System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information; means for analyzing text data using natural language processing; means for determining a negativity score; means for generating and transmitting an alert message to a user; and means for analyzing a user's behavioral history and generating periodic reports.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Negative information and aggressive comments are increasing on the internet and through various communication tools (social media, email, messaging apps, etc.), causing stress and conflict. It is extremely difficult for users to respond calmly to such negative information, which can result in emotional reactions. Users may also unintentionally send negative comments. This can lead to aggressive behavior and conflict, increasing social stress and discord, creating a challenge. [Means for solving the problem]

[0005] In order to solve these problems, the present invention provides the following system. First, an information gathering means is used to collect information received by the user from various communication tools. Next, a means for analyzing text data using natural language processing is used to determine a negativity score. Furthermore, a means for generating and sending a warning message to the user when the negativity exceeds a specific threshold is provided. Finally, by combining a means for analyzing the user's behavioral history and generating periodic reports, the system provides feedback to the user to reflect on their own behavior and prevent negative behavior. This series of means realizes a system that enables users to calmly respond to negative information and control aggressive emotions.

[0006] "Information collection means" refers to the means of acquiring and storing data on messages and emails received by users from multiple communication tools.

[0007] "Means for analyzing text data using natural language processing" means means for analyzing stored text data using natural language processing (NLP) techniques to perform sentence structure, tokenization, morphological analysis, and sentiment scoring.

[0008] The "means for determining a negativity score" is a means for assigning scores to specific negative words or phrases based on the analyzed text data and determining whether the total score exceeds a predetermined threshold.

[0009] The "means for generating and sending a warning message" refers to a means for generating a warning message to make the user aware of the risk when the negativity score exceeds a threshold, and sending the message as a pop-up notification, email notification, or in-app notification.

[0010] The "means for analyzing user behavior history and generating periodic reports" refers to a means for collecting and analyzing user behavior data, evaluating monthly behavioral trends and increases or decreases in negative behavior, and generating reports to provide feedback based on this.

[0011] The "threshold" is a numerical value that serves as a reference for determining the negativity score, and when this numerical value is exceeded, it triggers the generation of a warning message. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] This system collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback.

[0034] System configuration

[0035] The system consists of the following components:

[0036] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history.

[0037] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0038] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0039] Program processing flow

[0040] 1. Information gathering

[0041] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and then analyzed.

[0042] 2. Text Analysis

[0043] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google® Cloud Natural Language API), tokenizing and morphologically analyzing the text data, and calculating a sentiment score for each word or phrase.

[0044] 3. Determining the degree of negativity

[0045] The server aggregates the emotion scores obtained from the text data and calculates a negativity score. If this score exceeds a pre-set threshold, the server proceeds to the next step.

[0046] 4. Generating Warning Messages

[0047] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes the offending text and a message encouraging people to stay calm.

[0048] The generated warning messages are sent to the user's device in real time via pop-up notifications, email notifications, and in-app notifications.

[0049] 5. Analysis and reporting of behavioral history

[0050] The server collects and periodically analyzes user behavior history, compiling a report on the frequency, patterns, and changes in negative behavior for each month.

[0051] The generated report is either sent to the user's email address or made available in a viewable format within the app.

[0052] Specific examples

[0053] Example 1: Receiving negative email

[0054] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0055] Example 2: Posting to social media

[0056] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0057] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server sets up APIs or web hooks for each communication tool to automatically retrieve data on messages and emails received by users. The data is temporarily stored in the server's storage and prepared for analysis.

[0061] Step 2:

[0062] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[0063] Step 3:

[0064] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[0065] Step 4:

[0066] If the negativity score exceeds a threshold, the server generates a warning message for the user, including a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[0067] Step 5:

[0068] The server generates and sends the generated warning message in real time to the user's device, which receives it and displays it to the user, via a pop-up notification, email notification, or in-app notification.

[0069] Step 6:

[0070] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[0071] Step 7:

[0072] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0073] Step 8:

[0074] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0075] Example 1

[0076] 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."

[0077] In modern society, people receive and send a huge amount of information every day through various communication tools such as email, social media, and messaging apps. Some of this information may provoke negative emotions and aggressive behavior, raising concerns that such information may have a negative impact on people's mental health. Furthermore, the transmission of such content increases online conflicts and troubles, so measures to prevent this are necessary. Furthermore, there is a need for a system that provides feedback based on users' behavioral history to encourage long-term behavioral improvement.

[0078] 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.

[0079] In this invention, the server includes means for acquiring data from multiple communication methods, means for analyzing text data using natural language processing, means for calculating an emotion score from the analyzed text data, means for determining a negativity score, means for generating and sending a warning message based on the negativity score, and means for collecting and analyzing user behavioral history and generating periodic reports. This allows users to respond calmly to negative information, prevent aggressive emotions from being expressed, maintain their mental health, and reduce online conflicts. Furthermore, receiving feedback on behavioral history can lead to long-term behavioral improvements.

[0080] "Multiple means of communication" refers to multiple digital communication tools such as email, social media, and messaging apps.

[0081] "Means of obtaining data" refers to methods of collecting information from multiple communication means using APIs and web hooks.

[0082] "Natural language processing" refers to the technology of analyzing text data and performing sentence structure analysis and emotion scoring.

[0083] "Text data" refers to textual information such as messages and posted content obtained through communication means.

[0084] An "emotion score" refers to a numerical evaluation of the emotion of each word or phrase contained in text data.

[0085] "Negativity score" refers to a numerical evaluation of the degree of negative emotion based on the emotion score of the entire text data.

[0086] A "warning message" refers to a notification sent to the user based on the negativity score, encouraging them to remain calm.

[0087] "Behavioral history" refers to data that records messages sent and received by users through communication means and the system's response to them.

[0088] "Report" refers to a document that summarizes the results of collecting and analyzing user behavior history.

[0089] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback. The system is composed of the following elements:

[0090] Server: The central processing unit is used to collect information, analyze text, calculate sentiment scores, determine negativity, generate warning messages, and analyze behavioral history. Specifically, it analyzes text data using natural language processing (NLP) libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API). The server also obtains data from multiple communication tools using APIs and webhooks.

[0091] Terminal: A device used by a user (PC, smartphone, tablet, etc.). These terminals are responsible for receiving notifications and warning messages from the server.

[0092] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0093] Specifically, the server uses the Gmail API or SNS API to retrieve messages received by the user. This data is temporarily stored in the server's storage, and then a natural language processing library (such as NLTK or spaCy) is used to tokenize the text and perform morphological analysis. A sentiment score is then calculated for each word or phrase. The sentiment scores are then aggregated to calculate a negativity score. If this score exceeds a pre-set threshold, the server generates a warning message. The generated warning message is sent to the user's device in real time. Notification methods include pop-up notifications, email notifications, and in-app notifications.

[0094] In addition, the server collects and periodically analyzes the user's behavioral history. It compiles a report on the frequency, patterns, and changes in negative behaviors for each month. The generated report is sent to the user's email address or made available in a viewable format within the app. This allows users to reflect on their own behavior and make long-term improvements.

[0095] Specific examples

[0096] Example 1: Receiving negative email

[0097] The server retrieves the email received by the user saying "Your suggestions are completely useless" via the Gmail API and analyzes the text using a natural language processing library. In this case, if the phrase "useless" is determined to have a high degree of negativity, the server generates a warning message saying "This email contains negative content. Please respond calmly." The generated message is immediately sent to the user's device as a pop-up notification.

[0098] Example 2: Posting to social media

[0099] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0100] Prompt Sentence Examples

[0101] "When a user receives an email saying 'Your suggestions are completely useless,' explain how the system analyzes the content and generates a warning message."

[0102] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0103] Step 1: Gather information

[0104] The server retrieves the user's incoming messages using APIs and webhooks of multiple communication tools (email, SNS, messaging apps). Specifically, it uses API credentials to send requests to the API endpoints of each communication tool, receives message data in JSON format, and stores it in temporary storage. The input is the API request, and the output is the retrieved message data in JSON format.

[0105] Specific behavior:

[0106] The server sends a request to the Gmail API to retrieve the user's unread emails.

[0107] Analyze the JSON data returned from the API, extract the message body, and temporarily save it.

[0108] Step 2: Text analysis

[0109] The server uses a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API) to analyze the stored text data. It tokenizes the text data and performs morphological analysis. It then calculates a sentiment score for each word or phrase. The input is the text data stored in temporary storage, and the output is the tokenized text with a sentiment score.

[0110] Specific behavior:

[0111] The server tokenizes the saved email body using the spaCy library.

[0112] A sentiment score is calculated for each phrase, such as "useless," and assigned to each token.

[0113] Step 3: Determine the degree of negativity

[0114] The server aggregates a negativity score based on the emotion scores obtained from the analyzed text data. If the negativity score exceeds a preset threshold, the process proceeds to the next step. The input is the text data with the emotion scores assigned, and the output is an overall negativity score.

[0115] Specific behavior:

[0116] The server aggregates the negative emotion scores for each token to calculate an overall negativity score.

[0117] If the configured threshold (e.g. 70) is exceeded, proceed to generate a warning message.

[0118] Step 4: Generate a warning message

[0119] The server generates a corresponding warning message when the negativity score exceeds a threshold. The message contains the problematic text and a message encouraging the user to remain calm. The generated warning message is sent to the user's device in real time. The input is the overall negativity score and the text data, and the output is the warning message.

[0120] Specific behavior:

[0121] The server generates a warning message saying, "This email contains negative content. Please stay calm."

[0122] The generated message is sent to the device using Firebase Cloud Messaging.

[0123] Step 5: Analyze and report behavioral history

[0124] The server collects user behavior history and periodically analyzes it. It compiles a report on the frequency and patterns of negative behavior for each month and provides feedback to the user. The input is behavior history data, and the output is a report.

[0125] Specific behavior:

[0126] The server retrieves the warning message generation history for the past month from the database.

[0127] The data is analyzed to generate statistics such as "how many negative emails were received per month."

[0128] The report will be created in PDF format and sent to the user's email address.

[0129] By taking these steps, users can calmly respond to negative information, maintain their mental health, and hopefully lead to long-term behavioral improvements.

[0130] (Application example 1)

[0131] 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."

[0132] In today's world, while online communication is becoming more common, negative emotions and aggressive behavior are becoming a problem. Particularly on social media and messaging apps, users can unintentionally send offensive messages or receive negative messages from others, causing psychological damage. This can damage users' mental health and make them more susceptible to online trouble.

[0133] 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.

[0134] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for analyzing the user's behavior history and generating periodic reports, and a means for analyzing messages in real time and immediately displaying a warning message. This makes it possible to immediately display a warning when a user sends or receives a negative message, encouraging the user to respond calmly.

[0135] "Information collection means" refers to the function of obtaining message data from various communication tools used by users (email, SNS, messaging apps, etc.) via API or web hooks.

[0136] "Natural language processing" is a technology in which a computer program analyzes human language, and is a process that involves tokenizing text data, analyzing sentence structure, and scoring sentiment.

[0137] A "negativity score" is a numerical representation of the emotional negativity of words and phrases in text data.

[0138] A "warning message" is a notification sent to a user when the negativity score exceeds a certain threshold, and includes a message encouraging the user to remain calm.

[0139] "User behavior history" refers to data that records the messages sent and received by the user and the emotional scores at that time.

[0140] "Means for analyzing messages in real time and immediately displaying a warning message" refers to a function that immediately analyzes messages when they are sent or received, and immediately warns the user if they contain negative content.

[0141] "Server" refers to the central processing unit that aggregates and analyzes information, calculates negativity scores, and generates warning messages.

[0142] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system consists of the following elements:

[0143] System configuration

[0144] 1. Server

[0145] The server is a central processing unit that collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history. This server can also be deployed on a cloud service (e.g., AWS (registered trademark), Google Cloud).

[0146] 2. Terminal

[0147] A terminal is a device used by a user, typically a PC, smartphone, tablet, etc. An application is installed on the terminal to receive notifications and warning messages from the server.

[0148] 3. Users

[0149] Users are people who use the system, such as individuals, employees, and students.

[0150] Hardware and software used

[0151] Hardware

[0152] Servers (virtual machines on cloud services, physical servers)

[0153] Devices (PC, smartphone, tablet)

[0154] software

[0155] Natural language processing libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API)

[0156] Database (e.g., MySQL (registered trademark), PostgreSQL)

[0157] API clients (e.g., requests library)

[0158] Server frameworks (e.g., Flask, Django)

[0159] Data processing and calculation

[0160] 1. Information gathering

[0161] The server retrieves messages received by users using the API or web hooks of each communication tool. This data is temporarily stored in the server's storage.

[0162] 2. Text Analysis

[0163] The server analyzes the stored text data using natural language processing (NLP) libraries, tokenizing the text data, analyzing sentence structure, and calculating sentiment scores for each word and phrase.

[0164] 3. Determining the degree of negativity

[0165] The server aggregates the sentiment scores obtained from the text data, calculates a negativity score, and generates a warning message if the score exceeds a pre-set threshold.

[0166] 4. Generating and sending warning messages

[0167] If the negativity score exceeds the threshold, the server generates a corresponding warning message containing the problematic text and a message encouraging users to stay calm. The generated warning message is sent to the user's device in real time.

[0168] 5. Analysis and reporting of behavioral history

[0169] The server collects and periodically analyzes the user's behavioral history, compiling a report detailing the frequency, patterns, and changes in negative behaviors for each month. This report is sent to the user's email address or made available in a viewable format within the app.

[0170] Specific examples

[0171] Example 1: Receiving negative email

[0172] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0173] Example 2: Posting to social media

[0174] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0175] Prompt Sentence Examples

[0176] "Write Python code that uses natural language processing to parse negative content from messages received by users and generate a warning message. Use the Google Cloud Natural Language API."

[0177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0178] Step 1:

[0179] The server retrieves the user's received messages using the API or webhook of each communication tool (email, SNS, messaging app, etc.). Specifically, it sends an HTTP request to the API endpoint and temporarily stores the returned JSON-formatted message data in storage. The input is the API endpoint of each communication tool and the user's authentication information, and the output is the retrieved message data.

[0180] Step 2:

[0181] The server analyzes the message data stored in storage using a natural language processing (NLP) library. Specifically, it tokenizes the text data, analyzes the sentence structure, and calculates the sentiment score for each word and phrase. The NLP libraries used are NLTK, spaCy, and Google Cloud Natural Language API. The input is the message text read from storage, and the output is the sentiment score for each message.

[0182] Step 3:

[0183] The server determines the negativity score based on the analyzed sentiment score. Specifically, it aggregates the text analysis results and calculates an overall negativity score for each message. If the score exceeds a preset threshold, it proceeds to the next step. The input is the text analysis result (sentiment score), and the output is the negativity score.

[0184] Step 4:

[0185] If the negativity score exceeds a threshold, the server generates a corresponding warning message. Specifically, the server creates a warning message that includes text containing negative content as well as a message encouraging users to stay calm. The input is the negativity score, and the output is the warning message.

[0186] Step 5:

[0187] The server sends the generated warning message to the user's device in real time. Specifically, it sends a pop-up notification or an in-app notification to the target user's device. The input is the warning message, and the output is the warning notification displayed on the user's device.

