies the administrator of the generated report. Specifically, it sends a notification to the administrator's email address using an SMTP server. The input is the report, and the output is sending an email.

[0439] These processing steps make it possible to monitor the mental health of children and agents and respond in a timely manner.

[0440] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0441] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0442] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0446] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0447] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0448] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0449] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0450] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0451] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0452] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0453] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0454] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0455] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0456] The system of the present invention is a device for children equipped with a conversational AI character that checks the mental health of children through daily conversations, identifies stressors, and notifies parents or other relevant parties of the results. An embodiment of the system is described in detail below.

[0457] Overall system overview

[0458] The main components of this system are a device for children, a conversational AI character, data collection means, analysis means, and notification means. These allow for regular assessment of children's mental health and prompt notification to parents or other relevant parties when problems arise.

[0459] Explanation of program processing

[0460] Initial Setup

[0461] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[0462] Starting everyday conversations

[0463] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, how was school today?"

[0464] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[0465] Conversation data collection

[0466] Terminal: Uses a voice recognition system to collect user speech, converts the speech data into text, and then stores the collected text data in a database.

[0467] Mental health and stress checks

[0468] Device: The collected conversational text data is processed by a dedicated analysis module. Natural language processing (NLP) technology is used to analyze the text data and score the emotional state. For example, emotions such as "happy," "sad," and "stressed" are identified.

[0469] Identifying stress factors

[0470] Device: Identify stress factors from the analysis results. Analyze the frequency of co-occurrence of keywords in the collected text data to determine what causes stress for children. Examples include "a lot of homework" and "relationships with friends."

[0471] Sending check results

[0472] Terminal: Compile the analysis results and identified stress factors into a report.

[0473] Terminal: Sends the compiled report to the server.

[0474] Server: Based on the received data, the server uses the contact information of the parent or other relevant person to generate and send a notification message containing the analysis results and stress factors. For example, an email stating, "Your child is feeling stressed about their homework recently."

[0475] Specific examples

[0476] If the user is a 10-year-old child

[0477] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[0478] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[0479] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[0480] Mental health and stress check: Using natural language processing technology, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[0481] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[0482] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[0483] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[0484] The processing flow will be explained below.

[0485] Program processing details

[0486] Step 1: Initial Setup

[0487] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[0488] User (Parent): Enter your contact information (email address, phone number).

[0489] Terminal: Saves the entered information to the internal database. Displays a message that the setup is complete.

[0490] Step 2: Starting everyday conversations

[0491] Device: Periodically activates a conversational AI character that speaks to the child, asking questions such as, "Hello, what did you do at school today?"

[0492] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[0493] Step 3: Collect conversation data

[0494] Terminal: The child's answers are converted into text using a voice recognition system. This is the process of converting voice data into text data.

[0495] Terminal: The converted text data is temporarily stored in an internal database.

[0496] Step 4: Mental health and stress check

[0497] Terminal: Passes the collected text data to the analysis module, which analyzes the text data using natural language processing (NLP) techniques.

[0498] Device: Emotions are scored from text data. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[0499] Step 5: Identify the cause of stress

[0500] Device: Identify stress factors from emotion scoring results. Identify negative keywords and phrases in text data and analyze their co-occurrence frequency.

[0501] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[0502] Step 6: Submit the check results

[0503] Terminal: Generate a report containing the analysis results and identified stressors.

[0504] Terminal: Sends the generated report to the server.

[0505] Server: The server uses the received data to create a notification message using the parent's contact information.

[0506] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[0507] Step 7: Provide feedback

[0508] Server: Generates notification messages along with specific advice to the parent.

[0509] Server: Sends a message with detailed advice, for example, "Your child is stressed about a test. Give them some time to relax."

[0510] User (Parent): Receives notification messages sent and checks the status of their child.

[0511] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[0512] Example 1

[0513] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0514] Current devices for children lack systems that can properly monitor a child's mental health and immediately notify parents and other relevant parties. There are also insufficient means to analyze conversation data and identify stressors that children are experiencing. As a result, it is difficult to detect stress and anxiety that children experience on a daily basis early and deal with them appropriately.

[0515] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0516] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with the child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using voice recognition technology, means for sending the text data to a dedicated analysis module and evaluating the mental health state using natural language processing technology, means for identifying stress factors based on the evaluation results, and means for compiling the evaluation results and stress factors into a report and notifying parents or relevant parties. This makes it possible to monitor a child's mental health state through their everyday conversations, and to quickly identify stress factors and notify parents or relevant parties.

[0517] A "child-directed device" is an electronic device intended for use by children, including, for example, tablets and smartphones.

[0518] A "conversational AI character" is a software agent that uses AI technology to converse with users in natural language and can hold conversations with children.

[0519] "Speech recognition technology" is a technology for converting voice data into text data, and is used to convert a user's verbal utterances into text information.

[0520] "Natural language processing technology" is a technology for computer processing of human language, and is used to analyze text data to understand emotions and intentions.

[0521] "Means for scoring emotional states" refers to a method for quantifying and evaluating a user's emotions based on words and phrases extracted from text data.

[0522] "Keyword co-occurrence frequency" is an indicator of how often certain words or phrases appear together, allowing you to identify factors that are highly relevant.

[0523] A "report" is a document summarizing the analysis results and stress factors, and includes information for notifying parents or other relevant parties.

[0524] A "database" refers to a system that systematically stores collected data for later retrieval and analysis.

[0525] The system of the present invention is a device for children equipped with a conversational AI character that monitors the child's mental health through everyday conversations, identifies stressors, and notifies parents or other relevant parties. The components of this system include a device for children, a conversational AI character, voice recognition technology, natural language processing technology, a database, and a server.

[0526] Hardware and Software Configuration

[0527] Devices: Electronic devices such as tablets and smartphones used by children.

[0528] Conversational AI character: A software agent that can have natural conversations with children.

[0529] Speech recognition technology: Technology that converts a child's speech from voice data into text data.

[0530] Natural language processing technology: Technology that analyzes conversation data and scores emotional states.

[0531] Database: A system that stores and manages collected text data.

[0532] Server: A system that generates and sends messages to notify parents or other interested parties of the results of data analysis.

[0533] The operation of the system proceeds through the following steps.

[0534] Initial Setup

[0535] First, the parent starts up the device and enters the child's basic information (name, age, gender, interests) on the initial setup screen. The parent also enters the parent's contact information, which is then saved in a database. For example, the parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device screen, and registers their own email address.

[0536] Starting everyday conversations

[0537] When a child uses the device, a conversational AI character periodically initiates a conversation. For example, the character may display a prompt such as, "Hello, how did you do at school today?" to which the child may respond, "I had fun in gym class today."

[0538] Conversation data collection

[0539] The device uses voice recognition technology to convert the child's speech into text data, which is then stored in a database. At this time, software equipped with voice recognition technology is activated.

[0540] Mental health and stress checks

[0541] The collected text data is sent to a dedicated analysis module and analyzed using natural language processing technology. For example, emotions such as "happy," "sad," and "stressed" are identified, and the stress level is assessed based on the emotion score.

[0542] Identifying stress factors

[0543] Based on the analysis results, the device identifies the child's stressors by analyzing the frequency of co-occurrence of keywords in the conversation data, determining stressors such as "a lot of homework" and "relationships with friends."

[0544] Sending check results

[0545] The evaluation results and stress factors are compiled into a report and sent from the device to a server. The server then generates and sends a message notifying the parent or other relevant person of the analysis results using their contact information. For example, an email could be sent to the parent stating, "Your child has been feeling stressed about their homework recently."

[0546] This system allows early detection of everyday stress in children, enabling parents and other relevant parties to respond promptly. Specific examples of prompts include "Hello, what fun things did you do today?" and "Is there anything that's bothering you lately?"

[0547] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0548] Step 1: Initial Setup

[0549] User: The parent starts the device and accesses the initial setup screen.

[0550] Device: Displays a form for entering information such as the user's name, age, gender, interests, etc. Specifically, enter information such as "Taro," "10 years old," "boy," and "likes soccer."

[0551] User: The parent enters the required information and presses the complete button.

[0552] On the device: Display a screen to enter the parent's contact information (email address, phone number). The entered information is saved in the database.

[0553] Input: Name, Age, Gender, Interests, Parent Contact Information

[0554] Output: Child and parent information stored in a database

[0555] Step 2: Starting everyday conversations

[0556] Device: When a child turns on the device, a conversational AI character automatically launches.

[0557] Device: Periodically, such as in the morning or after school, display a prompt like "Hi, what happened at school today?"

[0558] User (child): The child replies, "I enjoyed gym class today."

[0559] Input: Child's speech

[0560] Output: Collected audio data

[0561] Step 3: Collect conversation data

[0562] Device: Activate the voice recognition system and convert the child's speech from voice data into text data.

[0563] Terminal: Save the converted text data in the database.

[0564] Input: Collected audio data

[0565] Output: Text data stored in a database

[0566] Step 4: Mental health and stress check

[0567] Terminal: The saved text data is sent to a dedicated analysis module.

[0568] Device: Analyzes text data using natural language processing (NLP) technology to score emotional states. For example, identify emotions such as "happy," "sad," or "stressed." Furthermore, evaluates stress levels based on the emotional scores.

[0569] Input: Text data stored in a database

[0570] Output: Emotional state score and stress level rating

[0571] Step 5: Identify the cause of stress

[0572] Terminal: Identify stress factors from the analysis results.

[0573] Device: Analyzes the frequency of co-occurrence of keywords in text data to determine stress factors such as "a lot of homework" and "relationships with friends."

[0574] Input: Emotional state scores and text data

[0575] Output: Identified stressors

[0576] Step 6: Submit the check results

[0577] Terminal: Compile the analysis results and identified stress factors into a report.

[0578] Terminal: Sends the compiled report to the server.

[0579] Server: Based on the received data, the server generates a notification message containing the analysis results and stress factors using the parent or interested party's contact information.

[0580] Server: Sends the generated notification message to the parent or other interested party. For example, an email stating, "Your child is feeling stressed about their homework these days."

[0581] Input: Analysis results and stress factors

[0582] Output: Notification message sent to parent or interested party

[0583] (Application example 1)

[0584] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0585] In modern society, understanding children's mental health is extremely important. However, it is difficult for parents and other concerned parties to immediately understand a child's daily stress and mental burden and take appropriate measures. This can lead to mental health problems being overlooked. The present invention aims to solve this problem by providing a system that quickly and accurately assesses a child's mental health, identifies stressors, and notifies the user in a timely manner.

[0586] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0587] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child on the terminal and collecting conversation data, means for analyzing the conversation data collected on the terminal or server and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying parents or relevant parties of the evaluation results and stress factors, and means for notifying if a threshold set based on the evaluation results is exceeded. This makes it possible to evaluate a child's mental health state in real time and promptly notify parents or relevant parties when a problem occurs, enabling appropriate measures to be taken.

[0588] "Children's devices" are electronic devices intended for use by children, including tablets and smartphones.

[0589] A "conversational AI character" is an AI program that can communicate with users in a dialogue format.

[0590] The "means for collecting conversation data" is a system that has the function of recording conversations with children and storing them in a database or server.

[0591] "Means for assessing mental health" refers to algorithms or programs that analyze collected conversation data and score users' emotions and psychological state.

[0592] "Means for identifying stress factors" refers to technology that analyzes specific keywords and phrases within conversation data to determine what causes stress for users.

[0593] "Means of notification" refers to the function for communicating evaluation results and stress factors to parents or relevant parties, and includes methods such as email and app notifications.

[0594] The "means for notifying when a set threshold is exceeded" is a function that automatically sends a notification to parents or related parties when the evaluation results exceed a pre-set standard value.

[0595] "Natural language processing technology" is a computer technology that analyzes human language and understands meaning and emotions.

[0596] "Means for scoring emotional states" refers to a technology that uses emotional information extracted from conversation data to generate numerical values ​​or evaluations.

[0597] "Means for analyzing the frequency of keyword co-occurrence" is a technology that analyzes words and phrases that frequently appear together in conversation data and evaluates their relevance and importance.

[0598] The present invention is a system for monitoring children's mental health status and notifying parents and other relevant parties at appropriate times. This system includes a conversational AI character installed on a device for children, a means for collecting conversation data, a means for evaluating mental health status, a means for identifying stress factors, a means for notifying the evaluation results and stress factors, and a means for notifying when a set threshold is exceeded based on the evaluation results.

[0599] System Configuration

[0600] 1. Devices for children:

[0601] This refers to smartphones and tablet devices for everyday use by children. These devices are equipped with conversational AI characters that can hold natural conversations with users.

[0602] 2. Conversational AI Characters:

[0603] It is a specialized software program that uses natural language processing (NLP) technology to analyze everyday conversations with children and score their mental health. The character utilizes NLP services such as Google Cloud Dialogflow.

[0604] 3. Conversation data collection methods:

[0605] All interactions between children and the conversational AI character are recorded and converted into text using voice recognition technology powered by the Google Cloud Speech-to-Text API.

[0606] 4. Mental health assessment tools:

[0607] This technology analyzes collected text data and scores emotions. It performs sentiment analysis using Google Cloud Natural Language API and other tools.

