system

Abstract

We provide the system. [Solution] An interactive interface for users to input questions and tasks, A method for analyzing input text using a natural language processing engine and extracting context, sentiment, and keywords, A means including a trained AI model for generating relevant open-end questions based on extracted information, A means of returning the generated question to the user, It provides an interface for users to answer questions returned by others, and a means to support continuous dialogue. A system that includes this.

Description

Technical Field

[0005]

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional communication support systems, one-way questions and information provision are mainly used, and there is a lack of an interactive interface for delving into specific problems and considerations of users. Therefore, sufficient support for users to comprehensively understand their own problems and find solutions has not been provided. Also, regarding the mental health care of users, it has been difficult to provide appropriate support. There is a need for a system that solves these problems and enables users to delve into their own problems to improve work efficiency and mental health.

Means for Solving the Problems

[0005] This invention provides an interactive interface for users to input questions and tasks. A server uses a natural language processing engine to analyze the input text, extracting context, sentiment, and keywords. Based on this extracted information, a trained AI model generates appropriate open-ended questions. These questions are returned to the user, who is then provided with an interface to answer them. Through this ongoing interaction, users can gain a multifaceted perspective on their challenges and discover new viewpoints and solutions. Furthermore, for mental support, the system includes a function to analyze input related to the user's mental state and generate appropriate questions. This makes it possible to improve the user's work efficiency and mental well-being.

[0006] An "interactive interface" is a user interface that allows users to input information and communicate with the system in a two-way manner.

[0007] A "natural language processing engine" is a software function that analyzes text data entered by a user and extracts context, sentiment, and keywords.

[0008] A "trained AI model" is an artificial intelligence model that is trained using past data and examples to make appropriate judgments and predictions.

[0009] An "open-ended question" is a type of question that asks users for detailed explanations or opinions rather than simple answers such as "yes" or "no."

[0010] A "server" is a computer system that receives input from a user interface and performs appropriate processing using a natural language processing engine and AI models.

[0011] A "user" is an individual or end-user who accesses a system through an interactive interface and provides input or responses.

[0012] "Mental support" is a function that analyzes the user's mental state and provides support and assistance for its improvement.

[0013] "Text analysis" is the process of breaking down text entered by a user into its constituent elements and extracting context, sentiment, and keywords.

[0014] "Question generation" is the process of creating appropriate open-ended questions based on user input using a pre-trained AI model.

[0015] "Continuous dialogue" is a process in which the system interacts with the user multiple times to delve deeper into the user's thoughts and concerns. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

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

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

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0037] The system related to this invention is based on an interactive interface that allows users to delve deeper into their own challenges and problems. The system generates appropriate open-ended questions in response to the questions and challenges entered by the user, enabling continuous dialogue. It also includes functions to provide mental support.

[0038] Specific implementations of the system

[0039] 1. User Interface

[0040] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[0041] 2. Receiving user input

[0042] The terminal retrieves text data entered by the user and sends it to the server.

[0043] 3. Server Initialization

[0044] The server receives text data sent by the user and uses a natural language processing engine (NLP) to analyze the text. Specifically, it extracts context, sentiment, and keywords.

[0045] 4. Question generation using AI models

[0046] The server inputs the data into a pre-trained AI model based on the analyzed information. The AI ​​model generates multiple open-ended questions and selects the most appropriate one from among them.

[0047] 5. Returning questions and continuing the dialogue

[0048] The server sends the selected questions back to the user's terminal. The user enters their answers to the received questions, and these answers are sent back to the server, continuing the dialogue. This allows the user to delve deeper into their own issues and gain new perspectives.

[0049] Examples of mental support

[0050] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine to generate open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. Through their responses, users can reflect on their mental state and consider ways to improve it.

[0051] Specific example

[0052] Examples of how to make a project progress smoothly

[0053] User: The project is currently behind schedule. How can we make it proceed more smoothly?

[0054] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[0055] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[0056] Examples of mental support

[0057] User: I've been feeling stressed lately due to project pressure. How can I cope?

[0058] The server analyzes the user's input, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[0059] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0060] This invention's system is expected to be a useful tool for comprehensively understanding and addressing users' specific challenges, and for finding solutions. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[0061] The following describes the processing flow.

[0062] Step 1:

[0063] The user launches a dedicated application or web browser and accesses an interactive interface.

[0064] Step 2:

[0065] Users use an interactive interface to input their questions and issues in text format.

[0066] Step 3:

[0067] The terminal receives text data entered by the user and sends that data to the server.

[0068] Step 4:

[0069] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[0070] Step 5:

[0071] The server inputs the extracted information into a pre-trained AI model. The AI ​​model generates multiple open-ended questions.

[0072] Step 6:

[0073] The server selects the most appropriate question from the open-ended questions generated, based on the context. The selection criteria are based on the content of the user's input text and extracted keywords.

[0074] Step 7:

[0075] The server sends the selected question back to the user's terminal.

[0076] Step 8:

[0077] The terminal displays the received question in an interactive interface.

[0078] Step 9:

[0079] The user reviews the displayed question and enters their answer.

[0080] Step 10:

[0081] The device resends the user's response to the server.

[0082] Step 11:

[0083] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[0084] Step 12:

[0085] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[0086] Step 13:

[0087] Users engage in continuous dialogue through an interactive interface, asking further questions as needed to delve deeper into the problem and discover new perspectives and solutions.

[0088] Step 14:

[0089] The server periodically incorporates new data to train the AI ​​model, improving the accuracy and relevance of the questions it generates.

[0090] (Example 1)

[0091] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] Traditional interactive interfaces often have inefficient processes for users to delve deeper into questions and issues. Furthermore, there are few interactive systems specifically designed for user mental support, making it difficult to adequately assist users' physical and mental well-being. Therefore, there is a need for a system that allows users to thoroughly examine their challenges and problems and resolve them effectively.

[0093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0094] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for providing the user with the opportunity to delve deeper into their tasks and problems; and means for analyzing stress and pressure-related issues and generating questions to support the user's mental state. This enables the user to consider and solve problems from a concrete and multifaceted perspective.

[0095] An "interactive interface" is an interface that allows users to input questions or tasks and engage in two-way interaction with the system.

[0096] A "natural language processing engine" is a software technology that analyzes input text data to extract context, sentiment, keywords, and other relevant information.

[0097] A "trained AI model" is an artificial intelligence model that has been trained to perform a specific task by learning from past data.

[0098] An "open-ended question" is a type of question that encourages users to answer freely and does not restrict them to providing specific answers.

[0099] "Continuous dialogue" is a process in which the user and the system repeatedly exchange questions and answers to reach a deep understanding and solution.

[0100] "Mental support" is a feature designed to provide appropriate assistance and advice to users regarding problems related to stress and pressure.

[0101] "In-depth analysis" is the process of thoroughly exploring the user's challenges and problems to find their root causes and solutions.

[0102] The system related to this invention is based on an interactive interface that allows users to delve deeper into challenges and problems and receive mental support. The following describes how this system is specifically implemented.

[0103] Building a User Interface

[0104] Users access the system using a dedicated application or a web browser. For example, a user enters the system's URL and authenticates on the login screen. Upon successful authentication, an interactive interface is displayed. This interface includes a text input form and a submit button.

[0105] Receiving user input

[0106] The device retrieves text data entered by the user. When the user writes a question or assignment in a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[0107] Initial processing by the server

[0108] The server analyzes the received text data using a natural language processing engine (e.g., IBM Watson® Natural Language Understanding or Google® Cloud Natural Language). During this analysis, context, sentiment, and keywords are extracted. Specifically, the server waits for HTTP requests to be received, and upon receiving a request, it extracts the text data and inputs it into the NLP engine to obtain the analysis results.

[0109] Question generation using AI models

[0110] The server inputs the data into a pre-trained AI model (e.g., GPT-4® or BERT) based on the analyzed information. The analysis results are converted into the AI ​​model's input format and input into the model. The AI ​​model generates multiple open-ended questions and selects the most appropriate one. To return the selected question to the user, the server sends the selected question back as an HTTP response.

[0111] Sending back questions and continuing the dialogue

[0112] The terminal displays questions received from the server to the user. The returned questions are displayed in a text area on the interface, and the user answers them. When the user enters a new answer into the text form and presses the submit button, the terminal sends the text data to the server again. This allows the dialogue to continue, enabling the user to delve deeper into their problem and gain new perspectives.

[0113] Examples of mental support

[0114] Users input mental health issues such as stress and pressure. The input is analyzed by an NLP engine, which generates open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. By answering these questions, users can broaden their perspective on their own mental health and explore concrete solutions.

[0115] Specific example

[0116] Examples of project progress:

[0117] User: "The project is currently behind schedule. How can we make it proceed more smoothly?"

[0118] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[0119] Users can use this question to interview team members and input the results, allowing for further in-depth discussions.

[0120] Examples of mental support:

[0121] User: "I've been feeling stressed lately due to project pressure. How can I cope?"

[0122] The server analyzes the user's input and generates the question, "Have you been able to take time to relax recently?", which it then sends back to the user.

[0123] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0124] Example of a prompt

[0125] Example regarding project progress: "Currently, the project is behind schedule. How can we make it proceed more smoothly?"

[0126] An example of mental support: "I've been feeling stressed lately due to project pressure. How can I cope?"

[0127] This system is a powerful tool for comprehensively understanding users' specific challenges and finding solutions. Furthermore, its mental support function allows users to address their challenges while maintaining their mental and physical health.

[0128] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0129] Program processing steps

[0130] Step 1:

[0131] Users access the system using a dedicated application or web browser. They enter the system's URL and then enter their authentication information on the login screen. This displays an interactive interface.

[0132] Input: System URL, Login credentials

[0133] Output: An interactive interface is displayed.

[0134] Specific actions:

[0135] 1. The user enters the system's URL into their web browser.

[0136] 2. The user enters their username and password on the login screen.

[0137] 3. If authentication is successful, an interactive interface will be displayed.

[0138] Step 2:

[0139] The device retrieves text data entered by the user. When the user enters a question or task into a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[0140] Input: Text data entered by the user (questions or assignments)

[0141] Output: Text data sent to the server as an HTTP request

[0142] Specific actions:

[0143] 1. The user enters a question or task into a text form.

[0144] 2. The user presses the submit button.

[0145] 3. The device retrieves the text data and sends it to the server as an HTTP request.

[0146] Step 3:

[0147] The server analyzes the received text data using a natural language processing (NLP) engine. The server inputs the text data into the NLP engine and obtains analysis results such as context, sentiment, and keywords.

[0148] Input: Text data sent as an HTTP request

[0149] Output: Analyzed context, sentiment, and keyword data

[0150] Specific actions:

[0151] 1. The server receives the HTTP request and extracts the text data.

[0152] 2. Input the text data into the NLP engine (NLP engines to use: IBM Watson Natural Language Understanding or Google Cloud Natural Language).

[0153] 3. Obtain analysis results from the NLP engine to obtain context, emotion, and keyword data.

[0154] Step 4:

[0155] The server inputs the data into a pre-trained AI model based on the analyzed information. The server converts the analysis results into the AI ​​model's input format and inputs them into the model to generate multiple open-ended questions.

[0156] Input: Analyzed context, sentiment, and keyword data

[0157] Output: Multiple open-ended questions generated

[0158] Specific actions:

[0159] 1. Convert the analysis results into an input format for the AI ​​model (AI models to use: GPT-4 or BERT).

[0160] 2. Input the converted data into the AI ​​model.

[0161] 3. The AI ​​model generates multiple open-ended questions.

[0162] Step 5:

[0163] The server selects the most appropriate question from the generated questions and sends it back to the user's terminal. The server then sends the selected question back as an HTTP response.

[0164] Input: Multiple open-ended questions generated

[0165] Output: The most appropriate question selected

[0166] Specific actions:

[0167] 1. Evaluate the generated questions and select the most appropriate one.

[0168] 2. The selected questions are sent back to the user's terminal as an HTTP response.

[0169] Step 6:

[0170] The terminal displays the question received from the server to the user. The user enters an answer to the displayed question and sends it back to the server.

[0171] Input: Question returned from the server

[0172] Output: User-entered response

[0173] Specific actions:

[0174] 1. The terminal receives an HTTP response from the server.

[0175] 2. Display the received question in the interactive interface.

[0176] 3. The user enters their answer to the question and presses the submit button.

[0177] 4. Resubmit your response to the server.

[0178] Step 7:

[0179] The server re-analyzes the user's responses and generates additional questions as needed, allowing the conversation to continue.

[0180] Input: User's response

[0181] Output: Re-analyzed context, sentiment, and keyword data, plus additional questions.

[0182] Specific actions:

[0183] 1. The server receives the user's response and analyzes it again using the NLP engine.

[0184] 2. Create input data for the AI ​​model based on the analysis results.

[0185] 3. The AI ​​model generates additional open-ended questions.

[0186] 4. Select the appropriate questions from among them and resend them to the user.

[0187] Examples of mental support

[0188] Users enter problems related to stress and pressure.

[0189] The server analyzes the input using an NLP engine and generates open-ended questions to support the user's mental state. For example, it might generate questions such as, "Have you had a moment recently where you felt relaxed?"

[0190] In summary, this system is a powerful tool for comprehensively understanding and addressing users' specific challenges. Furthermore, its mental support function allows users to work on problem-solving while maintaining their own mental and physical health.

[0191] (Application Example 1)

[0192] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0193] Conventional conversational systems have the ability to generate appropriate questions based on user input and support continuous dialogue, but specialized applications aimed at improving security awareness have not been sufficiently developed. Furthermore, the lack of feedback functions to support the improvement of user security behavior makes it difficult for users to obtain guidance for taking concrete security actions.

[0194] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0195] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for the AI ​​model to adapt the content of the generated questions based on the user's input in order to enhance security awareness; and means for providing a feedback function to support the improvement of the user's security behavior. This makes it possible to enhance the user's security awareness and provide guidance for specific security actions.

[0196] An "interactive interface" is an interface that allows users to input questions or tasks, enabling continuous dialogue.

[0197] A "natural language processing engine" is an engine that analyzes text data entered by users and extracts context, sentiment, and keywords.

[0198] A "pre-trained AI model" is an algorithm that generates appropriate open-end questions based on previously trained data.

[0199] An "open-ended question" is a type of question in which the user's answer is not limited to a specific set of choices, but can be expressed freely.

[0200] A "feedback function" is a feature that provides specific advice and guidelines for improvement based on the user's input and actions.

[0201] "Security awareness" refers to the knowledge, awareness, and attention that users have to protect their information and assets.

[0202] "Security actions" refer to the specific actions and measures that users actually take to protect information and assets.

[0203] "Analysis" is the process of examining user input data in detail to understand and extract its meaning, emotions, and context.