[0188] Step 6:

[0189] The server periodically collects and analyzes the user's behavioral history and generates a monthly report. Specifically, it analyzes the frequency and patterns of negative behavior each month and aggregates them to create a report. The report is sent to the user's email address or provided in a format that can be viewed within the app. The input is past behavioral history data, and the output is a report summarizing the analysis results.

[0190] 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.

[0191] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results.

[0192] System configuration

[0193] The system consists of the following components:

[0194] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[0195] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0196] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0197] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[0198] Program processing flow

[0199] 1. Information gathering

[0200] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and prepared for analysis.

[0201] 2. Emotion recognition

[0202] The device captures the user's voice input, facial recognition, or biometric data and sends it to the emotion engine.

[0203] The emotion engine analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[0204] 3. Text Analysis

[0205] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[0206] 4. Determining the degree of negativity

[0207] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[0208] The server then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may adjust the warning threshold lower.

[0209] 5. Generating Warning Messages

[0210] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[0211] Data from the emotion engine is used to customize the content and presentation of warning messages, for example, if the user is depressed, a more gentle tone of message will be displayed.

[0212] 6. Sending warning messages

[0213] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[0214] 7. Analysis of user behavior history

[0215] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0216] 8. Submitting the report

[0217] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0218] Specific examples

[0219] Example 1: Receiving negative email

[0220] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0221] Example 2: Posting to social media

[0222] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[0223] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[0224] The processing flow will be explained below.

[0225] Step 1:

[0226] The server sets up APIs or web hooks for each communication tool (email, SNS, messaging app) and automatically retrieves data on messages and emails received by users. The retrieved data is temporarily stored in the server's storage.

[0227] Step 2:

[0228] The device captures the user's voice input, facial expression data, or biometric data, thereby collecting the user's current emotions in real time.

[0229] Step 3:

[0230] The emotion engine analyzes the received voice input, facial expression data, or biometric data to determine the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.), and sends the determination result to the server.

[0231] Step 4:

[0232] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API), tokenizing the text data, performing morphological analysis, identifying each word and phrase, and assigning a sentiment score.

[0233] Step 5:

[0234] The server then aggregates the negativity scores for each analyzed phrase to calculate an overall negativity score. It then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may lower the warning threshold.

[0235] Step 6:

[0236] If the negativity score exceeds a threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a statement such as "This message contains negative content. Please remain calm." The server also customizes the content and presentation of the warning message based on data from the emotion engine (e.g., if the user is depressed, a more gentle tone may be used).

[0237] Step 7:

[0238] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[0239] Step 8:

[0240] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[0241] Step 9:

[0242] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0243] Step 10:

[0244] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0245] Example 2

[0246] 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."

[0247] In recent years, while communication over the Internet has increased, negative emotions and aggressive comments have become a problem. This increases the risk of harming users' mental health and makes it difficult to maintain healthy online communities. Conventional systems have had difficulty recognizing users' emotions in real time, detecting negative content, and issuing warnings. In particular, flexible responses that reflect the user's current emotional state are required.

[0248] 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.

[0249] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for recognizing the user's emotions and correcting the analysis results, and a means for analyzing the user's behavior history and generating periodic reports, thereby making it possible to maintain the user's mental health and prevent negative emotions and aggressive behavior online.

[0250] An "information collection means" is a device or system that acquires data from multiple communication means used by a user.

[0251] "Means for analyzing text data using natural language processing" refers to a device or system that processes language data and analyzes its content and sentiment.

[0252] The "means for determining the negativity score" is a device or system that quantifies and determines the degree of negative emotion in text data.

[0253] "Means for generating and sending a warning message to a user" refers to a device or system that creates a warning message and notifies a user when a message containing negative content is detected.

[0254] The "means for recognizing the user's emotions and correcting the analysis results" refers to a device or system that analyzes the user's voice input and facial expression data and corrects the analysis results based on the user's current emotional state.

[0255] "Means for analyzing user behavior history and generating periodic reports" refers to a device or system that collects and analyzes a user's communication history and generates periodic reports.

[0256] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results. The system consists of the following elements:

[0257] System Components

[0258] 1. Server: The central processing unit collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history. Specifically, it collects information using the Gmail API and SNS APIs (e.g., Twitter API), and performs text analysis using natural language processing (NLP) libraries (e.g., Python's NLTK or spaCy).

[0259] 2. Device: The device used by the user, typically a PC, smartphone, or tablet. The device receives warning messages from the server and notifies the user. It also has the function of sending the user's voice and facial expression data to the emotion engine.

[0260] 3. Emotion Engine: Analyzes the user's voice input, facial recognition, or biometric data to determine the user's current emotion in real time. This is done using data collected by the camera and microphone on the user's smartphone.

[0261] Example of system operation

[0262] Example 1: Receiving negative email

[0263] The server uses the Gmail API to retrieve emails received by the user. For example, if an email containing the phrase "Your suggestions are completely useless" is received, the text is temporarily stored in the server's database. The device captures the user's facial expressions using the camera and analyzes them with an emotion engine. If the emotion engine determines that the user is already in a state of high stress, the server analyzes the text with a natural language processing library and assigns a high negativity score to the phrase "useless." If this score exceeds a pre-set threshold, a warning message is generated stating, "This email contains negative content. Please remain calm," and is sent to the user's device in real time as a pop-up notification.

[0264] Example 2: Suppressing offensive posts on social media

[0265] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media. This text data is immediately sent to the server. The server analyzes the received text and calculates an emotion score. At the same time, the emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated saying "This content is offensive. Please check again before sending," and is sent as a pop-up notification to the user's device.

[0266] Prompt Sentence Examples

[0267] >(Prompt example)

[0268] "The server extracts specific phrases from emails received by users and calculates an emotion score. If the phrase has a high negative impact, it generates a warning message and sends it to the user's device."

[0269] Hardware and Software

[0270] Hardware: User devices such as computers, smartphones, and tablets.

[0271] Software: Gmail API, Twitter API, Natural Language Processing libraries (NLTK, spaCy), Sentiment Engine.

[0272] As described above, the present invention is a system that can prevent negative emotions and aggressive behavior and maintain the user's mental health by collecting and analyzing information from the user's various communication tools.

[0273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0274] Step 1: Gather information

[0275] The server retrieves the user's received messages using APIs and webhooks of various communication tools (email, SNS, messaging apps). This data is temporarily stored in the server's storage. Specifically, the server retrieves the latest emails from the user's inbox using the Gmail API and collects user messages using SNS APIs (e.g., Twitter API).

[0276] Input: Message data from the Gmail API and SNS API.

[0277] Output: Text data saved in the server storage.

[0278] Step 2: Emotion Recognition

[0279] The device captures the user's voice input and facial expression recognition data through a camera and microphone. This data is sent to the emotion engine, which determines the user's current emotion in real time. Specifically, an application installed on the device takes a picture of the user's face with the smartphone camera and transmits the facial expression data in real time. At the same time, the voice input is also analyzed using the microphone.

[0280] Input: User's voice and facial expression data.

[0281] Output: The user's emotional state according to the emotion engine.

[0282] Step 3: Text analysis

[0283] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. It then performs sentiment scoring and assigns a score of positivity or negativity to each phrase.

[0284] Input: Text data stored on the server.

[0285] Output: Sentiment score for each phrase.

[0286] Step 4: Determine the degree of negativity

[0287] The server aggregates the negativity scores for each analyzed phrase and calculates an overall negativity score. It then determines whether this score exceeds a preset threshold. Specifically, it assigns a high negativity score to phrases such as "useless," and adds up the scores of other negative phrases to calculate the overall negativity score.

[0288] Input: Sentiment score from text analysis.

[0289] Output: Overall negativity score and judgment result.

[0290] Step 5: Emotion Data Correction

[0291] The server adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. Specifically, if the user is in a high stress state, the server lowers the warning threshold and changes the settings to issue more sensitive warnings than usual.

[0292] Input: The user's emotional state according to the emotion engine.

[0293] Output: Corrected negativity score.

[0294] Step 6: Generate a warning message

[0295] If the negativity score exceeds the threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a warning statement. Specifically, the server generates a message saying, "This email contains negative content. Please respond calmly." and saves it along with the text.

[0296] Input: Corrected negativity score.

[0297] Output: A warning message.

[0298] Step 7: Sending a warning message

[0299] The server sends the generated warning message to the user's device in real time. The device then notifies the user. Specifically, the server sends the message as a push notification, and a pop-up notification appears on the device.

[0300] Input: Warning message.

[0301] Output: A popup notification on the user's device.

[0302] Step 8: Analyzing behavioral history

[0303] The server periodically collects and analyzes user behavior history and creates a monthly report, which compiles the frequency of negative messages sent by users and the negativity score of each message.

[0304] Input: The user's communication history.

[0305] Output: Monthly report.

[0306] Step 9: Submit your report

[0307] The server will then send the generated report to the user's email address or make it available for viewing within the app. Specifically, the server will generate a monthly report in PDF format and send it to the user's email address or make it available for viewing on a dedicated dashboard within the app.

[0308] Enter: Monthly report.

[0309] Output: Send monthly report to user (either email or in-app).

[0310] (Application example 2)

[0311] 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."

[0312] In recent years, with the spread of online communication tools, users are increasingly receiving a large number of messages. Consequently, the stress and psychological burden caused by messages containing negative or offensive content have become a problem. Furthermore, in order to properly process these messages, the user's emotional state must also be taken into consideration. However, current technology does not provide a system that can detect negative content in online communications in real time and issue appropriate warnings that take the user's emotional state into account. Therefore, there is a need for technology that can prevent negative online interactions and maintain users' mental health.

[0313] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, and a means for determining a negativity score. This makes it possible to collect information from various communication tools used by users and detect content that may cause negative emotions or aggressive behavior in real time.

[0314] The system further includes a means for generating and sending a warning message to the user, a means for recognizing the user's emotional state in real time, and a means for analyzing the user's behavioral history and generating periodic reports. This allows the system to generate appropriate warning messages by adjusting the warning threshold if the user is already in a high stress state. Furthermore, by analyzing the user's behavioral history, the system can evaluate positive changes and negative increases and decreases and provide feedback to the user.

[0315] "Information collection means" refers to functions for collecting information from various communication tools (email, SNS, messaging apps, etc.).

[0316] "Means for analyzing text data using natural language processing" refers to a technology for analyzing acquired text data and understanding its contents.

[0317] The "means for determining negativity score" is a function for calculating and evaluating the positivity and negativity scores for the analyzed text data.

[0318] The "means for generating and sending a warning message to the user" is a function for generating and sending an appropriate warning message to the user when the negativity score exceeds a threshold.

[0319] "Means for analyzing user behavior history and generating periodic reports" refers to a function for collecting and analyzing data on users' online activities and reporting their behavior history.

[0320] "Means for recognizing the user's emotional state in real time" refers to a function that analyzes the user's current emotions in real time using the user's voice input, facial expression recognition, biometric data, etc.

[0321] This invention is a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system can be implemented in the following way.

[0322] System configuration

[0323] The system consists of the following components:

[0324] Server: As the central processing unit, it collects and analyzes information, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[0325] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0326] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0327] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[0328] System Operation

[0329] Information gathering

[0330] The server retrieves the user's incoming messages using the API or web hook of each communication tool (email, SNS, messaging app) and temporarily stores them in the server's storage.

[0331] emotion recognition

[0332] The device captures the user's voice input, facial expression recognition, or biometric data (e.g., heart rate data) and sends it to the emotion engine, which analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[0333] Text analytics

[0334] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase.

[0335] Determining the degree of negativity

[0336] The server aggregates the negativity scores for each analyzed phrase, calculates the overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's current emotional data obtained from the emotion engine.

[0337] Generate and send warning messages

[0338] If the negativity score exceeds a threshold, the server generates an appropriate warning message. For example, it generates a message that reads, "This message contains negative content. Please respond calmly." The content and display method of the warning message are customized based on data from the emotion engine. The generated warning message is sent to the user's device in real time as a pop-up notification.

[0339] Analyzing user behavior history and sending reports

[0340] The server periodically collects and analyzes the user's behavioral history. Based on this data, it evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases or decreases. The generated report is sent to the user's email address or made available for viewing within the app.

[0341] Specific examples

[0342] Example 1: Receiving negative email

[0343] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0344] Example 2: Posting to social media

[0345] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[0346] Prompt Sentence Examples

[0347] "Calculate the sentiment score for the following message: Your suggestion is completely useless."

[0348] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0349] Step 1:

[0350] The server receives messages received by users through the API or webhook of each communication tool. The input is the message data obtained from the API endpoint. The server temporarily stores this message data in storage, preparing the text data to be analyzed.

[0351] Step 2:

[0352] The device captures the user's voice input, facial recognition, or biometric data. The inputs include real-time user voice data, camera facial recognition data, and heart rate data. The device sends this data to the server. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.) in real time. The output is data indicating the user's emotional state.

[0353] Step 3:

[0354] The server analyzes the stored text data. The input is the message data stored in temporary storage. The server uses a natural language processing (NLP) library (e.g., Python's NLTK or spaCy) to tokenize the text data and perform morphological analysis to identify each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase. The output is the analysis results, including the sentiment score for each message.

[0355] Step 4:

[0356] The server aggregates the negativity scores for each analyzed phrase. The input is the sentiment score obtained in step 3. The server calculates the overall negativity according to specific scoring rules and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's emotional state data obtained in step 2. The output is the final negativity score.

[0357] Step 5:

[0358] The server generates a warning message if the negativity score exceeds a threshold. The input is the final negativity score and the user's emotional state data from the emotion engine. The server generates a warning message, for example, "This message contains negative content. Please respond calmly." If the user is depressed, the server adjusts the tone of the message to be displayed to be gentler. The output is the warning message.

[0359] Step 6:

[0360] The server sends the generated warning message to the user's terminal. The input is the generated warning message. The terminal displays it to the user as a popup notification. The output is the warning message displayed on the user's terminal.

[0361] Step 7:

[0362] The server periodically collects and analyzes the user's behavioral history. The input is data about the user's online activities. The server evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases and decreases. The output is a report containing the results of the analysis of the user's behavioral history.

[0363] Step 8:

[0364] The server sends the generated report to the user. The input is a report containing the analysis results of the behavioral history. The report is sent to the user's email address or made available for viewing within the app. The output is the report sent to the user.

[0365] 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.

[0366] 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.

[0367] 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.

[0368] [Second embodiment]

[0369] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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).

[0375] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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."

[0381] This system collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback.

[0382] System configuration

[0383] The system consists of the following components:

[0384] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history.

[0385] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0386] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0387] Program processing flow

[0388] 1. Information gathering

[0389] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and then analyzed.

[0390] 2. Text Analysis

[0391] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API), tokenizing and morphologically analyzing the text data, and calculating a sentiment score for each word or phrase.

[0392] 3. Determining the degree of negativity

[0393] The server aggregates the emotion scores obtained from the text data and calculates a negativity score. If this score exceeds a pre-set threshold, the server proceeds to the next step.