[0608] 5. Ways to identify stressors:

[0609] This technology analyzes the frequency of co-occurrence of keywords in collected data to determine what causes stress.

[0610] 6. Means of Notification:

[0611] The analysis results and stress factors are notified to parents and other relevant parties via email or SMS. This notification function uses the Twilio API.

[0612] 7. Means of notification when thresholds are exceeded:

[0613] If the mental health assessment results exceed a set threshold, a notification will be sent automatically, allowing parents to keep track of their child's condition in real time.

[0614] Program processing

[0615] The server collects voice data spoken by the child into the smartphone and converts it into text using speech recognition technology. This converted text data is then analyzed using Google Cloud Dialogflow to manage the conversation session. Based on the analysis results, sentiment analysis is performed using the Google Cloud Natural Language API to score the emotional state. If the scoring result exceeds a set threshold, parents and other relevant parties are automatically notified using the Twilio API.

[0616] Specific examples

[0617] If your child is 10 years old:

[0618] A child speaks into the device, saying, "I had a math test today, and it was a little difficult." The device collects this voice data and converts it into text using speech recognition. This text data is analyzed using natural language processing technology, and the child's emotional state is scored. Stress is identified from the keywords "test" and "difficult," and the evaluation results are notified to the parent.

[0619] Prompt Sentence Examples

[0620] "I enjoyed the gym class today, but the math test was a little difficult."

[0621] This system will enable real-time assessment of a child's mental health and promptly notify parents and other relevant parties, enabling appropriate intervention and support.

[0622] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0623] Step 1:

[0624] The user speaks into the smartphone or tablet device that the child uses on a daily basis, and this speech is input into the device as voice data.

[0625] Step 2:

[0626] The device converts the input voice data into text data using the Google Cloud Speech-to-Text API, which outputs the voice data as text data.

[0627] Step 3:

[0628] The device sends the converted text data to Google Cloud Dialogflow, which starts a conversation session and manages the interaction between the user and the conversational AI character. The input is text data, and the output is conversation responses and session information.

[0629] Step 4:

[0630] The server uses the Google Cloud Natural Language API to analyze the text data returned from Dialogflow and score the emotional state, outputting a numerical score for positive, negative, or other emotional states.

[0631] Step 5:

[0632] The server performs co-occurrence analysis on the analyzed emotion scores and extracts specific keywords and phrases from the conversation data to identify stress factors. The input is text data and emotion scores, and the output is the identified stress factors.

[0633] Step 6:

[0634] The server uses the Twilio API to send a notification to parents or other relevant parties when the identified stressors and emotional score exceed a set threshold. This notification includes the emotional assessment result and the identified stressors. The input is the emotional score and stressors, and the output is a notification message to parents or other relevant parties.

[0635] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0636] The present invention relates to a system that uses a conversational AI character and emotion engine installed in a device for children to assess the mental health of children through everyday conversations, identify stress factors, and notify parents or other relevant parties of the results.

[0637] Overall system overview

[0638] The system consists of the following main parts:

[0639] 1. Devices for children

[0640] 2. Conversational AI Characters

[0641] 3. Data Collection Methods

[0642] 4. Emotion Engine

[0643] 5. Analysis method

[0644] 6. Means of notification

[0645] This makes it possible to assess a child's mental health through their everyday conversations and quickly notify parents and other relevant parties if a problem arises.

[0646] Explanation of program processing

[0647] Initial Setup

[0648] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[0649] Starting everyday conversations

[0650] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, what did you do at school today?"

[0651] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[0652] Conversation data collection

[0653] Terminal: A voice recognition system is used to collect user speech, convert the speech data into text, and then store the collected text data in a database.

[0654] Emotion recognition

[0655] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the tone of the voice and the content of the text.

[0656] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[0657] Mental health and stress checks

[0658] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[0659] Device: Evaluates overall health based on collected data and emotional scores.

[0660] Identifying stress factors

[0661] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[0662] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[0663] Sending check results

[0664] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[0665] Terminal: Sends the generated report to the server.

[0666] Server: The server uses the received data to create a notification message using the parent's contact information.

[0667] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[0668] Specific examples

[0669] If the user is a 10-year-old child

[0670] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[0671] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[0672] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[0673] Emotion recognition: The emotion engine recognizes from the text "It was a little difficult" and the tone of the voice that the user is feeling a little stressed.

[0674] Mental health and stress check: Using the results of the emotion engine, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[0675] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[0676] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[0677] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[0678] The processing flow will be explained below.

[0679] MODE FOR CARRYING OUT THE INVENTION

[0680] Step 1: Initial Setup

[0681] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[0682] User (Parent): Enter the parent's contact information (email address, phone number).

[0683] Terminal: Saves the entered information to an internal database and displays a message that the setup is complete.

[0684] Step 2: Starting everyday conversations

[0685] Terminal: A conversational AI character periodically initiates everyday conversations, such as asking questions like, "Hello, what did you do at school today?"

[0686] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[0687] Step 3: Collect conversation data

[0688] Terminal: The user's response is converted into text using a voice recognition system, which is the process of converting voice data into text data.

[0689] Terminal: The converted text data is temporarily stored in an internal database.

[0690] Step 4: Recognize emotions

[0691] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the voice tone and text content.

[0692] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[0693] Step 5: Mental health and stress check

[0694] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[0695] Device: Evaluates overall health based on collected data and emotional scores.

[0696] Step 6: Identify the source of stress

[0697] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[0698] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[0699] Step 7: Submit the check results

[0700] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[0701] Terminal: Sends the generated report to the server.

[0702] Server: The server uses the received data to create a notification message using the parent's contact information.

[0703] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[0704] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[0705] Example 2

[0706] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0707] In recent years, the mental health of children has become increasingly important, and there is a need to detect stress and mental problems early and respond appropriately. However, traditional methods make it difficult for parents and educators to accurately grasp changes and problems in children's daily lives, making it difficult to continuously and objectively evaluate children's mental health. In particular, when children have difficulty clearly expressing their emotions and stressors, there is a risk that these problems will be overlooked.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0709] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with a child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using a voice recognition system and storing it in a database, means for recognizing the child's emotions and identifying their emotional state using an emotion engine that analyzes the text data and voice data, means for evaluating and scoring the child's mental health state based on the analysis results, and means for notifying parents or other relevant parties of the evaluation results and stress factors. This enables parents and educators to understand a child's mental health state in real time through the child's everyday conversations and to identify and address stress factors early on.

[0710] A "children's device" is an electronic device designed primarily for use by minors, and is a device with functionality suitable for everyday conversation and educational activities.

[0711] A "conversational AI character" is a software program that can hold natural conversations with users, and is a virtual character that responds to user utterances using voice recognition and natural language processing technology.

[0712] The "data collection means" is a system component that has the function of collecting input data from a user, and is a device or software that acquires voice data or text data.

[0713] A "voice recognition system" is a technology or software that automatically converts voice data into text data.

[0714] A "database" is a digital storage system that stores collected information in an organized manner and facilitates retrieval and analysis as needed.

[0715] An "emotion engine" is software that includes algorithms and machine learning models to analyze voice and text data and identify a user's emotions.

[0716] The "means for assessing mental health status" is a function that scores the user's psychological state based on collected data and evaluates the user's health status numerically or qualitatively.

[0717] The "means for identifying stress factors" is a function that analyzes the collected data and emotion determination results to identify the specific causes and situations that cause the user to feel stressed.

[0718] "Notification means" is a system component that communicates identified stressors and mental health assessment results to parents or other relevant parties, and is a device or software that sends email or message notifications.

[0719] A "generative AI model" is a machine learning model that learns from large amounts of data and generates natural conversational prompts.

[0720] A "prompt sentence" is a question or statement presented by a conversational AI character to initiate a conversation with the user, and is a guidance sentence to elicit a response from the user.

[0721] This invention relates to a system that uses a conversational AI character installed on a device for children, and the device and a server to collect and analyze data on children's everyday conversations, evaluate their mental health, identify stress factors, and notify parents or other relevant parties of the results.

[0722] Hardware and software used

[0723] Device:

[0724] Portable electronic devices (e.g., tablets, smartphones) used by children are used.

[0725] The device is equipped with basic audio and video collection devices such as a microphone, camera, and speaker.

[0726] Conversational AI Character:

[0727] Conversational AI characters incorporate voice recognition software (e.g., Google Speech-to-Text) and natural language processing engines (e.g., NVIDIA Riva).

[0728] A generative AI model creates prompts, enabling natural conversations with users.

[0729] Database:

[0730] A cloud-based database is used to store the collected data (voice data, text data, emotion recognition results, etc.).

[0731] Emotion Engine:

[0732] The emotion engine utilizes emotion recognition algorithms (e.g., IBM Watson Tone Analyzer) to analyze voice tone, facial expressions, and text content to identify the user's emotional state.

[0733] server:

[0734] A central server is used to analyze the collected data and notify parents or other relevant parties via email, push notifications, or other methods.

[0735] System Operation

[0736] Initial Settings:

[0737] When the device is first started, parents are prompted to enter basic information about their child (such as name, age, gender, and interests) as well as their own contact information, which is then securely stored in a database.

[0738] Starting everyday conversations:

[0739] The device will talk to the child through a conversational AI character based on a pre-set schedule, for example, using a generative AI model to generate and display prompts such as "Hello, what did you do at school today?"

[0740] Conversation data collection:

[0741] The device collects the child's speech through a microphone and converts it into text data using a voice recognition system. The converted text data and the original voice data are stored in a database.

[0742] Emotion Recognition:

[0743] The device uses an emotion engine to analyze the collected voice and text data, for example, to identify the user's emotions (happy, sad, angry, etc.) based on the tone of the voice, the content of the text, and even facial expression data collected by the camera.

[0744] Mental health assessment:

[0745] The device evaluates and quantifies the state of mental health based on the analysis results of the emotion engine, and accumulates daily data to monitor long-term health.

[0746] Identifying stressors:

[0747] The device analyzes negative keywords (e.g., "test" and "fight") in the text data based on their frequency and co-occurrence, and identifies stress factors.

[0748] Notification of results:

[0749] The device and server then compile the analysis results into a report and notify parents and other relevant parties. An example of the content of the report might be a message such as, "Taro is feeling stressed about today's math test."

[0750] Examples of prompts:

[0751] "Hello, what did you do at school today?"

[0752] "What fun things happened today?"

[0753] "Tell me what you've been enjoying lately."

[0754] This will enable early detection of mental changes and stress that children experience on a daily basis, allowing parents and educators to respond quickly and effectively manage and support children's mental health.

[0755] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0756] Step 1: Initial Setup

[0757] Input: Parents enter their child's basic information (such as name, age, gender, interests) and their own contact information into the device.

[0758] Data processing: The device stores this information securely in a database.

[0759] Output: Basic information of parents and children saved is available.

[0760] Specific actions: Parents enter information through the user interface and press the registration button to submit the data.

[0761] Step 2: Starting everyday conversations

[0762] Enter: Your child starts or begins using the device.

[0763] Data processing: The device uses a generative AI model to create prompts based on pre-set schedules and conditions.

[0764] Output: Display a prompt sentence on the screen, such as "Hello, what did you do at school today?"

[0765] Specific actions: The conversational AI character reads out the displayed prompt aloud and asks the child a question.

[0766] Step 3: Collect conversation data

[0767] Input: The child speaks in response to the prompt.

[0768] Data processing: Voice data is collected through the device's microphone and converted into text data using a voice recognition system. The converted text data is then stored in a database.

[0769] Output: The audio data and its converted text are stored in a database for later analysis.

[0770] How it works: Your child's responses are collected by a microphone and converted into text in real time by speech recognition software.

[0771] Step 4: Recognize emotions

[0772] Input: Stored text and audio data.

[0773] Data processing: The device uses an emotion engine to analyze text and voice, recognizing emotions from voice tone and text content to identify emotional states such as happy, sad, or angry.

[0774] Output: Emotion recognition results are generated and stored in a database.

[0775] Specific operation: The emotion engine determines the emotion from the tone of the voice and the content of the text, and assigns a label such as "fun."

[0776] Step 5: Mental health assessment

[0777] Input: Emotion recognition results and text data.

[0778] Data processing: The device quantifies the emotion recognition results and assigns a score to the user's mental health. The score is evaluated as a positive or negative number and stored in a database.

[0779] Output: A mental health assessment score is generated and used for daily health monitoring.

[0780] What it does: A scoring algorithm calculates a number based on emotion data and updates your overall health score.

[0781] Step 6: Identify the stressors

[0782] Input: Scoring results and text data.

[0783] Data processing: The device analyzes negative keywords in the text data based on frequency and co-occurrence relationships to identify stress factors.

[0784] Output: Specific stressors (e.g., "test" or "fight") are identified and stored in a database.

[0785] What it does: A keyword extraction algorithm extracts important negative phrases from the text and performs a frequency analysis.

[0786] Step 7: Notification of results

[0787] Input: Mental health assessment scores and stressors.

[0788] Data processing: The device and server compile the analysis results into a report and notify parents and other relevant parties via email or push notification.

[0789] Output: A specific notification message (e.g., "Taro is stressed about today's math test") is sent to the parent.