[0204] The system for implementing this invention is designed as an application for improving security awareness. Users access an interactive interface through a device such as a smartphone or smart glasses. Through this interface, users can input security-related questions or issues and begin interacting with the system.

[0205] System Configuration

[0206] 1. Hardware Configuration

[0207] Devices: Smartphones, smart glasses

[0208] Server: Internet-connected computer system

[0209] Network: Internet

[0210] 2. Software Configuration

[0211] Interactive Interface: A dedicated application is installed on smartphones and smart glasses as the user interface.

[0212] Natural Language Processing Engine (NLP engine): A software engine that performs text analysis.

[0213] Pre-trained AI model: An AI algorithm for generating open-ended questions.

[0214] Processing Overview

[0215] Receiving user input: The terminal receives security-related text data entered by the user and sends it to the server.

[0216] Initial analysis: The server uses a natural language processing engine to analyze the received text data and extract context, sentiment, and keywords.

[0217] Question generation: Based on the analyzed information, the server inputs data into a trained AI model to generate open-end questions designed to enhance security awareness.

[0218] Question return: The generated questions are returned to the user's device, and the user answers them. By repeating this process, the user can gradually increase their security awareness.

[0219] Feedback function: Based on user input and actions, the server generates appropriate feedback and provides users with specific security action guidelines.

[0220] Specific example

[0221] The user launches a smartphone app and enters the question, "I feel like I've been getting a lot of phishing emails lately. How should I deal with them?" The server analyzes this text using a natural language processing engine to extract context, sentiment, and keywords.

[0222] The server then inputs the following prompts into the trained AI model.

[0223] "User question: 'I feel like I've been getting a lot of phishing emails lately. How should I deal with them?' Please generate an open-ended question to raise security awareness in response to this."

[0224] An example of a generated question sent back to the user is, "What information have you recently learned about the characteristics of phishing emails? And how do you apply that knowledge to your daily email checking?" The user then enters their answer to this question, allowing the server to continue further analysis and dialogue.

[0225] This will strengthen users' specific security knowledge and actions, and improve their security awareness.

[0226] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0227] Step 1:

[0228] Receiving user input

[0229] The user uses a smartphone or smart glasses to input questions or tasks into an interactive interface. For example, the user might input the question, "I've been receiving a lot of phishing emails lately. How should I deal with this?" The device receives the input as text data and sends it to the server via the internet.

[0230] Step 2:

[0231] Analysis using a natural language processing engine

[0232] The server inputs the text data received from the user into a natural language processing engine (NLP engine). Here, the NLP engine analyzes the context, sentiment, and keywords of the text to deepen its understanding of the context. This analysis result (context, sentiment, and keywords) is output as a dataset to be used in the next step.

[0233] Step 3:

[0234] Question generation using a pre-trained AI model

[0235] The server inputs data into a trained AI model based on the analysis results of the NLP engine. The AI ​​model generates multiple open-ended questions to raise security awareness and selects the most appropriate question from among them. For example, the AI ​​model might generate the question, "What information have you recently learned about the characteristics of phishing emails?" and the selected question is sent back to the user in the next step.

[0236] Step 4:

[0237] Return of question

[0238] The server sends the generated question back to the user's terminal. The user's terminal displays this question, and the user answers it. Through this interaction, the user continues to input information to gain a deeper understanding.

[0239] Step 5:

[0240] Feedback function

[0241] The device sends new input from the user back to the server, which analyzes this input using an NLP engine and an AI model. The analysis results are generated as specific feedback to improve the user's security behavior. For example, feedback such as, "Learn the characteristics of phishing emails and think about how to apply that knowledge," might be generated. This feedback is sent back to the user's device and displayed again.

[0242] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0243] This invention's system, based on an interactive interface that allows users to delve deeper into their own challenges and problems, combines this with an emotion engine to recognize the user's emotional state and generate more appropriate open-ended questions. This enables users to effectively solve their problems and manage their mental health.

[0244] Specific implementations of the system

[0245] 1. User Interface

[0246] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[0247] 2. Receiving user input

[0248] The terminal retrieves text data entered by the user and sends it to the server.

[0249] 3. Server Initialization

[0250] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[0251] 4. Utilizing the Emotion Engine

[0252] As the server analyzes text data, it utilizes an emotion engine to recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions based on words and context in the input text.

[0253] 5. Question generation using AI models

[0254] The server inputs data into a pre-trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state.

[0255] 6. Selection and submission of questions

[0256] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[0257] 7. Returning questions and continuing the dialogue

[0258] The server sends the selected question back to the user's terminal. The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[0259] Examples of mental support

[0260] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[0261] Specific example

[0262] Examples of how to make a project progress smoothly

[0263] User: The project is currently behind schedule. How can we make it progress more smoothly?

[0264] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[0265] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[0266] Examples of mental support

[0267] User: I've been feeling stressed lately due to project pressure. How can I cope?

[0268] The server analyzes the user's input, recognizes the user's high stress level using an emotion engine, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[0269] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0270] This invention's system is expected to be a useful tool for comprehensively understanding the user's specific challenges and finding solutions based on emotions and context. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[0271] The following describes the processing flow.

[0272] Step 1:

[0273] The user launches a dedicated application or web browser and accesses the interactive interface.

[0274] Step 2:

[0275] The user uses the interactive interface to input their questions and issues in text form.

[0276] Step 3:

[0277] The terminal obtains the text data input by the user and sends the data to the server.

[0278] Step 4:

[0279] The server passes the received text data to a natural language processing (NLP) engine and starts text analysis. Specifically, the NLP engine decomposes the input text and extracts context, sentiment, and keywords.

[0280] Step 5:

[0281] In parallel with text analysis, the server uses a sentiment engine to recognize the user's emotional state (e.g., happiness, anger, sadness, etc.). The sentiment engine uses an algorithm that evaluates sentiment from the words and context in the input text.

[0282] Step 6:

[0283] Based on the extracted context information, sentiment data, and keywords, the server inputs the data into a trained AI model.

[0284] Step 7:

[0285] Using the AI model, the server generates multiple open-ended questions based on the user's context and emotional state.

[0286] Step 8:

[0287] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[0288] Step 9:

[0289] The server sends the selected question back to the user's terminal.

[0290] Step 10:

[0291] The terminal displays the received question in an interactive interface.

[0292] Step 11:

[0293] The user reviews the displayed question and enters their answer.

[0294] Step 12:

[0295] The device resends the user's response to the server.

[0296] Step 13:

[0297] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[0298] Step 14:

[0299] The server saves the extracted information as history, which influences subsequent interactions and generated questions.

[0300] Step 15:

[0301] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[0302] Step 16:

[0303] The user conducts continuous conversations through an interactive interface, enters more questions as needed to delve deeper into the problem, and finds new perspectives and solutions.

[0304] Step 17:

[0305] The server regularly incorporates new data to train the AI model and improve the accuracy and relevance of the generated questions.

[0306] (Example 2)

[0307] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0308] In a conventional interactive system, it was difficult to accurately grasp the user's emotional state and generate appropriate questions accordingly. As a result, it was difficult to continue effective conversations in solving the user's problems and providing mental care support. Also, when the generated questions did not match the context or emotion, there was a problem that the user's satisfaction decreased and the usefulness of the system was impaired.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for evaluating the user's emotional state, means for evaluating the user's emotional state, means for including a trained AI model for generating relevant open-ended questions based on the extracted information and emotional data, and means for selecting the optimal question from the generated questions. This enables the generation and selection of appropriate questions that reflect the user's emotional state.

[0310] The "user" refers to the entity that inputs problems and questions using this system.

[0311] An "interactive interface" is an interface that allows users to input tasks or questions and then answer the generated questions.

[0312] A "natural language processing engine" is a machine learning algorithm that analyzes input text and extracts context, sentiment, and keywords.

[0313] "Context" refers to information that helps us understand the meaning and relevance of the entered text.

[0314] "Emotion" refers to the emotional state (e.g., joy, anger, sadness, etc.) extracted from the user's input text.

[0315] "Keywords" are important words or phrases extracted from the input text.

[0316] A "trained AI model" is artificial intelligence that is trained based on past data and generates questions in response to user input.

[0317] An "emotion recognition engine" is an algorithm that evaluates the emotional state of a user based on their input text.

[0318] "Methods for selecting questions" refer to methods for choosing the question that best fits the context and sentiment from among several generated questions.

[0319] "Means of supporting continuous dialogue" refers to methods that allow users to answer questions returned, analyze those answers again, and continue the dialogue.

[0320] "Mental support" refers to a function that aims to support the user's mental health by analyzing input related to the user's mental state and generating appropriate open-ended questions.

[0321] This invention is a system that recognizes the user's emotional state and generates more appropriate open-end questions by combining an emotional engine with an interactive interface that allows users to delve deeper into their own challenges and problems.

[0322] 1. User Interface

[0323] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or issues into text forms. For example, a user might enter, "The project is behind schedule. How can we make it run more smoothly?"

[0324] 2. Receiving user input

[0325] The terminal retrieves text data entered by the user and sends it to the server. The retrieved text data is sent to the server via a dedicated API.

[0326] 3. Server Initialization

[0327] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords. For example, words like "project," "in progress," and "delayed" might be extracted.

[0328] 4. Utilizing the Emotion Engine

[0329] The server uses an emotion engine to analyze text data and recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions from words and context in the input text. For example, emotions such as "anxiety" or "fear" may be recognized from the user's input.

[0330] 5. Question generation using AI models

[0331] The server inputs data into a trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. For example, it might generate a question like, "Have you asked each member of the project team how they feel about the recent progress?"

[0332] 6. Selection and submission of questions

[0333] The server selects the question that best fits the context and sentiment from among the multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data. After the optimal question is selected, it is sent to the user's terminal.

[0334] 7. Returning questions and continuing the dialogue

[0335] The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the conversation continues when that answer is sent back to the server. For example, the user might enter "I'll check the status of the project members," and a new conversation will follow based on that.

[0336] Examples of mental support

[0337] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[0338] Examples of how to make project progress smoother

[0339] User: The project is currently behind schedule. How can we make it progress more smoothly?

[0340] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[0341] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[0342] keyword:

[0343] Generative AI model, prompt sentence

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] Users access an interactive interface and enter their questions or tasks into a text form.

[0347] Input: Text entered by the user (e.g., "The project is behind schedule").

[0348] Action: Enter a question in the text form and click the submit button.

[0349] Output: The input text data is retrieved by the terminal.

[0350] Step 2:

[0351] The terminal retrieves text data entered by the user and sends it to the server.

[0352] Input: Text data (user questions or issues).

[0353] Operation: The device sends text data to the server using the API.

[0354] Output: The server receives text data.

[0355] Step 3:

[0356] The server passes the received text data to the natural language processing engine (NLP engine) and begins text analysis.

[0357] Input: Received text data.

[0358] Operation: The NLP engine breaks down text data and extracts context, sentiment, and keywords.

[0359] Output: Analyzed contextual information, sentiment data, and keywords.

[0360] Step 4:

[0361] The server passes the analyzed text data to the emotion engine to recognize the user's emotional state.

[0362] Input: Analyzed text data (contextual information, keywords).

[0363] Operation: The emotion engine evaluates emotions from text data and recognizes the user's emotional state.

[0364] Output: User's emotional state (e.g., impatience, anxiety).

[0365] Step 5:

[0366] The server inputs the data into a trained AI model based on the analyzed information and sentiment data, generating appropriate open-ended questions.

[0367] Input: Analyzed information (contextual information, keywords, sentiment data).

[0368] Operation: The AI ​​model generates appropriate questions based on the data.

[0369] Output: Multiple open-ended questions generated.

[0370] Step 6:

[0371] The server selects the question that best fits the context and sentiment from among the generated questions.

[0372] Input: Multiple questions generated.

[0373] Operation: The server selects questions based on selection criteria (contextual information, keywords, sentiment data).

[0374] Output: The best open-ended question.

[0375] Step 7:

[0376] The server sends the selected question back to the user's terminal, which then displays the question in an interactive interface.

[0377] Input: The best open-ended question.

[0378] Operation: The server sends a question to the terminal, and the terminal displays that question on the interface.

[0379] Output: The question displayed in the user's interactive interface.

[0380] Step 8:

[0381] The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[0382] Input: User's response text (e.g., "I will check the status of the project members").

[0383] Action: The user enters their answer and clicks the submit button.

[0384] Output: The terminal sends the response text to the server, and the next analysis process begins.

[0385] keyword:

[0386] Generative AI model, prompt sentence

[0387] (Application Example 2)

[0388] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0389] Traditional food delivery services have problems such as difficulty for users to place orders and make inquiries smoothly, and in particular, insufficient responses tailored to users' emotional states, leading to low service satisfaction. Furthermore, there was a lack of mechanisms to provide users with mental support through continuous dialogue, so there was a need to improve the user experience.

[0390] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an interactive interface means for the user to input questions or tasks; a means for analyzing the input text using a natural language processing engine and extracting context, emotions, and keywords; a means including a trained AI model for generating relevant open-ended questions based on the extracted information; a means for returning the generated questions to the user; a means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; and a means for running as a food delivery assistant application that provides appropriate suggestions and questions based on the user's emotional state. As a result, the user can receive appropriate responses according to their emotions, improving service satisfaction and enabling the provision of mental support.

[0391] An "interactive interface" is an interactive user interface that allows users to input questions or tasks.

[0392] A "natural language processing engine" refers to algorithms and related technologies used to analyze input text and extract context, sentiment, and keywords.

[0393] A "trained AI model" refers to an artificial intelligence model that has already been trained on data and is capable of producing highly accurate results for a specific task.

[0394] "Emotional state" refers to the psychological state or emotions a user exhibits when typing text.

[0395] A "food delivery assistant application" is a smartphone application that aims to improve food delivery services by providing appropriate suggestions and questions based on the user's emotional state.

[0396] An "open-ended question" is a type of question in which users can freely enter their answers and are not limited to specific choices.

[0397] "User experience" is a general term for the experiences and satisfaction that users gain through using a service or product.

[0398] In order to implement this invention, it is necessary to construct a system comprising the following elements and processes.

[0399] System Configuration

[0400] 1. User Interface

[0401] Users access the assistant using a smartphone app. The app provides an interactive interface, allowing users to input messages via text forms or voice input.

[0402] 2. Receiving user input

[0403] The terminal acquires text and voice data entered by the user and sends it to the server.

[0404] 3. Server Initialization

[0405] The server passes the received text and audio data to a natural language processing (NLP) engine to begin text analysis. Specifically, the NLP engine (for example, Google Cloud Natural Language API) extracts context, sentiment, and keywords from the input text.

[0406] 4. Utilizing the Emotion Engine

[0407] During the process of analyzing text and audio data, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. The emotion engine employs algorithms that evaluate emotions based on words and context in the input text.