[0394] 4. Generating Warning Messages

[0395] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes the offending text and a message encouraging people to stay calm.

[0396] The generated warning messages are sent to the user's device in real time via pop-up notifications, email notifications, and in-app notifications.

[0397] 5. Analysis and reporting of behavioral history

[0398] The server collects and periodically analyzes user behavior history, compiling a report on the frequency, patterns, and changes in negative behavior for each month.

[0399] The generated report is either sent to the user's email address or made available in a viewable format within the app.

[0400] Specific examples

[0401] Example 1: Receiving negative email

[0402] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0403] Example 2: Posting to social media

[0404] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0405] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[0406] The processing flow will be explained below.

[0407] Step 1:

[0408] The server sets up APIs or web hooks for each communication tool to automatically retrieve data on messages and emails received by users. The data is temporarily stored in the server's storage and prepared for analysis.

[0409] Step 2:

[0410] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[0411] Step 3:

[0412] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[0413] Step 4:

[0414] If the negativity score exceeds a threshold, the server generates a warning message for the user, including a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[0415] Step 5:

[0416] The server generates and sends the generated warning message in real time to the user's device, which receives it and displays it to the user, via a pop-up notification, email notification, or in-app notification.

[0417] Step 6:

[0418] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[0419] Step 7:

[0420] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0421] Step 8:

[0422] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0423] Example 1

[0424] 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."

[0425] In modern society, people receive and send a huge amount of information every day through various communication tools such as email, social media, and messaging apps. Some of this information may provoke negative emotions and aggressive behavior, raising concerns that such information may have a negative impact on people's mental health. Furthermore, the transmission of such content increases online conflicts and troubles, so measures to prevent this are necessary. Furthermore, there is a need for a system that provides feedback based on users' behavioral history to encourage long-term behavioral improvement.

[0426] 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.

[0427] In this invention, the server includes means for acquiring data from multiple communication methods, means for analyzing text data using natural language processing, means for calculating an emotion score from the analyzed text data, means for determining a negativity score, means for generating and sending a warning message based on the negativity score, and means for collecting and analyzing user behavioral history and generating periodic reports. This allows users to respond calmly to negative information, prevent aggressive emotions from being expressed, maintain their mental health, and reduce online conflicts. Furthermore, receiving feedback on behavioral history can lead to long-term behavioral improvements.

[0428] "Multiple means of communication" refers to multiple digital communication tools such as email, social media, and messaging apps.

[0429] "Means of obtaining data" refers to methods of collecting information from multiple communication means using APIs and web hooks.

[0430] "Natural language processing" refers to the technology of analyzing text data and performing sentence structure analysis and emotion scoring.

[0431] "Text data" refers to textual information such as messages and posted content obtained through communication means.

[0432] An "emotion score" refers to a numerical evaluation of the emotion of each word or phrase contained in text data.

[0433] "Negativity score" refers to a numerical evaluation of the degree of negative emotion based on the emotion score of the entire text data.

[0434] A "warning message" refers to a notification sent to the user based on the negativity score, encouraging them to remain calm.

[0435] "Behavioral history" refers to data that records messages sent and received by users through communication means and the system's response to them.

[0436] "Report" refers to a document that summarizes the results of collecting and analyzing user behavior history.

[0437] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback. The system is composed of the following elements:

[0438] Server: The central processing unit is used to collect information, analyze text, calculate sentiment scores, determine negativity, generate warning messages, and analyze behavioral history. Specifically, it analyzes text data using natural language processing (NLP) libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API). The server also obtains data from multiple communication tools using APIs and webhooks.

[0439] Terminal: A device used by a user (PC, smartphone, tablet, etc.). These terminals are responsible for receiving notifications and warning messages from the server.

[0440] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0441] Specifically, the server uses the Gmail API or SNS API to retrieve messages received by the user. This data is temporarily stored in the server's storage, and then a natural language processing library (such as NLTK or spaCy) is used to tokenize the text and perform morphological analysis. A sentiment score is then calculated for each word or phrase. The sentiment scores are then aggregated to calculate a negativity score. If this score exceeds a pre-set threshold, the server generates a warning message. The generated warning message is sent to the user's device in real time. Notification methods include pop-up notifications, email notifications, and in-app notifications.

[0442] In addition, the server collects and periodically analyzes the user's behavioral history. It compiles a report on the frequency, patterns, and changes in negative behaviors for each month. The generated report is sent to the user's email address or made available in a viewable format within the app. This allows users to reflect on their own behavior and make long-term improvements.

[0443] Specific examples

[0444] Example 1: Receiving negative email

[0445] The server retrieves the email received by the user saying "Your suggestions are completely useless" via the Gmail API and analyzes the text using a natural language processing library. In this case, if the phrase "useless" is determined to have a high degree of negativity, the server generates a warning message saying "This email contains negative content. Please respond calmly." The generated message is immediately sent to the user's device as a pop-up notification.

[0446] Example 2: Posting to social media

[0447] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0448] Prompt Sentence Examples

[0449] "When a user receives an email saying 'Your suggestions are completely useless,' explain how the system analyzes the content and generates a warning message."

[0450] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0451] Step 1: Gather information

[0452] The server retrieves the user's incoming messages using APIs and webhooks of multiple communication tools (email, SNS, messaging apps). Specifically, it uses API credentials to send requests to the API endpoints of each communication tool, receives message data in JSON format, and stores it in temporary storage. The input is the API request, and the output is the retrieved message data in JSON format.

[0453] Specific behavior:

[0454] The server sends a request to the Gmail API to retrieve the user's unread emails.

[0455] Analyze the JSON data returned from the API, extract the message body, and temporarily save it.

[0456] Step 2: Text analysis

[0457] The server uses a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API) to analyze the stored text data. It tokenizes the text data and performs morphological analysis. It then calculates a sentiment score for each word or phrase. The input is the text data stored in temporary storage, and the output is the tokenized text with a sentiment score.

[0458] Specific behavior:

[0459] The server tokenizes the saved email body using the spaCy library.

[0460] A sentiment score is calculated for each phrase, such as "useless," and assigned to each token.

[0461] Step 3: Determine the degree of negativity

[0462] The server aggregates a negativity score based on the emotion scores obtained from the analyzed text data. If the negativity score exceeds a preset threshold, the process proceeds to the next step. The input is the text data with the emotion scores assigned, and the output is an overall negativity score.

[0463] Specific behavior:

[0464] The server aggregates the negative emotion scores for each token to calculate an overall negativity score.

[0465] If the configured threshold (e.g. 70) is exceeded, proceed to generate a warning message.

[0466] Step 4: Generate a warning message

[0467] The server generates a corresponding warning message when the negativity score exceeds a threshold. The message contains the problematic text and a message encouraging the user to remain calm. The generated warning message is sent to the user's device in real time. The input is the overall negativity score and the text data, and the output is the warning message.

[0468] Specific behavior:

[0469] The server generates a warning message saying, "This email contains negative content. Please stay calm."

[0470] The generated message is sent to the device using Firebase Cloud Messaging.

[0471] Step 5: Analyze and report behavioral history

[0472] The server collects user behavior history and periodically analyzes it. It compiles a report on the frequency and patterns of negative behavior for each month and provides feedback to the user. The input is behavior history data, and the output is a report.

[0473] Specific behavior:

[0474] The server retrieves the warning message generation history for the past month from the database.

[0475] The data is analyzed to generate statistics such as "how many negative emails were received per month."

[0476] The report will be created in PDF format and sent to the user's email address.

[0477] By taking these steps, users can calmly respond to negative information, maintain their mental health, and hopefully lead to long-term behavioral improvements.

[0478] (Application example 1)

[0479] 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."

[0480] In today's world, while online communication is becoming more common, negative emotions and aggressive behavior are becoming a problem. Particularly on social media and messaging apps, users can unintentionally send offensive messages or receive negative messages from others, causing psychological damage. This can damage users' mental health and make them more susceptible to online trouble.

[0481] 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.

[0482] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for analyzing the user's behavior history and generating periodic reports, and a means for analyzing messages in real time and immediately displaying a warning message. This makes it possible to immediately display a warning when a user sends or receives a negative message, encouraging the user to respond calmly.

[0483] "Information collection means" refers to the function of obtaining message data from various communication tools used by users (email, SNS, messaging apps, etc.) via API or web hooks.

[0484] "Natural language processing" is a technology in which a computer program analyzes human language, and is a process that involves tokenizing text data, analyzing sentence structure, and scoring sentiment.

[0485] A "negativity score" is a numerical representation of the emotional negativity of words and phrases in text data.

[0486] A "warning message" is a notification sent to a user when the negativity score exceeds a certain threshold, and includes a message encouraging the user to remain calm.

[0487] "User behavior history" refers to data that records the messages sent and received by the user and the emotional scores at that time.

[0488] "Means for analyzing messages in real time and immediately displaying a warning message" refers to a function that immediately analyzes messages when they are sent or received, and immediately warns the user if they contain negative content.

[0489] "Server" refers to the central processing unit that aggregates and analyzes information, calculates negativity scores, and generates warning messages.

[0490] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system consists of the following elements:

[0491] System configuration

[0492] 1. Server

[0493] The server is a central processing unit that collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history. This server can also be deployed on cloud services (e.g., AWS, Google Cloud).

[0494] 2. Terminal

[0495] A terminal is a device used by a user, typically a PC, smartphone, tablet, etc. An application is installed on the terminal to receive notifications and warning messages from the server.

[0496] 3. Users

[0497] Users are people who use the system, such as individuals, employees, and students.

[0498] Hardware and software used

[0499] Hardware

[0500] Servers (virtual machines on cloud services, physical servers)

[0501] Devices (PC, smartphone, tablet)

[0502] software

[0503] Natural language processing libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API)

[0504] Database (e.g. MySQL, PostgreSQL)

[0505] API clients (e.g., requests library)

[0506] Server frameworks (e.g., Flask, Django)

[0507] Data processing and calculation

[0508] 1. Information gathering

[0509] The server retrieves messages received by users using the API or web hooks of each communication tool. This data is temporarily stored in the server's storage.

[0510] 2. Text Analysis

[0511] The server analyzes the stored text data using natural language processing (NLP) libraries, tokenizing the text data, analyzing sentence structure, and calculating sentiment scores for each word and phrase.

[0512] 3. Determining the degree of negativity

[0513] The server aggregates the sentiment scores obtained from the text data, calculates a negativity score, and generates a warning message if the score exceeds a pre-set threshold.

[0514] 4. Generating and sending warning messages

[0515] If the negativity score exceeds the threshold, the server generates a corresponding warning message containing the problematic text and a message encouraging users to stay calm. The generated warning message is sent to the user's device in real time.

[0516] 5. Analysis and reporting of behavioral history

[0517] The server collects and periodically analyzes the user's behavioral history, compiling a report detailing the frequency, patterns, and changes in negative behaviors for each month. This report is sent to the user's email address or made available in a viewable format within the app.

[0518] Specific examples

[0519] Example 1: Receiving negative email

[0520] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0521] Example 2: Posting to social media

[0522] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0523] Prompt Sentence Examples

[0524] "Write Python code that uses natural language processing to parse negative content from messages received by users and generate a warning message. Use the Google Cloud Natural Language API."

[0525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0526] Step 1:

[0527] The server retrieves the user's received messages using the API or webhook of each communication tool (email, SNS, messaging app, etc.). Specifically, it sends an HTTP request to the API endpoint and temporarily stores the returned JSON-formatted message data in storage. The input is the API endpoint of each communication tool and the user's authentication information, and the output is the retrieved message data.

[0528] Step 2:

[0529] The server analyzes the message data stored in storage using a natural language processing (NLP) library. Specifically, it tokenizes the text data, analyzes the sentence structure, and calculates the sentiment score for each word and phrase. The NLP libraries used are NLTK, spaCy, and Google Cloud Natural Language API. The input is the message text read from storage, and the output is the sentiment score for each message.

[0530] Step 3:

[0531] The server determines the negativity score based on the analyzed sentiment score. Specifically, it aggregates the text analysis results and calculates an overall negativity score for each message. If the score exceeds a preset threshold, it proceeds to the next step. The input is the text analysis result (sentiment score), and the output is the negativity score.

[0532] Step 4:

[0533] If the negativity score exceeds a threshold, the server generates a corresponding warning message. Specifically, the server creates a warning message that includes text containing negative content as well as a message encouraging users to stay calm. The input is the negativity score, and the output is the warning message.

[0534] Step 5:

[0535] The server sends the generated warning message to the user's device in real time. Specifically, it sends a pop-up notification or an in-app notification to the target user's device. The input is the warning message, and the output is the warning notification displayed on the user's device.

[0536] Step 6:

[0537] The server periodically collects and analyzes the user's behavioral history and generates a monthly report. Specifically, it analyzes the frequency and patterns of negative behavior each month and aggregates them to create a report. The report is sent to the user's email address or provided in a format that can be viewed within the app. The input is past behavioral history data, and the output is a report summarizing the analysis results.

[0538] 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.

[0539] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results.

[0540] System configuration

[0541] The system consists of the following components:

[0542] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[0543] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0544] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0545] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[0546] Program processing flow

[0547] 1. Information gathering

[0548] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and prepared for analysis.

[0549] 2. Emotion recognition

[0550] The device captures the user's voice input, facial recognition, or biometric data and sends it to the emotion engine.

[0551] The emotion engine analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[0552] 3. Text Analysis

[0553] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[0554] 4. Determining the degree of negativity

[0555] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[0556] The server then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may adjust the warning threshold lower.

[0557] 5. Generating Warning Messages

[0558] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[0559] Data from the emotion engine is used to customize the content and presentation of warning messages, for example, if the user is depressed, a more gentle tone of message will be displayed.

[0560] 6. Sending warning messages

[0561] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[0562] 7. Analysis of user behavior history

[0563] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0564] 8. Submitting the report

[0565] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0566] Specific examples

[0567] Example 1: Receiving negative email

[0568] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0569] Example 2: Posting to social media

[0570] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[0571] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[0572] The processing flow will be explained below.

[0573] Step 1:

[0574] The server sets up APIs or web hooks for each communication tool (email, SNS, messaging app) and automatically retrieves data on messages and emails received by users. The retrieved data is temporarily stored in the server's storage.

[0575] Step 2:

[0576] The device captures the user's voice input, facial expression data, or biometric data, thereby collecting the user's current emotions in real time.

[0577] Step 3:

[0578] The emotion engine analyzes the received voice input, facial expression data, or biometric data to determine the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.), and sends the determination result to the server.

[0579] Step 4:

[0580] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API), tokenizing the text data, performing morphological analysis, identifying each word and phrase, and assigning a sentiment score.

[0581] Step 5:

[0582] The server then aggregates the negativity scores for each analyzed phrase to calculate an overall negativity score. It then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may lower the warning threshold.

[0583] Step 6:

[0584] If the negativity score exceeds a threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a statement such as "This message contains negative content. Please remain calm." The server also customizes the content and presentation of the warning message based on data from the emotion engine (e.g., if the user is depressed, a more gentle tone may be used).

[0585] Step 7:

[0586] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[0587] Step 8:

[0588] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[0589] Step 9:

[0590] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0591] Step 10:

[0592] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0593] Example 2

[0594] 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."