[0790] What happens: The report generation module creates a report based on the data, and the notification system sends it to the parent's email address or other contact.

[0791] This will allow children's mental health to be monitored on a daily basis, and parents and other relevant parties to respond quickly if a problem arises.

[0792] (Application example 2)

[0793] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0794] Currently, there is no fully developed system that can assess the mental health of children or agents from everyday conversations, identify stress factors, and quickly notify relevant parties of the results. As a result, it is difficult to detect changes in mental health early and take appropriate action. There is a need to provide a system that can solve this problem and monitor mental health more quickly and accurately.

[0795] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0796] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child and the agent and collecting conversation data, means for analyzing the collected conversation data and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying the parent, manager, or relevant person of the evaluation results and stress factors, and means for installing a program for evaluating the agent's mental health state, identifying stress factors, and notifying the manager or relevant person of the results. This makes it possible to detect changes in mental health state early and take appropriate measures.

[0797] A "children's device" is an electronic device intended for use by children that includes a conversational artificial intelligence character.

[0798] A "conversational AI character" is an AI-based character that can converse with users using natural language processing technology.

[0799] "Conversational Data" means data in the form of voice or text exchanged between a user and a conversational AI character.

[0800] "Emotional state" refers to the user's psychological or emotional state analyzed from conversation data.

[0801] "Means of collection" includes the technical means by which a terminal or associated device captures a user's voice or text data.

[0802] "Means for analyzing and assessing mental health status" refers to technology or programs that use collected conversation data to assess a user's psychological health status.

[0803] A "stressor" is a specific event or situation that may have a negative impact on a user's mental well-being.

[0804] "Means of notification" includes techniques or methods for informing parents, administrators, and other stakeholders about assessment results and stressors.

[0805] "Assessment Results" refers to information about a user's health and emotional state obtained based on collected and analyzed data.

[0806] "Controller" means a person who is responsible for the supervision and management of an Agent's or Child's well-being.

[0807] "Means for installing a program" refers to the methods and technologies for installing software with specific functions onto a terminal or server.

[0808] MODE FOR CARRYING OUT THE INVENTION

[0809] This invention relates to a system for assessing the mental health of children and agents and identifying stress factors. This system mainly comprises a device for children, a conversational AI character, a data collection means, an emotion engine, an analysis means, and a notification means. It also includes a means for installing a program for assessing the mental health of the agent.

[0810] Overall system overview

[0811] The system consists of the following main parts:

[0812] 1. Devices for children

[0813] The device is equipped with a conversational artificial intelligence character that can hold everyday conversations with children.

[0814] 2. Conversational AI Characters

[0815] The conversational AI character uses natural language processing technology to collect conversational data through conversations with users and score their emotions.

[0816] 3. Data Collection Methods

[0817] The device uses a speech recognition system (e.g., Google Speech Recognition API) to collect the user's voice and text data, which is then converted into text.

[0818] 4. Emotion engine and analysis methods

[0819] The collected data is subjected to sentiment analysis by an emotion engine (e.g., TextBlob). Based on the sentiment scoring, the user's mental health is evaluated.

[0820] 5. Evaluation results and identification of stress factors

[0821] Stress factors are identified based on the results of the emotion engine and keyword analysis in the conversation data. For example, negative keywords such as "tired" and "tough" are detected by analyzing the frequency of co-occurrence of keywords.

[0822] 6. Means of notification

[0823] A report is generated based on the assessment results and identified stressors, and parents and administrators are notified via email or other means using SMTP.

[0824] 7. Installing the program

[0825] A program to assess the agent's mental health will be installed on the device or server, and will comprehensively perform voice recognition, emotion analysis, stress assessment, and notifications.

[0826] Specific examples

[0827] For example, if Agent Taro says to the conversation system after a delivery, "I'm tired because there were a lot of orders today," this voice data is collected and converted into text. The emotion engine detects negative emotions from the expression "tired" and evaluates the mental health state as "high stress." The detected stress factors are "many orders" and "tired." Based on this, a notification is sent to the manager via email stating, "There were a lot of orders today, and the agent is feeling tired."

[0828] Prompt example

[0829] The agent and child are presented with the following prompt:

[0830] "It's been tough with so many orders. How can I make deliveries easier?"

[0831] "I'm tired after a long drive today. How can I relieve this fatigue?"

[0832] In this way, the system assesses the mental health of children and agents through everyday conversations, quickly and accurately identifies stressors, and notifies relevant parties, enabling early response.

[0833] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0834] Step 1:

[0835] Initial Setup

[0836] The server saves the initial information of the agent (such as name, age, contact details, etc.) and the administrator's contact details in a database. This operation is performed based on the information entered by the user (agent or administrator) and saved in a database (e.g., a JSON file or SQL database).

[0837] Step 2:

[0838] Starting everyday conversations

[0839] The terminal starts a conversational AI character and displays a prompt to the user (agent). An example of a prompt is "How was your day?". The input is the agent's voice.

[0840] Step 3:

[0841] Conversation data collection

[0842] The terminal uses a speech recognition system to convert the agent's speech into text data (e.g., Google Speech Recognition API). The collected text data is stored in a database. The input is speech data, and the output is text data.

[0843] Step 4:

[0844] Emotion recognition

[0845] Based on the collected text data, the server performs sentiment analysis using an emotion engine (e.g., TextBlob). It performs sentiment scoring and quantifies the user's mental health. The input is text data, and the output is a sentiment score.

[0846] Step 5:

[0847] Mental health assessment

[0848] The server evaluates the agent's mental health state based on the emotion score. Depending on the range of the score, the state is classified as "high stress," "mild stress," "normal," etc. The input is the emotion score, and the output is the health state evaluation result.

[0849] Step 6:

[0850] Identifying stressors

[0851] The server detects negative keywords (e.g., "tired" or "tough") from the collected text data and identifies stress factors by analyzing their co-occurrence frequency. The input is text data, and the output is stress factors.

[0852] Step 7:

[0853] Generating check results

[0854] Based on the assessment results and stressors, the server generates a report that includes the agent's health status and identified stressors. The inputs are the assessment results and stressors, and the output is the report.

[0855] Step 8:

[0856] Notification of check results

[0857] The server notifies the administrator of the generated report. Specifically, it sends a notification to the administrator's email address using an SMTP server. The input is the report, and the output is sending an email.

[0858] These processing steps make it possible to monitor the mental health of children and agents and respond in a timely manner.

[0859] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0860] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0861] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0862] [Third embodiment]

[0863] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0864] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0865] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0866] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0867] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0868] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0869] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0870] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0871] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0872] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0873] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0874] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0875] The system of the present invention is a device for children equipped with a conversational AI character that checks the mental health of children through daily conversations, identifies stressors, and notifies parents or other relevant parties of the results. An embodiment of the system is described in detail below.

[0876] Overall system overview

[0877] The main components of this system are a device for children, a conversational AI character, data collection means, analysis means, and notification means. These allow for regular assessment of children's mental health and prompt notification to parents or other relevant parties when problems arise.

[0878] Explanation of program processing

[0879] Initial Setup

[0880] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[0881] Starting everyday conversations

[0882] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, how was school today?"

[0883] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[0884] Conversation data collection

[0885] Terminal: Uses a voice recognition system to collect user speech, converts the speech data into text, and then stores the collected text data in a database.

[0886] Mental health and stress checks

[0887] Device: The collected conversational text data is processed by a dedicated analysis module. Natural language processing (NLP) technology is used to analyze the text data and score the emotional state. For example, emotions such as "happy," "sad," and "stressed" are identified.

[0888] Identifying stress factors

[0889] Device: Identify stress factors from the analysis results. Analyze the frequency of co-occurrence of keywords in the collected text data to determine what causes stress for children. Examples include "a lot of homework" and "relationships with friends."

[0890] Sending check results

[0891] Terminal: Compile the analysis results and identified stress factors into a report.

[0892] Terminal: Sends the compiled report to the server.

[0893] Server: Based on the received data, the server uses the contact information of the parent or other relevant person to generate and send a notification message containing the analysis results and stress factors. For example, an email stating, "Your child is feeling stressed about their homework recently."

[0894] Specific examples

[0895] If the user is a 10-year-old child

[0896] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[0897] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[0898] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[0899] Mental health and stress check: Using natural language processing technology, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[0900] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[0901] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[0902] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[0903] The processing flow will be explained below.

[0904] Program processing details

[0905] Step 1: Initial Setup

[0906] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[0907] User (Parent): Enter your contact information (email address, phone number).

[0908] Terminal: Saves the entered information to the internal database. Displays a message that the setup is complete.

[0909] Step 2: Starting everyday conversations

[0910] Device: Periodically activates a conversational AI character that speaks to the child, asking questions such as, "Hello, what did you do at school today?"

[0911] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[0912] Step 3: Collect conversation data

[0913] Terminal: The child's answers are converted into text using a voice recognition system. This is the process of converting voice data into text data.

[0914] Terminal: The converted text data is temporarily stored in an internal database.

[0915] Step 4: Mental health and stress check

[0916] Terminal: Passes the collected text data to the analysis module, which analyzes the text data using natural language processing (NLP) techniques.

[0917] Device: Emotions are scored from text data. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[0918] Step 5: Identify the cause of stress

[0919] Device: Identify stress factors from emotion scoring results. Identify negative keywords and phrases in text data and analyze their co-occurrence frequency.

[0920] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[0921] Step 6: Submit the check results

[0922] Terminal: Generate a report containing the analysis results and identified stressors.

[0923] Terminal: Sends the generated report to the server.

[0924] Server: The server uses the received data to create a notification message using the parent's contact information.

[0925] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[0926] Step 7: Provide feedback

[0927] Server: Generates notification messages along with specific advice to the parent.

[0928] Server: Sends a message with detailed advice, for example, "Your child is stressed about a test. Give them some time to relax."

[0929] User (Parent): Receives notification messages sent and checks the status of their child.

[0930] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[0931] Example 1

[0932] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0933] Current devices for children lack systems that can properly monitor a child's mental health and immediately notify parents and other relevant parties. There are also insufficient means to analyze conversation data and identify stressors that children are experiencing. As a result, it is difficult to detect stress and anxiety that children experience on a daily basis early and deal with them appropriately.

[0934] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0935] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with the child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using voice recognition technology, means for sending the text data to a dedicated analysis module and evaluating the mental health state using natural language processing technology, means for identifying stress factors based on the evaluation results, and means for compiling the evaluation results and stress factors into a report and notifying parents or relevant parties. This makes it possible to monitor a child's mental health state through their everyday conversations, and to quickly identify stress factors and notify parents or relevant parties.

[0936] A "child-directed device" is an electronic device intended for use by children, including, for example, tablets and smartphones.

[0937] A "conversational AI character" is a software agent that uses AI technology to converse with users in natural language and can hold conversations with children.

[0938] "Speech recognition technology" is a technology for converting voice data into text data, and is used to convert a user's verbal utterances into text information.

[0939] "Natural language processing technology" is a technology for computer processing of human language, and is used to analyze text data to understand emotions and intentions.

[0940] "Means for scoring emotional states" refers to a method for quantifying and evaluating a user's emotions based on words and phrases extracted from text data.

[0941] "Keyword co-occurrence frequency" is an indicator of how often certain words or phrases appear together, allowing you to identify factors that are highly relevant.

[0942] A "report" is a document summarizing the analysis results and stress factors, and includes information for notifying parents or other relevant parties.

[0943] A "database" refers to a system that systematically stores collected data for later retrieval and analysis.

[0944] The system of the present invention is a device for children equipped with a conversational AI character that monitors the child's mental health through everyday conversations, identifies stressors, and notifies parents or other relevant parties. The components of this system include a device for children, a conversational AI character, voice recognition technology, natural language processing technology, a database, and a server.

[0945] Hardware and Software Configuration

[0946] Devices: Electronic devices such as tablets and smartphones used by children.

[0947] Conversational AI character: A software agent that can have natural conversations with children.

[0948] Speech recognition technology: Technology that converts a child's speech from voice data into text data.

[0949] Natural language processing technology: Technology that analyzes conversation data and scores emotional states.

[0950] Database: A system that stores and manages collected text data.

[0951] Server: A system that generates and sends messages to notify parents or other interested parties of the results of data analysis.

[0952] The operation of the system proceeds through the following steps.

[0953] Initial Setup

[0954] First, the parent starts up the device and enters the child's basic information (name, age, gender, interests) on the initial setup screen. The parent also enters the parent's contact information, which is then saved in a database. For example, the parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device screen, and registers their own email address.

[0955] Starting everyday conversations

[0956] When a child uses the device, a conversational AI character periodically initiates a conversation. For example, the character may display a prompt such as, "Hello, how did you do at school today?" to which the child may respond, "I had fun in gym class today."

[0957] Conversation data collection

[0958] The device uses voice recognition technology to convert the child's speech into text data, which is then stored in a database. At this time, software equipped with voice recognition technology is activated.

[0959] Mental health and stress checks

[0960] The collected text data is sent to a dedicated analysis module and analyzed using natural language processing technology. For example, emotions such as "happy," "sad," and "stressed" are identified, and the stress level is assessed based on the emotion score.