[0408] 5. Question generation using AI models

[0409] The server inputs the analyzed information and sentiment data into a pre-trained AI model (for example, OpenAI®'s generative AI model). The AI ​​model generates appropriate open-end questions based on the user's emotional state.

[0410] 6. Selection and submission of questions

[0411] The server selects the most appropriate question from among the multiple questions generated, based on context and sentiment.

[0412] 7. Returning questions and continuing the dialogue

[0413] The server sends the selected question back to the user's terminal, which displays it in an interactive interface. The user answers the displayed question and sends it back to the server, continuing the interaction.

[0414] Hardware and software to use

[0415] Hardware: Smartphone (iOS / ANDROID®)

[0416] software:

[0417] Natural Language Processing Engine: Google Cloud Natural Language API

[0418] Emotion Engine: IBM Watson Tone Analyzer

[0419] Pre-trained AI models: Generative AI models from OpenAI

[0420] Specific example

[0421] Specific example 1:

[0422] User: Lately, my cooking has become monotonous...

[0423] AI Assistant: You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?

[0424] Specific example 2:

[0425] User: My ordered food hasn't arrived yet.

[0426] AI Assistant: We apologize for any concern regarding the order delay. We will check the latest shipping status. Have you been busy lately?

[0427] Example of a prompt

[0428] Examples of prompt statements are as follows:

[0429] Prompt: A user has sent a message about "cooking becoming monotonous." Analyze the user's emotional state and generate an appropriate open-end question.

[0430] Example response: "You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?"

[0431] This system allows users to receive appropriate responses based on their emotions, improving service satisfaction and enabling the provision of mental support.

[0432] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0433] Step 1:

[0434] The user accesses the interactive interface using a smartphone app. Here, the user enters a message using a text form or voice input. The input data is then generated.

[0435] Step 2:

[0436] The terminal acquires the input text and audio data and sends it to the server. Here, the input data is transferred from the terminal to the server.

[0437] Step 3:

[0438] The server passes the received text and audio data to a natural language processing (NLP) engine. The server uses the NLP engine (e.g., Google Cloud Natural Language API) to analyze the input text and extract context, sentiment, and keywords. Analysis results data is then generated.

[0439] Step 4:

[0440] The server passes the analyzed text data to the sentiment engine to recognize the user's emotional state. The sentiment engine (for example, IBM Watson Tone Analyzer) evaluates the emotions from the words and context in the input text and outputs sentiment data.

[0441] Step 5:

[0442] The server inputs data into a trained AI model (e.g., OpenAI's generative AI model) based on sentiment data and contextual data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. Question data is then generated.

[0443] Step 6:

[0444] The server selects the most appropriate question from the multiple questions generated, based on context and sentiment. The question selection algorithm narrows down the questions according to the selection criteria. The final question data is then generated.

[0445] Step 7:

[0446] The server sends the selected questions back to the user's terminal. The terminal receives the question data and displays it in the interactive interface. The user can then view the questions that have been sent to them.

[0447] Step 8:

[0448] The user enters an answer to the displayed question and sends it back to the server. This continues the interaction. The answer data is sent to the server and proceeds to the next processing step.

[0449] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0450] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0451] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0452] [Second Embodiment]

[0453] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0454] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0455] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0456] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0457] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0458] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0459] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0460] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0461] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0462] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0463] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0464] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0465] The system related to this invention is based on an interactive interface that allows users to delve deeper into their own challenges and problems. The system generates appropriate open-ended questions in response to the questions and challenges entered by the user, enabling continuous dialogue. It also includes functions to provide mental support.

[0466] Specific implementations of the system

[0467] 1. User Interface

[0468] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[0469] 2. Receiving user input

[0470] The terminal retrieves text data entered by the user and sends it to the server.

[0471] 3. Server Initialization

[0472] The server receives text data sent by the user and uses a natural language processing engine (NLP) to analyze the text. Specifically, it extracts context, sentiment, and keywords.

[0473] 4. Question generation using AI models

[0474] The server inputs the data into a pre-trained AI model based on the analyzed information. The AI ​​model generates multiple open-ended questions and selects the most appropriate one from among them.

[0475] 5. Returning questions and continuing the dialogue

[0476] The server sends the selected questions back to the user's terminal. The user enters their answers to the received questions, and these answers are sent back to the server, continuing the dialogue. This allows the user to delve deeper into their own issues and gain new perspectives.

[0477] Examples of mental support

[0478] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine to generate open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. Through their responses, users can reflect on their mental state and consider ways to improve it.

[0479] Specific example

[0480] Examples of how to make a project progress smoothly

[0481] User: The project is currently behind schedule. How can we make it proceed more smoothly?

[0482] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[0483] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[0484] Examples of mental support

[0485] User: I've been feeling stressed lately due to project pressure. How can I cope?

[0486] The server analyzes the user's input, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[0487] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0488] This invention's system is expected to be a useful tool for comprehensively understanding and addressing users' specific challenges, and for finding solutions. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The user launches a dedicated application or web browser and accesses an interactive interface.

[0492] Step 2:

[0493] Users use an interactive interface to input their questions and issues in text format.

[0494] Step 3:

[0495] The terminal receives text data entered by the user and sends that data to the server.

[0496] Step 4:

[0497] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[0498] Step 5:

[0499] The server inputs the extracted information into a pre-trained AI model. The AI ​​model generates multiple open-ended questions.

[0500] Step 6:

[0501] The server selects the most appropriate question from the open-ended questions generated, based on the context. The selection criteria are based on the content of the user's input text and extracted keywords.

[0502] Step 7:

[0503] The server sends the selected question back to the user's terminal.

[0504] Step 8:

[0505] The terminal displays the received question in an interactive interface.

[0506] Step 9:

[0507] The user reviews the displayed question and enters their answer.

[0508] Step 10:

[0509] The device resends the user's response to the server.

[0510] Step 11:

[0511] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[0512] Step 12:

[0513] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[0514] Step 13:

[0515] Users engage in continuous dialogue through an interactive interface, asking further questions as needed to delve deeper into the problem and discover new perspectives and solutions.

[0516] Step 14:

[0517] The server periodically incorporates new data to train the AI ​​model, improving the accuracy and relevance of the questions it generates.

[0518] (Example 1)

[0519] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0520] Traditional interactive interfaces often have inefficient processes for users to delve deeper into questions and issues. Furthermore, there are few interactive systems specifically designed for user mental support, making it difficult to adequately assist users' physical and mental well-being. Therefore, there is a need for a system that allows users to thoroughly examine their challenges and problems and resolve them effectively.

[0521] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0522] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for providing the user with the opportunity to delve deeper into their tasks and problems; and means for analyzing stress and pressure-related issues and generating questions to support the user's mental state. This enables the user to consider and solve problems from a concrete and multifaceted perspective.

[0523] An "interactive interface" is an interface that allows users to input questions or tasks and engage in two-way interaction with the system.

[0524] A "natural language processing engine" is a software technology that analyzes input text data to extract context, sentiment, keywords, and other relevant information.

[0525] A "trained AI model" is an artificial intelligence model that has been trained to perform a specific task by learning from past data.

[0526] An "open-ended question" is a type of question that encourages users to answer freely and does not restrict them to providing specific answers.

[0527] "Continuous dialogue" is a process in which the user and the system repeatedly exchange questions and answers to reach a deep understanding and solution.

[0528] "Mental support" is a feature designed to provide appropriate assistance and advice to users regarding problems related to stress and pressure.

[0529] "In-depth analysis" is the process of thoroughly exploring the user's challenges and problems to find their root causes and solutions.

[0530] The system related to this invention is based on an interactive interface that allows users to delve deeper into challenges and problems and receive mental support. The following describes how this system is specifically implemented.

[0531] Building a User Interface

[0532] Users access the system using a dedicated application or a web browser. For example, a user enters the system's URL and authenticates on the login screen. Upon successful authentication, an interactive interface is displayed. This interface includes a text input form and a submit button.

[0533] Receiving user input

[0534] The device retrieves text data entered by the user. When the user writes a question or assignment in a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[0535] Initial processing by the server

[0536] The server analyzes the received text data using a natural language processing engine (e.g., IBM Watson Natural Language Understanding or Google Cloud Natural Language). During this analysis, context, sentiment, and keywords are extracted. Specifically, the server waits for HTTP requests to be received, extracts the text data upon receiving a request, and inputs it into the NLP engine to obtain the analysis results.

[0537] Question generation using AI models

[0538] The server inputs the analyzed data into a pre-trained AI model (e.g., GPT-4 or BERT). The analysis results are converted into the AI ​​model's input format and input into the model. The AI ​​model generates multiple open-ended questions and selects the most appropriate one. To return the selected question to the user, the server sends the selected question back as an HTTP response.

[0539] Sending back questions and continuing the dialogue

[0540] The terminal displays questions received from the server to the user. The returned questions are displayed in a text area on the interface, and the user answers them. When the user enters a new answer into the text form and presses the submit button, the terminal sends the text data to the server again. This allows the dialogue to continue, enabling the user to delve deeper into their problem and gain new perspectives.

[0541] Examples of mental support

[0542] Users input mental health issues such as stress and pressure. The input is analyzed by an NLP engine, which generates open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. By answering these questions, users can broaden their perspective on their own mental health and explore concrete solutions.

[0543] Specific example

[0544] Examples of project progress:

[0545] User: "The project is currently behind schedule. How can we make it proceed more smoothly?"

[0546] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[0547] Users can use this question to interview team members and input the results, allowing for further in-depth discussions.

[0548] Examples of mental support:

[0549] User: "I've been feeling stressed lately due to project pressure. How can I cope?"

[0550] The server analyzes the user's input and generates the question, "Have you been able to take time to relax recently?", which it then sends back to the user.

[0551] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0552] Example of a prompt

[0553] Example regarding project progress: "Currently, the project is behind schedule. How can we make it proceed more smoothly?"

[0554] An example of mental support: "I've been feeling stressed lately due to project pressure. How can I cope?"

[0555] This system is a powerful tool for comprehensively understanding users' specific challenges and finding solutions. Furthermore, its mental support function allows users to address their challenges while maintaining their mental and physical health.

[0556] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0557] Program processing steps

[0558] Step 1:

[0559] Users access the system using a dedicated application or web browser. They enter the system's URL and then enter their authentication information on the login screen. This displays an interactive interface.

[0560] Input: System URL, Login credentials

[0561] Output: An interactive interface is displayed.

[0562] Specific actions:

[0563] 1. The user enters the system's URL into their web browser.

[0564] 2. The user enters their username and password on the login screen.

[0565] 3. If authentication is successful, an interactive interface will be displayed.

[0566] Step 2:

[0567] The device retrieves text data entered by the user. When the user enters a question or task into a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[0568] Input: Text data entered by the user (questions or assignments)

[0569] Output: Text data sent to the server as an HTTP request

[0570] Specific actions:

[0571] 1. The user enters a question or task into a text form.

[0572] 2. The user presses the submit button.

[0573] 3. The device retrieves the text data and sends it to the server as an HTTP request.

[0574] Step 3:

[0575] The server analyzes the received text data using a natural language processing (NLP) engine. The server inputs the text data into the NLP engine and obtains analysis results such as context, sentiment, and keywords.

[0576] Input: Text data sent as an HTTP request

[0577] Output: Analyzed context, sentiment, and keyword data

[0578] Specific actions:

[0579] 1. The server receives the HTTP request and extracts the text data.

[0580] 2. Input the text data into the NLP engine (NLP engines to use: IBM Watson Natural Language Understanding or Google Cloud Natural Language).

[0581] 3. Obtain analysis results from the NLP engine to obtain context, emotion, and keyword data.

[0582] Step 4:

[0583] The server inputs the data into a pre-trained AI model based on the analyzed information. The server converts the analysis results into the AI ​​model's input format and inputs them into the model to generate multiple open-ended questions.

[0584] Input: Analyzed context, sentiment, and keyword data

[0585] Output: Multiple open-ended questions generated

[0586] Specific actions:

[0587] 1. Convert the analysis results into an input format for the AI ​​model (AI models to use: GPT-4 or BERT).

[0588] 2. Input the converted data into the AI ​​model.

[0589] 3. The AI ​​model generates multiple open-ended questions.

[0590] Step 5:

[0591] The server selects the most appropriate question from the generated questions and sends it back to the user's terminal. The server then sends the selected question back as an HTTP response.

[0592] Input: Multiple open-ended questions generated

[0593] Output: The most appropriate question selected

[0594] Specific actions:

[0595] 1. Evaluate the generated questions and select the most appropriate one.

[0596] 2. The selected questions are sent back to the user's terminal as an HTTP response.

[0597] Step 6:

[0598] The terminal displays the question received from the server to the user. The user enters an answer to the displayed question and sends it back to the server.

[0599] Input: Question returned from the server

[0600] Output: User-entered response

[0601] Specific actions:

[0602] 1. The terminal receives an HTTP response from the server.

[0603] 2. Display the received question in the interactive interface.

[0604] 3. The user enters their answer to the question and presses the submit button.

[0605] 4. Resubmit your response to the server.

[0606] Step 7:

[0607] The server re-analyzes the user's responses and generates additional questions as needed, allowing the conversation to continue.

[0608] Input: User's response

[0609] Output: Re-analyzed context, sentiment, and keyword data, plus additional questions.

[0610] Specific actions:

[0611] 1. The server receives the user's response and analyzes it again using the NLP engine.

[0612] 2. Create input data for the AI ​​model based on the analysis results.

[0613] 3. The AI ​​model generates additional open-ended questions.

[0614] 4. Select the appropriate questions from among them and resend them to the user.

[0615] Examples of mental support

[0616] Users enter problems related to stress and pressure.

[0617] The server analyzes the input using an NLP engine and generates open-ended questions to support the user's mental state. For example, it might generate questions such as, "Have you had a moment recently where you felt relaxed?"

[0618] In summary, this system is a powerful tool for comprehensively understanding and addressing users' specific challenges. Furthermore, its mental support function allows users to work on problem-solving while maintaining their own mental and physical health.

[0619] (Application Example 1)

[0620] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0621] Conventional conversational systems have the ability to generate appropriate questions based on user input and support continuous dialogue, but specialized applications aimed at improving security awareness have not been sufficiently developed. Furthermore, the lack of feedback functions to support the improvement of user security behavior makes it difficult for users to obtain guidance for taking concrete security actions.

[0622] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0623] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for the AI ​​model to adapt the content of the generated questions based on the user's input in order to enhance security awareness; and means for providing a feedback function to support the improvement of the user's security behavior. This makes it possible to enhance the user's security awareness and provide guidance for specific security actions.

[0624] An "interactive interface" is an interface that allows users to input questions or tasks, enabling continuous dialogue.

[0625] A "natural language processing engine" is an engine that analyzes text data entered by users and extracts context, sentiment, and keywords.