[0595] In recent years, while communication over the Internet has increased, negative emotions and aggressive comments have become a problem. This increases the risk of harming users' mental health and makes it difficult to maintain healthy online communities. Conventional systems have had difficulty recognizing users' emotions in real time, detecting negative content, and issuing warnings. In particular, flexible responses that reflect the user's current emotional state are required.

[0596] 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.

[0597] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for recognizing the user's emotions and correcting the analysis results, and a means for analyzing the user's behavior history and generating periodic reports, thereby making it possible to maintain the user's mental health and prevent negative emotions and aggressive behavior online.

[0598] An "information collection means" is a device or system that acquires data from multiple communication means used by a user.

[0599] "Means for analyzing text data using natural language processing" refers to a device or system that processes language data and analyzes its content and sentiment.

[0600] The "means for determining the negativity score" is a device or system that quantifies and determines the degree of negative emotion in text data.

[0601] "Means for generating and sending a warning message to a user" refers to a device or system that creates a warning message and notifies a user when a message containing negative content is detected.

[0602] The "means for recognizing the user's emotions and correcting the analysis results" refers to a device or system that analyzes the user's voice input and facial expression data and corrects the analysis results based on the user's current emotional state.

[0603] "Means for analyzing user behavior history and generating periodic reports" refers to a device or system that collects and analyzes a user's communication history and generates periodic reports.

[0604] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results. The system consists of the following elements:

[0605] System Components

[0606] 1. Server: The central processing unit collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history. Specifically, it collects information using the Gmail API and SNS APIs (e.g., Twitter API), and performs text analysis using natural language processing (NLP) libraries (e.g., Python's NLTK or spaCy).

[0607] 2. Device: The device used by the user, typically a PC, smartphone, or tablet. The device receives warning messages from the server and notifies the user. It also has the function of sending the user's voice and facial expression data to the emotion engine.

[0608] 3. Emotion Engine: Analyzes the user's voice input, facial recognition, or biometric data to determine the user's current emotion in real time. This is done using data collected by the camera and microphone on the user's smartphone.

[0609] Example of system operation

[0610] Example 1: Receiving negative email

[0611] The server uses the Gmail API to retrieve emails received by the user. For example, if an email containing the phrase "Your suggestions are completely useless" is received, the text is temporarily stored in the server's database. The device captures the user's facial expressions using the camera and analyzes them with an emotion engine. If the emotion engine determines that the user is already in a state of high stress, the server analyzes the text with a natural language processing library and assigns a high negativity score to the phrase "useless." If this score exceeds a pre-set threshold, a warning message is generated stating, "This email contains negative content. Please remain calm," and is sent to the user's device in real time as a pop-up notification.

[0612] Example 2: Suppressing offensive posts on social media

[0613] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media. This text data is immediately sent to the server. The server analyzes the received text and calculates an emotion score. At the same time, the emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated saying "This content is offensive. Please check again before sending," and is sent as a pop-up notification to the user's device.

[0614] Prompt Sentence Examples

[0615] >(Prompt example)

[0616] "The server extracts specific phrases from emails received by users and calculates an emotion score. If the phrase has a high negative impact, it generates a warning message and sends it to the user's device."

[0617] Hardware and Software

[0618] Hardware: User devices such as computers, smartphones, and tablets.

[0619] Software: Gmail API, Twitter API, Natural Language Processing libraries (NLTK, spaCy), Sentiment Engine.

[0620] As described above, the present invention is a system that can prevent negative emotions and aggressive behavior and maintain the user's mental health by collecting and analyzing information from the user's various communication tools.

[0621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0622] Step 1: Gather information

[0623] The server retrieves the user's received messages using APIs and webhooks of various communication tools (email, SNS, messaging apps). This data is temporarily stored in the server's storage. Specifically, the server retrieves the latest emails from the user's inbox using the Gmail API and collects user messages using SNS APIs (e.g., Twitter API).

[0624] Input: Message data from the Gmail API and SNS API.

[0625] Output: Text data saved in the server storage.

[0626] Step 2: Emotion Recognition

[0627] The device captures the user's voice input and facial expression recognition data through a camera and microphone. This data is sent to the emotion engine, which determines the user's current emotion in real time. Specifically, an application installed on the device takes a picture of the user's face with the smartphone camera and transmits the facial expression data in real time. At the same time, the voice input is also analyzed using the microphone.

[0628] Input: User's voice and facial expression data.

[0629] Output: The user's emotional state according to the emotion engine.

[0630] Step 3: Text analysis

[0631] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. It then performs sentiment scoring and assigns a score of positivity or negativity to each phrase.

[0632] Input: Text data stored on the server.

[0633] Output: Sentiment score for each phrase.

[0634] Step 4: Determine the degree of negativity

[0635] The server aggregates the negativity scores for each analyzed phrase and calculates an overall negativity score. It then determines whether this score exceeds a preset threshold. Specifically, it assigns a high negativity score to phrases such as "useless," and adds up the scores of other negative phrases to calculate the overall negativity score.

[0636] Input: Sentiment score from text analysis.

[0637] Output: Overall negativity score and judgment result.

[0638] Step 5: Emotion Data Correction

[0639] The server adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. Specifically, if the user is in a high stress state, the server lowers the warning threshold and changes the settings to issue more sensitive warnings than usual.

[0640] Input: The user's emotional state according to the emotion engine.

[0641] Output: Corrected negativity score.

[0642] Step 6: Generate a warning message

[0643] If the negativity score exceeds the threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a warning statement. Specifically, the server generates a message saying, "This email contains negative content. Please respond calmly." and saves it along with the text.

[0644] Input: Corrected negativity score.

[0645] Output: A warning message.

[0646] Step 7: Sending a warning message

[0647] The server sends the generated warning message to the user's device in real time. The device then notifies the user. Specifically, the server sends the message as a push notification, and a pop-up notification appears on the device.

[0648] Input: Warning message.

[0649] Output: A popup notification on the user's device.

[0650] Step 8: Analyzing behavioral history

[0651] The server periodically collects and analyzes user behavior history and creates a monthly report, which compiles the frequency of negative messages sent by users and the negativity score of each message.

[0652] Input: The user's communication history.

[0653] Output: Monthly report.

[0654] Step 9: Submit your report

[0655] The server will then send the generated report to the user's email address or make it available for viewing within the app. Specifically, the server will generate a monthly report in PDF format and send it to the user's email address or make it available for viewing on a dedicated dashboard within the app.

[0656] Enter: Monthly report.

[0657] Output: Send monthly report to user (either email or in-app).

[0658] (Application example 2)

[0659] 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."

[0660] In recent years, with the spread of online communication tools, users are increasingly receiving a large number of messages. Consequently, the stress and psychological burden caused by messages containing negative or offensive content have become a problem. Furthermore, in order to properly process these messages, the user's emotional state must also be taken into consideration. However, current technology does not provide a system that can detect negative content in online communications in real time and issue appropriate warnings that take the user's emotional state into account. Therefore, there is a need for technology that can prevent negative online interactions and maintain users' mental health.

[0661] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, and a means for determining a negativity score. This makes it possible to collect information from various communication tools used by users and detect content that may cause negative emotions or aggressive behavior in real time.

[0662] The system further includes a means for generating and sending a warning message to the user, a means for recognizing the user's emotional state in real time, and a means for analyzing the user's behavioral history and generating periodic reports. This allows the system to generate appropriate warning messages by adjusting the warning threshold if the user is already in a high stress state. Furthermore, by analyzing the user's behavioral history, the system can evaluate positive changes and negative increases and decreases and provide feedback to the user.

[0663] "Information collection means" refers to functions for collecting information from various communication tools (email, SNS, messaging apps, etc.).

[0664] "Means for analyzing text data using natural language processing" refers to a technology for analyzing acquired text data and understanding its contents.

[0665] The "means for determining negativity score" is a function for calculating and evaluating the positivity and negativity scores for the analyzed text data.

[0666] The "means for generating and sending a warning message to the user" is a function for generating and sending an appropriate warning message to the user when the negativity score exceeds a threshold.

[0667] "Means for analyzing user behavior history and generating periodic reports" refers to a function for collecting and analyzing data on users' online activities and reporting their behavior history.

[0668] "Means for recognizing the user's emotional state in real time" refers to a function that analyzes the user's current emotions in real time using the user's voice input, facial expression recognition, biometric data, etc.

[0669] This invention is a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system can be implemented in the following way.

[0670] System configuration

[0671] The system consists of the following components:

[0672] Server: As the central processing unit, it collects and analyzes information, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[0673] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0674] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0675] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[0676] System Operation

[0677] Information gathering

[0678] The server retrieves the user's incoming messages using the API or web hook of each communication tool (email, SNS, messaging app) and temporarily stores them in the server's storage.

[0679] emotion recognition

[0680] The device captures the user's voice input, facial expression recognition, or biometric data (e.g., heart rate data) and sends it to the emotion engine, which analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[0681] Text analytics

[0682] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase.

[0683] Determining the degree of negativity

[0684] The server aggregates the negativity scores for each analyzed phrase, calculates the overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's current emotional data obtained from the emotion engine.

[0685] Generate and send warning messages

[0686] If the negativity score exceeds a threshold, the server generates an appropriate warning message. For example, it generates a message that reads, "This message contains negative content. Please respond calmly." The content and display method of the warning message are customized based on data from the emotion engine. The generated warning message is sent to the user's device in real time as a pop-up notification.

[0687] Analyzing user behavior history and sending reports

[0688] The server periodically collects and analyzes the user's behavioral history. Based on this data, it evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases or decreases. The generated report is sent to the user's email address or made available for viewing within the app.

[0689] Specific examples

[0690] Example 1: Receiving negative email

[0691] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0692] Example 2: Posting to social media

[0693] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[0694] Prompt Sentence Examples

[0695] "Calculate the sentiment score for the following message: Your suggestion is completely useless."

[0696] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0697] Step 1:

[0698] The server receives messages received by users through the API or webhook of each communication tool. The input is the message data obtained from the API endpoint. The server temporarily stores this message data in storage, preparing the text data to be analyzed.

[0699] Step 2:

[0700] The device captures the user's voice input, facial recognition, or biometric data. The inputs include real-time user voice data, camera facial recognition data, and heart rate data. The device sends this data to the server. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.) in real time. The output is data indicating the user's emotional state.

[0701] Step 3:

[0702] The server analyzes the stored text data. The input is the message data stored in temporary storage. The server uses a natural language processing (NLP) library (e.g., Python's NLTK or spaCy) to tokenize the text data and perform morphological analysis to identify each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase. The output is the analysis results, including the sentiment score for each message.

[0703] Step 4:

[0704] The server aggregates the negativity scores for each analyzed phrase. The input is the sentiment score obtained in step 3. The server calculates the overall negativity according to specific scoring rules and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's emotional state data obtained in step 2. The output is the final negativity score.

[0705] Step 5:

[0706] The server generates a warning message if the negativity score exceeds a threshold. The input is the final negativity score and the user's emotional state data from the emotion engine. The server generates a warning message, for example, "This message contains negative content. Please respond calmly." If the user is depressed, the server adjusts the tone of the message to be displayed to be gentler. The output is the warning message.

[0707] Step 6:

[0708] The server sends the generated warning message to the user's terminal. The input is the generated warning message. The terminal displays it to the user as a popup notification. The output is the warning message displayed on the user's terminal.

[0709] Step 7:

[0710] The server periodically collects and analyzes the user's behavioral history. The input is data about the user's online activities. The server evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases and decreases. The output is a report containing the results of the analysis of the user's behavioral history.

[0711] Step 8:

[0712] The server sends the generated report to the user. The input is a report containing the analysis results of the behavioral history. The report is sent to the user's email address or made available for viewing within the app. The output is the report sent to the user.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] [Third embodiment]

[0717] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0718] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0719] 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).

[0720] 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.

[0721] 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.

[0722] 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).

[0723] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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."

[0729] This system collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback.

[0730] System configuration

[0731] The system consists of the following components:

[0732] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history.

[0733] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0734] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0735] Program processing flow

[0736] 1. Information gathering

[0737] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and then analyzed.

[0738] 2. Text Analysis

[0739] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API), tokenizing and morphologically analyzing the text data, and calculating a sentiment score for each word or phrase.

[0740] 3. Determining the degree of negativity

[0741] The server aggregates the emotion scores obtained from the text data and calculates a negativity score. If this score exceeds a pre-set threshold, the server proceeds to the next step.

[0742] 4. Generating Warning Messages

[0743] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes the offending text and a message encouraging people to stay calm.

[0744] The generated warning messages are sent to the user's device in real time via pop-up notifications, email notifications, and in-app notifications.

[0745] 5. Analysis and reporting of behavioral history

[0746] The server collects and periodically analyzes user behavior history, compiling a report on the frequency, patterns, and changes in negative behavior for each month.

[0747] The generated report is either sent to the user's email address or made available in a viewable format within the app.

[0748] Specific examples

[0749] Example 1: Receiving negative email

[0750] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0751] Example 2: Posting to social media

[0752] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0753] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[0754] The processing flow will be explained below.

[0755] Step 1:

[0756] The server sets up APIs or web hooks for each communication tool to automatically retrieve data on messages and emails received by users. The data is temporarily stored in the server's storage and prepared for analysis.

[0757] Step 2:

[0758] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[0759] Step 3:

[0760] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[0761] Step 4:

[0762] If the negativity score exceeds a threshold, the server generates a warning message for the user, including a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[0763] Step 5:

[0764] The server generates and sends the generated warning message in real time to the user's device, which receives it and displays it to the user, via a pop-up notification, email notification, or in-app notification.

[0765] Step 6:

[0766] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[0767] Step 7:

[0768] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0769] Step 8:

[0770] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0771] Example 1

[0772] 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."

[0773] In modern society, people receive and send a huge amount of information every day through various communication tools such as email, social media, and messaging apps. Some of this information may provoke negative emotions and aggressive behavior, raising concerns that such information may have a negative impact on people's mental health. Furthermore, the transmission of such content increases online conflicts and troubles, so measures to prevent this are necessary. Furthermore, there is a need for a system that provides feedback based on users' behavioral history to encourage long-term behavioral improvement.

[0774] 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.

[0775] In this invention, the server includes means for acquiring data from multiple communication methods, means for analyzing text data using natural language processing, means for calculating an emotion score from the analyzed text data, means for determining a negativity score, means for generating and sending a warning message based on the negativity score, and means for collecting and analyzing user behavioral history and generating periodic reports. This allows users to respond calmly to negative information, prevent aggressive emotions from being expressed, maintain their mental health, and reduce online conflicts. Furthermore, receiving feedback on behavioral history can lead to long-term behavioral improvements.

[0776] "Multiple means of communication" refers to multiple digital communication tools such as email, social media, and messaging apps.

[0777] "Means of obtaining data" refers to methods of collecting information from multiple communication means using APIs and web hooks.

[0778] "Natural language processing" refers to the technology of analyzing text data and performing sentence structure analysis and emotion scoring.

[0779] "Text data" refers to textual information such as messages and posted content obtained through communication means.