[0961] Identifying stress factors

[0962] Based on the analysis results, the device identifies the child's stressors by analyzing the frequency of co-occurrence of keywords in the conversation data, determining stressors such as "a lot of homework" and "relationships with friends."

[0963] Sending check results

[0964] The evaluation results and stress factors are compiled into a report and sent from the device to a server. The server then generates and sends a message notifying the parent or other relevant person of the analysis results using their contact information. For example, an email could be sent to the parent stating, "Your child has been feeling stressed about their homework recently."

[0965] This system allows early detection of everyday stress in children, enabling parents and other relevant parties to respond promptly. Specific examples of prompts include "Hello, what fun things did you do today?" and "Is there anything that's bothering you lately?"

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

[0967] Step 1: Initial Setup

[0968] User: The parent starts the device and accesses the initial setup screen.

[0969] Device: Displays a form for entering information such as the user's name, age, gender, interests, etc. Specifically, enter information such as "Taro," "10 years old," "boy," and "likes soccer."

[0970] User: The parent enters the required information and presses the complete button.

[0971] On the device: Display a screen to enter the parent's contact information (email address, phone number). The entered information is saved in the database.

[0972] Input: Name, Age, Gender, Interests, Parent Contact Information

[0973] Output: Child and parent information stored in a database

[0974] Step 2: Starting everyday conversations

[0975] Device: When a child turns on the device, a conversational AI character automatically launches.

[0976] Device: Periodically, such as in the morning or after school, display a prompt like "Hi, what happened at school today?"

[0977] User (child): The child replies, "I enjoyed gym class today."

[0978] Input: Child's speech

[0979] Output: Collected audio data

[0980] Step 3: Collect conversation data

[0981] Device: Activate the voice recognition system and convert the child's speech from voice data into text data.

[0982] Terminal: Save the converted text data in the database.

[0983] Input: Collected audio data

[0984] Output: Text data stored in a database

[0985] Step 4: Mental health and stress check

[0986] Terminal: The saved text data is sent to a dedicated analysis module.

[0987] Device: Analyzes text data using natural language processing (NLP) technology to score emotional states. For example, identify emotions such as "happy," "sad," or "stressed." Furthermore, evaluates stress levels based on the emotional scores.

[0988] Input: Text data stored in a database

[0989] Output: Emotional state score and stress level rating

[0990] Step 5: Identify the cause of stress

[0991] Terminal: Identify stress factors from the analysis results.

[0992] Device: Analyzes the frequency of co-occurrence of keywords in text data to determine stress factors such as "a lot of homework" and "relationships with friends."

[0993] Input: Emotional state scores and text data

[0994] Output: Identified stressors

[0995] Step 6: Submit the check results

[0996] Terminal: Compile the analysis results and identified stress factors into a report.

[0997] Terminal: Sends the compiled report to the server.

[0998] Server: Based on the received data, the server generates a notification message containing the analysis results and stress factors using the parent or interested party's contact information.

[0999] Server: Sends the generated notification message to the parent or other interested party. For example, an email stating, "Your child is feeling stressed about their homework these days."

[1000] Input: Analysis results and stress factors

[1001] Output: Notification message sent to parent or interested party

[1002] (Application example 1)

[1003] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1004] In modern society, understanding children's mental health is extremely important. However, it is difficult for parents and other concerned parties to immediately understand a child's daily stress and mental burden and take appropriate measures. This can lead to mental health problems being overlooked. The present invention aims to solve this problem by providing a system that quickly and accurately assesses a child's mental health, identifies stressors, and notifies the user in a timely manner.

[1005] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1006] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child on the terminal and collecting conversation data, means for analyzing the conversation data collected on the terminal or server and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying parents or relevant parties of the evaluation results and stress factors, and means for notifying if a threshold set based on the evaluation results is exceeded. This makes it possible to evaluate a child's mental health state in real time and promptly notify parents or relevant parties when a problem occurs, enabling appropriate measures to be taken.

[1007] "Children's devices" are electronic devices intended for use by children, including tablets and smartphones.

[1008] A "conversational AI character" is an AI program that can communicate with users in a dialogue format.

[1009] The "means for collecting conversation data" is a system that has the function of recording conversations with children and storing them in a database or server.

[1010] "Means for assessing mental health" refers to algorithms or programs that analyze collected conversation data and score users' emotions and psychological state.

[1011] "Means for identifying stress factors" refers to technology that analyzes specific keywords and phrases within conversation data to determine what causes stress for users.

[1012] "Means of notification" refers to the function for communicating evaluation results and stress factors to parents or relevant parties, and includes methods such as email and app notifications.

[1013] The "means for notifying when a set threshold is exceeded" is a function that automatically sends a notification to parents or related parties when the evaluation results exceed a pre-set standard value.

[1014] "Natural language processing technology" is a computer technology that analyzes human language and understands meaning and emotions.

[1015] "Means for scoring emotional states" refers to a technology that uses emotional information extracted from conversation data to generate numerical values ​​or evaluations.

[1016] "Means for analyzing the frequency of keyword co-occurrence" is a technology that analyzes words and phrases that frequently appear together in conversation data and evaluates their relevance and importance.

[1017] The present invention is a system for monitoring children's mental health status and notifying parents and other relevant parties at appropriate times. This system includes a conversational AI character installed on a device for children, a means for collecting conversation data, a means for evaluating mental health status, a means for identifying stress factors, a means for notifying the evaluation results and stress factors, and a means for notifying when a set threshold is exceeded based on the evaluation results.

[1018] System Configuration

[1019] 1. Devices for children:

[1020] This refers to smartphones and tablet devices for everyday use by children. These devices are equipped with conversational AI characters that can hold natural conversations with users.

[1021] 2. Conversational AI Characters:

[1022] It is a specialized software program that uses natural language processing (NLP) technology to analyze everyday conversations with children and score their mental health. The character utilizes NLP services such as Google Cloud Dialogflow.

[1023] 3. Conversation data collection methods:

[1024] All interactions between children and the conversational AI character are recorded and converted into text using voice recognition technology powered by the Google Cloud Speech-to-Text API.

[1025] 4. Mental health assessment tools:

[1026] This technology analyzes collected text data and scores emotions. It performs sentiment analysis using Google Cloud Natural Language API and other tools.

[1027] 5. Ways to identify stressors:

[1028] This technology analyzes the frequency of co-occurrence of keywords in collected data to determine what causes stress.

[1029] 6. Means of Notification:

[1030] The analysis results and stress factors are notified to parents and other relevant parties via email or SMS. This notification function uses the Twilio API.

[1031] 7. Means of notification when thresholds are exceeded:

[1032] If the mental health assessment results exceed a set threshold, a notification will be sent automatically, allowing parents to keep track of their child's condition in real time.

[1033] Program processing

[1034] The server collects voice data spoken by the child into the smartphone and converts it into text using speech recognition technology. This converted text data is then analyzed using Google Cloud Dialogflow to manage the conversation session. Based on the analysis results, sentiment analysis is performed using the Google Cloud Natural Language API to score the emotional state. If the scoring result exceeds a set threshold, parents and other relevant parties are automatically notified using the Twilio API.

[1035] Specific examples

[1036] If your child is 10 years old:

[1037] A child speaks into the device, saying, "I had a math test today, and it was a little difficult." The device collects this voice data and converts it into text using speech recognition. This text data is analyzed using natural language processing technology, and the child's emotional state is scored. Stress is identified from the keywords "test" and "difficult," and the evaluation results are notified to the parent.

[1038] Prompt Sentence Examples

[1039] "I enjoyed the gym class today, but the math test was a little difficult."

[1040] This system will enable real-time assessment of a child's mental health and promptly notify parents and other relevant parties, enabling appropriate intervention and support.

[1041] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1042] Step 1:

[1043] The user speaks into the smartphone or tablet device that the child uses on a daily basis, and this speech is input into the device as voice data.

[1044] Step 2:

[1045] The device converts the input voice data into text data using the Google Cloud Speech-to-Text API, which outputs the voice data as text data.

[1046] Step 3:

[1047] The device sends the converted text data to Google Cloud Dialogflow, which starts a conversation session and manages the interaction between the user and the conversational AI character. The input is text data, and the output is conversation responses and session information.

[1048] Step 4:

[1049] The server uses the Google Cloud Natural Language API to analyze the text data returned from Dialogflow and score the emotional state, outputting a numerical score for positive, negative, or other emotional states.

[1050] Step 5:

[1051] The server performs co-occurrence analysis on the analyzed emotion scores and extracts specific keywords and phrases from the conversation data to identify stress factors. The input is text data and emotion scores, and the output is the identified stress factors.

[1052] Step 6:

[1053] The server uses the Twilio API to send a notification to parents or other relevant parties when the identified stressors and emotional score exceed a set threshold. This notification includes the emotional assessment result and the identified stressors. The input is the emotional score and stressors, and the output is a notification message to parents or other relevant parties.

[1054] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1055] The present invention relates to a system that uses a conversational AI character and emotion engine installed in a device for children to assess the mental health of children through everyday conversations, identify stress factors, and notify parents or other relevant parties of the results.

[1056] Overall system overview

[1057] The system consists of the following main parts:

[1058] 1. Devices for children

[1059] 2. Conversational AI Characters

[1060] 3. Data Collection Methods

[1061] 4. Emotion Engine

[1062] 5. Analysis method

[1063] 6. Means of notification

[1064] This makes it possible to assess a child's mental health through their everyday conversations and quickly notify parents and other relevant parties if a problem arises.

[1065] Explanation of program processing

[1066] Initial Setup

[1067] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[1068] Starting everyday conversations

[1069] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, what did you do at school today?"

[1070] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[1071] Conversation data collection

[1072] Terminal: A voice recognition system is used to collect user speech, convert the speech data into text, and then store the collected text data in a database.

[1073] Emotion recognition

[1074] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the tone of the voice and the content of the text.

[1075] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[1076] Mental health and stress checks

[1077] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[1078] Device: Evaluates overall health based on collected data and emotional scores.

[1079] Identifying stress factors

[1080] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[1081] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[1082] Sending check results

[1083] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[1084] Terminal: Sends the generated report to the server.

[1085] Server: The server uses the received data to create a notification message using the parent's contact information.

[1086] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[1087] Specific examples

[1088] If the user is a 10-year-old child

[1089] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[1090] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[1091] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[1092] Emotion recognition: The emotion engine recognizes from the text "It was a little difficult" and the tone of the voice that the user is feeling a little stressed.

[1093] Mental health and stress check: Using the results of the emotion engine, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[1094] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[1095] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[1096] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[1097] The processing flow will be explained below.

[1098] MODE FOR CARRYING OUT THE INVENTION

[1099] Step 1: Initial Setup

[1100] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[1101] User (Parent): Enter the parent's contact information (email address, phone number).

[1102] Terminal: Saves the entered information to an internal database and displays a message that the setup is complete.

[1103] Step 2: Starting everyday conversations

[1104] Terminal: A conversational AI character periodically initiates everyday conversations, such as asking questions like, "Hello, what did you do at school today?"

[1105] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[1106] Step 3: Collect conversation data

[1107] Terminal: The user's response is converted into text using a voice recognition system, which is the process of converting voice data into text data.

[1108] Terminal: The converted text data is temporarily stored in an internal database.

[1109] Step 4: Recognize emotions

[1110] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the voice tone and text content.

[1111] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[1112] Step 5: Mental health and stress check

[1113] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[1114] Device: Evaluates overall health based on collected data and emotional scores.

[1115] Step 6: Identify the source of stress

[1116] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[1117] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[1118] Step 7: Submit the check results

[1119] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[1120] Terminal: Sends the generated report to the server.

[1121] Server: The server uses the received data to create a notification message using the parent's contact information.

[1122] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[1123] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[1124] Example 2

[1125] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1126] In recent years, the mental health of children has become increasingly important, and there is a need to detect stress and mental problems early and respond appropriately. However, traditional methods make it difficult for parents and educators to accurately grasp changes and problems in children's daily lives, making it difficult to continuously and objectively evaluate children's mental health. In particular, when children have difficulty clearly expressing their emotions and stressors, there is a risk that these problems will be overlooked.

[1127] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1128] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with a child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using a voice recognition system and storing it in a database, means for recognizing the child's emotions and identifying their emotional state using an emotion engine that analyzes the text data and voice data, means for evaluating and scoring the child's mental health state based on the analysis results, and means for notifying parents or other relevant parties of the evaluation results and stress factors. This enables parents and educators to understand a child's mental health state in real time through the child's everyday conversations and to identify and address stress factors early on.

[1129] A "children's device" is an electronic device designed primarily for use by minors, and is a device with functionality suitable for everyday conversation and educational activities.

[1130] A "conversational AI character" is a software program that can hold natural conversations with users, and is a virtual character that responds to user utterances using voice recognition and natural language processing technology.

[1131] The "data collection means" is a system component that has the function of collecting input data from a user, and is a device or software that acquires voice data or text data.

[1132] A "voice recognition system" is a technology or software that automatically converts voice data into text data.

[1133] A "database" is a digital storage system that stores collected information in an organized manner and facilitates retrieval and analysis as needed.

[1134] An "emotion engine" is software that includes algorithms and machine learning models to analyze voice and text data and identify a user's emotions.