[0626] A "pre-trained AI model" is an algorithm that generates appropriate open-end questions based on previously trained data.

[0627] An "open-ended question" is a type of question in which the user's answer is not limited to a specific set of choices, but can be expressed freely.

[0628] A "feedback function" is a feature that provides specific advice and guidelines for improvement based on the user's input and actions.

[0629] "Security awareness" refers to the knowledge, awareness, and attention that users have to protect their information and assets.

[0630] "Security actions" refer to the specific actions and measures that users actually take to protect information and assets.

[0631] "Analysis" is the process of examining user input data in detail to understand and extract its meaning, emotions, and context.

[0632] The system for implementing this invention is designed as an application for improving security awareness. Users access an interactive interface through a device such as a smartphone or smart glasses. Through this interface, users can input security-related questions or issues and begin interacting with the system.

[0633] System Configuration

[0634] 1. Hardware Configuration

[0635] Devices: Smartphones, smart glasses

[0636] Server: Internet-connected computer system

[0637] Network: Internet

[0638] 2. Software Configuration

[0639] Interactive Interface: A dedicated application is installed on smartphones and smart glasses as the user interface.

[0640] Natural Language Processing Engine (NLP engine): A software engine that performs text analysis.

[0641] Pre-trained AI model: An AI algorithm for generating open-ended questions.

[0642] Processing Overview

[0643] Receiving user input: The terminal receives security-related text data entered by the user and sends it to the server.

[0644] Initial analysis: The server uses a natural language processing engine to analyze the received text data and extract context, sentiment, and keywords.

[0645] Question generation: Based on the analyzed information, the server inputs data into a trained AI model to generate open-end questions designed to enhance security awareness.

[0646] Question return: The generated questions are returned to the user's device, and the user answers them. By repeating this process, the user can gradually increase their security awareness.

[0647] Feedback function: Based on user input and actions, the server generates appropriate feedback and provides users with specific security action guidelines.

[0648] Specific example

[0649] The user launches a smartphone app and enters the question, "I feel like I've been getting a lot of phishing emails lately. How should I deal with them?" The server analyzes this text using a natural language processing engine to extract context, sentiment, and keywords.

[0650] The server then inputs the following prompts into the trained AI model.

[0651] "User question: 'I feel like I've been getting a lot of phishing emails lately. How should I deal with them?' Please generate an open-ended question to raise security awareness in response to this."

[0652] An example of a generated question sent back to the user is, "What information have you recently learned about the characteristics of phishing emails? And how do you apply that knowledge to your daily email checking?" The user then enters their answer to this question, allowing the server to continue further analysis and dialogue.

[0653] This will strengthen users' specific security knowledge and actions, and improve their security awareness.

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] Receiving user input

[0657] The user uses a smartphone or smart glasses to input questions or tasks into an interactive interface. For example, the user might input the question, "I've been receiving a lot of phishing emails lately. How should I deal with this?" The device receives the input as text data and sends it to the server via the internet.

[0658] Step 2:

[0659] Analysis using a natural language processing engine

[0660] The server inputs the text data received from the user into a natural language processing engine (NLP engine). Here, the NLP engine analyzes the context, sentiment, and keywords of the text to deepen its understanding of the context. This analysis result (context, sentiment, and keywords) is output as a dataset to be used in the next step.

[0661] Step 3:

[0662] Question generation using a pre-trained AI model

[0663] The server inputs data into a trained AI model based on the analysis results of the NLP engine. The AI ​​model generates multiple open-ended questions to raise security awareness and selects the most appropriate question from among them. For example, the AI ​​model might generate the question, "What information have you recently learned about the characteristics of phishing emails?" and the selected question is sent back to the user in the next step.

[0664] Step 4:

[0665] Return of question

[0666] The server sends the generated question back to the user's terminal. The user's terminal displays this question, and the user answers it. Through this interaction, the user continues to input information to gain a deeper understanding.

[0667] Step 5:

[0668] Feedback function

[0669] The device sends new input from the user back to the server, which analyzes this input using an NLP engine and an AI model. The analysis results are generated as specific feedback to improve the user's security behavior. For example, feedback such as, "Learn the characteristics of phishing emails and think about how to apply that knowledge," might be generated. This feedback is sent back to the user's device and displayed again.

[0670] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0671] This invention's system, based on an interactive interface that allows users to delve deeper into their own challenges and problems, combines this with an emotion engine to recognize the user's emotional state and generate more appropriate open-ended questions. This enables users to effectively solve their problems and manage their mental health.

[0672] Specific implementations of the system

[0673] 1. User Interface

[0674] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[0675] 2. Receiving user input

[0676] The terminal retrieves text data entered by the user and sends it to the server.

[0677] 3. Server Initialization

[0678] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[0679] 4. Utilizing the Emotion Engine

[0680] As the server analyzes text data, it utilizes an emotion engine to recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions based on words and context in the input text.

[0681] 5. Question generation using AI models

[0682] The server inputs data into a pre-trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state.

[0683] 6. Selection and submission of questions

[0684] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[0685] 7. Returning questions and continuing the dialogue

[0686] The server sends the selected question back to the user's terminal. The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[0687] Examples of mental support

[0688] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[0689] Specific example

[0690] Examples of how to make a project progress smoothly

[0691] User: The project is currently behind schedule. How can we make it progress more smoothly?

[0692] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[0693] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[0694] Examples of mental support

[0695] User: I've been feeling stressed lately due to project pressure. How can I cope?

[0696] The server analyzes the user's input, recognizes the user's high stress level using an emotion engine, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[0697] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0698] This invention's system is expected to be a useful tool for comprehensively understanding the user's specific challenges and finding solutions based on emotions and context. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[0699] The following describes the processing flow.

[0700] Step 1:

[0701] The user launches a dedicated application or web browser and accesses an interactive interface.

[0702] Step 2:

[0703] Users use an interactive interface to input their questions and issues in text format.

[0704] Step 3:

[0705] The terminal retrieves text data entered by the user and sends that data to the server.

[0706] Step 4:

[0707] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[0708] Step 5:

[0709] In parallel with text analysis, the server uses an emotion engine to recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions based on words and context in the input text.

[0710] Step 6:

[0711] The server uses the extracted contextual information, sentiment data, and keywords to input data into a pre-trained AI model.

[0712] Step 7:

[0713] The server uses an AI model to generate multiple open-ended questions based on the user's context and emotional state.

[0714] Step 8:

[0715] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[0716] Step 9:

[0717] The server sends the selected question back to the user's terminal.

[0718] Step 10:

[0719] The terminal displays the received question in an interactive interface.

[0720] Step 11:

[0721] The user reviews the displayed question and enters their answer.

[0722] Step 12:

[0723] The device resends the user's response to the server.

[0724] Step 13:

[0725] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[0726] Step 14:

[0727] The server saves the extracted information as history, which influences subsequent interactions and generated questions.

[0728] Step 15:

[0729] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[0730] Step 16:

[0731] Users engage in continuous dialogue through an interactive interface, asking further questions as needed to delve deeper into the problem and discover new perspectives and solutions.

[0732] Step 17:

[0733] The server periodically incorporates new data to train the AI ​​model, improving the accuracy and relevance of the questions it generates.

[0734] (Example 2)

[0735] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0736] In conventional conversational systems, accurately understanding the user's emotional state and generating appropriate questions accordingly was difficult. As a result, maintaining effective dialogue in solving users' problems and providing mental care support was challenging. Furthermore, if the generated questions did not fit the context or emotions, user satisfaction decreased, and the usefulness of the system was impaired.

[0737] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means including an emotion recognition engine for evaluating the user's emotional state, means including a trained AI model for generating relevant open-ended questions based on extracted information and emotion data, and means for selecting the optimal question from among the generated questions. This makes it possible to generate and select appropriate questions that reflect the user's emotional state.

[0738] A "user" is the entity that uses this system to input tasks or questions.

[0739] An "interactive interface" is an interface that allows users to input tasks or questions and then answer the generated questions.

[0740] A "natural language processing engine" is a machine learning algorithm that analyzes input text and extracts context, sentiment, and keywords.

[0741] "Context" refers to information that helps us understand the meaning and relevance of the entered text.

[0742] "Emotion" refers to the emotional state (e.g., joy, anger, sadness, etc.) extracted from the user's input text.

[0743] "Keywords" are important words or phrases extracted from the input text.

[0744] A "trained AI model" is artificial intelligence that is trained based on past data and generates questions in response to user input.

[0745] An "emotion recognition engine" is an algorithm that evaluates the emotional state of a user based on their input text.

[0746] "Methods for selecting questions" refer to methods for choosing the question that best fits the context and sentiment from among several generated questions.

[0747] "Means of supporting continuous dialogue" refers to methods that allow users to answer questions returned, analyze those answers again, and continue the dialogue.

[0748] "Mental support" refers to a function that aims to support the user's mental health by analyzing input related to the user's mental state and generating appropriate open-ended questions.

[0749] This invention is a system that recognizes the user's emotional state and generates more appropriate open-end questions by combining an emotional engine with an interactive interface that allows users to delve deeper into their own challenges and problems.

[0750] 1. User Interface

[0751] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or issues into text forms. For example, a user might enter, "The project is behind schedule. How can we make it run more smoothly?"

[0752] 2. Receiving user input

[0753] The terminal retrieves text data entered by the user and sends it to the server. The retrieved text data is sent to the server via a dedicated API.

[0754] 3. Server Initialization

[0755] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords. For example, words like "project," "in progress," and "delayed" might be extracted.

[0756] 4. Utilizing the Emotion Engine

[0757] The server uses an emotion engine to analyze text data and recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions from words and context in the input text. For example, emotions such as "anxiety" or "fear" may be recognized from the user's input.

[0758] 5. Question generation using AI models

[0759] The server inputs data into a trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. For example, it might generate a question like, "Have you asked each member of the project team how they feel about the recent progress?"

[0760] 6. Selection and submission of questions

[0761] The server selects the question that best fits the context and sentiment from among the multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data. After the optimal question is selected, it is sent to the user's terminal.

[0762] 7. Returning questions and continuing the dialogue

[0763] The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the conversation continues when that answer is sent back to the server. For example, the user might enter "I'll check the status of the project members," and a new conversation will follow based on that.

[0764] Examples of mental support

[0765] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[0766] Examples of how to make project progress smoother

[0767] User: The project is currently behind schedule. How can we make it progress more smoothly?

[0768] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[0769] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[0770] keyword:

[0771] Generative AI model, prompt sentence

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] Users access an interactive interface and enter their questions or tasks into a text form.

[0775] Input: Text entered by the user (e.g., "The project is behind schedule").

[0776] Action: Enter a question in the text form and click the submit button.

[0777] Output: The input text data is retrieved by the terminal.

[0778] Step 2:

[0779] The terminal retrieves text data entered by the user and sends it to the server.

[0780] Input: Text data (user questions or issues).

[0781] Operation: The device sends text data to the server using the API.

[0782] Output: The server receives text data.

[0783] Step 3:

[0784] The server passes the received text data to the natural language processing engine (NLP engine) and begins text analysis.

[0785] Input: Received text data.

[0786] Operation: The NLP engine breaks down text data and extracts context, sentiment, and keywords.

[0787] Output: Analyzed contextual information, sentiment data, and keywords.

[0788] Step 4:

[0789] The server passes the analyzed text data to the emotion engine to recognize the user's emotional state.

[0790] Input: Analyzed text data (contextual information, keywords).

[0791] Operation: The emotion engine evaluates emotions from text data and recognizes the user's emotional state.

[0792] Output: User's emotional state (e.g., impatience, anxiety).

[0793] Step 5:

[0794] The server inputs the data into a trained AI model based on the analyzed information and sentiment data, generating appropriate open-ended questions.

[0795] Input: Analyzed information (contextual information, keywords, sentiment data).

[0796] Operation: The AI ​​model generates appropriate questions based on the data.

[0797] Output: Multiple open-ended questions generated.

[0798] Step 6:

[0799] The server selects the question that best fits the context and sentiment from among the generated questions.

[0800] Input: Multiple questions generated.

[0801] Operation: The server selects questions based on selection criteria (contextual information, keywords, sentiment data).

[0802] Output: The best open-ended question.

[0803] Step 7:

[0804] The server sends the selected question back to the user's terminal, which then displays the question in an interactive interface.

[0805] Input: The best open-ended question.

[0806] Operation: The server sends a question to the terminal, and the terminal displays that question on the interface.

[0807] Output: The question displayed in the user's interactive interface.

[0808] Step 8:

[0809] The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[0810] Input: User's response text (e.g., "I will check the status of the project members").

[0811] Action: The user enters their answer and clicks the submit button.

[0812] Output: The terminal sends the response text to the server, and the next analysis process begins.

[0813] keyword:

[0814] Generative AI model, prompt sentence

[0815] (Application Example 2)

[0816] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0817] Traditional food delivery services have problems such as difficulty for users to place orders and make inquiries smoothly, and in particular, insufficient responses tailored to users' emotional states, leading to low service satisfaction. Furthermore, there was a lack of mechanisms to provide users with mental support through continuous dialogue, so there was a need to improve the user experience.

[0818] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an interactive interface means for the user to input questions or tasks; a means for analyzing the input text using a natural language processing engine and extracting context, emotions, and keywords; a means including a trained AI model for generating relevant open-ended questions based on the extracted information; a means for returning the generated questions to the user; a means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; and a means for running as a food delivery assistant application that provides appropriate suggestions and questions based on the user's emotional state. As a result, the user can receive appropriate responses according to their emotions, improving service satisfaction and enabling the provision of mental support.

[0819] An "interactive interface" is an interactive user interface that allows users to input questions or tasks.

[0820] A "natural language processing engine" refers to algorithms and related technologies used to analyze input text and extract context, sentiment, and keywords.

[0821] A "trained AI model" refers to an artificial intelligence model that has already been trained on data and is capable of producing highly accurate results for a specific task.

[0822] "Emotional state" refers to the psychological state or emotions a user exhibits when typing text.

[0823] A "food delivery assistant application" is a smartphone application that aims to improve food delivery services by providing appropriate suggestions and questions based on the user's emotional state.

[0824] An "open-ended question" is a type of question in which users can freely enter their answers and are not limited to specific choices.

[0825] "User experience" is a general term for the experiences and satisfaction that users gain through using a service or product.

[0826] In order to implement this invention, it is necessary to construct a system comprising the following elements and processes.

[0827] System Configuration

[0828] 1. User Interface

[0829] Users access the assistant using a smartphone app. The app provides an interactive interface, allowing users to input messages via text forms or voice input.

[0830] 2. Receiving user input

[0831] The terminal acquires text and voice data entered by the user and sends it to the server.