[0780] An "emotion score" refers to a numerical evaluation of the emotion of each word or phrase contained in text data.

[0781] "Negativity score" refers to a numerical evaluation of the degree of negative emotion based on the emotion score of the entire text data.

[0782] A "warning message" refers to a notification sent to the user based on the negativity score, encouraging them to remain calm.

[0783] "Behavioral history" refers to data that records messages sent and received by users through communication means and the system's response to them.

[0784] "Report" refers to a document that summarizes the results of collecting and analyzing user behavior history.

[0785] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback. The system is composed of the following elements:

[0786] Server: The central processing unit is used to collect information, analyze text, calculate sentiment scores, determine negativity, generate warning messages, and analyze behavioral history. Specifically, it analyzes text data using natural language processing (NLP) libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API). The server also obtains data from multiple communication tools using APIs and webhooks.

[0787] Terminal: A device used by a user (PC, smartphone, tablet, etc.). These terminals are responsible for receiving notifications and warning messages from the server.

[0788] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0789] Specifically, the server uses the Gmail API or SNS API to retrieve messages received by the user. This data is temporarily stored in the server's storage, and then a natural language processing library (such as NLTK or spaCy) is used to tokenize the text and perform morphological analysis. A sentiment score is then calculated for each word or phrase. The sentiment scores are then aggregated to calculate a negativity score. If this score exceeds a pre-set threshold, the server generates a warning message. The generated warning message is sent to the user's device in real time. Notification methods include pop-up notifications, email notifications, and in-app notifications.

[0790] In addition, the server collects and periodically analyzes the user's behavioral history. It compiles a report on the frequency, patterns, and changes in negative behaviors for each month. The generated report is sent to the user's email address or made available in a viewable format within the app. This allows users to reflect on their own behavior and make long-term improvements.

[0791] Specific examples

[0792] Example 1: Receiving negative email

[0793] The server retrieves the email received by the user saying "Your suggestions are completely useless" via the Gmail API and analyzes the text using a natural language processing library. In this case, if the phrase "useless" is determined to have a high degree of negativity, the server generates a warning message saying "This email contains negative content. Please respond calmly." The generated message is immediately sent to the user's device as a pop-up notification.

[0794] Example 2: Posting to social media

[0795] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0796] Prompt Sentence Examples

[0797] "When a user receives an email saying 'Your suggestions are completely useless,' explain how the system analyzes the content and generates a warning message."

[0798] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0799] Step 1: Gather information

[0800] The server retrieves the user's incoming messages using APIs and webhooks of multiple communication tools (email, SNS, messaging apps). Specifically, it uses API credentials to send requests to the API endpoints of each communication tool, receives message data in JSON format, and stores it in temporary storage. The input is the API request, and the output is the retrieved message data in JSON format.

[0801] Specific behavior:

[0802] The server sends a request to the Gmail API to retrieve the user's unread emails.

[0803] Analyze the JSON data returned from the API, extract the message body, and temporarily save it.

[0804] Step 2: Text analysis

[0805] The server uses a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API) to analyze the stored text data. It tokenizes the text data and performs morphological analysis. It then calculates a sentiment score for each word or phrase. The input is the text data stored in temporary storage, and the output is the tokenized text with a sentiment score.

[0806] Specific behavior:

[0807] The server tokenizes the saved email body using the spaCy library.

[0808] A sentiment score is calculated for each phrase, such as "useless," and assigned to each token.

[0809] Step 3: Determine the degree of negativity

[0810] The server aggregates a negativity score based on the emotion scores obtained from the analyzed text data. If the negativity score exceeds a preset threshold, the process proceeds to the next step. The input is the text data with the emotion scores assigned, and the output is an overall negativity score.

[0811] Specific behavior:

[0812] The server aggregates the negative emotion scores for each token to calculate an overall negativity score.

[0813] If the configured threshold (e.g. 70) is exceeded, proceed to generate a warning message.

[0814] Step 4: Generate a warning message

[0815] The server generates a corresponding warning message when the negativity score exceeds a threshold. The message contains the problematic text and a message encouraging the user to remain calm. The generated warning message is sent to the user's device in real time. The input is the overall negativity score and the text data, and the output is the warning message.

[0816] Specific behavior:

[0817] The server generates a warning message saying, "This email contains negative content. Please stay calm."

[0818] The generated message is sent to the device using Firebase Cloud Messaging.

[0819] Step 5: Analyze and report behavioral history

[0820] The server collects user behavior history and periodically analyzes it. It compiles a report on the frequency and patterns of negative behavior for each month and provides feedback to the user. The input is behavior history data, and the output is a report.

[0821] Specific behavior:

[0822] The server retrieves the warning message generation history for the past month from the database.

[0823] The data is analyzed to generate statistics such as "how many negative emails were received per month."

[0824] The report will be created in PDF format and sent to the user's email address.

[0825] By taking these steps, users can calmly respond to negative information, maintain their mental health, and hopefully lead to long-term behavioral improvements.

[0826] (Application example 1)

[0827] 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."

[0828] In today's world, while online communication is becoming more common, negative emotions and aggressive behavior are becoming a problem. Particularly on social media and messaging apps, users can unintentionally send offensive messages or receive negative messages from others, causing psychological damage. This can damage users' mental health and make them more susceptible to online trouble.

[0829] 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.

[0830] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for analyzing the user's behavior history and generating periodic reports, and a means for analyzing messages in real time and immediately displaying a warning message. This makes it possible to immediately display a warning when a user sends or receives a negative message, encouraging the user to respond calmly.

[0831] "Information collection means" refers to the function of obtaining message data from various communication tools used by users (email, SNS, messaging apps, etc.) via API or web hooks.

[0832] "Natural language processing" is a technology in which a computer program analyzes human language, and is a process that involves tokenizing text data, analyzing sentence structure, and scoring sentiment.

[0833] A "negativity score" is a numerical representation of the emotional negativity of words and phrases in text data.

[0834] A "warning message" is a notification sent to a user when the negativity score exceeds a certain threshold, and includes a message encouraging the user to remain calm.

[0835] "User behavior history" refers to data that records the messages sent and received by the user and the emotional scores at that time.

[0836] "Means for analyzing messages in real time and immediately displaying a warning message" refers to a function that immediately analyzes messages when they are sent or received, and immediately warns the user if they contain negative content.

[0837] "Server" refers to the central processing unit that aggregates and analyzes information, calculates negativity scores, and generates warning messages.

[0838] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system consists of the following elements:

[0839] System configuration

[0840] 1. Server

[0841] The server is a central processing unit that collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history. This server can also be deployed on cloud services (e.g., AWS, Google Cloud).

[0842] 2. Terminal

[0843] A terminal is a device used by a user, typically a PC, smartphone, tablet, etc. An application is installed on the terminal to receive notifications and warning messages from the server.

[0844] 3. Users

[0845] Users are people who use the system, such as individuals, employees, and students.

[0846] Hardware and software used

[0847] Hardware

[0848] Servers (virtual machines on cloud services, physical servers)

[0849] Devices (PC, smartphone, tablet)

[0850] software

[0851] Natural language processing libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API)

[0852] Database (e.g. MySQL, PostgreSQL)

[0853] API clients (e.g., requests library)

[0854] Server frameworks (e.g., Flask, Django)

[0855] Data processing and calculation

[0856] 1. Information gathering

[0857] The server retrieves messages received by users using the API or web hooks of each communication tool. This data is temporarily stored in the server's storage.

[0858] 2. Text Analysis

[0859] The server analyzes the stored text data using natural language processing (NLP) libraries, tokenizing the text data, analyzing sentence structure, and calculating sentiment scores for each word and phrase.

[0860] 3. Determining the degree of negativity

[0861] The server aggregates the sentiment scores obtained from the text data, calculates a negativity score, and generates a warning message if the score exceeds a pre-set threshold.

[0862] 4. Generating and sending warning messages

[0863] If the negativity score exceeds the threshold, the server generates a corresponding warning message containing the problematic text and a message encouraging users to stay calm. The generated warning message is sent to the user's device in real time.

[0864] 5. Analysis and reporting of behavioral history

[0865] The server collects and periodically analyzes the user's behavioral history, compiling a report detailing the frequency, patterns, and changes in negative behaviors for each month. This report is sent to the user's email address or made available in a viewable format within the app.

[0866] Specific examples

[0867] Example 1: Receiving negative email

[0868] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0869] Example 2: Posting to social media

[0870] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[0871] Prompt Sentence Examples

[0872] "Write Python code that uses natural language processing to parse negative content from messages received by users and generate a warning message. Use the Google Cloud Natural Language API."

[0873] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0874] Step 1:

[0875] The server retrieves the user's received messages using the API or webhook of each communication tool (email, SNS, messaging app, etc.). Specifically, it sends an HTTP request to the API endpoint and temporarily stores the returned JSON-formatted message data in storage. The input is the API endpoint of each communication tool and the user's authentication information, and the output is the retrieved message data.

[0876] Step 2:

[0877] The server analyzes the message data stored in storage using a natural language processing (NLP) library. Specifically, it tokenizes the text data, analyzes the sentence structure, and calculates the sentiment score for each word and phrase. The NLP libraries used are NLTK, spaCy, and Google Cloud Natural Language API. The input is the message text read from storage, and the output is the sentiment score for each message.

[0878] Step 3:

[0879] The server determines the negativity score based on the analyzed sentiment score. Specifically, it aggregates the text analysis results and calculates an overall negativity score for each message. If the score exceeds a preset threshold, it proceeds to the next step. The input is the text analysis result (sentiment score), and the output is the negativity score.

[0880] Step 4:

[0881] If the negativity score exceeds a threshold, the server generates a corresponding warning message. Specifically, the server creates a warning message that includes text containing negative content as well as a message encouraging users to stay calm. The input is the negativity score, and the output is the warning message.

[0882] Step 5:

[0883] The server sends the generated warning message to the user's device in real time. Specifically, it sends a pop-up notification or an in-app notification to the target user's device. The input is the warning message, and the output is the warning notification displayed on the user's device.

[0884] Step 6:

[0885] The server periodically collects and analyzes the user's behavioral history and generates a monthly report. Specifically, it analyzes the frequency and patterns of negative behavior each month and aggregates them to create a report. The report is sent to the user's email address or provided in a format that can be viewed within the app. The input is past behavioral history data, and the output is a report summarizing the analysis results.

[0886] 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.

[0887] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results.

[0888] System configuration

[0889] The system consists of the following components:

[0890] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[0891] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[0892] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[0893] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[0894] Program processing flow

[0895] 1. Information gathering

[0896] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and prepared for analysis.

[0897] 2. Emotion recognition

[0898] The device captures the user's voice input, facial recognition, or biometric data and sends it to the emotion engine.

[0899] The emotion engine analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[0900] 3. Text Analysis

[0901] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[0902] 4. Determining the degree of negativity

[0903] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[0904] The server then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may adjust the warning threshold lower.

[0905] 5. Generating Warning Messages

[0906] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[0907] Data from the emotion engine is used to customize the content and presentation of warning messages, for example, if the user is depressed, a more gentle tone of message will be displayed.

[0908] 6. Sending warning messages

[0909] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[0910] 7. Analysis of user behavior history

[0911] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0912] 8. Submitting the report

[0913] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0914] Specific examples

[0915] Example 1: Receiving negative email

[0916] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[0917] Example 2: Posting to social media

[0918] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[0919] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[0920] The processing flow will be explained below.

[0921] Step 1:

[0922] The server sets up APIs or web hooks for each communication tool (email, SNS, messaging app) and automatically retrieves data on messages and emails received by users. The retrieved data is temporarily stored in the server's storage.

[0923] Step 2:

[0924] The device captures the user's voice input, facial expression data, or biometric data, thereby collecting the user's current emotions in real time.

[0925] Step 3:

[0926] The emotion engine analyzes the received voice input, facial expression data, or biometric data to determine the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.), and sends the determination result to the server.

[0927] Step 4:

[0928] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API), tokenizing the text data, performing morphological analysis, identifying each word and phrase, and assigning a sentiment score.

[0929] Step 5:

[0930] The server then aggregates the negativity scores for each analyzed phrase to calculate an overall negativity score. It then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may lower the warning threshold.

[0931] Step 6:

[0932] If the negativity score exceeds a threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a statement such as "This message contains negative content. Please remain calm." The server also customizes the content and presentation of the warning message based on data from the emotion engine (e.g., if the user is depressed, a more gentle tone may be used).

[0933] Step 7:

[0934] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[0935] Step 8:

[0936] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[0937] Step 9:

[0938] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[0939] Step 10:

[0940] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[0941] Example 2

[0942] 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."

[0943] In recent years, while communication over the Internet has increased, negative emotions and aggressive comments have become a problem. This increases the risk of harming users' mental health and makes it difficult to maintain healthy online communities. Conventional systems have had difficulty recognizing users' emotions in real time, detecting negative content, and issuing warnings. In particular, flexible responses that reflect the user's current emotional state are required.

[0944] 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.

[0945] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for recognizing the user's emotions and correcting the analysis results, and a means for analyzing the user's behavior history and generating periodic reports, thereby making it possible to maintain the user's mental health and prevent negative emotions and aggressive behavior online.

[0946] An "information collection means" is a device or system that acquires data from multiple communication means used by a user.

[0947] "Means for analyzing text data using natural language processing" refers to a device or system that processes language data and analyzes its content and sentiment.

[0948] The "means for determining the negativity score" is a device or system that quantifies and determines the degree of negative emotion in text data.

[0949] "Means for generating and sending a warning message to a user" refers to a device or system that creates a warning message and notifies a user when a message containing negative content is detected.

[0950] The "means for recognizing the user's emotions and correcting the analysis results" refers to a device or system that analyzes the user's voice input and facial expression data and corrects the analysis results based on the user's current emotional state.

[0951] "Means for analyzing user behavior history and generating periodic reports" refers to a device or system that collects and analyzes a user's communication history and generates periodic reports.

[0952] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results. The system consists of the following elements:

[0953] System Components

[0954] 1. Server: The central processing unit collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history. Specifically, it collects information using the Gmail API and SNS APIs (e.g., Twitter API), and performs text analysis using natural language processing (NLP) libraries (e.g., Python's NLTK or spaCy).

[0955] 2. Device: The device used by the user, typically a PC, smartphone, or tablet. The device receives warning messages from the server and notifies the user. It also has the function of sending the user's voice and facial expression data to the emotion engine.

[0956] 3. Emotion Engine: Analyzes the user's voice input, facial recognition, or biometric data to determine the user's current emotion in real time. This is done using data collected by the camera and microphone on the user's smartphone.

[0957] Example of system operation

[0958] Example 1: Receiving negative email

[0959] The server uses the Gmail API to retrieve emails received by the user. For example, if an email containing the phrase "Your suggestions are completely useless" is received, the text is temporarily stored in the server's database. The device captures the user's facial expressions using the camera and analyzes them with an emotion engine. If the emotion engine determines that the user is already in a state of high stress, the server analyzes the text with a natural language processing library and assigns a high negativity score to the phrase "useless." If this score exceeds a pre-set threshold, a warning message is generated stating, "This email contains negative content. Please remain calm," and is sent to the user's device in real time as a pop-up notification.