[1135] The "means for assessing mental health status" is a function that scores the user's psychological state based on collected data and evaluates the user's health status numerically or qualitatively.

[1136] The "means for identifying stress factors" is a function that analyzes the collected data and emotion determination results to identify the specific causes and situations that cause the user to feel stressed.

[1137] "Notification means" is a system component that communicates identified stressors and mental health assessment results to parents or other relevant parties, and is a device or software that sends email or message notifications.

[1138] A "generative AI model" is a machine learning model that learns from large amounts of data and generates natural conversational prompts.

[1139] A "prompt sentence" is a question or statement presented by a conversational AI character to initiate a conversation with the user, and is a guidance sentence to elicit a response from the user.

[1140] This invention relates to a system that uses a conversational AI character installed on a device for children, and the device and a server to collect and analyze data on children's everyday conversations, evaluate their mental health, identify stress factors, and notify parents or other relevant parties of the results.

[1141] Hardware and software used

[1142] Device:

[1143] Portable electronic devices (e.g., tablets, smartphones) used by children are used.

[1144] The device is equipped with basic audio and video collection devices such as a microphone, camera, and speaker.

[1145] Conversational AI Character:

[1146] Conversational AI characters incorporate voice recognition software (e.g., Google Speech-to-Text) and natural language processing engines (e.g., NVIDIA Riva).

[1147] A generative AI model creates prompts, enabling natural conversations with users.

[1148] Database:

[1149] A cloud-based database is used to store the collected data (voice data, text data, emotion recognition results, etc.).

[1150] Emotion Engine:

[1151] The emotion engine utilizes emotion recognition algorithms (e.g., IBM Watson Tone Analyzer) to analyze voice tone, facial expressions, and text content to identify the user's emotional state.

[1152] server:

[1153] A central server is used to analyze the collected data and notify parents or other relevant parties via email, push notifications, or other methods.

[1154] System Operation

[1155] Initial Settings:

[1156] When the device is first started, parents are prompted to enter basic information about their child (such as name, age, gender, and interests) as well as their own contact information, which is then securely stored in a database.

[1157] Starting everyday conversations:

[1158] The device will talk to the child through a conversational AI character based on a pre-set schedule, for example, using a generative AI model to generate and display prompts such as "Hello, what did you do at school today?"

[1159] Conversation data collection:

[1160] The device collects the child's speech through a microphone and converts it into text data using a voice recognition system. The converted text data and the original voice data are stored in a database.

[1161] Emotion Recognition:

[1162] The device uses an emotion engine to analyze the collected voice and text data, for example, to identify the user's emotions (happy, sad, angry, etc.) based on the tone of the voice, the content of the text, and even facial expression data collected by the camera.

[1163] Mental health assessment:

[1164] The device evaluates and quantifies the state of mental health based on the analysis results of the emotion engine, and accumulates daily data to monitor long-term health.

[1165] Identifying stressors:

[1166] The device analyzes negative keywords (e.g., "test" and "fight") in the text data based on their frequency and co-occurrence, and identifies stress factors.

[1167] Notification of results:

[1168] The device and server then compile the analysis results into a report and notify parents and other relevant parties. An example of the content of the report might be a message such as, "Taro is feeling stressed about today's math test."

[1169] Examples of prompts:

[1170] "Hello, what did you do at school today?"

[1171] "What fun things happened today?"

[1172] "Tell me what you've been enjoying lately."

[1173] This will enable early detection of mental changes and stress that children experience on a daily basis, allowing parents and educators to respond quickly and effectively manage and support children's mental health.

[1174] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1175] Step 1: Initial Setup

[1176] Input: Parents enter their child's basic information (such as name, age, gender, interests) and their own contact information into the device.

[1177] Data processing: The device stores this information securely in a database.

[1178] Output: Basic information of parents and children saved is available.

[1179] Specific actions: Parents enter information through the user interface and press the registration button to submit the data.

[1180] Step 2: Starting everyday conversations

[1181] Enter: Your child starts or begins using the device.

[1182] Data processing: The device uses a generative AI model to create prompts based on pre-set schedules and conditions.

[1183] Output: Display a prompt sentence on the screen, such as "Hello, what did you do at school today?"

[1184] Specific actions: The conversational AI character reads out the displayed prompt aloud and asks the child a question.

[1185] Step 3: Collect conversation data

[1186] Input: The child speaks in response to the prompt.

[1187] Data processing: Voice data is collected through the device's microphone and converted into text data using a voice recognition system. The converted text data is then stored in a database.

[1188] Output: The audio data and its converted text are stored in a database for later analysis.

[1189] How it works: Your child's responses are collected by a microphone and converted into text in real time by speech recognition software.

[1190] Step 4: Recognize emotions

[1191] Input: Stored text and audio data.

[1192] Data processing: The device uses an emotion engine to analyze text and voice, recognizing emotions from voice tone and text content to identify emotional states such as happy, sad, or angry.

[1193] Output: Emotion recognition results are generated and stored in a database.

[1194] Specific operation: The emotion engine determines the emotion from the tone of the voice and the content of the text, and assigns a label such as "fun."

[1195] Step 5: Mental health assessment

[1196] Input: Emotion recognition results and text data.

[1197] Data processing: The device quantifies the emotion recognition results and assigns a score to the user's mental health. The score is evaluated as a positive or negative number and stored in a database.

[1198] Output: A mental health assessment score is generated and used for daily health monitoring.

[1199] What it does: A scoring algorithm calculates a number based on emotion data and updates your overall health score.

[1200] Step 6: Identify the stressors

[1201] Input: Scoring results and text data.

[1202] Data processing: The device analyzes negative keywords in the text data based on frequency and co-occurrence relationships to identify stress factors.

[1203] Output: Specific stressors (e.g., "test" or "fight") are identified and stored in a database.

[1204] What it does: A keyword extraction algorithm extracts important negative phrases from the text and performs a frequency analysis.

[1205] Step 7: Notification of results

[1206] Input: Mental health assessment scores and stressors.

[1207] Data processing: The device and server compile the analysis results into a report and notify parents and other relevant parties via email or push notification.

[1208] Output: A specific notification message (e.g., "Taro is stressed about today's math test") is sent to the parent.

[1209] What happens: The report generation module creates a report based on the data, and the notification system sends it to the parent's email address or other contact.

[1210] This will allow children's mental health to be monitored on a daily basis, and parents and other relevant parties to respond quickly if a problem arises.

[1211] (Application example 2)

[1212] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1213] Currently, there is no fully developed system that can assess the mental health of children or agents from everyday conversations, identify stress factors, and quickly notify relevant parties of the results. As a result, it is difficult to detect changes in mental health early and take appropriate action. There is a need to provide a system that can solve this problem and monitor mental health more quickly and accurately.

[1214] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1215] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child and the agent and collecting conversation data, means for analyzing the collected conversation data and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying the parent, manager, or relevant person of the evaluation results and stress factors, and means for installing a program for evaluating the agent's mental health state, identifying stress factors, and notifying the manager or relevant person of the results. This makes it possible to detect changes in mental health state early and take appropriate measures.

[1216] A "children's device" is an electronic device intended for use by children that includes a conversational artificial intelligence character.

[1217] A "conversational AI character" is an AI-based character that can converse with users using natural language processing technology.

[1218] "Conversational Data" means data in the form of voice or text exchanged between a user and a conversational AI character.

[1219] "Emotional state" refers to the user's psychological or emotional state analyzed from conversation data.

[1220] "Means of collection" includes the technical means by which a terminal or associated device captures a user's voice or text data.

[1221] "Means for analyzing and assessing mental health status" refers to technology or programs that use collected conversation data to assess a user's psychological health status.

[1222] A "stressor" is a specific event or situation that may have a negative impact on a user's mental well-being.

[1223] "Means of notification" includes techniques or methods for informing parents, administrators, and other stakeholders about assessment results and stressors.

[1224] "Assessment Results" refers to information about a user's health and emotional state obtained based on collected and analyzed data.

[1225] "Controller" means a person who is responsible for the supervision and management of an Agent's or Child's well-being.

[1226] "Means for installing a program" refers to the methods and technologies for installing software with specific functions onto a terminal or server.

[1227] MODE FOR CARRYING OUT THE INVENTION

[1228] This invention relates to a system for assessing the mental health of children and agents and identifying stress factors. This system mainly comprises a device for children, a conversational AI character, a data collection means, an emotion engine, an analysis means, and a notification means. It also includes a means for installing a program for assessing the mental health of the agent.

[1229] Overall system overview

[1230] The system consists of the following main parts:

[1231] 1. Devices for children

[1232] The device is equipped with a conversational artificial intelligence character that can hold everyday conversations with children.

[1233] 2. Conversational AI Characters

[1234] The conversational AI character uses natural language processing technology to collect conversational data through conversations with users and score their emotions.

[1235] 3. Data Collection Methods

[1236] The device uses a speech recognition system (e.g., Google Speech Recognition API) to collect the user's voice and text data, which is then converted into text.

[1237] 4. Emotion engine and analysis methods

[1238] The collected data is subjected to sentiment analysis by an emotion engine (e.g., TextBlob). Based on the sentiment scoring, the user's mental health is evaluated.

[1239] 5. Evaluation results and identification of stress factors

[1240] Stress factors are identified based on the results of the emotion engine and keyword analysis in the conversation data. For example, negative keywords such as "tired" and "tough" are detected by analyzing the frequency of co-occurrence of keywords.

[1241] 6. Means of notification

[1242] A report is generated based on the assessment results and identified stressors, and parents and administrators are notified via email or other means using SMTP.

[1243] 7. Installing the program

[1244] A program to assess the agent's mental health will be installed on the device or server, and will comprehensively perform voice recognition, emotion analysis, stress assessment, and notifications.

[1245] Specific examples

[1246] For example, if Agent Taro says to the conversation system after a delivery, "I'm tired because there were a lot of orders today," this voice data is collected and converted into text. The emotion engine detects negative emotions from the expression "tired" and evaluates the mental health state as "high stress." The detected stress factors are "many orders" and "tired." Based on this, a notification is sent to the manager via email stating, "There were a lot of orders today, and the agent is feeling tired."

[1247] Prompt example

[1248] The agent and child are presented with the following prompt:

[1249] "It's been tough with so many orders. How can I make deliveries easier?"

[1250] "I'm tired after a long drive today. How can I relieve this fatigue?"

[1251] In this way, the system assesses the mental health of children and agents through everyday conversations, quickly and accurately identifies stressors, and notifies relevant parties, enabling early response.

[1252] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1253] Step 1:

[1254] Initial Setup

[1255] The server saves the initial information of the agent (such as name, age, contact details, etc.) and the administrator's contact details in a database. This operation is performed based on the information entered by the user (agent or administrator) and saved in a database (e.g., a JSON file or SQL database).

[1256] Step 2:

[1257] Starting everyday conversations

[1258] The terminal starts a conversational AI character and displays a prompt to the user (agent). An example of a prompt is "How was your day?". The input is the agent's voice.

[1259] Step 3:

[1260] Conversation data collection

[1261] The terminal uses a speech recognition system to convert the agent's speech into text data (e.g., Google Speech Recognition API). The collected text data is stored in a database. The input is speech data, and the output is text data.

[1262] Step 4:

[1263] Emotion recognition

[1264] Based on the collected text data, the server performs sentiment analysis using an emotion engine (e.g., TextBlob). It performs sentiment scoring and quantifies the user's mental health. The input is text data, and the output is a sentiment score.

[1265] Step 5:

[1266] Mental health assessment

[1267] The server evaluates the agent's mental health state based on the emotion score. Depending on the range of the score, the state is classified as "high stress," "mild stress," "normal," etc. The input is the emotion score, and the output is the health state evaluation result.

[1268] Step 6:

[1269] Identifying stressors

[1270] The server detects negative keywords (e.g., "tired" or "tough") from the collected text data and identifies stress factors by analyzing their co-occurrence frequency. The input is text data, and the output is stress factors.

[1271] Step 7:

[1272] Generating check results

[1273] Based on the assessment results and stressors, the server generates a report that includes the agent's health status and identified stressors. The inputs are the assessment results and stressors, and the output is the report.

[1274] Step 8:

[1275] Notification of check results

[1276] The server notifies the administrator of the generated report. Specifically, it sends a notification to the administrator's email address using an SMTP server. The input is the report, and the output is sending an email.

[1277] These processing steps make it possible to monitor the mental health of children and agents and respond in a timely manner.

[1278] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1279] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1280] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1281] [Fourth embodiment]

[1282] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1283] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1284] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1285] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1286] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1287] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1288] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1289] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1290] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1291] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1292] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1293] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1294] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1295] The system of the present invention is a device for children equipped with a conversational AI character that checks the mental health of children through daily conversations, identifies stressors, and notifies parents or other relevant parties of the results. An embodiment of the system is described in detail below.

[1296] Overall system overview

[1297] The main components of this system are a device for children, a conversational AI character, data collection means, analysis means, and notification means. These allow for regular assessment of children's mental health and prompt notification to parents or other relevant parties when problems arise.

[1298] Explanation of program processing

[1299] Initial Setup

[1300] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[1301] Starting everyday conversations

[1302] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, how was school today?"