[0832] 3. Server Initialization

[0833] The server passes the received text and audio data to a natural language processing (NLP) engine to begin text analysis. Specifically, the NLP engine (for example, Google Cloud Natural Language API) extracts context, sentiment, and keywords from the input text.

[0834] 4. Utilizing the Emotion Engine

[0835] During the process of analyzing text and audio data, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. The emotion engine employs algorithms that evaluate emotions based on words and context in the input text.

[0836] 5. Question generation using AI models

[0837] The server inputs the analyzed information and sentiment data into a pre-trained AI model (for example, OpenAI's generative AI model). The AI ​​model generates appropriate open-end questions based on the user's emotional state.

[0838] 6. Selection and submission of questions

[0839] The server selects the most appropriate question from among the multiple questions generated, based on context and sentiment.

[0840] 7. Returning questions and continuing the dialogue

[0841] The server sends the selected question back to the user's terminal, which displays it in an interactive interface. The user answers the displayed question and sends it back to the server, continuing the interaction.

[0842] Hardware and software to use

[0843] Hardware: Smartphone (iOS / Android)

[0844] software:

[0845] Natural Language Processing Engine: Google Cloud Natural Language API

[0846] Emotion Engine: IBM Watson Tone Analyzer

[0847] Pre-trained AI models: Generative AI models from OpenAI

[0848] Specific example

[0849] Specific example 1:

[0850] User: Lately, my cooking has become monotonous...

[0851] AI Assistant: You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?

[0852] Specific example 2:

[0853] User: My ordered food hasn't arrived yet.

[0854] AI Assistant: We apologize for any concern regarding the order delay. We will check the latest shipping status. Have you been busy lately?

[0855] Example of a prompt

[0856] Examples of prompt statements are as follows:

[0857] Prompt: A user has sent a message about "cooking becoming monotonous." Analyze the user's emotional state and generate an appropriate open-end question.

[0858] Example response: "You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?"

[0859] This system allows users to receive appropriate responses based on their emotions, improving service satisfaction and enabling the provision of mental support.

[0860] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0861] Step 1:

[0862] The user accesses the interactive interface using a smartphone app. Here, the user enters a message using a text form or voice input. The input data is then generated.

[0863] Step 2:

[0864] The terminal acquires the input text and audio data and sends it to the server. Here, the input data is transferred from the terminal to the server.

[0865] Step 3:

[0866] The server passes the received text and audio data to a natural language processing (NLP) engine. The server uses the NLP engine (e.g., Google Cloud Natural Language API) to analyze the input text and extract context, sentiment, and keywords. Analysis results data is then generated.

[0867] Step 4:

[0868] The server passes the analyzed text data to the sentiment engine to recognize the user's emotional state. The sentiment engine (for example, IBM Watson Tone Analyzer) evaluates the emotions from the words and context in the input text and outputs sentiment data.

[0869] Step 5:

[0870] The server inputs data into a trained AI model (e.g., OpenAI's generative AI model) based on sentiment data and contextual data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. Question data is then generated.

[0871] Step 6:

[0872] The server selects the most appropriate question from the multiple questions generated, based on context and sentiment. The question selection algorithm narrows down the questions according to the selection criteria. The final question data is then generated.

[0873] Step 7:

[0874] The server sends the selected questions back to the user's terminal. The terminal receives the question data and displays it in the interactive interface. The user can then view the questions that have been sent to them.

[0875] Step 8:

[0876] The user enters an answer to the displayed question and sends it back to the server. This continues the interaction. The answer data is sent to the server and proceeds to the next processing step.

[0877] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0878] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0879] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0880] [Third Embodiment]

[0881] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0882] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0883] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0884] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0885] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0886] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0887] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0888] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0889] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0890] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0891] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0892] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0893] The system related to this invention is based on an interactive interface that allows users to delve deeper into their own challenges and problems. The system generates appropriate open-ended questions in response to the questions and challenges entered by the user, enabling continuous dialogue. It also includes functions to provide mental support.

[0894] Specific implementations of the system

[0895] 1. User Interface

[0896] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[0897] 2. Receiving user input

[0898] The terminal retrieves text data entered by the user and sends it to the server.

[0899] 3. Server Initialization

[0900] The server receives text data sent by the user and uses a natural language processing engine (NLP) to analyze the text. Specifically, it extracts context, sentiment, and keywords.

[0901] 4. Question generation using AI models

[0902] The server inputs the data into a pre-trained AI model based on the analyzed information. The AI ​​model generates multiple open-ended questions and selects the most appropriate one from among them.

[0903] 5. Returning questions and continuing the dialogue

[0904] The server sends the selected questions back to the user's terminal. The user enters their answers to the received questions, and these answers are sent back to the server, continuing the dialogue. This allows the user to delve deeper into their own issues and gain new perspectives.

[0905] Examples of mental support

[0906] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine to generate open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. Through their responses, users can reflect on their mental state and consider ways to improve it.

[0907] Specific example

[0908] Examples of how to make a project progress smoothly

[0909] User: The project is currently behind schedule. How can we make it proceed more smoothly?

[0910] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[0911] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[0912] Examples of mental support

[0913] User: I've been feeling stressed lately due to project pressure. How can I cope?

[0914] The server analyzes the user's input, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[0915] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0916] This invention's system is expected to be a useful tool for comprehensively understanding and addressing users' specific challenges, and for finding solutions. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[0917] The following describes the processing flow.

[0918] Step 1:

[0919] The user launches a dedicated application or web browser and accesses an interactive interface.

[0920] Step 2:

[0921] Users use an interactive interface to input their questions and issues in text format.

[0922] Step 3:

[0923] The terminal receives text data entered by the user and sends that data to the server.

[0924] Step 4:

[0925] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[0926] Step 5:

[0927] The server inputs the extracted information into a pre-trained AI model. The AI ​​model generates multiple open-ended questions.

[0928] Step 6:

[0929] The server selects the most appropriate question from the open-ended questions generated, based on the context. The selection criteria are based on the content of the user's input text and extracted keywords.

[0930] Step 7:

[0931] The server sends the selected question back to the user's terminal.

[0932] Step 8:

[0933] The terminal displays the received question in an interactive interface.

[0934] Step 9:

[0935] The user reviews the displayed question and enters their answer.

[0936] Step 10:

[0937] The device resends the user's response to the server.

[0938] Step 11:

[0939] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[0940] Step 12:

[0941] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[0942] Step 13:

[0943] Users engage in continuous dialogue through an interactive interface, asking further questions as needed to delve deeper into the problem and discover new perspectives and solutions.

[0944] Step 14:

[0945] The server periodically incorporates new data to train the AI ​​model, improving the accuracy and relevance of the questions it generates.

[0946] (Example 1)

[0947] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0948] Traditional interactive interfaces often have inefficient processes for users to delve deeper into questions and issues. Furthermore, there are few interactive systems specifically designed for user mental support, making it difficult to adequately assist users' physical and mental well-being. Therefore, there is a need for a system that allows users to thoroughly examine their challenges and problems and resolve them effectively.

[0949] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0950] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for providing the user with the opportunity to delve deeper into their tasks and problems; and means for analyzing stress and pressure-related issues and generating questions to support the user's mental state. This enables the user to consider and solve problems from a concrete and multifaceted perspective.

[0951] An "interactive interface" is an interface that allows users to input questions or tasks and engage in two-way interaction with the system.

[0952] A "natural language processing engine" is a software technology that analyzes input text data to extract context, sentiment, keywords, and other relevant information.

[0953] A "trained AI model" is an artificial intelligence model that has been trained to perform a specific task by learning from past data.

[0954] An "open-ended question" is a type of question that encourages users to answer freely and does not restrict them to providing specific answers.

[0955] "Continuous dialogue" is a process in which the user and the system repeatedly exchange questions and answers to reach a deep understanding and solution.

[0956] "Mental support" is a feature designed to provide appropriate assistance and advice to users regarding problems related to stress and pressure.

[0957] "In-depth analysis" is the process of thoroughly exploring the user's challenges and problems to find their root causes and solutions.

[0958] The system related to this invention is based on an interactive interface that allows users to delve deeper into challenges and problems and receive mental support. The following describes how this system is specifically implemented.

[0959] Building a User Interface

[0960] Users access the system using a dedicated application or a web browser. For example, a user enters the system's URL and authenticates on the login screen. Upon successful authentication, an interactive interface is displayed. This interface includes a text input form and a submit button.

[0961] Receiving user input

[0962] The device retrieves text data entered by the user. When the user writes a question or assignment in a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[0963] Initial processing by the server

[0964] The server analyzes the received text data using a natural language processing engine (e.g., IBM Watson Natural Language Understanding or Google Cloud Natural Language). During this analysis, context, sentiment, and keywords are extracted. Specifically, the server waits for HTTP requests to be received, extracts the text data upon receiving a request, and inputs it into the NLP engine to obtain the analysis results.

[0965] Question generation using AI models

[0966] The server inputs the analyzed data into a pre-trained AI model (e.g., GPT-4 or BERT). The analysis results are converted into the AI ​​model's input format and input into the model. The AI ​​model generates multiple open-ended questions and selects the most appropriate one. To return the selected question to the user, the server sends the selected question back as an HTTP response.

[0967] Sending back questions and continuing the dialogue

[0968] The terminal displays questions received from the server to the user. The returned questions are displayed in a text area on the interface, and the user answers them. When the user enters a new answer into the text form and presses the submit button, the terminal sends the text data to the server again. This allows the dialogue to continue, enabling the user to delve deeper into their problem and gain new perspectives.

[0969] Examples of mental support

[0970] Users input mental health issues such as stress and pressure. The input is analyzed by an NLP engine, which generates open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. By answering these questions, users can broaden their perspective on their own mental health and explore concrete solutions.

[0971] Specific example

[0972] Examples of project progress:

[0973] User: "The project is currently behind schedule. How can we make it proceed more smoothly?"

[0974] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[0975] Users can use this question to interview team members and input the results, allowing for further in-depth discussions.

[0976] Examples of mental support:

[0977] User: "I've been feeling stressed lately due to project pressure. How can I cope?"

[0978] The server analyzes the user's input and generates the question, "Have you been able to take time to relax recently?", which it then sends back to the user.

[0979] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[0980] Example of a prompt

[0981] Example regarding project progress: "Currently, the project is behind schedule. How can we make it proceed more smoothly?"

[0982] An example of mental support: "I've been feeling stressed lately due to project pressure. How can I cope?"

[0983] This system is a powerful tool for comprehensively understanding users' specific challenges and finding solutions. Furthermore, its mental support function allows users to address their challenges while maintaining their mental and physical health.

[0984] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0985] Program processing steps

[0986] Step 1:

[0987] Users access the system using a dedicated application or web browser. They enter the system's URL and then enter their authentication information on the login screen. This displays an interactive interface.

[0988] Input: System URL, Login credentials

[0989] Output: An interactive interface is displayed.

[0990] Specific actions:

[0991] 1. The user enters the system's URL into their web browser.

[0992] 2. The user enters their username and password on the login screen.

[0993] 3. If authentication is successful, an interactive interface will be displayed.

[0994] Step 2:

[0995] The device retrieves text data entered by the user. When the user enters a question or task into a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[0996] Input: Text data entered by the user (questions or assignments)

[0997] Output: Text data sent to the server as an HTTP request

[0998] Specific actions:

[0999] 1. The user enters a question or task into a text form.

[1000] 2. The user presses the submit button.

[1001] 3. The device retrieves the text data and sends it to the server as an HTTP request.

[1002] Step 3:

[1003] The server analyzes the received text data using a natural language processing (NLP) engine. The server inputs the text data into the NLP engine and obtains analysis results such as context, sentiment, and keywords.

[1004] Input: Text data sent as an HTTP request

[1005] Output: Analyzed context, sentiment, and keyword data

[1006] Specific actions:

[1007] 1. The server receives the HTTP request and extracts the text data.

[1008] 2. Input the text data into the NLP engine (NLP engines to use: IBM Watson Natural Language Understanding or Google Cloud Natural Language).

[1009] 3. Obtain analysis results from the NLP engine to obtain context, emotion, and keyword data.

[1010] Step 4:

[1011] The server inputs the data into a pre-trained AI model based on the analyzed information. The server converts the analysis results into the AI ​​model's input format and inputs them into the model to generate multiple open-ended questions.

[1012] Input: Analyzed context, sentiment, and keyword data

[1013] Output: Multiple open-ended questions generated

[1014] Specific actions:

[1015] 1. Convert the analysis results into an input format for the AI ​​model (AI models to use: GPT-4 or BERT).

[1016] 2. Input the converted data into the AI ​​model.

[1017] 3. The AI ​​model generates multiple open-ended questions.

[1018] Step 5:

[1019] The server selects the most appropriate question from the generated questions and sends it back to the user's terminal. The server then sends the selected question back as an HTTP response.

[1020] Input: Multiple open-ended questions generated

[1021] Output: The most appropriate question selected

[1022] Specific actions:

[1023] 1. Evaluate the generated questions and select the most appropriate one.

[1024] 2. The selected questions are sent back to the user's terminal as an HTTP response.

[1025] Step 6:

[1026] The terminal displays the question received from the server to the user. The user enters an answer to the displayed question and sends it back to the server.

[1027] Input: Question returned from the server

[1028] Output: User-entered response

[1029] Specific actions:

[1030] 1. The terminal receives an HTTP response from the server.

[1031] 2. Display the received question in the interactive interface.

[1032] 3. The user enters their answer to the question and presses the submit button.

[1033] 4. Resubmit your response to the server.

[1034] Step 7:

[1035] The server re-analyzes the user's responses and generates additional questions as needed, allowing the conversation to continue.

[1036] Input: User's response

[1037] Output: Re-analyzed context, sentiment, and keyword data, plus additional questions.

[1038] Specific actions:

[1039] 1. The server receives the user's response and analyzes it again using the NLP engine.

[1040] 2. Create input data for the AI ​​model based on the analysis results.

[1041] 3. The AI ​​model generates additional open-ended questions.

[1042] 4. Select the appropriate questions from among them and resend them to the user.

[1043] Examples of mental support

[1044] Users enter problems related to stress and pressure.

[1045] The server analyzes the input using an NLP engine and generates open-ended questions to support the user's mental state. For example, it might generate questions such as, "Have you had a moment recently where you felt relaxed?"

[1046] In summary, this system is a powerful tool for comprehensively understanding and addressing users' specific challenges. Furthermore, its mental support function allows users to work on problem-solving while maintaining their own mental and physical health.

[1047] (Application Example 1)

[1048] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1049] Conventional conversational systems have the ability to generate appropriate questions based on user input and support continuous dialogue, but specialized applications aimed at improving security awareness have not been sufficiently developed. Furthermore, the lack of feedback functions to support the improvement of user security behavior makes it difficult for users to obtain guidance for taking concrete security actions.