[0960] Example 2: Suppressing offensive posts on social media

[0961] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media. This text data is immediately sent to the server. The server analyzes the received text and calculates an emotion score. At the same time, the emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated saying "This content is offensive. Please check again before sending," and is sent as a pop-up notification to the user's device.

[0962] Prompt Sentence Examples

[0963] >(Prompt example)

[0964] "The server extracts specific phrases from emails received by users and calculates an emotion score. If the phrase has a high negative impact, it generates a warning message and sends it to the user's device."

[0965] Hardware and Software

[0966] Hardware: User devices such as computers, smartphones, and tablets.

[0967] Software: Gmail API, Twitter API, Natural Language Processing libraries (NLTK, spaCy), Sentiment Engine.

[0968] As described above, the present invention is a system that can prevent negative emotions and aggressive behavior and maintain the user's mental health by collecting and analyzing information from the user's various communication tools.

[0969] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0970] Step 1: Gather information

[0971] The server retrieves the user's received messages using APIs and webhooks of various communication tools (email, SNS, messaging apps). This data is temporarily stored in the server's storage. Specifically, the server retrieves the latest emails from the user's inbox using the Gmail API and collects user messages using SNS APIs (e.g., Twitter API).

[0972] Input: Message data from the Gmail API and SNS API.

[0973] Output: Text data saved in the server storage.

[0974] Step 2: Emotion Recognition

[0975] The device captures the user's voice input and facial expression recognition data through a camera and microphone. This data is sent to the emotion engine, which determines the user's current emotion in real time. Specifically, an application installed on the device takes a picture of the user's face with the smartphone camera and transmits the facial expression data in real time. At the same time, the voice input is also analyzed using the microphone.

[0976] Input: User's voice and facial expression data.

[0977] Output: The user's emotional state according to the emotion engine.

[0978] Step 3: Text analysis

[0979] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. It then performs sentiment scoring and assigns a score of positivity or negativity to each phrase.

[0980] Input: Text data stored on the server.

[0981] Output: Sentiment score for each phrase.

[0982] Step 4: Determine the degree of negativity

[0983] The server aggregates the negativity scores for each analyzed phrase and calculates an overall negativity score. It then determines whether this score exceeds a preset threshold. Specifically, it assigns a high negativity score to phrases such as "useless," and adds up the scores of other negative phrases to calculate the overall negativity score.

[0984] Input: Sentiment score from text analysis.

[0985] Output: Overall negativity score and judgment result.

[0986] Step 5: Emotion Data Correction

[0987] The server adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. Specifically, if the user is in a high stress state, the server lowers the warning threshold and changes the settings to issue more sensitive warnings than usual.

[0988] Input: The user's emotional state according to the emotion engine.

[0989] Output: Corrected negativity score.

[0990] Step 6: Generate a warning message

[0991] If the negativity score exceeds the threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a warning statement. Specifically, the server generates a message saying, "This email contains negative content. Please respond calmly." and saves it along with the text.

[0992] Input: Corrected negativity score.

[0993] Output: A warning message.

[0994] Step 7: Sending a warning message

[0995] The server sends the generated warning message to the user's device in real time. The device then notifies the user. Specifically, the server sends the message as a push notification, and a pop-up notification appears on the device.

[0996] Input: Warning message.

[0997] Output: A popup notification on the user's device.

[0998] Step 8: Analyzing behavioral history

[0999] The server periodically collects and analyzes user behavior history and creates a monthly report, which compiles the frequency of negative messages sent by users and the negativity score of each message.

[1000] Input: The user's communication history.

[1001] Output: Monthly report.

[1002] Step 9: Submit your report

[1003] The server will then send the generated report to the user's email address or make it available for viewing within the app. Specifically, the server will generate a monthly report in PDF format and send it to the user's email address or make it available for viewing on a dedicated dashboard within the app.

[1004] Enter: Monthly report.

[1005] Output: Send monthly report to user (either email or in-app).

[1006] (Application example 2)

[1007] 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."

[1008] In recent years, with the spread of online communication tools, users are increasingly receiving a large number of messages. Consequently, the stress and psychological burden caused by messages containing negative or offensive content have become a problem. Furthermore, in order to properly process these messages, the user's emotional state must also be taken into consideration. However, current technology does not provide a system that can detect negative content in online communications in real time and issue appropriate warnings that take the user's emotional state into account. Therefore, there is a need for technology that can prevent negative online interactions and maintain users' mental health.

[1009] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, and a means for determining a negativity score. This makes it possible to collect information from various communication tools used by users and detect content that may cause negative emotions or aggressive behavior in real time.

[1010] The system further includes a means for generating and sending a warning message to the user, a means for recognizing the user's emotional state in real time, and a means for analyzing the user's behavioral history and generating periodic reports. This allows the system to generate appropriate warning messages by adjusting the warning threshold if the user is already in a high stress state. Furthermore, by analyzing the user's behavioral history, the system can evaluate positive changes and negative increases and decreases and provide feedback to the user.

[1011] "Information collection means" refers to functions for collecting information from various communication tools (email, SNS, messaging apps, etc.).

[1012] "Means for analyzing text data using natural language processing" refers to a technology for analyzing acquired text data and understanding its contents.

[1013] The "means for determining negativity score" is a function for calculating and evaluating the positivity and negativity scores for the analyzed text data.

[1014] The "means for generating and sending a warning message to the user" is a function for generating and sending an appropriate warning message to the user when the negativity score exceeds a threshold.

[1015] "Means for analyzing user behavior history and generating periodic reports" refers to a function for collecting and analyzing data on users' online activities and reporting their behavior history.

[1016] "Means for recognizing the user's emotional state in real time" refers to a function that analyzes the user's current emotions in real time using the user's voice input, facial expression recognition, biometric data, etc.

[1017] This invention is a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system can be implemented in the following way.

[1018] System configuration

[1019] The system consists of the following components:

[1020] Server: As the central processing unit, it collects and analyzes information, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[1021] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[1022] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[1023] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[1024] System Operation

[1025] Information gathering

[1026] The server retrieves the user's incoming messages using the API or web hook of each communication tool (email, SNS, messaging app) and temporarily stores them in the server's storage.

[1027] emotion recognition

[1028] The device captures the user's voice input, facial expression recognition, or biometric data (e.g., heart rate data) and sends it to the emotion engine, which analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[1029] Text analytics

[1030] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase.

[1031] Determining the degree of negativity

[1032] The server aggregates the negativity scores for each analyzed phrase, calculates the overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's current emotional data obtained from the emotion engine.

[1033] Generate and send warning messages

[1034] If the negativity score exceeds a threshold, the server generates an appropriate warning message. For example, it generates a message that reads, "This message contains negative content. Please respond calmly." The content and display method of the warning message are customized based on data from the emotion engine. The generated warning message is sent to the user's device in real time as a pop-up notification.

[1035] Analyzing user behavior history and sending reports

[1036] The server periodically collects and analyzes the user's behavioral history. Based on this data, it evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases or decreases. The generated report is sent to the user's email address or made available for viewing within the app.

[1037] Specific examples

[1038] Example 1: Receiving negative email

[1039] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[1040] Example 2: Posting to social media

[1041] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[1042] Prompt Sentence Examples

[1043] "Calculate the sentiment score for the following message: Your suggestion is completely useless."

[1044] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1045] Step 1:

[1046] The server receives messages received by users through the API or webhook of each communication tool. The input is the message data obtained from the API endpoint. The server temporarily stores this message data in storage, preparing the text data to be analyzed.

[1047] Step 2:

[1048] The device captures the user's voice input, facial recognition, or biometric data. The inputs include real-time user voice data, camera facial recognition data, and heart rate data. The device sends this data to the server. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.) in real time. The output is data indicating the user's emotional state.

[1049] Step 3:

[1050] The server analyzes the stored text data. The input is the message data stored in temporary storage. The server uses a natural language processing (NLP) library (e.g., Python's NLTK or spaCy) to tokenize the text data and perform morphological analysis to identify each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase. The output is the analysis results, including the sentiment score for each message.

[1051] Step 4:

[1052] The server aggregates the negativity scores for each analyzed phrase. The input is the sentiment score obtained in step 3. The server calculates the overall negativity according to specific scoring rules and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's emotional state data obtained in step 2. The output is the final negativity score.

[1053] Step 5:

[1054] The server generates a warning message if the negativity score exceeds a threshold. The input is the final negativity score and the user's emotional state data from the emotion engine. The server generates a warning message, for example, "This message contains negative content. Please respond calmly." If the user is depressed, the server adjusts the tone of the message to be displayed to be gentler. The output is the warning message.

[1055] Step 6:

[1056] The server sends the generated warning message to the user's terminal. The input is the generated warning message. The terminal displays it to the user as a popup notification. The output is the warning message displayed on the user's terminal.

[1057] Step 7:

[1058] The server periodically collects and analyzes the user's behavioral history. The input is data about the user's online activities. The server evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases and decreases. The output is a report containing the results of the analysis of the user's behavioral history.

[1059] Step 8:

[1060] The server sends the generated report to the user. The input is a report containing the analysis results of the behavioral history. The report is sent to the user's email address or made available for viewing within the app. The output is the report sent to the user.

[1061] 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.

[1062] 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.

[1063] 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.

[1064] [Fourth embodiment]

[1065] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1066] 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.

[1067] 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).

[1068] 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.

[1069] 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.

[1070] 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).

[1071] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1072] 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.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] 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.

[1077] 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."

[1078] This system collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback.

[1079] System configuration

[1080] The system consists of the following components:

[1081] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history.

[1082] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[1083] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[1084] Program processing flow

[1085] 1. Information gathering

[1086] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and then analyzed.

[1087] 2. Text Analysis

[1088] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API), tokenizing and morphologically analyzing the text data, and calculating a sentiment score for each word or phrase.

[1089] 3. Determining the degree of negativity

[1090] The server aggregates the emotion scores obtained from the text data and calculates a negativity score. If this score exceeds a pre-set threshold, the server proceeds to the next step.

[1091] 4. Generating Warning Messages

[1092] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes the offending text and a message encouraging people to stay calm.

[1093] The generated warning messages are sent to the user's device in real time via pop-up notifications, email notifications, and in-app notifications.

[1094] 5. Analysis and reporting of behavioral history

[1095] The server collects and periodically analyzes user behavior history, compiling a report on the frequency, patterns, and changes in negative behavior for each month.

[1096] The generated report is either sent to the user's email address or made available in a viewable format within the app.

[1097] Specific examples

[1098] Example 1: Receiving negative email

[1099] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[1100] Example 2: Posting to social media

[1101] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[1102] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[1103] The processing flow will be explained below.

[1104] Step 1:

[1105] The server sets up APIs or web hooks for each communication tool to automatically retrieve data on messages and emails received by users. The data is temporarily stored in the server's storage and prepared for analysis.

[1106] Step 2:

[1107] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[1108] Step 3:

[1109] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[1110] Step 4:

[1111] If the negativity score exceeds a threshold, the server generates a warning message for the user, including a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[1112] Step 5:

[1113] The server generates and sends the generated warning message in real time to the user's device, which receives it and displays it to the user, via a pop-up notification, email notification, or in-app notification.

[1114] Step 6:

[1115] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[1116] Step 7:

[1117] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[1118] Step 8:

[1119] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[1120] Example 1

[1121] 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."

[1122] In modern society, people receive and send a huge amount of information every day through various communication tools such as email, social media, and messaging apps. Some of this information may provoke negative emotions and aggressive behavior, raising concerns that such information may have a negative impact on people's mental health. Furthermore, the transmission of such content increases online conflicts and troubles, so measures to prevent this are necessary. Furthermore, there is a need for a system that provides feedback based on users' behavioral history to encourage long-term behavioral improvement.

[1123] 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.

[1124] In this invention, the server includes means for acquiring data from multiple communication methods, means for analyzing text data using natural language processing, means for calculating an emotion score from the analyzed text data, means for determining a negativity score, means for generating and sending a warning message based on the negativity score, and means for collecting and analyzing user behavioral history and generating periodic reports. This allows users to respond calmly to negative information, prevent aggressive emotions from being expressed, maintain their mental health, and reduce online conflicts. Furthermore, receiving feedback on behavioral history can lead to long-term behavioral improvements.

[1125] "Multiple means of communication" refers to multiple digital communication tools such as email, social media, and messaging apps.

[1126] "Means of obtaining data" refers to methods of collecting information from multiple communication means using APIs and web hooks.

[1127] "Natural language processing" refers to the technology of analyzing text data and performing sentence structure analysis and emotion scoring.

[1128] "Text data" refers to textual information such as messages and posted content obtained through communication means.

[1129] An "emotion score" refers to a numerical evaluation of the emotion of each word or phrase contained in text data.

[1130] "Negativity score" refers to a numerical evaluation of the degree of negative emotion based on the emotion score of the entire text data.

[1131] A "warning message" refers to a notification sent to the user based on the negativity score, encouraging them to remain calm.

[1132] "Behavioral history" refers to data that records messages sent and received by users through communication means and the system's response to them.

[1133] "Report" refers to a document that summarizes the results of collecting and analyzing user behavior history.

[1134] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system has a series of means for analyzing the received information, determining the degree of negativity, generating and sending a warning message, and analyzing behavioral history and providing feedback. The system is composed of the following elements:

[1135] Server: The central processing unit is used to collect information, analyze text, calculate sentiment scores, determine negativity, generate warning messages, and analyze behavioral history. Specifically, it analyzes text data using natural language processing (NLP) libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API). The server also obtains data from multiple communication tools using APIs and webhooks.

[1136] Terminal: A device used by a user (PC, smartphone, tablet, etc.). These terminals are responsible for receiving notifications and warning messages from the server.

[1137] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[1138] Specifically, the server uses the Gmail API or SNS API to retrieve messages received by the user. This data is temporarily stored in the server's storage, and then a natural language processing library (such as NLTK or spaCy) is used to tokenize the text and perform morphological analysis. A sentiment score is then calculated for each word or phrase. The sentiment scores are then aggregated to calculate a negativity score. If this score exceeds a pre-set threshold, the server generates a warning message. The generated warning message is sent to the user's device in real time. Notification methods include pop-up notifications, email notifications, and in-app notifications.

[1139] In addition, the server collects and periodically analyzes the user's behavioral history. It compiles a report on the frequency, patterns, and changes in negative behaviors for each month. The generated report is sent to the user's email address or made available in a viewable format within the app. This allows users to reflect on their own behavior and make long-term improvements.

[1140] Specific examples

[1141] Example 1: Receiving negative email

[1142] The server retrieves the email received by the user saying "Your suggestions are completely useless" via the Gmail API and analyzes the text using a natural language processing library. In this case, if the phrase "useless" is determined to have a high degree of negativity, the server generates a warning message saying "This email contains negative content. Please respond calmly." The generated message is immediately sent to the user's device as a pop-up notification.

[1143] Example 2: Posting to social media

[1144] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[1145] Prompt Sentence Examples

[1146] "When a user receives an email saying 'Your suggestions are completely useless,' explain how the system analyzes the content and generates a warning message."