[1303] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[1304] Conversation data collection

[1305] Terminal: Uses a voice recognition system to collect user speech, converts the speech data into text, and then stores the collected text data in a database.

[1306] Mental health and stress checks

[1307] Device: The collected conversational text data is processed by a dedicated analysis module. Natural language processing (NLP) technology is used to analyze the text data and score the emotional state. For example, emotions such as "happy," "sad," and "stressed" are identified.

[1308] Identifying stress factors

[1309] Device: Identify stress factors from the analysis results. Analyze the frequency of co-occurrence of keywords in the collected text data to determine what causes stress for children. Examples include "a lot of homework" and "relationships with friends."

[1310] Sending check results

[1311] Terminal: Compile the analysis results and identified stress factors into a report.

[1312] Terminal: Sends the compiled report to the server.

[1313] Server: Based on the received data, the server uses the contact information of the parent or other relevant person to generate and send a notification message containing the analysis results and stress factors. For example, an email stating, "Your child is feeling stressed about their homework recently."

[1314] Specific examples

[1315] If the user is a 10-year-old child

[1316] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[1317] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[1318] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[1319] Mental health and stress check: Using natural language processing technology, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[1320] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[1321] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[1322] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[1323] The processing flow will be explained below.

[1324] Program processing details

[1325] Step 1: Initial Setup

[1326] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[1327] User (Parent): Enter your contact information (email address, phone number).

[1328] Terminal: Saves the entered information to the internal database. Displays a message that the setup is complete.

[1329] Step 2: Starting everyday conversations

[1330] Device: Periodically activates a conversational AI character that speaks to the child, asking questions such as, "Hello, what did you do at school today?"

[1331] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[1332] Step 3: Collect conversation data

[1333] Terminal: The child's answers are converted into text using a voice recognition system. This is the process of converting voice data into text data.

[1334] Terminal: The converted text data is temporarily stored in an internal database.

[1335] Step 4: Mental health and stress check

[1336] Terminal: Passes the collected text data to the analysis module, which analyzes the text data using natural language processing (NLP) techniques.

[1337] Device: Emotions are scored from text data. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[1338] Step 5: Identify the cause of stress

[1339] Device: Identify stress factors from emotion scoring results. Identify negative keywords and phrases in text data and analyze their co-occurrence frequency.

[1340] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[1341] Step 6: Submit the check results

[1342] Terminal: Generate a report containing the analysis results and identified stressors.

[1343] Terminal: Sends the generated report to the server.

[1344] Server: The server uses the received data to create a notification message using the parent's contact information.

[1345] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[1346] Step 7: Provide feedback

[1347] Server: Generates notification messages along with specific advice to the parent.

[1348] Server: Sends a message with detailed advice, for example, "Your child is stressed about a test. Give them some time to relax."

[1349] User (Parent): Receives notification messages sent and checks the status of their child.

[1350] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[1351] Example 1

[1352] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1353] Current devices for children lack systems that can properly monitor a child's mental health and immediately notify parents and other relevant parties. There are also insufficient means to analyze conversation data and identify stressors that children are experiencing. As a result, it is difficult to detect stress and anxiety that children experience on a daily basis early and deal with them appropriately.

[1354] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1355] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with the child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using voice recognition technology, means for sending the text data to a dedicated analysis module and evaluating the mental health state using natural language processing technology, means for identifying stress factors based on the evaluation results, and means for compiling the evaluation results and stress factors into a report and notifying parents or relevant parties. This makes it possible to monitor a child's mental health state through their everyday conversations, and to quickly identify stress factors and notify parents or relevant parties.

[1356] A "child-directed device" is an electronic device intended for use by children, including, for example, tablets and smartphones.

[1357] A "conversational AI character" is a software agent that uses AI technology to converse with users in natural language and can hold conversations with children.

[1358] "Speech recognition technology" is a technology for converting voice data into text data, and is used to convert a user's verbal utterances into text information.

[1359] "Natural language processing technology" is a technology for computer processing of human language, and is used to analyze text data to understand emotions and intentions.

[1360] "Means for scoring emotional states" refers to a method for quantifying and evaluating a user's emotions based on words and phrases extracted from text data.

[1361] "Keyword co-occurrence frequency" is an indicator of how often certain words or phrases appear together, allowing you to identify factors that are highly relevant.

[1362] A "report" is a document summarizing the analysis results and stress factors, and includes information for notifying parents or other relevant parties.

[1363] A "database" refers to a system that systematically stores collected data for later retrieval and analysis.

[1364] The system of the present invention is a device for children equipped with a conversational AI character that monitors the child's mental health through everyday conversations, identifies stressors, and notifies parents or other relevant parties. The components of this system include a device for children, a conversational AI character, voice recognition technology, natural language processing technology, a database, and a server.

[1365] Hardware and Software Configuration

[1366] Devices: Electronic devices such as tablets and smartphones used by children.

[1367] Conversational AI character: A software agent that can have natural conversations with children.

[1368] Speech recognition technology: Technology that converts a child's speech from voice data into text data.

[1369] Natural language processing technology: Technology that analyzes conversation data and scores emotional states.

[1370] Database: A system that stores and manages collected text data.

[1371] Server: A system that generates and sends messages to notify parents or other interested parties of the results of data analysis.

[1372] The operation of the system proceeds through the following steps.

[1373] Initial Setup

[1374] First, the parent starts up the device and enters the child's basic information (name, age, gender, interests) on the initial setup screen. The parent also enters the parent's contact information, which is then saved in a database. For example, the parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device screen, and registers their own email address.

[1375] Starting everyday conversations

[1376] When a child uses the device, a conversational AI character periodically initiates a conversation. For example, the character may display a prompt such as, "Hello, how did you do at school today?" to which the child may respond, "I had fun in gym class today."

[1377] Conversation data collection

[1378] The device uses voice recognition technology to convert the child's speech into text data, which is then stored in a database. At this time, software equipped with voice recognition technology is activated.

[1379] Mental health and stress checks

[1380] The collected text data is sent to a dedicated analysis module and analyzed using natural language processing technology. For example, emotions such as "happy," "sad," and "stressed" are identified, and the stress level is assessed based on the emotion score.

[1381] Identifying stress factors

[1382] Based on the analysis results, the device identifies the child's stressors by analyzing the frequency of co-occurrence of keywords in the conversation data, determining stressors such as "a lot of homework" and "relationships with friends."

[1383] Sending check results

[1384] The evaluation results and stress factors are compiled into a report and sent from the device to a server. The server then generates and sends a message notifying the parent or other relevant person of the analysis results using their contact information. For example, an email could be sent to the parent stating, "Your child has been feeling stressed about their homework recently."

[1385] This system allows early detection of everyday stress in children, enabling parents and other relevant parties to respond promptly. Specific examples of prompts include "Hello, what fun things did you do today?" and "Is there anything that's bothering you lately?"

[1386] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1387] Step 1: Initial Setup

[1388] User: The parent starts the device and accesses the initial setup screen.

[1389] Device: Displays a form for entering information such as the user's name, age, gender, interests, etc. Specifically, enter information such as "Taro," "10 years old," "boy," and "likes soccer."

[1390] User: The parent enters the required information and presses the complete button.

[1391] On the device: Display a screen to enter the parent's contact information (email address, phone number). The entered information is saved in the database.

[1392] Input: Name, Age, Gender, Interests, Parent Contact Information

[1393] Output: Child and parent information stored in a database

[1394] Step 2: Starting everyday conversations

[1395] Device: When a child turns on the device, a conversational AI character automatically launches.

[1396] Device: Periodically, such as in the morning or after school, display a prompt like "Hi, what happened at school today?"

[1397] User (child): The child replies, "I enjoyed gym class today."

[1398] Input: Child's speech

[1399] Output: Collected audio data

[1400] Step 3: Collect conversation data

[1401] Device: Activate the voice recognition system and convert the child's speech from voice data into text data.

[1402] Terminal: Save the converted text data in the database.

[1403] Input: Collected audio data

[1404] Output: Text data stored in a database

[1405] Step 4: Mental health and stress check

[1406] Terminal: The saved text data is sent to a dedicated analysis module.

[1407] Device: Analyzes text data using natural language processing (NLP) technology to score emotional states. For example, identify emotions such as "happy," "sad," or "stressed." Furthermore, evaluates stress levels based on the emotional scores.

[1408] Input: Text data stored in a database

[1409] Output: Emotional state score and stress level rating

[1410] Step 5: Identify the cause of stress

[1411] Terminal: Identify stress factors from the analysis results.

[1412] Device: Analyzes the frequency of co-occurrence of keywords in text data to determine stress factors such as "a lot of homework" and "relationships with friends."

[1413] Input: Emotional state scores and text data

[1414] Output: Identified stressors

[1415] Step 6: Submit the check results

[1416] Terminal: Compile the analysis results and identified stress factors into a report.

[1417] Terminal: Sends the compiled report to the server.

[1418] Server: Based on the received data, the server generates a notification message containing the analysis results and stress factors using the parent or interested party's contact information.

[1419] Server: Sends the generated notification message to the parent or other interested party. For example, an email stating, "Your child is feeling stressed about their homework these days."

[1420] Input: Analysis results and stress factors

[1421] Output: Notification message sent to parent or interested party

[1422] (Application example 1)

[1423] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1424] In modern society, understanding children's mental health is extremely important. However, it is difficult for parents and other concerned parties to immediately understand a child's daily stress and mental burden and take appropriate measures. This can lead to mental health problems being overlooked. The present invention aims to solve this problem by providing a system that quickly and accurately assesses a child's mental health, identifies stressors, and notifies the user in a timely manner.

[1425] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1426] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child on the terminal and collecting conversation data, means for analyzing the conversation data collected on the terminal or server and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying parents or relevant parties of the evaluation results and stress factors, and means for notifying if a threshold set based on the evaluation results is exceeded. This makes it possible to evaluate a child's mental health state in real time and promptly notify parents or relevant parties when a problem occurs, enabling appropriate measures to be taken.

[1427] "Children's devices" are electronic devices intended for use by children, including tablets and smartphones.

[1428] A "conversational AI character" is an AI program that can communicate with users in a dialogue format.

[1429] The "means for collecting conversation data" is a system that has the function of recording conversations with children and storing them in a database or server.

[1430] "Means for assessing mental health" refers to algorithms or programs that analyze collected conversation data and score users' emotions and psychological state.

[1431] "Means for identifying stress factors" refers to technology that analyzes specific keywords and phrases within conversation data to determine what causes stress for users.

[1432] "Means of notification" refers to the function for communicating evaluation results and stress factors to parents or relevant parties, and includes methods such as email and app notifications.

[1433] The "means for notifying when a set threshold is exceeded" is a function that automatically sends a notification to parents or related parties when the evaluation results exceed a pre-set standard value.

[1434] "Natural language processing technology" is a computer technology that analyzes human language and understands meaning and emotions.

[1435] "Means for scoring emotional states" refers to a technology that uses emotional information extracted from conversation data to generate numerical values ​​or evaluations.

[1436] "Means for analyzing the frequency of keyword co-occurrence" is a technology that analyzes words and phrases that frequently appear together in conversation data and evaluates their relevance and importance.

[1437] The present invention is a system for monitoring children's mental health status and notifying parents and other relevant parties at appropriate times. This system includes a conversational AI character installed on a device for children, a means for collecting conversation data, a means for evaluating mental health status, a means for identifying stress factors, a means for notifying the evaluation results and stress factors, and a means for notifying when a set threshold is exceeded based on the evaluation results.

[1438] System Configuration

[1439] 1. Devices for children:

[1440] This refers to smartphones and tablet devices for everyday use by children. These devices are equipped with conversational AI characters that can hold natural conversations with users.

[1441] 2. Conversational AI Characters:

[1442] It is a specialized software program that uses natural language processing (NLP) technology to analyze everyday conversations with children and score their mental health. The character utilizes NLP services such as Google Cloud Dialogflow.

[1443] 3. Conversation data collection methods:

[1444] All interactions between children and the conversational AI character are recorded and converted into text using voice recognition technology powered by the Google Cloud Speech-to-Text API.

[1445] 4. Mental health assessment tools:

[1446] This technology analyzes collected text data and scores emotions. It performs sentiment analysis using Google Cloud Natural Language API and other tools.

[1447] 5. Ways to identify stressors:

[1448] This technology analyzes the frequency of co-occurrence of keywords in collected data to determine what causes stress.

[1449] 6. Means of Notification:

[1450] The analysis results and stress factors are notified to parents and other relevant parties via email or SMS. This notification function uses the Twilio API.

[1451] 7. Means of notification when thresholds are exceeded:

[1452] If the mental health assessment results exceed a set threshold, a notification will be sent automatically, allowing parents to keep track of their child's condition in real time.

[1453] Program processing

[1454] The server collects voice data spoken by the child into the smartphone and converts it into text using speech recognition technology. This converted text data is then analyzed using Google Cloud Dialogflow to manage the conversation session. Based on the analysis results, sentiment analysis is performed using the Google Cloud Natural Language API to score the emotional state. If the scoring result exceeds a set threshold, parents and other relevant parties are automatically notified using the Twilio API.