[1050] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1051] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for the AI ​​model to adapt the content of the generated questions based on the user's input in order to enhance security awareness; and means for providing a feedback function to support the improvement of the user's security behavior. This makes it possible to enhance the user's security awareness and provide guidance for specific security actions.

[1052] An "interactive interface" is an interface that allows users to input questions or tasks, enabling continuous dialogue.

[1053] A "natural language processing engine" is an engine that analyzes text data entered by users and extracts context, sentiment, and keywords.

[1054] A "pre-trained AI model" is an algorithm that generates appropriate open-end questions based on previously trained data.

[1055] An "open-ended question" is a type of question in which the user's answer is not limited to a specific set of choices, but can be expressed freely.

[1056] A "feedback function" is a feature that provides specific advice and guidelines for improvement based on the user's input and actions.

[1057] "Security awareness" refers to the knowledge, awareness, and attention that users have to protect their information and assets.

[1058] "Security actions" refer to the specific actions and measures that users actually take to protect information and assets.

[1059] "Analysis" is the process of examining user input data in detail to understand and extract its meaning, emotions, and context.

[1060] The system for implementing this invention is designed as an application for improving security awareness. Users access an interactive interface through a device such as a smartphone or smart glasses. Through this interface, users can input security-related questions or issues and begin interacting with the system.

[1061] System Configuration

[1062] 1. Hardware Configuration

[1063] Devices: Smartphones, smart glasses

[1064] Server: Internet-connected computer system

[1065] Network: Internet

[1066] 2. Software Configuration

[1067] Interactive Interface: A dedicated application is installed on smartphones and smart glasses as the user interface.

[1068] Natural Language Processing Engine (NLP engine): A software engine that performs text analysis.

[1069] Pre-trained AI model: An AI algorithm for generating open-ended questions.

[1070] Processing Overview

[1071] Receiving user input: The terminal receives security-related text data entered by the user and sends it to the server.

[1072] Initial analysis: The server uses a natural language processing engine to analyze the received text data and extract context, sentiment, and keywords.

[1073] Question generation: Based on the analyzed information, the server inputs data into a trained AI model to generate open-end questions designed to enhance security awareness.

[1074] Question return: The generated questions are returned to the user's device, and the user answers them. By repeating this process, the user can gradually increase their security awareness.

[1075] Feedback function: Based on user input and actions, the server generates appropriate feedback and provides users with specific security action guidelines.

[1076] Specific example

[1077] The user launches a smartphone app and enters the question, "I feel like I've been getting a lot of phishing emails lately. How should I deal with them?" The server analyzes this text using a natural language processing engine to extract context, sentiment, and keywords.

[1078] The server then inputs the following prompts into the trained AI model.

[1079] "User question: 'I feel like I've been getting a lot of phishing emails lately. How should I deal with them?' Please generate an open-ended question to raise security awareness in response to this."

[1080] An example of a generated question sent back to the user is, "What information have you recently learned about the characteristics of phishing emails? And how do you apply that knowledge to your daily email checking?" The user then enters their answer to this question, allowing the server to continue further analysis and dialogue.

[1081] This will strengthen users' specific security knowledge and actions, and improve their security awareness.

[1082] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1083] Step 1:

[1084] Receiving user input

[1085] The user uses a smartphone or smart glasses to input questions or tasks into an interactive interface. For example, the user might input the question, "I've been receiving a lot of phishing emails lately. How should I deal with this?" The device receives the input as text data and sends it to the server via the internet.

[1086] Step 2:

[1087] Analysis using a natural language processing engine

[1088] The server inputs the text data received from the user into a natural language processing engine (NLP engine). Here, the NLP engine analyzes the context, sentiment, and keywords of the text to deepen its understanding of the context. This analysis result (context, sentiment, and keywords) is output as a dataset to be used in the next step.

[1089] Step 3:

[1090] Question generation using a pre-trained AI model

[1091] The server inputs data into a trained AI model based on the analysis results of the NLP engine. The AI ​​model generates multiple open-ended questions to raise security awareness and selects the most appropriate question from among them. For example, the AI ​​model might generate the question, "What information have you recently learned about the characteristics of phishing emails?" and the selected question is sent back to the user in the next step.

[1092] Step 4:

[1093] Return of question

[1094] The server sends the generated question back to the user's terminal. The user's terminal displays this question, and the user answers it. Through this interaction, the user continues to input information to gain a deeper understanding.

[1095] Step 5:

[1096] Feedback function

[1097] The device sends new input from the user back to the server, which analyzes this input using an NLP engine and an AI model. The analysis results are generated as specific feedback to improve the user's security behavior. For example, feedback such as, "Learn the characteristics of phishing emails and think about how to apply that knowledge," might be generated. This feedback is sent back to the user's device and displayed again.

[1098] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1099] This invention's system, based on an interactive interface that allows users to delve deeper into their own challenges and problems, combines this with an emotion engine to recognize the user's emotional state and generate more appropriate open-ended questions. This enables users to effectively solve their problems and manage their mental health.

[1100] Specific implementations of the system

[1101] 1. User Interface

[1102] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[1103] 2. Receiving user input

[1104] The terminal retrieves text data entered by the user and sends it to the server.

[1105] 3. Server Initialization

[1106] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[1107] 4. Utilizing the Emotion Engine

[1108] As the server analyzes text data, it utilizes an emotion engine to recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions based on words and context in the input text.

[1109] 5. Question generation using AI models

[1110] The server inputs data into a pre-trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state.

[1111] 6. Selection and submission of questions

[1112] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[1113] 7. Returning questions and continuing the dialogue

[1114] The server sends the selected question back to the user's terminal. The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[1115] Examples of mental support

[1116] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[1117] Specific example

[1118] Examples of how to make a project progress smoothly

[1119] User: The project is currently behind schedule. How can we make it progress more smoothly?

[1120] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[1121] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[1122] Examples of mental support

[1123] User: I've been feeling stressed lately due to project pressure. How can I cope?

[1124] The server analyzes the user's input, recognizes the user's high stress level using an emotion engine, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[1125] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[1126] This invention's system is expected to be a useful tool for comprehensively understanding the user's specific challenges and finding solutions based on emotions and context. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[1127] The following describes the processing flow.

[1128] Step 1:

[1129] The user launches a dedicated application or web browser and accesses an interactive interface.

[1130] Step 2:

[1131] Users use an interactive interface to input their questions and issues in text format.

[1132] Step 3:

[1133] The terminal retrieves text data entered by the user and sends that data to the server.

[1134] Step 4:

[1135] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[1136] Step 5:

[1137] In parallel with text analysis, the server uses an emotion engine to recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions based on words and context in the input text.

[1138] Step 6:

[1139] The server uses the extracted contextual information, sentiment data, and keywords to input data into a pre-trained AI model.

[1140] Step 7:

[1141] The server uses an AI model to generate multiple open-ended questions based on the user's context and emotional state.

[1142] Step 8:

[1143] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[1144] Step 9:

[1145] The server sends the selected question back to the user's terminal.

[1146] Step 10:

[1147] The terminal displays the received question in an interactive interface.

[1148] Step 11:

[1149] The user reviews the displayed question and enters their answer.

[1150] Step 12:

[1151] The device resends the user's response to the server.

[1152] Step 13:

[1153] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[1154] Step 14:

[1155] The server saves the extracted information as history, which influences subsequent interactions and generated questions.

[1156] Step 15:

[1157] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[1158] Step 16:

[1159] Users engage in continuous dialogue through an interactive interface, asking further questions as needed to delve deeper into the problem and discover new perspectives and solutions.

[1160] Step 17:

[1161] The server periodically incorporates new data to train the AI ​​model, improving the accuracy and relevance of the questions it generates.

[1162] (Example 2)

[1163] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1164] In conventional conversational systems, accurately understanding the user's emotional state and generating appropriate questions accordingly was difficult. As a result, maintaining effective dialogue in solving users' problems and providing mental care support was challenging. Furthermore, if the generated questions did not fit the context or emotions, user satisfaction decreased, and the usefulness of the system was impaired.

[1165] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means including an emotion recognition engine for evaluating the user's emotional state, means including a trained AI model for generating relevant open-ended questions based on extracted information and emotion data, and means for selecting the optimal question from among the generated questions. This makes it possible to generate and select appropriate questions that reflect the user's emotional state.

[1166] A "user" is the entity that uses this system to input tasks or questions.

[1167] An "interactive interface" is an interface that allows users to input tasks or questions and then answer the generated questions.

[1168] A "natural language processing engine" is a machine learning algorithm that analyzes input text and extracts context, sentiment, and keywords.

[1169] "Context" refers to information that helps us understand the meaning and relevance of the entered text.

[1170] "Emotion" refers to the emotional state (e.g., joy, anger, sadness, etc.) extracted from the user's input text.

[1171] "Keywords" are important words or phrases extracted from the input text.

[1172] A "trained AI model" is artificial intelligence that is trained based on past data and generates questions in response to user input.

[1173] An "emotion recognition engine" is an algorithm that evaluates the emotional state of a user based on their input text.

[1174] "Methods for selecting questions" refer to methods for choosing the question that best fits the context and sentiment from among several generated questions.

[1175] "Means of supporting continuous dialogue" refers to methods that allow users to answer questions returned, analyze those answers again, and continue the dialogue.

[1176] "Mental support" refers to a function that aims to support the user's mental health by analyzing input related to the user's mental state and generating appropriate open-ended questions.

[1177] This invention is a system that recognizes the user's emotional state and generates more appropriate open-end questions by combining an emotional engine with an interactive interface that allows users to delve deeper into their own challenges and problems.

[1178] 1. User Interface

[1179] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or issues into text forms. For example, a user might enter, "The project is behind schedule. How can we make it run more smoothly?"

[1180] 2. Receiving user input

[1181] The terminal retrieves text data entered by the user and sends it to the server. The retrieved text data is sent to the server via a dedicated API.

[1182] 3. Server Initialization

[1183] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords. For example, words like "project," "in progress," and "delayed" might be extracted.

[1184] 4. Utilizing the Emotion Engine

[1185] The server uses an emotion engine to analyze text data and recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions from words and context in the input text. For example, emotions such as "anxiety" or "fear" may be recognized from the user's input.

[1186] 5. Question generation using AI models

[1187] The server inputs data into a trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. For example, it might generate a question like, "Have you asked each member of the project team how they feel about the recent progress?"

[1188] 6. Selection and submission of questions

[1189] The server selects the question that best fits the context and sentiment from among the multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data. After the optimal question is selected, it is sent to the user's terminal.

[1190] 7. Returning questions and continuing the dialogue

[1191] The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the conversation continues when that answer is sent back to the server. For example, the user might enter "I'll check the status of the project members," and a new conversation will follow based on that.

[1192] Examples of mental support

[1193] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[1194] Examples of how to make project progress smoother

[1195] User: The project is currently behind schedule. How can we make it progress more smoothly?

[1196] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[1197] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[1198] keyword:

[1199] Generative AI model, prompt sentence

[1200] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1201] Step 1:

[1202] Users access an interactive interface and enter their questions or tasks into a text form.

[1203] Input: Text entered by the user (e.g., "The project is behind schedule").

[1204] Action: Enter a question in the text form and click the submit button.

[1205] Output: The input text data is retrieved by the terminal.

[1206] Step 2:

[1207] The terminal retrieves text data entered by the user and sends it to the server.

[1208] Input: Text data (user questions or issues).

[1209] Operation: The device sends text data to the server using the API.

[1210] Output: The server receives text data.

[1211] Step 3:

[1212] The server passes the received text data to the natural language processing engine (NLP engine) and begins text analysis.

[1213] Input: Received text data.

[1214] Operation: The NLP engine breaks down text data and extracts context, sentiment, and keywords.

[1215] Output: Analyzed contextual information, sentiment data, and keywords.

[1216] Step 4:

[1217] The server passes the analyzed text data to the emotion engine to recognize the user's emotional state.

[1218] Input: Analyzed text data (contextual information, keywords).

[1219] Operation: The emotion engine evaluates emotions from text data and recognizes the user's emotional state.

[1220] Output: User's emotional state (e.g., impatience, anxiety).

[1221] Step 5:

[1222] The server inputs the data into a trained AI model based on the analyzed information and sentiment data, generating appropriate open-ended questions.

[1223] Input: Analyzed information (contextual information, keywords, sentiment data).

[1224] Operation: The AI ​​model generates appropriate questions based on the data.

[1225] Output: Multiple open-ended questions generated.

[1226] Step 6:

[1227] The server selects the question that best fits the context and sentiment from among the generated questions.

[1228] Input: Multiple questions generated.

[1229] Operation: The server selects questions based on selection criteria (contextual information, keywords, sentiment data).

[1230] Output: The best open-ended question.

[1231] Step 7:

[1232] The server sends the selected question back to the user's terminal, which then displays the question in an interactive interface.

[1233] Input: The best open-ended question.

[1234] Operation: The server sends a question to the terminal, and the terminal displays that question on the interface.

[1235] Output: The question displayed in the user's interactive interface.

[1236] Step 8:

[1237] The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[1238] Input: User's response text (e.g., "I will check the status of the project members").

[1239] Action: The user enters their answer and clicks the submit button.

[1240] Output: The terminal sends the response text to the server, and the next analysis process begins.

[1241] keyword:

[1242] Generative AI model, prompt sentence

[1243] (Application Example 2)

[1244] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1245] Traditional food delivery services have problems such as difficulty for users to place orders and make inquiries smoothly, and in particular, insufficient responses tailored to users' emotional states, leading to low service satisfaction. Furthermore, there was a lack of mechanisms to provide users with mental support through continuous dialogue, so there was a need to improve the user experience.

[1246] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an interactive interface means for the user to input questions or tasks; a means for analyzing the input text using a natural language processing engine and extracting context, emotions, and keywords; a means including a trained AI model for generating relevant open-ended questions based on the extracted information; a means for returning the generated questions to the user; a means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; and a means for running as a food delivery assistant application that provides appropriate suggestions and questions based on the user's emotional state. As a result, the user can receive appropriate responses according to their emotions, improving service satisfaction and enabling the provision of mental support.

[1247] An "interactive interface" is an interactive user interface that allows users to input questions or tasks.

[1248] A "natural language processing engine" refers to algorithms and related technologies used to analyze input text and extract context, sentiment, and keywords.

[1249] A "trained AI model" refers to an artificial intelligence model that has already been trained on data and is capable of producing highly accurate results for a specific task.

[1250] "Emotional state" refers to the psychological state or emotions a user exhibits when typing text.

[1251] A "food delivery assistant application" is a smartphone application that aims to improve food delivery services by providing appropriate suggestions and questions based on the user's emotional state.

[1252] An "open-ended question" is a type of question in which users can freely enter their answers and are not limited to specific choices.