[1147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1148] Step 1: Gather information

[1149] The server retrieves the user's incoming messages using APIs and webhooks of multiple communication tools (email, SNS, messaging apps). Specifically, it uses API credentials to send requests to the API endpoints of each communication tool, receives message data in JSON format, and stores it in temporary storage. The input is the API request, and the output is the retrieved message data in JSON format.

[1150] Specific behavior:

[1151] The server sends a request to the Gmail API to retrieve the user's unread emails.

[1152] Analyze the JSON data returned from the API, extract the message body, and temporarily save it.

[1153] Step 2: Text analysis

[1154] The server uses a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API) to analyze the stored text data. It tokenizes the text data and performs morphological analysis. It then calculates a sentiment score for each word or phrase. The input is the text data stored in temporary storage, and the output is the tokenized text with a sentiment score.

[1155] Specific behavior:

[1156] The server tokenizes the saved email body using the spaCy library.

[1157] A sentiment score is calculated for each phrase, such as "useless," and assigned to each token.

[1158] Step 3: Determine the degree of negativity

[1159] The server aggregates a negativity score based on the emotion scores obtained from the analyzed text data. If the negativity score exceeds a preset threshold, the process proceeds to the next step. The input is the text data with the emotion scores assigned, and the output is an overall negativity score.

[1160] Specific behavior:

[1161] The server aggregates the negative emotion scores for each token to calculate an overall negativity score.

[1162] If the configured threshold (e.g. 70) is exceeded, proceed to generate a warning message.

[1163] Step 4: Generate a warning message

[1164] The server generates a corresponding warning message when the negativity score exceeds a threshold. The message contains the problematic text and a message encouraging the user to remain calm. The generated warning message is sent to the user's device in real time. The input is the overall negativity score and the text data, and the output is the warning message.

[1165] Specific behavior:

[1166] The server generates a warning message saying, "This email contains negative content. Please stay calm."

[1167] The generated message is sent to the device using Firebase Cloud Messaging.

[1168] Step 5: Analyze and report behavioral history

[1169] The server collects user behavior history and periodically analyzes it. It compiles a report on the frequency and patterns of negative behavior for each month and provides feedback to the user. The input is behavior history data, and the output is a report.

[1170] Specific behavior:

[1171] The server retrieves the warning message generation history for the past month from the database.

[1172] The data is analyzed to generate statistics such as "how many negative emails were received per month."

[1173] The report will be created in PDF format and sent to the user's email address.

[1174] By taking these steps, users can calmly respond to negative information, maintain their mental health, and hopefully lead to long-term behavioral improvements.

[1175] (Application example 1)

[1176] 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."

[1177] In today's world, while online communication is becoming more common, negative emotions and aggressive behavior are becoming a problem. Particularly on social media and messaging apps, users can unintentionally send offensive messages or receive negative messages from others, causing psychological damage. This can damage users' mental health and make them more susceptible to online trouble.

[1178] 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.

[1179] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for analyzing the user's behavior history and generating periodic reports, and a means for analyzing messages in real time and immediately displaying a warning message. This makes it possible to immediately display a warning when a user sends or receives a negative message, encouraging the user to respond calmly.

[1180] "Information collection means" refers to the function of obtaining message data from various communication tools used by users (email, SNS, messaging apps, etc.) via API or web hooks.

[1181] "Natural language processing" is a technology in which a computer program analyzes human language, and is a process that involves tokenizing text data, analyzing sentence structure, and scoring sentiment.

[1182] A "negativity score" is a numerical representation of the emotional negativity of words and phrases in text data.

[1183] A "warning message" is a notification sent to a user when the negativity score exceeds a certain threshold, and includes a message encouraging the user to remain calm.

[1184] "User behavior history" refers to data that records the messages sent and received by the user and the emotional scores at that time.

[1185] "Means for analyzing messages in real time and immediately displaying a warning message" refers to a function that immediately analyzes messages when they are sent or received, and immediately warns the user if they contain negative content.

[1186] "Server" refers to the central processing unit that aggregates and analyzes information, calculates negativity scores, and generates warning messages.

[1187] This invention is a system that collects information from various communication tools used by users (email, social media, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system consists of the following elements:

[1188] System configuration

[1189] 1. Server

[1190] The server is a central processing unit that collects information, analyzes text, determines the degree of negativity, generates warning messages, and analyzes behavioral history. This server can also be deployed on cloud services (e.g., AWS, Google Cloud).

[1191] 2. Terminal

[1192] A terminal is a device used by a user, typically a PC, smartphone, tablet, etc. An application is installed on the terminal to receive notifications and warning messages from the server.

[1193] 3. Users

[1194] Users are people who use the system, such as individuals, employees, and students.

[1195] Hardware and software used

[1196] Hardware

[1197] Servers (virtual machines on cloud services, physical servers)

[1198] Devices (PC, smartphone, tablet)

[1199] software

[1200] Natural language processing libraries (e.g., NLTK, spaCy, Google Cloud Natural Language API)

[1201] Database (e.g. MySQL, PostgreSQL)

[1202] API clients (e.g., requests library)

[1203] Server frameworks (e.g., Flask, Django)

[1204] Data processing and calculation

[1205] 1. Information gathering

[1206] The server retrieves messages received by users using the API or web hooks of each communication tool. This data is temporarily stored in the server's storage.

[1207] 2. Text Analysis

[1208] The server analyzes the stored text data using natural language processing (NLP) libraries, tokenizing the text data, analyzing sentence structure, and calculating sentiment scores for each word and phrase.

[1209] 3. Determining the degree of negativity

[1210] The server aggregates the sentiment scores obtained from the text data, calculates a negativity score, and generates a warning message if the score exceeds a pre-set threshold.

[1211] 4. Generating and sending warning messages

[1212] If the negativity score exceeds the threshold, the server generates a corresponding warning message containing the problematic text and a message encouraging users to stay calm. The generated warning message is sent to the user's device in real time.

[1213] 5. Analysis and reporting of behavioral history

[1214] The server collects and periodically analyzes the user's behavioral history, compiling a report detailing the frequency, patterns, and changes in negative behaviors for each month. This report is sent to the user's email address or made available in a viewable format within the app.

[1215] Specific examples

[1216] Example 1: Receiving negative email

[1217] The server retrieves emails received by users via an API. For example, it saves the text "Your suggestions are completely useless." It then analyzes this text using a natural language processing library to evaluate the sentiment score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[1218] Example 2: Posting to social media

[1219] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. If the phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The generated message is immediately sent to the user's device as a pop-up notification.

[1220] Prompt Sentence Examples

[1221] "Write Python code that uses natural language processing to parse negative content from messages received by users and generate a warning message. Use the Google Cloud Natural Language API."

[1222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1223] Step 1:

[1224] The server retrieves the user's received messages using the API or webhook of each communication tool (email, SNS, messaging app, etc.). Specifically, it sends an HTTP request to the API endpoint and temporarily stores the returned JSON-formatted message data in storage. The input is the API endpoint of each communication tool and the user's authentication information, and the output is the retrieved message data.

[1225] Step 2:

[1226] The server analyzes the message data stored in storage using a natural language processing (NLP) library. Specifically, it tokenizes the text data, analyzes the sentence structure, and calculates the sentiment score for each word and phrase. The NLP libraries used are NLTK, spaCy, and Google Cloud Natural Language API. The input is the message text read from storage, and the output is the sentiment score for each message.

[1227] Step 3:

[1228] The server determines the negativity score based on the analyzed sentiment score. Specifically, it aggregates the text analysis results and calculates an overall negativity score for each message. If the score exceeds a preset threshold, it proceeds to the next step. The input is the text analysis result (sentiment score), and the output is the negativity score.

[1229] Step 4:

[1230] If the negativity score exceeds a threshold, the server generates a corresponding warning message. Specifically, the server creates a warning message that includes text containing negative content as well as a message encouraging users to stay calm. The input is the negativity score, and the output is the warning message.

[1231] Step 5:

[1232] The server sends the generated warning message to the user's device in real time. Specifically, it sends a pop-up notification or an in-app notification to the target user's device. The input is the warning message, and the output is the warning notification displayed on the user's device.

[1233] Step 6:

[1234] The server periodically collects and analyzes the user's behavioral history and generates a monthly report. Specifically, it analyzes the frequency and patterns of negative behavior each month and aggregates them to create a report. The report is sent to the user's email address or provided in a format that can be viewed within the app. The input is past behavioral history data, and the output is a report summarizing the analysis results.

[1235] 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.

[1236] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results.

[1237] System configuration

[1238] The system consists of the following components:

[1239] Server: As the central processing unit, it collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[1240] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[1241] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[1242] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[1243] Program processing flow

[1244] 1. Information gathering

[1245] The server retrieves messages received by users using the APIs or web hooks of each communication tool (email, SNS, messaging app). This data is temporarily stored in the server's storage and prepared for analysis.

[1246] 2. Emotion recognition

[1247] The device captures the user's voice input, facial recognition, or biometric data and sends it to the emotion engine.

[1248] The emotion engine analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[1249] 3. Text Analysis

[1250] The server analyzes the stored text data using natural language processing (NLP) libraries. Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning each phrase a score of positivity or negativity.

[1251] 4. Determining the degree of negativity

[1252] The server aggregates the negativity scores for each analyzed phrase, calculates an overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-defined threshold.

[1253] The server then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may adjust the warning threshold lower.

[1254] 5. Generating Warning Messages

[1255] If the negativity score exceeds a threshold, the server generates a corresponding warning message, which includes a snippet of the offending text and a statement such as "This message contains negative content. Please remain calm."

[1256] Data from the emotion engine is used to customize the content and presentation of warning messages, for example, if the user is depressed, a more gentle tone of message will be displayed.

[1257] 6. Sending warning messages

[1258] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[1259] 7. Analysis of user behavior history

[1260] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[1261] 8. Submitting the report

[1262] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[1263] Specific examples

[1264] Example 1: Receiving negative email

[1265] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[1266] Example 2: Posting to social media

[1267] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[1268] This allows users to respond calmly to negative information and prevent aggressive feelings. The system aims to maintain users' mental health and reduce online conflicts.

[1269] The processing flow will be explained below.

[1270] Step 1:

[1271] The server sets up APIs or web hooks for each communication tool (email, SNS, messaging app) and automatically retrieves data on messages and emails received by users. The retrieved data is temporarily stored in the server's storage.

[1272] Step 2:

[1273] The device captures the user's voice input, facial expression data, or biometric data, thereby collecting the user's current emotions in real time.

[1274] Step 3:

[1275] The emotion engine analyzes the received voice input, facial expression data, or biometric data to determine the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.), and sends the determination result to the server.

[1276] Step 4:

[1277] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., NLTK, spaCy, Google Cloud Natural Language API), tokenizing the text data, performing morphological analysis, identifying each word and phrase, and assigning a sentiment score.

[1278] Step 5:

[1279] The server then aggregates the negativity scores for each analyzed phrase to calculate an overall negativity score. It then adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. For example, if the user is already in a high stress state, the server may lower the warning threshold.

[1280] Step 6:

[1281] If the negativity score exceeds a threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a statement such as "This message contains negative content. Please remain calm." The server also customizes the content and presentation of the warning message based on data from the emotion engine (e.g., if the user is depressed, a more gentle tone may be used).

[1282] Step 7:

[1283] The server generates and sends the generated warning message in real time to the user's device, either as a pop-up notification, email notification, or in-app notification, which is then received and displayed to the user.

[1284] Step 8:

[1285] Users can check the warning message notification, calmly reevaluate the content of the message they received, and in some cases, postpone replying or responding to the message to prevent a chain reaction of negative emotions.

[1286] Step 9:

[1287] The server periodically collects and analyzes user behavior history, and based on this data, evaluates the frequency and trends of negative behaviors each month and creates a report detailing positive changes and increases or decreases in negative behaviors.

[1288] Step 10:

[1289] The server will then send the generated report to the user's email address or make it available within the app, allowing the user to review their actions and receive feedback to make any necessary improvements.

[1290] Example 2

[1291] 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."

[1292] In recent years, while communication over the Internet has increased, negative emotions and aggressive comments have become a problem. This increases the risk of harming users' mental health and makes it difficult to maintain healthy online communities. Conventional systems have had difficulty recognizing users' emotions in real time, detecting negative content, and issuing warnings. In particular, flexible responses that reflect the user's current emotional state are required.

[1293] 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.

[1294] In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, a means for determining a negativity score, a means for generating and sending a warning message to the user, a means for recognizing the user's emotions and correcting the analysis results, and a means for analyzing the user's behavior history and generating periodic reports, thereby making it possible to maintain the user's mental health and prevent negative emotions and aggressive behavior online.

[1295] An "information collection means" is a device or system that acquires data from multiple communication means used by a user.

[1296] "Means for analyzing text data using natural language processing" refers to a device or system that processes language data and analyzes its content and sentiment.

[1297] The "means for determining the negativity score" is a device or system that quantifies and determines the degree of negative emotion in text data.

[1298] "Means for generating and sending a warning message to a user" refers to a device or system that creates a warning message and notifies a user when a message containing negative content is detected.

[1299] The "means for recognizing the user's emotions and correcting the analysis results" refers to a device or system that analyzes the user's voice input and facial expression data and corrects the analysis results based on the user's current emotional state.

[1300] "Means for analyzing user behavior history and generating periodic reports" refers to a device or system that collects and analyzes a user's communication history and generates periodic reports.

[1301] This invention relates to a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. The system also incorporates an emotion engine that recognizes the user's emotions, and has the ability to determine the user's emotions in real time and correct the analysis results. The system consists of the following elements:

[1302] System Components

[1303] 1. Server: The central processing unit collects information, analyzes text, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history. Specifically, it collects information using the Gmail API and SNS APIs (e.g., Twitter API), and performs text analysis using natural language processing (NLP) libraries (e.g., Python's NLTK or spaCy).

[1304] 2. Device: The device used by the user, typically a PC, smartphone, or tablet. The device receives warning messages from the server and notifies the user. It also has the function of sending the user's voice and facial expression data to the emotion engine.

[1305] 3. Emotion Engine: Analyzes the user's voice input, facial recognition, or biometric data to determine the user's current emotion in real time. This is done using data collected by the camera and microphone on the user's smartphone.

[1306] Example of system operation

[1307] Example 1: Receiving negative email

[1308] The server uses the Gmail API to retrieve emails received by the user. For example, if an email containing the phrase "Your suggestions are completely useless" is received, the text is temporarily stored in the server's database. The device captures the user's facial expressions using the camera and analyzes them with an emotion engine. If the emotion engine determines that the user is already in a state of high stress, the server analyzes the text with a natural language processing library and assigns a high negativity score to the phrase "useless." If this score exceeds a pre-set threshold, a warning message is generated stating, "This email contains negative content. Please remain calm," and is sent to the user's device in real time as a pop-up notification.

[1309] Example 2: Suppressing offensive posts on social media

[1310] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media. This text data is immediately sent to the server. The server analyzes the received text and calculates an emotion score. At the same time, the emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated saying "This content is offensive. Please check again before sending," and is sent as a pop-up notification to the user's device.