[1455] Specific examples

[1456] If your child is 10 years old:

[1457] A child speaks into the device, saying, "I had a math test today, and it was a little difficult." The device collects this voice data and converts it into text using speech recognition. This text data is analyzed using natural language processing technology, and the child's emotional state is scored. Stress is identified from the keywords "test" and "difficult," and the evaluation results are notified to the parent.

[1458] Prompt Sentence Examples

[1459] "I enjoyed the gym class today, but the math test was a little difficult."

[1460] This system will enable real-time assessment of a child's mental health and promptly notify parents and other relevant parties, enabling appropriate intervention and support.

[1461] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1462] Step 1:

[1463] The user speaks into the smartphone or tablet device that the child uses on a daily basis, and this speech is input into the device as voice data.

[1464] Step 2:

[1465] The device converts the input voice data into text data using the Google Cloud Speech-to-Text API, which outputs the voice data as text data.

[1466] Step 3:

[1467] The device sends the converted text data to Google Cloud Dialogflow, which starts a conversation session and manages the interaction between the user and the conversational AI character. The input is text data, and the output is conversation responses and session information.

[1468] Step 4:

[1469] The server uses the Google Cloud Natural Language API to analyze the text data returned from Dialogflow and score the emotional state, outputting a numerical score for positive, negative, or other emotional states.

[1470] Step 5:

[1471] The server performs co-occurrence analysis on the analyzed emotion scores and extracts specific keywords and phrases from the conversation data to identify stress factors. The input is text data and emotion scores, and the output is the identified stress factors.

[1472] Step 6:

[1473] The server uses the Twilio API to send a notification to parents or other relevant parties when the identified stressors and emotional score exceed a set threshold. This notification includes the emotional assessment result and the identified stressors. The input is the emotional score and stressors, and the output is a notification message to parents or other relevant parties.

[1474] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1475] The present invention relates to a system that uses a conversational AI character and emotion engine installed in a device for children to assess the mental health of children through everyday conversations, identify stress factors, and notify parents or other relevant parties of the results.

[1476] Overall system overview

[1477] The system consists of the following main parts:

[1478] 1. Devices for children

[1479] 2. Conversational AI Characters

[1480] 3. Data Collection Methods

[1481] 4. Emotion Engine

[1482] 5. Analysis method

[1483] 6. Means of notification

[1484] This makes it possible to assess a child's mental health through their everyday conversations and quickly notify parents and other relevant parties if a problem arises.

[1485] Explanation of program processing

[1486] Initial Setup

[1487] Device: First, the system performs basic setup on the device. Specifically, it displays a screen for entering information such as the user's (child's) name, age, gender, and interests. Parents enter contact information (email address, phone number) and save it in the database.

[1488] Starting everyday conversations

[1489] Device: When a child uses the device, a conversational AI character periodically initiates a conversation, prompting them with something like, "Hello, what did you do at school today?"

[1490] User (child): The user responds in a natural way, such as "I enjoyed gym class today."

[1491] Conversation data collection

[1492] Terminal: A voice recognition system is used to collect user speech, convert the speech data into text, and then store the collected text data in a database.

[1493] Emotion recognition

[1494] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the tone of the voice and the content of the text.

[1495] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[1496] Mental health and stress checks

[1497] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[1498] Device: Evaluates overall health based on collected data and emotional scores.

[1499] Identifying stress factors

[1500] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[1501] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[1502] Sending check results

[1503] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[1504] Terminal: Sends the generated report to the server.

[1505] Server: The server uses the received data to create a notification message using the parent's contact information.

[1506] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[1507] Specific examples

[1508] If the user is a 10-year-old child

[1509] Initial setup: The parent enters information such as "Taro," "10 years old," "boy," and "likes soccer" on the device, and registers their own email address.

[1510] Starting a daily conversation: The device asks, "Hello, Taro. What did you do today?"

[1511] Conversational data collection: A user responds, "I had a math test today, and it was a little difficult."

[1512] Emotion recognition: The emotion engine recognizes from the text "It was a little difficult" and the tone of the voice that the user is feeling a little stressed.

[1513] Mental health and stress check: Using the results of the emotion engine, the device determines that the user is feeling stressed based on the text data "It was a little difficult."

[1514] Identifying the cause of stress: The device identifies the test as a stressor based on the keywords "test" and "difficult."

[1515] Sending the check results: The device compiles this information into a report and sends it to the server, which then sends an email notification to the parent saying, "Taro is feeling stressed about today's math test."

[1516] This system makes it possible to detect stress experienced by children at an early stage and provide an environment in which parents or other relevant parties can respond promptly. In this way, children's mental health can be managed in detail and appropriate support can be provided.

[1517] The processing flow will be explained below.

[1518] MODE FOR CARRYING OUT THE INVENTION

[1519] Step 1: Initial Setup

[1520] User (Parent): When starting up the device for the first time, enter the child's basic information (name, age, gender, interests) on the settings screen.

[1521] User (Parent): Enter the parent's contact information (email address, phone number).

[1522] Terminal: Saves the entered information to an internal database and displays a message that the setup is complete.

[1523] Step 2: Starting everyday conversations

[1524] Terminal: A conversational AI character periodically initiates everyday conversations, such as asking questions like, "Hello, what did you do at school today?"

[1525] User (child): Responds naturally to questions (e.g., "I had a math test today.").

[1526] Step 3: Collect conversation data

[1527] Terminal: The user's response is converted into text using a voice recognition system, which is the process of converting voice data into text data.

[1528] Terminal: The converted text data is temporarily stored in an internal database.

[1529] Step 4: Recognize emotions

[1530] On the device: The emotion engine analyzes the collected voice and text data to recognize the user's emotions. It identifies emotions such as "happy" or "sad" from the voice tone and text content.

[1531] On the device: If necessary, the emotion engine also analyzes the user's facial expression data for more accurate emotion recognition.

[1532] Step 5: Mental health and stress check

[1533] Device: Using the emotion recognition results from the emotion engine, the device scores the user's mental health. For example, emotions such as "happy," "sad," and "stressed" are quantified and evaluated.

[1534] Device: Evaluates overall health based on collected data and emotional scores.

[1535] Step 6: Identify the source of stress

[1536] Device: Works with the emotion engine to identify stressors from mental health assessment results, identifies negative keywords and phrases in text data, and analyzes their co-occurrence frequency.

[1537] Device: Extract specific stress factors (e.g., "The test was difficult" or "I had a fight with a friend").

[1538] Step 7: Submit the check results

[1539] Terminal: Generates a report containing the stressors identified by the analytics and emotion engine.

[1540] Terminal: Sends the generated report to the server.

[1541] Server: The server uses the received data to create a notification message using the parent's contact information.

[1542] Server: Send the created notification message (e.g., "Taro is stressed about today's math test.") to the parent's email address.

[1543] In this way, the system continuously monitors children's mental health, detects stress early, and promptly notifies parents and other relevant parties, thereby supporting the healthy development of children.

[1544] Example 2

[1545] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1546] In recent years, the mental health of children has become increasingly important, and there is a need to detect stress and mental problems early and respond appropriately. However, traditional methods make it difficult for parents and educators to accurately grasp changes and problems in children's daily lives, making it difficult to continuously and objectively evaluate children's mental health. In particular, when children have difficulty clearly expressing their emotions and stressors, there is a risk that these problems will be overlooked.

[1547] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1548] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having everyday conversations with a child on the terminal and collecting conversation data, means for converting the conversation data collected on the terminal or server into text data using a voice recognition system and storing it in a database, means for recognizing the child's emotions and identifying their emotional state using an emotion engine that analyzes the text data and voice data, means for evaluating and scoring the child's mental health state based on the analysis results, and means for notifying parents or other relevant parties of the evaluation results and stress factors. This enables parents and educators to understand a child's mental health state in real time through the child's everyday conversations and to identify and address stress factors early on.

[1549] A "children's device" is an electronic device designed primarily for use by minors, and is a device with functionality suitable for everyday conversation and educational activities.

[1550] A "conversational AI character" is a software program that can hold natural conversations with users, and is a virtual character that responds to user utterances using voice recognition and natural language processing technology.

[1551] The "data collection means" is a system component that has the function of collecting input data from a user, and is a device or software that acquires voice data or text data.

[1552] A "voice recognition system" is a technology or software that automatically converts voice data into text data.

[1553] A "database" is a digital storage system that stores collected information in an organized manner and facilitates retrieval and analysis as needed.

[1554] An "emotion engine" is software that includes algorithms and machine learning models to analyze voice and text data and identify a user's emotions.

[1555] The "means for assessing mental health status" is a function that scores the user's psychological state based on collected data and evaluates the user's health status numerically or qualitatively.

[1556] The "means for identifying stress factors" is a function that analyzes the collected data and emotion determination results to identify the specific causes and situations that cause the user to feel stressed.

[1557] "Notification means" is a system component that communicates identified stressors and mental health assessment results to parents or other relevant parties, and is a device or software that sends email or message notifications.

[1558] A "generative AI model" is a machine learning model that learns from large amounts of data and generates natural conversational prompts.

[1559] A "prompt sentence" is a question or statement presented by a conversational AI character to initiate a conversation with the user, and is a guidance sentence to elicit a response from the user.

[1560] This invention relates to a system that uses a conversational AI character installed on a device for children, and the device and a server to collect and analyze data on children's everyday conversations, evaluate their mental health, identify stress factors, and notify parents or other relevant parties of the results.

[1561] Hardware and software used

[1562] Device:

[1563] Portable electronic devices (e.g., tablets, smartphones) used by children are used.

[1564] The device is equipped with basic audio and video collection devices such as a microphone, camera, and speaker.

[1565] Conversational AI Character:

[1566] Conversational AI characters incorporate voice recognition software (e.g., Google Speech-to-Text) and natural language processing engines (e.g., NVIDIA Riva).

[1567] A generative AI model creates prompts, enabling natural conversations with users.

[1568] Database:

[1569] A cloud-based database is used to store the collected data (voice data, text data, emotion recognition results, etc.).

[1570] Emotion Engine:

[1571] The emotion engine utilizes emotion recognition algorithms (e.g., IBM Watson Tone Analyzer) to analyze voice tone, facial expressions, and text content to identify the user's emotional state.

[1572] server:

[1573] A central server is used to analyze the collected data and notify parents or other relevant parties via email, push notifications, or other methods.

[1574] System Operation

[1575] Initial Settings:

[1576] When the device is first started, parents are prompted to enter basic information about their child (such as name, age, gender, and interests) as well as their own contact information, which is then securely stored in a database.

[1577] Starting everyday conversations:

[1578] The device will talk to the child through a conversational AI character based on a pre-set schedule, for example, using a generative AI model to generate and display prompts such as "Hello, what did you do at school today?"

[1579] Conversation data collection:

[1580] The device collects the child's speech through a microphone and converts it into text data using a voice recognition system. The converted text data and the original voice data are stored in a database.

[1581] Emotion Recognition:

[1582] The device uses an emotion engine to analyze the collected voice and text data, for example, to identify the user's emotions (happy, sad, angry, etc.) based on the tone of the voice, the content of the text, and even facial expression data collected by the camera.

[1583] Mental health assessment:

[1584] The device evaluates and quantifies the state of mental health based on the analysis results of the emotion engine, and accumulates daily data to monitor long-term health.

[1585] Identifying stressors:

[1586] The device analyzes negative keywords (e.g., "test" and "fight") in the text data based on their frequency and co-occurrence, and identifies stress factors.

[1587] Notification of results:

[1588] The device and server then compile the analysis results into a report and notify parents and other relevant parties. An example of the content of the report might be a message such as, "Taro is feeling stressed about today's math test."

[1589] Examples of prompts:

[1590] "Hello, what did you do at school today?"

[1591] "What fun things happened today?"

[1592] "Tell me what you've been enjoying lately."

[1593] This will enable early detection of mental changes and stress that children experience on a daily basis, allowing parents and educators to respond quickly and effectively manage and support children's mental health.

[1594] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1595] Step 1: Initial Setup

[1596] Input: Parents enter their child's basic information (such as name, age, gender, interests) and their own contact information into the device.

[1597] Data processing: The device stores this information securely in a database.

[1598] Output: Basic information of parents and children saved is available.

[1599] Specific actions: Parents enter information through the user interface and press the registration button to submit the data.

[1600] Step 2: Starting everyday conversations

[1601] Enter: Your child starts or begins using the device.

[1602] Data processing: The device uses a generative AI model to create prompts based on pre-set schedules and conditions.

[1603] Output: Display a prompt sentence on the screen, such as "Hello, what did you do at school today?"

[1604] Specific actions: The conversational AI character reads out the displayed prompt aloud and asks the child a question.

[1605] Step 3: Collect conversation data

[1606] Input: The child speaks in response to the prompt.

[1607] Data processing: Voice data is collected through the device's microphone and converted into text data using a voice recognition system. The converted text data is then stored in a database.

[1608] Output: The audio data and its converted text are stored in a database for later analysis.

[1609] How it works: Your child's responses are collected by a microphone and converted into text in real time by speech recognition software.

[1610] Step 4: Recognize emotions

[1611] Input: Stored text and audio data.