[1253] "User experience" is a general term for the experiences and satisfaction that users gain through using a service or product.

[1254] In order to implement this invention, it is necessary to construct a system comprising the following elements and processes.

[1255] System Configuration

[1256] 1. User Interface

[1257] Users access the assistant using a smartphone app. The app provides an interactive interface, allowing users to input messages via text forms or voice input.

[1258] 2. Receiving user input

[1259] The terminal acquires text and voice data entered by the user and sends it to the server.

[1260] 3. Server Initialization

[1261] The server passes the received text and audio data to a natural language processing (NLP) engine to begin text analysis. Specifically, the NLP engine (for example, Google Cloud Natural Language API) extracts context, sentiment, and keywords from the input text.

[1262] 4. Utilizing the Emotion Engine

[1263] During the process of analyzing text and audio data, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. The emotion engine employs algorithms that evaluate emotions based on words and context in the input text.

[1264] 5. Question generation using AI models

[1265] The server inputs the analyzed information and sentiment data into a pre-trained AI model (for example, OpenAI's generative AI model). The AI ​​model generates appropriate open-end questions based on the user's emotional state.

[1266] 6. Selection and submission of questions

[1267] The server selects the most appropriate question from among the multiple questions generated, based on context and sentiment.

[1268] 7. Returning questions and continuing the dialogue

[1269] The server sends the selected question back to the user's terminal, which displays it in an interactive interface. The user answers the displayed question and sends it back to the server, continuing the interaction.

[1270] Hardware and software to use

[1271] Hardware: Smartphone (iOS / Android)

[1272] software:

[1273] Natural Language Processing Engine: Google Cloud Natural Language API

[1274] Emotion Engine: IBM Watson Tone Analyzer

[1275] Pre-trained AI models: Generative AI models from OpenAI

[1276] Specific example

[1277] Specific example 1:

[1278] User: Lately, my cooking has become monotonous...

[1279] AI Assistant: You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?

[1280] Specific example 2:

[1281] User: My ordered food hasn't arrived yet.

[1282] AI Assistant: We apologize for any concern regarding the order delay. We will check the latest shipping status. Have you been busy lately?

[1283] Example of a prompt

[1284] Examples of prompt statements are as follows:

[1285] Prompt: A user has sent a message about "cooking becoming monotonous." Analyze the user's emotional state and generate an appropriate open-end question.

[1286] Example response: "You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?"

[1287] This system allows users to receive appropriate responses based on their emotions, improving service satisfaction and enabling the provision of mental support.

[1288] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1289] Step 1:

[1290] The user accesses the interactive interface using a smartphone app. Here, the user enters a message using a text form or voice input. The input data is then generated.

[1291] Step 2:

[1292] The terminal acquires the input text and audio data and sends it to the server. Here, the input data is transferred from the terminal to the server.

[1293] Step 3:

[1294] The server passes the received text and audio data to a natural language processing (NLP) engine. The server uses the NLP engine (e.g., Google Cloud Natural Language API) to analyze the input text and extract context, sentiment, and keywords. Analysis results data is then generated.

[1295] Step 4:

[1296] The server passes the analyzed text data to the sentiment engine to recognize the user's emotional state. The sentiment engine (for example, IBM Watson Tone Analyzer) evaluates the emotions from the words and context in the input text and outputs sentiment data.

[1297] Step 5:

[1298] The server inputs data into a trained AI model (e.g., OpenAI's generative AI model) based on sentiment data and contextual data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. Question data is then generated.

[1299] Step 6:

[1300] The server selects the most appropriate question from the multiple questions generated, based on context and sentiment. The question selection algorithm narrows down the questions according to the selection criteria. The final question data is then generated.

[1301] Step 7:

[1302] The server sends the selected questions back to the user's terminal. The terminal receives the question data and displays it in the interactive interface. The user can then view the questions that have been sent to them.

[1303] Step 8:

[1304] The user enters an answer to the displayed question and sends it back to the server. This continues the interaction. The answer data is sent to the server and proceeds to the next processing step.

[1305] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1306] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1307] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1308] [Fourth Embodiment]

[1309] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1310] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1311] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1312] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1313] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1314] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1315] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1316] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1317] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1318] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1319] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1320] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1321] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1322] The system related to this invention is based on an interactive interface that allows users to delve deeper into their own challenges and problems. The system generates appropriate open-ended questions in response to the questions and challenges entered by the user, enabling continuous dialogue. It also includes functions to provide mental support.

[1323] Specific implementations of the system

[1324] 1. User Interface

[1325] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[1326] 2. Receiving user input

[1327] The terminal retrieves text data entered by the user and sends it to the server.

[1328] 3. Server Initialization

[1329] The server receives text data sent by the user and uses a natural language processing engine (NLP) to analyze the text. Specifically, it extracts context, sentiment, and keywords.

[1330] 4. Question generation using AI models

[1331] The server inputs the data into a pre-trained AI model based on the analyzed information. The AI ​​model generates multiple open-ended questions and selects the most appropriate one from among them.

[1332] 5. Returning questions and continuing the dialogue

[1333] The server sends the selected questions back to the user's terminal. The user enters their answers to the received questions, and these answers are sent back to the server, continuing the dialogue. This allows the user to delve deeper into their own issues and gain new perspectives.

[1334] Examples of mental support

[1335] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine to generate open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. Through their responses, users can reflect on their mental state and consider ways to improve it.

[1336] Specific example

[1337] Examples of how to make a project progress smoothly

[1338] User: The project is currently behind schedule. How can we make it proceed more smoothly?

[1339] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[1340] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[1341] Examples of mental support

[1342] User: I've been feeling stressed lately due to project pressure. How can I cope?

[1343] The server analyzes the user's input, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[1344] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[1345] This invention's system is expected to be a useful tool for comprehensively understanding and addressing users' specific challenges, and for finding solutions. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[1346] The following describes the processing flow.

[1347] Step 1:

[1348] The user launches a dedicated application or web browser and accesses an interactive interface.

[1349] Step 2:

[1350] Users use an interactive interface to input their questions and issues in text format.

[1351] Step 3:

[1352] The terminal receives text data entered by the user and sends that data to the server.

[1353] Step 4:

[1354] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[1355] Step 5:

[1356] The server inputs the extracted information into a pre-trained AI model. The AI ​​model generates multiple open-ended questions.

[1357] Step 6:

[1358] The server selects the most appropriate question from the open-ended questions generated, based on the context. The selection criteria are based on the content of the user's input text and extracted keywords.

[1359] Step 7:

[1360] The server sends the selected question back to the user's terminal.

[1361] Step 8:

[1362] The terminal displays the received question in an interactive interface.

[1363] Step 9:

[1364] The user reviews the displayed question and enters their answer.

[1365] Step 10:

[1366] The device resends the user's response to the server.

[1367] Step 11:

[1368] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[1369] Step 12:

[1370] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[1371] Step 13:

[1372] Users engage in continuous dialogue through an interactive interface, asking further questions as needed to delve deeper into the problem and discover new perspectives and solutions.

[1373] Step 14:

[1374] The server periodically incorporates new data to train the AI ​​model, improving the accuracy and relevance of the questions it generates.

[1375] (Example 1)

[1376] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1377] Traditional interactive interfaces often have inefficient processes for users to delve deeper into questions and issues. Furthermore, there are few interactive systems specifically designed for user mental support, making it difficult to adequately assist users' physical and mental well-being. Therefore, there is a need for a system that allows users to thoroughly examine their challenges and problems and resolve them effectively.

[1378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1379] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for providing the user with the opportunity to delve deeper into their tasks and problems; and means for analyzing stress and pressure-related issues and generating questions to support the user's mental state. This enables the user to consider and solve problems from a concrete and multifaceted perspective.

[1380] An "interactive interface" is an interface that allows users to input questions or tasks and engage in two-way interaction with the system.

[1381] A "natural language processing engine" is a software technology that analyzes input text data to extract context, sentiment, keywords, and other relevant information.

[1382] A "trained AI model" is an artificial intelligence model that has been trained to perform a specific task by learning from past data.

[1383] An "open-ended question" is a type of question that encourages users to answer freely and does not restrict them to providing specific answers.

[1384] "Continuous dialogue" is a process in which the user and the system repeatedly exchange questions and answers to reach a deep understanding and solution.

[1385] "Mental support" is a feature designed to provide appropriate assistance and advice to users regarding problems related to stress and pressure.

[1386] "In-depth analysis" is the process of thoroughly exploring the user's challenges and problems to find their root causes and solutions.

[1387] The system related to this invention is based on an interactive interface that allows users to delve deeper into challenges and problems and receive mental support. The following describes how this system is specifically implemented.

[1388] Building a User Interface

[1389] Users access the system using a dedicated application or a web browser. For example, a user enters the system's URL and authenticates on the login screen. Upon successful authentication, an interactive interface is displayed. This interface includes a text input form and a submit button.

[1390] Receiving user input

[1391] The device retrieves text data entered by the user. When the user writes a question or assignment in a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[1392] Initial processing by the server

[1393] The server analyzes the received text data using a natural language processing engine (e.g., IBM Watson Natural Language Understanding or Google Cloud Natural Language). During this analysis, context, sentiment, and keywords are extracted. Specifically, the server waits for HTTP requests to be received, extracts the text data upon receiving a request, and inputs it into the NLP engine to obtain the analysis results.

[1394] Question generation using AI models

[1395] The server inputs the analyzed data into a pre-trained AI model (e.g., GPT-4 or BERT). The analysis results are converted into the AI ​​model's input format and input into the model. The AI ​​model generates multiple open-ended questions and selects the most appropriate one. To return the selected question to the user, the server sends the selected question back as an HTTP response.

[1396] Sending back questions and continuing the dialogue

[1397] The terminal displays questions received from the server to the user. The returned questions are displayed in a text area on the interface, and the user answers them. When the user enters a new answer into the text form and presses the submit button, the terminal sends the text data to the server again. This allows the dialogue to continue, enabling the user to delve deeper into their problem and gain new perspectives.

[1398] Examples of mental support

[1399] Users input mental health issues such as stress and pressure. The input is analyzed by an NLP engine, which generates open-ended questions specifically designed for mental support. For example, questions like, "Have you recently had a moment where you felt relaxed?" are generated. By answering these questions, users can broaden their perspective on their own mental health and explore concrete solutions.

[1400] Specific example

[1401] Examples of project progress:

[1402] User: "The project is currently behind schedule. How can we make it proceed more smoothly?"

[1403] The server analyzes the user's question and generates a question, "Have you asked each member of the project team how they feel about the recent progress?", which it then sends back to the user.

[1404] Users can use this question to interview team members and input the results, allowing for further in-depth discussions.

[1405] Examples of mental support:

[1406] User: "I've been feeling stressed lately due to project pressure. How can I cope?"

[1407] The server analyzes the user's input and generates the question, "Have you been able to take time to relax recently?", which it then sends back to the user.

[1408] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[1409] Example of a prompt

[1410] Example regarding project progress: "Currently, the project is behind schedule. How can we make it proceed more smoothly?"

[1411] An example of mental support: "I've been feeling stressed lately due to project pressure. How can I cope?"

[1412] This system is a powerful tool for comprehensively understanding users' specific challenges and finding solutions. Furthermore, its mental support function allows users to address their challenges while maintaining their mental and physical health.

[1413] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1414] Program processing steps

[1415] Step 1:

[1416] Users access the system using a dedicated application or web browser. They enter the system's URL and then enter their authentication information on the login screen. This displays an interactive interface.

[1417] Input: System URL, Login credentials

[1418] Output: An interactive interface is displayed.

[1419] Specific actions:

[1420] 1. The user enters the system's URL into their web browser.

[1421] 2. The user enters their username and password on the login screen.

[1422] 3. If authentication is successful, an interactive interface will be displayed.

[1423] Step 2:

[1424] The device retrieves text data entered by the user. When the user enters a question or task into a text form and presses the submit button, the device retrieves this text data and sends it to the server as an HTTP request.

[1425] Input: Text data entered by the user (questions or assignments)

[1426] Output: Text data sent to the server as an HTTP request

[1427] Specific actions:

[1428] 1. The user enters a question or task into a text form.

[1429] 2. The user presses the submit button.

[1430] 3. The device retrieves the text data and sends it to the server as an HTTP request.

[1431] Step 3:

[1432] The server analyzes the received text data using a natural language processing (NLP) engine. The server inputs the text data into the NLP engine and obtains analysis results such as context, sentiment, and keywords.

[1433] Input: Text data sent as an HTTP request

[1434] Output: Analyzed context, sentiment, and keyword data

[1435] Specific actions:

[1436] 1. The server receives the HTTP request and extracts the text data.

[1437] 2. Input the text data into the NLP engine (NLP engines to use: IBM Watson Natural Language Understanding or Google Cloud Natural Language).

[1438] 3. Obtain analysis results from the NLP engine to obtain context, emotion, and keyword data.

[1439] Step 4:

[1440] The server inputs the data into a pre-trained AI model based on the analyzed information. The server converts the analysis results into the AI ​​model's input format and inputs them into the model to generate multiple open-ended questions.

[1441] Input: Analyzed context, sentiment, and keyword data

[1442] Output: Multiple open-ended questions generated

[1443] Specific actions:

[1444] 1. Convert the analysis results into an input format for the AI ​​model (AI models to use: GPT-4 or BERT).

[1445] 2. Input the converted data into the AI ​​model.

[1446] 3. The AI ​​model generates multiple open-ended questions.

[1447] Step 5:

[1448] The server selects the most appropriate question from the generated questions and sends it back to the user's terminal. The server then sends the selected question back as an HTTP response.

[1449] Input: Multiple open-ended questions generated

[1450] Output: The most appropriate question selected

[1451] Specific actions:

[1452] 1. Evaluate the generated questions and select the most appropriate one.

[1453] 2. The selected questions are sent back to the user's terminal as an HTTP response.

[1454] Step 6:

[1455] The terminal displays the question received from the server to the user. The user enters an answer to the displayed question and sends it back to the server.

[1456] Input: Question returned from the server

[1457] Output: User-entered response

[1458] Specific actions:

[1459] 1. The terminal receives an HTTP response from the server.

[1460] 2. Display the received question in the interactive interface.

[1461] 3. The user enters their answer to the question and presses the submit button.

[1462] 4. Resubmit your response to the server.

[1463] Step 7:

[1464] The server re-analyzes the user's responses and generates additional questions as needed, allowing the conversation to continue.

[1465] Input: User's response

[1466] Output: Re-analyzed context, sentiment, and keyword data, plus additional questions.

[1467] Specific actions:

[1468] 1. The server receives the user's response and analyzes it again using the NLP engine.

[1469] 2. Create input data for the AI ​​model based on the analysis results.

[1470] 3. The AI ​​model generates additional open-ended questions.