[1311] Prompt Sentence Examples

[1312] >(Prompt example)

[1313] "The server extracts specific phrases from emails received by users and calculates an emotion score. If the phrase has a high negative impact, it generates a warning message and sends it to the user's device."

[1314] Hardware and Software

[1315] Hardware: User devices such as computers, smartphones, and tablets.

[1316] Software: Gmail API, Twitter API, Natural Language Processing libraries (NLTK, spaCy), Sentiment Engine.

[1317] As described above, the present invention is a system that can prevent negative emotions and aggressive behavior and maintain the user's mental health by collecting and analyzing information from the user's various communication tools.

[1318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1319] Step 1: Gather information

[1320] The server retrieves the user's received messages using APIs and webhooks of various communication tools (email, SNS, messaging apps). This data is temporarily stored in the server's storage. Specifically, the server retrieves the latest emails from the user's inbox using the Gmail API and collects user messages using SNS APIs (e.g., Twitter API).

[1321] Input: Message data from the Gmail API and SNS API.

[1322] Output: Text data saved in the server storage.

[1323] Step 2: Emotion Recognition

[1324] The device captures the user's voice input and facial expression recognition data through a camera and microphone. This data is sent to the emotion engine, which determines the user's current emotion in real time. Specifically, an application installed on the device takes a picture of the user's face with the smartphone camera and transmits the facial expression data in real time. At the same time, the voice input is also analyzed using the microphone.

[1325] Input: User's voice and facial expression data.

[1326] Output: The user's emotional state according to the emotion engine.

[1327] Step 3: Text analysis

[1328] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. It then performs sentiment scoring and assigns a score of positivity or negativity to each phrase.

[1329] Input: Text data stored on the server.

[1330] Output: Sentiment score for each phrase.

[1331] Step 4: Determine the degree of negativity

[1332] The server aggregates the negativity scores for each analyzed phrase and calculates an overall negativity score. It then determines whether this score exceeds a preset threshold. Specifically, it assigns a high negativity score to phrases such as "useless," and adds up the scores of other negative phrases to calculate the overall negativity score.

[1333] Input: Sentiment score from text analysis.

[1334] Output: Overall negativity score and judgment result.

[1335] Step 5: Emotion Data Correction

[1336] The server adjusts the negativity score based on the user's current emotional data obtained from the emotion engine. Specifically, if the user is in a high stress state, the server lowers the warning threshold and changes the settings to issue more sensitive warnings than usual.

[1337] Input: The user's emotional state according to the emotion engine.

[1338] Output: Corrected negativity score.

[1339] Step 6: Generate a warning message

[1340] If the negativity score exceeds the threshold, the server generates a corresponding warning message. The warning message includes a portion of the problematic text and a warning statement. Specifically, the server generates a message saying, "This email contains negative content. Please respond calmly." and saves it along with the text.

[1341] Input: Corrected negativity score.

[1342] Output: A warning message.

[1343] Step 7: Sending a warning message

[1344] The server sends the generated warning message to the user's device in real time. The device then notifies the user. Specifically, the server sends the message as a push notification, and a pop-up notification appears on the device.

[1345] Input: Warning message.

[1346] Output: A popup notification on the user's device.

[1347] Step 8: Analyzing behavioral history

[1348] The server periodically collects and analyzes user behavior history and creates a monthly report, which compiles the frequency of negative messages sent by users and the negativity score of each message.

[1349] Input: The user's communication history.

[1350] Output: Monthly report.

[1351] Step 9: Submit your report

[1352] The server will then send the generated report to the user's email address or make it available for viewing within the app. Specifically, the server will generate a monthly report in PDF format and send it to the user's email address or make it available for viewing on a dedicated dashboard within the app.

[1353] Enter: Monthly report.

[1354] Output: Send monthly report to user (either email or in-app).

[1355] (Application example 2)

[1356] 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."

[1357] In recent years, with the spread of online communication tools, users are increasingly receiving a large number of messages. Consequently, the stress and psychological burden caused by messages containing negative or offensive content have become a problem. Furthermore, in order to properly process these messages, the user's emotional state must also be taken into consideration. However, current technology does not provide a system that can detect negative content in online communications in real time and issue appropriate warnings that take the user's emotional state into account. Therefore, there is a need for technology that can prevent negative online interactions and maintain users' mental health.

[1358] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an information collection means, a means for analyzing text data using natural language processing, and a means for determining a negativity score. This makes it possible to collect information from various communication tools used by users and detect content that may cause negative emotions or aggressive behavior in real time.

[1359] The system further includes a means for generating and sending a warning message to the user, a means for recognizing the user's emotional state in real time, and a means for analyzing the user's behavioral history and generating periodic reports. This allows the system to generate appropriate warning messages by adjusting the warning threshold if the user is already in a high stress state. Furthermore, by analyzing the user's behavioral history, the system can evaluate positive changes and negative increases and decreases and provide feedback to the user.

[1360] "Information collection means" refers to functions for collecting information from various communication tools (email, SNS, messaging apps, etc.).

[1361] "Means for analyzing text data using natural language processing" refers to a technology for analyzing acquired text data and understanding its contents.

[1362] The "means for determining negativity score" is a function for calculating and evaluating the positivity and negativity scores for the analyzed text data.

[1363] The "means for generating and sending a warning message to the user" is a function for generating and sending an appropriate warning message to the user when the negativity score exceeds a threshold.

[1364] "Means for analyzing user behavior history and generating periodic reports" refers to a function for collecting and analyzing data on users' online activities and reporting their behavior history.

[1365] "Means for recognizing the user's emotional state in real time" refers to a function that analyzes the user's current emotions in real time using the user's voice input, facial expression recognition, biometric data, etc.

[1366] This invention is a system that collects information from various communication tools used by users (email, SNS, messaging apps, etc.), detects content that may trigger negative emotions or aggressive behavior, and issues a warning to the user. This system can be implemented in the following way.

[1367] System configuration

[1368] The system consists of the following components:

[1369] Server: As the central processing unit, it collects and analyzes information, determines the degree of negativity, generates and sends warning messages, and analyzes behavioral history.

[1370] Device: The device used by the user, usually a PC, smartphone, or tablet, that receives notifications and warning messages from the server.

[1371] User: A person who uses the system. This mainly applies to individuals, employees, students, etc.

[1372] Emotion Engine: Recognizes the user's current emotion in real time using the user's voice input, facial recognition, or biometric data.

[1373] System Operation

[1374] Information gathering

[1375] The server retrieves the user's incoming messages using the API or web hook of each communication tool (email, SNS, messaging app) and temporarily stores them in the server's storage.

[1376] emotion recognition

[1377] The device captures the user's voice input, facial expression recognition, or biometric data (e.g., heart rate data) and sends it to the emotion engine, which analyzes the received data and determines the user's current emotion (e.g., joy, anger, sadness, surprise, etc.) in real time.

[1378] Text analytics

[1379] The server analyzes the stored text data using a natural language processing (NLP) library (e.g., Python's NLTK or spaCy). Specifically, it tokenizes the text data, performs morphological analysis, and identifies each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase.

[1380] Determining the degree of negativity

[1381] The server aggregates the negativity scores for each analyzed phrase, calculates the overall negativity score from the analysis results according to specific scoring rules, and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's current emotional data obtained from the emotion engine.

[1382] Generate and send warning messages

[1383] If the negativity score exceeds a threshold, the server generates an appropriate warning message. For example, it generates a message that reads, "This message contains negative content. Please respond calmly." The content and display method of the warning message are customized based on data from the emotion engine. The generated warning message is sent to the user's device in real time as a pop-up notification.

[1384] Analyzing user behavior history and sending reports

[1385] The server periodically collects and analyzes the user's behavioral history. Based on this data, it evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases or decreases. The generated report is sent to the user's email address or made available for viewing within the app.

[1386] Specific examples

[1387] Example 1: Receiving negative email

[1388] The server retrieves emails received by the user via an API. For example, it saves the text "Your suggestions are completely useless." The device analyzes the user's facial expressions with an emotion engine and recognizes that the user is already in a stressed state. The device then analyzes this text with a natural language processing library and evaluates the emotion score of the phrase "useless." If this phrase is assigned a high degree of negativity and exceeds a threshold, a warning message is generated stating, "This email contains negative content. Please respond calmly." This message is immediately sent to the user's device as a pop-up notification.

[1389] Example 2: Posting to social media

[1390] The device captures the text "I don't want to hear your opinion" that the user is about to post on social media and sends it to the server. The server analyzes the received text and calculates an emotion score. The emotion engine analyzes the user's voice input and determines whether the user is in an excited state. If this phrase has a high degree of negativity and exceeds the threshold, a warning message is generated stating "This content is offensive. Please check again before sending." The tone of the message is adjusted according to the user's emotional state. The generated message is immediately sent to the user's device as a pop-up notification.

[1391] Prompt Sentence Examples

[1392] "Calculate the sentiment score for the following message: Your suggestion is completely useless."

[1393] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1394] Step 1:

[1395] The server receives messages received by users through the API or webhook of each communication tool. The input is the message data obtained from the API endpoint. The server temporarily stores this message data in storage, preparing the text data to be analyzed.

[1396] Step 2:

[1397] The device captures the user's voice input, facial recognition, or biometric data. The inputs include real-time user voice data, camera facial recognition data, and heart rate data. The device sends this data to the server. The emotion engine analyzes the received data and determines the user's current emotional state (e.g., joy, anger, sadness, surprise, etc.) in real time. The output is data indicating the user's emotional state.

[1398] Step 3:

[1399] The server analyzes the stored text data. The input is the message data stored in temporary storage. The server uses a natural language processing (NLP) library (e.g., Python's NLTK or spaCy) to tokenize the text data and perform morphological analysis to identify each word and phrase. Next, it performs sentiment scoring, assigning a score of positivity or negativity to each phrase. The output is the analysis results, including the sentiment score for each message.

[1400] Step 4:

[1401] The server aggregates the negativity scores for each analyzed phrase. The input is the sentiment score obtained in step 3. The server calculates the overall negativity according to specific scoring rules and determines whether this score exceeds a pre-set threshold. It also adjusts the negativity score based on the user's emotional state data obtained in step 2. The output is the final negativity score.

[1402] Step 5:

[1403] The server generates a warning message if the negativity score exceeds a threshold. The input is the final negativity score and the user's emotional state data from the emotion engine. The server generates a warning message, for example, "This message contains negative content. Please respond calmly." If the user is depressed, the server adjusts the tone of the message to be displayed to be gentler. The output is the warning message.

[1404] Step 6:

[1405] The server sends the generated warning message to the user's terminal. The input is the generated warning message. The terminal displays it to the user as a popup notification. The output is the warning message displayed on the user's terminal.

[1406] Step 7:

[1407] The server periodically collects and analyzes the user's behavioral history. The input is data about the user's online activities. The server evaluates the frequency and trends of negative behaviors and creates a report detailing positive changes and negative increases and decreases. The output is a report containing the results of the analysis of the user's behavioral history.

[1408] Step 8:

[1409] The server sends the generated report to the user. The input is a report containing the analysis results of the behavioral history. The report is sent to the user's email address or made available for viewing within the app. The output is the report sent to the user.

[1410] 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.

[1411] 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.

[1412] 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.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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).

[1417] 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.

[1418] 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."

[1419] 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.

[1420] 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).

[1421] 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.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] The following is further disclosed regarding the above embodiment.

[1432] (Claim 1)

[1433] Information gathering means;

[1434] means for analyzing text data using natural language processing;

[1435] a means for determining a negativity score;

[1436] means for generating and sending a warning message to a user;

[1437] A means for analyzing user behavior history and generating periodic reports;

[1438] A system including:

[1439] (Claim 2)

[1440] The system of claim 1, wherein the information collection means utilizes APIs or web hooks of multiple communication tools.

[1441] (Claim 3)

[1442] 10. The system of claim 1, wherein the means for analyzing the text data using natural language processing performs sentence structure analysis and sentiment scoring.

[1443] "Example 1"

[1444] (Claim 1)

[1445] a means for acquiring data of a plurality of communication means;

[1446] means for analyzing text data using natural language processing;

[1447] means for calculating an emotion score from the analyzed text data;

[1448] a means for determining a negativity score;

[1449] means for generating and transmitting a warning message based on the negativity score;

[1450] A means of collecting and analyzing user behavior history and generating periodic reports;

[1451] A system including:

[1452] (Claim 2)

[1453] 10. The system of claim 1, wherein the plurality of communication means utilizes APIs or web hooks of the plurality of communication tools.

[1454] (Claim 3)

[1455] 10. The system of claim 1, wherein the means for analyzing the text data using natural language processing performs sentence structure analysis and sentiment scoring.

[1456] "Application Example 1"

[1457] (Claim 1)

[1458] Information gathering means;

[1459] means for analyzing text data using natural language processing;

[1460] a means for determining a negativity score;

[1461] means for generating and sending a warning message to a user;

[1462] A means for analyzing user behavior history and generating periodic reports;

[1463] A means of analyzing messages in real time and displaying warning messages immediately;

[1464] A system including:

[1465] (Claim 2)

[1466] The system of claim 1, wherein the information collection means utilizes APIs or web hooks of multiple communication tools.

[1467] (Claim 3)

[1468] 10. The system of claim 1, wherein the means for analyzing the text data using natural language processing performs sentence structure analysis and sentiment scoring.

[1469] "Example 2: Combining Emotion Engines"

[1470] (Claim 1)

[1471] Information gathering means;

[1472] means for analyzing text data using natural language processing;

[1473] a means for determining a negativity score;

[1474] means for generating and sending a warning message to a user;

[1475] A means of recognizing user emotions and correcting the analysis results;

[1476] A means for analyzing user behavior history and generating periodic reports;

[1477] A system including:

[1478] (Claim 2)

[1479] 10. The system of claim 1, wherein the information collection means utilizes APIs or web hooks of multiple communication means.

[1480] (Claim 3)

[1481] 2. The system of claim 1, wherein the means for analyzing text data using natural language processing performs sentence structure analysis and sentiment scoring to calculate and correct negativity scores.

[1482] "Application example 2 when combining emotion engines"

[1483] (Claim 1)

[1484] Information gathering means;

[1485] means for analyzing text data using natural language processing;

[1486] a means for determining a negativity score;

[1487] means for generating and sending a warning message to a user;

[1488] a means for recognizing the user's emotional state in real time;

[1489] A means for analyzing user behavior history and generating periodic reports;

[1490] A system including:

[1491] (Claim 2)

[1492] The system of claim 1, wherein the information collection means utilizes APIs or web hooks of multiple communication tools.

[1493] (Claim 3)

[1494] 10. The system of claim 1, wherein the means for analyzing the text data using natural language processing performs sentence structure analysis and sentiment scoring. [Explanation of symbols]

[1495] 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. Information gathering means; means for analyzing text data using natural language processing; a means for determining a negativity score; means for generating and sending a warning message to a user; A means for analyzing user behavior history and generating periodic reports; A system including:

2. The system of claim 1 , wherein the information collection means utilizes APIs or web hooks of multiple communication tools.

3. The system of claim 1 , wherein the means for analyzing the text data using natural language processing performs sentence structure analysis and sentiment scoring.

Images