[1612] Data processing: The device uses an emotion engine to analyze text and voice, recognizing emotions from voice tone and text content to identify emotional states such as happy, sad, or angry.

[1613] Output: Emotion recognition results are generated and stored in a database.

[1614] Specific operation: The emotion engine determines the emotion from the tone of the voice and the content of the text, and assigns a label such as "fun."

[1615] Step 5: Mental health assessment

[1616] Input: Emotion recognition results and text data.

[1617] Data processing: The device quantifies the emotion recognition results and assigns a score to the user's mental health. The score is evaluated as a positive or negative number and stored in a database.

[1618] Output: A mental health assessment score is generated and used for daily health monitoring.

[1619] What it does: A scoring algorithm calculates a number based on emotion data and updates your overall health score.

[1620] Step 6: Identify the stressors

[1621] Input: Scoring results and text data.

[1622] Data processing: The device analyzes negative keywords in the text data based on frequency and co-occurrence relationships to identify stress factors.

[1623] Output: Specific stressors (e.g., "test" or "fight") are identified and stored in a database.

[1624] What it does: A keyword extraction algorithm extracts important negative phrases from the text and performs a frequency analysis.

[1625] Step 7: Notification of results

[1626] Input: Mental health assessment scores and stressors.

[1627] Data processing: The device and server compile the analysis results into a report and notify parents and other relevant parties via email or push notification.

[1628] Output: A specific notification message (e.g., "Taro is stressed about today's math test") is sent to the parent.

[1629] What happens: The report generation module creates a report based on the data, and the notification system sends it to the parent's email address or other contact.

[1630] This will allow children's mental health to be monitored on a daily basis, and parents and other relevant parties to respond quickly if a problem arises.

[1631] (Application example 2)

[1632] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1633] Currently, there is no fully developed system that can assess the mental health of children or agents from everyday conversations, identify stress factors, and quickly notify relevant parties of the results. As a result, it is difficult to detect changes in mental health early and take appropriate action. There is a need to provide a system that can solve this problem and monitor mental health more quickly and accurately.

[1634] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1635] In this invention, the server includes a conversational AI character installed in a child-oriented terminal, means for having daily conversations with the child and the agent and collecting conversation data, means for analyzing the collected conversation data and evaluating the mental health state, means for identifying stress factors based on the evaluation results, means for notifying the parent, manager, or relevant person of the evaluation results and stress factors, and means for installing a program for evaluating the agent's mental health state, identifying stress factors, and notifying the manager or relevant person of the results. This makes it possible to detect changes in mental health state early and take appropriate measures.

[1636] A "children's device" is an electronic device intended for use by children that includes a conversational artificial intelligence character.

[1637] A "conversational AI character" is an AI-based character that can converse with users using natural language processing technology.

[1638] "Conversational Data" means data in the form of voice or text exchanged between a user and a conversational AI character.

[1639] "Emotional state" refers to the user's psychological or emotional state analyzed from conversation data.

[1640] "Means of collection" includes the technical means by which a terminal or associated device captures a user's voice or text data.

[1641] "Means for analyzing and assessing mental health status" refers to technology or programs that use collected conversation data to assess a user's psychological health status.

[1642] A "stressor" is a specific event or situation that may have a negative impact on a user's mental well-being.

[1643] "Means of notification" includes techniques or methods for informing parents, administrators, and other stakeholders about assessment results and stressors.

[1644] "Assessment Results" refers to information about a user's health and emotional state obtained based on collected and analyzed data.

[1645] "Controller" means a person who is responsible for the supervision and management of an Agent's or Child's well-being.

[1646] "Means for installing a program" refers to the methods and technologies for installing software with specific functions onto a terminal or server.

[1647] MODE FOR CARRYING OUT THE INVENTION

[1648] This invention relates to a system for assessing the mental health of children and agents and identifying stress factors. This system mainly comprises a device for children, a conversational AI character, a data collection means, an emotion engine, an analysis means, and a notification means. It also includes a means for installing a program for assessing the mental health of the agent.

[1649] Overall system overview

[1650] The system consists of the following main parts:

[1651] 1. Devices for children

[1652] The device is equipped with a conversational artificial intelligence character that can hold everyday conversations with children.

[1653] 2. Conversational AI Characters

[1654] The conversational AI character uses natural language processing technology to collect conversational data through conversations with users and score their emotions.

[1655] 3. Data Collection Methods

[1656] The device uses a speech recognition system (e.g., Google Speech Recognition API) to collect the user's voice and text data, which is then converted into text.

[1657] 4. Emotion engine and analysis methods

[1658] The collected data is subjected to sentiment analysis by an emotion engine (e.g., TextBlob). Based on the sentiment scoring, the user's mental health is evaluated.

[1659] 5. Evaluation results and identification of stress factors

[1660] Stress factors are identified based on the results of the emotion engine and keyword analysis in the conversation data. For example, negative keywords such as "tired" and "tough" are detected by analyzing the frequency of co-occurrence of keywords.

[1661] 6. Means of notification

[1662] A report is generated based on the assessment results and identified stressors, and parents and administrators are notified via email or other means using SMTP.

[1663] 7. Installing the program

[1664] A program to assess the agent's mental health will be installed on the device or server, and will comprehensively perform voice recognition, emotion analysis, stress assessment, and notifications.

[1665] Specific examples

[1666] For example, if Agent Taro says to the conversation system after a delivery, "I'm tired because there were a lot of orders today," this voice data is collected and converted into text. The emotion engine detects negative emotions from the expression "tired" and evaluates the mental health state as "high stress." The detected stress factors are "many orders" and "tired." Based on this, a notification is sent to the manager via email stating, "There were a lot of orders today, and the agent is feeling tired."

[1667] Prompt example

[1668] The agent and child are presented with the following prompt:

[1669] "It's been tough with so many orders. How can I make deliveries easier?"

[1670] "I'm tired after a long drive today. How can I relieve this fatigue?"

[1671] In this way, the system assesses the mental health of children and agents through everyday conversations, quickly and accurately identifies stressors, and notifies relevant parties, enabling early response.

[1672] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1673] Step 1:

[1674] Initial Setup

[1675] The server saves the initial information of the agent (such as name, age, contact details, etc.) and the administrator's contact details in a database. This operation is performed based on the information entered by the user (agent or administrator) and saved in a database (e.g., a JSON file or SQL database).

[1676] Step 2:

[1677] Starting everyday conversations

[1678] The terminal starts a conversational AI character and displays a prompt to the user (agent). An example of a prompt is "How was your day?". The input is the agent's voice.

[1679] Step 3:

[1680] Conversation data collection

[1681] The terminal uses a speech recognition system to convert the agent's speech into text data (e.g., Google Speech Recognition API). The collected text data is stored in a database. The input is speech data, and the output is text data.

[1682] Step 4:

[1683] Emotion recognition

[1684] Based on the collected text data, the server performs sentiment analysis using an emotion engine (e.g., TextBlob). It performs sentiment scoring and quantifies the user's mental health. The input is text data, and the output is a sentiment score.

[1685] Step 5:

[1686] Mental health assessment

[1687] The server evaluates the agent's mental health state based on the emotion score. Depending on the range of the score, the state is classified as "high stress," "mild stress," "normal," etc. The input is the emotion score, and the output is the health state evaluation result.

[1688] Step 6:

[1689] Identifying stressors

[1690] The server detects negative keywords (e.g., "tired" or "tough") from the collected text data and identifies stress factors by analyzing their co-occurrence frequency. The input is text data, and the output is stress factors.

[1691] Step 7:

[1692] Generating check results

[1693] Based on the assessment results and stressors, the server generates a report that includes the agent's health status and identified stressors. The inputs are the assessment results and stressors, and the output is the report.

[1694] Step 8:

[1695] Notification of check results

[1696] The server notifies the administrator of the generated report. Specifically, it sends a notification to the administrator's email address using an SMTP server. The input is the report, and the output is sending an email.

[1697] These processing steps make it possible to monitor the mental health of children and agents and respond in a timely manner.

[1698] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1699] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1700] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1701] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1702] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1703] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1704] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1705] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1706] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1707] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1708] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1709] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1710] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1711] 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.

[1712] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1713] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1714] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1715] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1716] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1717] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1718] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1719] The following is further disclosed regarding the above embodiment.

[1720] (Claim 1)

[1721] A conversational AI character installed on a device for children,

[1722] means for having daily conversations with a child on the terminal and collecting conversation data;

[1723] A means for analyzing the conversation data collected in the terminal or server and evaluating mental health status;

[1724] A means for identifying a cause of stress based on the evaluation results;

[1725] The system includes a means for notifying a parent or interested party of the results of the assessment and the stressors.

[1726] (Claim 2)

[1727] 10. The system of claim 1, wherein the conversational artificial intelligence character comprises means for analyzing conversation data using natural language processing techniques and scoring emotional states.

[1728] (Claim 3)

[1729] 2. The system according to claim 1, further comprising means for analyzing the frequency of co-occurrence of keywords in conversation data in order to identify the causes of stress.

[1730] "Example 1"

[1731] (Claim 1)

[1732] A conversational AI character installed on a device for children,

[1733] means for having daily conversations with a child on the terminal and collecting conversation data;

[1734] means for converting the collected conversation data into text data using a voice recognition technology in the terminal or server;

[1735] a means for transmitting the text data to a dedicated analysis module and evaluating mental health status using natural language processing technology;

[1736] A means for identifying a cause of stress based on the evaluation results;

[1737] The system includes a means for compiling the evaluation results and stress factors into a report and notifying parents or other concerned parties.

[1738] (Claim 2)

[1739] 10. The system of claim 1, wherein the conversational artificial intelligence character comprises means for analyzing conversation data using natural language processing techniques and scoring emotional states.

[1740] (Claim 3)

[1741] 2. The system according to claim 1, further comprising means for analyzing the frequency of co-occurrence of keywords in conversation data in order to identify the causes of stress.

[1742] "Application Example 1"

[1743] (Claim 1)

[1744] A conversational AI character installed on a device for children,

[1745] means for having daily conversations with a child on the terminal and collecting conversation data;

[1746] A means for analyzing the conversation data collected in the terminal or server and evaluating mental health status;

[1747] A means for identifying a cause of stress based on the evaluation results;

[1748] a means for informing a parent or interested party of the results of the assessment and the stressors;

[1749] The system includes a means for issuing a notification when a threshold set based on the evaluation result is exceeded.

[1750] (Claim 2)

[1751] 10. The system of claim 1, wherein the conversational artificial intelligence character comprises means for analyzing conversation data using natural language processing techniques and scoring emotional states.

[1752] (Claim 3)

[1753] 2. The system according to claim 1, further comprising means for analyzing the frequency of co-occurrence of keywords in conversation data in order to identify the causes of stress.

[1754] "Example 2: Combining Emotion Engines"

[1755] (Claim 1)

[1756] A conversational AI character installed on a device for children,

[1757] means for having daily conversations with a child on the terminal and collecting conversation data;

[1758] means for converting the conversation data collected in the terminal or server into text data using a voice recognition system and storing the text data in a database;

[1759] means for recognizing emotions and identifying emotional states of a child, the means comprising an emotion engine for analyzing the text data and voice data;

[1760] A means for evaluating and scoring mental health status based on the analysis results;

[1761] a means for informing a parent or interested party of the results of the assessment and the stressors;

[1762] ...

[1763] A system including:

[1764] (Claim 2)

[1765] 10. The system of claim 1, further comprising means for the conversational artificial intelligence character to use a generative AI model to create prompts to facilitate natural conversation with the child.

[1766] (Claim 3)

[1767] 2. The system according to claim 1, further comprising means for analyzing the frequency of co-occurrence of keywords in conversation data in order to identify the causes of stress.

[1768] "Application example 2 when combining emotion engines"

[1769] (Claim 1)

[1770] A conversational AI character installed on a device for children,

[1771] means for having daily conversations with a child on the terminal and collecting conversation data;

[1772] A means for analyzing the conversation data collected in the terminal or server and evaluating mental health status;

[1773] A means for identifying a cause of stress based on the evaluation results;

[1774] a means for informing a parent or interested party of the results of the assessment and the stressors;

[1775] A system that includes a means to install a program to assess the mental health of agents, identify stressors, and notify managers and other relevant parties of the results.

[1776] (Claim 2)

[1777] 10. The system of claim 1, wherein the conversational artificial intelligence character comprises means for analyzing the conversation data using natural language processing techniques and scoring the emotional state.

[1778] (Claim 3)

[1779] 2. The system according to claim 1, further comprising means for analyzing the frequency of co-occurrence of keywords in the conversation data in order to identify causes of stress. [Explanation of symbols]

[1780] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A conversational AI character installed on a device for children, means for having daily conversations with a child on the terminal and collecting conversation data; A means for analyzing the conversation data collected in the terminal or server and evaluating mental health status; A means for identifying a cause of stress based on the evaluation results; The system includes a means for notifying a parent or interested party of the results of the assessment and the stressors.

2. 10. The system of claim 1, wherein the conversational artificial intelligence character comprises means for analyzing conversational data and scoring emotional states using natural language processing techniques.

3. 2. The system according to claim 1, further comprising means for analyzing the frequency of co-occurrence of keywords in conversation data in order to identify the causes of said stress.

Images