[1471] 4. Select the appropriate questions from among them and resend them to the user.

[1472] Examples of mental support

[1473] Users enter problems related to stress and pressure.

[1474] The server analyzes the input using an NLP engine and generates open-ended questions to support the user's mental state. For example, it might generate questions such as, "Have you had a moment recently where you felt relaxed?"

[1475] In summary, this system is a powerful tool for comprehensively understanding and addressing users' specific challenges. Furthermore, its mental support function allows users to work on problem-solving while maintaining their own mental and physical health.

[1476] (Application Example 1)

[1477] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1478] Conventional conversational systems have the ability to generate appropriate questions based on user input and support continuous dialogue, but specialized applications aimed at improving security awareness have not been sufficiently developed. Furthermore, the lack of feedback functions to support the improvement of user security behavior makes it difficult for users to obtain guidance for taking concrete security actions.

[1479] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1480] In this invention, the server includes means for providing an interactive interface for the user to input questions or tasks; means for analyzing the input text using a natural language processing engine and extracting context, sentiment, and keywords; means including a trained AI model for generating relevant open-ended questions based on the extracted information; means for returning the generated questions to the user; means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; means for the AI ​​model to adapt the content of the generated questions based on the user's input in order to enhance security awareness; and means for providing a feedback function to support the improvement of the user's security behavior. This makes it possible to enhance the user's security awareness and provide guidance for specific security actions.

[1481] An "interactive interface" is an interface that allows users to input questions or tasks, enabling continuous dialogue.

[1482] A "natural language processing engine" is an engine that analyzes text data entered by users and extracts context, sentiment, and keywords.

[1483] A "pre-trained AI model" is an algorithm that generates appropriate open-end questions based on previously trained data.

[1484] An "open-ended question" is a type of question in which the user's answer is not limited to a specific set of choices, but can be expressed freely.

[1485] A "feedback function" is a feature that provides specific advice and guidelines for improvement based on the user's input and actions.

[1486] "Security awareness" refers to the knowledge, awareness, and attention that users have to protect their information and assets.

[1487] "Security actions" refer to the specific actions and measures that users actually take to protect information and assets.

[1488] "Analysis" is the process of examining user input data in detail to understand and extract its meaning, emotions, and context.

[1489] The system for implementing this invention is designed as an application for improving security awareness. Users access an interactive interface through a device such as a smartphone or smart glasses. Through this interface, users can input security-related questions or issues and begin interacting with the system.

[1490] System Configuration

[1491] 1. Hardware Configuration

[1492] Devices: Smartphones, smart glasses

[1493] Server: Internet-connected computer system

[1494] Network: Internet

[1495] 2. Software Configuration

[1496] Interactive Interface: A dedicated application is installed on smartphones and smart glasses as the user interface.

[1497] Natural Language Processing Engine (NLP engine): A software engine that performs text analysis.

[1498] Pre-trained AI model: An AI algorithm for generating open-ended questions.

[1499] Processing Overview

[1500] Receiving user input: The terminal receives security-related text data entered by the user and sends it to the server.

[1501] Initial analysis: The server uses a natural language processing engine to analyze the received text data and extract context, sentiment, and keywords.

[1502] Question generation: Based on the analyzed information, the server inputs data into a trained AI model to generate open-end questions designed to enhance security awareness.

[1503] Question return: The generated questions are returned to the user's device, and the user answers them. By repeating this process, the user can gradually increase their security awareness.

[1504] Feedback function: Based on user input and actions, the server generates appropriate feedback and provides users with specific security action guidelines.

[1505] Specific example

[1506] The user launches a smartphone app and enters the question, "I feel like I've been getting a lot of phishing emails lately. How should I deal with them?" The server analyzes this text using a natural language processing engine to extract context, sentiment, and keywords.

[1507] The server then inputs the following prompts into the trained AI model.

[1508] "User question: 'I feel like I've been getting a lot of phishing emails lately. How should I deal with them?' Please generate an open-ended question to raise security awareness in response to this."

[1509] An example of a generated question sent back to the user is, "What information have you recently learned about the characteristics of phishing emails? And how do you apply that knowledge to your daily email checking?" The user then enters their answer to this question, allowing the server to continue further analysis and dialogue.

[1510] This will strengthen users' specific security knowledge and actions, and improve their security awareness.

[1511] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1512] Step 1:

[1513] Receiving user input

[1514] The user uses a smartphone or smart glasses to input questions or tasks into an interactive interface. For example, the user might input the question, "I've been receiving a lot of phishing emails lately. How should I deal with this?" The device receives the input as text data and sends it to the server via the internet.

[1515] Step 2:

[1516] Analysis using a natural language processing engine

[1517] The server inputs the text data received from the user into a natural language processing engine (NLP engine). Here, the NLP engine analyzes the context, sentiment, and keywords of the text to deepen its understanding of the context. This analysis result (context, sentiment, and keywords) is output as a dataset to be used in the next step.

[1518] Step 3:

[1519] Question generation using a pre-trained AI model

[1520] The server inputs data into a trained AI model based on the analysis results of the NLP engine. The AI ​​model generates multiple open-ended questions to raise security awareness and selects the most appropriate question from among them. For example, the AI ​​model might generate the question, "What information have you recently learned about the characteristics of phishing emails?" and the selected question is sent back to the user in the next step.

[1521] Step 4:

[1522] Return of question

[1523] The server sends the generated question back to the user's terminal. The user's terminal displays this question, and the user answers it. Through this interaction, the user continues to input information to gain a deeper understanding.

[1524] Step 5:

[1525] Feedback function

[1526] The device sends new input from the user back to the server, which analyzes this input using an NLP engine and an AI model. The analysis results are generated as specific feedback to improve the user's security behavior. For example, feedback such as, "Learn the characteristics of phishing emails and think about how to apply that knowledge," might be generated. This feedback is sent back to the user's device and displayed again.

[1527] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1528] This invention's system, based on an interactive interface that allows users to delve deeper into their own challenges and problems, combines this with an emotion engine to recognize the user's emotional state and generate more appropriate open-ended questions. This enables users to effectively solve their problems and manage their mental health.

[1529] Specific implementations of the system

[1530] 1. User Interface

[1531] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or tasks into text forms.

[1532] 2. Receiving user input

[1533] The terminal retrieves text data entered by the user and sends it to the server.

[1534] 3. Server Initialization

[1535] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[1536] 4. Utilizing the Emotion Engine

[1537] As the server analyzes text data, it utilizes an emotion engine to recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions based on words and context in the input text.

[1538] 5. Question generation using AI models

[1539] The server inputs data into a pre-trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state.

[1540] 6. Selection and submission of questions

[1541] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[1542] 7. Returning questions and continuing the dialogue

[1543] The server sends the selected question back to the user's terminal. The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[1544] Examples of mental support

[1545] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[1546] Specific example

[1547] Examples of how to make a project progress smoothly

[1548] User: The project is currently behind schedule. How can we make it progress more smoothly?

[1549] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[1550] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[1551] Examples of mental support

[1552] User: I've been feeling stressed lately due to project pressure. How can I cope?

[1553] The server analyzes the user's input, recognizes the user's high stress level using an emotion engine, generates the question "Have you been able to take time to relax recently?", and sends it back to the user.

[1554] By answering this question, users can broaden their perspective on their own mental health care and explore specific ways to improve it.

[1555] This invention's system is expected to be a useful tool for comprehensively understanding the user's specific challenges and finding solutions based on emotions and context. Furthermore, its mental support function can help maintain the user's physical and mental well-being.

[1556] The following describes the processing flow.

[1557] Step 1:

[1558] The user launches a dedicated application or web browser and accesses an interactive interface.

[1559] Step 2:

[1560] Users use an interactive interface to input their questions and issues in text format.

[1561] Step 3:

[1562] The terminal retrieves text data entered by the user and sends that data to the server.

[1563] Step 4:

[1564] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords.

[1565] Step 5:

[1566] In parallel with text analysis, the server uses an emotion engine to recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions based on words and context in the input text.

[1567] Step 6:

[1568] The server uses the extracted contextual information, sentiment data, and keywords to input data into a pre-trained AI model.

[1569] Step 7:

[1570] The server uses an AI model to generate multiple open-ended questions based on the user's context and emotional state.

[1571] Step 8:

[1572] The server selects the question that best fits the context and sentiment from among multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data.

[1573] Step 9:

[1574] The server sends the selected question back to the user's terminal.

[1575] Step 10:

[1576] The terminal displays the received question in an interactive interface.

[1577] Step 11:

[1578] The user reviews the displayed question and enters their answer.

[1579] Step 12:

[1580] The device resends the user's response to the server.

[1581] Step 13:

[1582] The server analyzes the newly received response using an NLP engine and extracts context, sentiment, and keywords again.

[1583] Step 14:

[1584] The server saves the extracted information as history, which influences subsequent interactions and generated questions.

[1585] Step 15:

[1586] The server re-inputs the extracted information into the AI ​​model to generate new open-ended questions. This process is repeated until the user finds a satisfactory answer or an in-depth solution.

[1587] Step 16:

[1588] Users engage in continuous dialogue through an interactive interface, asking further questions as needed to delve deeper into the problem and discover new perspectives and solutions.

[1589] Step 17:

[1590] The server periodically incorporates new data to train the AI ​​model, improving the accuracy and relevance of the questions it generates.

[1591] (Example 2)

[1592] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1593] In conventional conversational systems, accurately understanding the user's emotional state and generating appropriate questions accordingly was difficult. As a result, maintaining effective dialogue in solving users' problems and providing mental care support was challenging. Furthermore, if the generated questions did not fit the context or emotions, user satisfaction decreased, and the usefulness of the system was impaired.

[1594] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means including an emotion recognition engine for evaluating the user's emotional state, means including a trained AI model for generating relevant open-ended questions based on extracted information and emotion data, and means for selecting the optimal question from among the generated questions. This makes it possible to generate and select appropriate questions that reflect the user's emotional state.

[1595] A "user" is the entity that uses this system to input tasks or questions.

[1596] An "interactive interface" is an interface that allows users to input tasks or questions and then answer the generated questions.

[1597] A "natural language processing engine" is a machine learning algorithm that analyzes input text and extracts context, sentiment, and keywords.

[1598] "Context" refers to information that helps us understand the meaning and relevance of the entered text.

[1599] "Emotion" refers to the emotional state (e.g., joy, anger, sadness, etc.) extracted from the user's input text.

[1600] "Keywords" are important words or phrases extracted from the input text.

[1601] A "trained AI model" is artificial intelligence that is trained based on past data and generates questions in response to user input.

[1602] An "emotion recognition engine" is an algorithm that evaluates the emotional state of a user based on their input text.

[1603] "Methods for selecting questions" refer to methods for choosing the question that best fits the context and sentiment from among several generated questions.

[1604] "Means of supporting continuous dialogue" refers to methods that allow users to answer questions returned, analyze those answers again, and continue the dialogue.

[1605] "Mental support" refers to a function that aims to support the user's mental health by analyzing input related to the user's mental state and generating appropriate open-ended questions.

[1606] This invention is a system that recognizes the user's emotional state and generates more appropriate open-end questions by combining an emotional engine with an interactive interface that allows users to delve deeper into their own challenges and problems.

[1607] 1. User Interface

[1608] Users access the system using a dedicated application or a web browser. An interactive interface is provided, allowing users to enter their questions or issues into text forms. For example, a user might enter, "The project is behind schedule. How can we make it run more smoothly?"

[1609] 2. Receiving user input

[1610] The terminal retrieves text data entered by the user and sends it to the server. The retrieved text data is sent to the server via a dedicated API.

[1611] 3. Server Initialization

[1612] The server passes the received text data to a natural language processing (NLP) engine, which then begins text analysis. Specifically, the NLP engine breaks down the input text and extracts context, sentiment, and keywords. For example, words like "project," "in progress," and "delayed" might be extracted.

[1613] 4. Utilizing the Emotion Engine

[1614] The server uses an emotion engine to analyze text data and recognize the user's emotional state (e.g., joy, anger, sadness). The emotion engine uses algorithms that evaluate emotions from words and context in the input text. For example, emotions such as "anxiety" or "fear" may be recognized from the user's input.

[1615] 5. Question generation using AI models

[1616] The server inputs data into a trained AI model based on the analyzed information and sentiment data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. For example, it might generate a question like, "Have you asked each member of the project team how they feel about the recent progress?"

[1617] 6. Selection and submission of questions

[1618] The server selects the question that best fits the context and sentiment from among the multiple questions generated. The selection criteria are based on contextual information, keywords, and sentiment data. After the optimal question is selected, it is sent to the user's terminal.

[1619] 7. Returning questions and continuing the dialogue

[1620] The terminal displays the received question in an interactive interface. The user enters an answer to the displayed question, and the conversation continues when that answer is sent back to the server. For example, the user might enter "I'll check the status of the project members," and a new conversation will follow based on that.

[1621] Examples of mental support

[1622] Users input mental health issues such as stress and pressure. This input is then analyzed by an NLP engine and an emotion engine to generate open-ended questions specifically designed for mental support. For example, questions such as, "Have you had a moment of relaxation recently?" are generated. By answering these questions, users can reflect on their mental state and explore ways to improve it.

[1623] Examples of how to make project progress smoother

[1624] User: The project is currently behind schedule. How can we make it progress more smoothly?

[1625] The server analyzes the user's question and, using its sentiment engine, recognizes that the user is feeling impatient or anxious. It then generates and sends back the question, "Have you asked each member of the project team how they feel about the recent progress?"

[1626] Users can conduct interviews with team members based on this question and input the results, allowing for further in-depth dialogue.

[1627] keyword:

[1628] Generative AI model, prompt sentence

[1629] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1630] Step 1:

[1631] Users access an interactive interface and enter their questions or tasks into a text form.

[1632] Input: Text entered by the user (e.g., "The project is behind schedule").

[1633] Action: Enter a question in the text form and click the submit button.

[1634] Output: The input text data is retrieved by the terminal.

[1635] Step 2:

[1636] The terminal retrieves text data entered by the user and sends it to the server.

[1637] Input: Text data (user questions or issues).

[1638] Operation: The device sends text data to the server using the API.

[1639] Output: The server receives text data.

[1640] Step 3:

[1641] The server passes the received text data to the natural language processing engine (NLP engine) and begins text analysis.

[1642] Input: Received text data.

[1643] Operation: The NLP engine breaks down text data and extracts context, sentiment, and keywords.

[1644] Output: Analyzed contextual information, sentiment data, and keywords.

[1645] Step 4:

[1646] The server passes the analyzed text data to the emotion engine to recognize the user's emotional state.

[1647] Input: Analyzed text data (contextual information, keywords).

[1648] Operation: The emotion engine evaluates emotions from text data and recognizes the user's emotional state.

[1649] Output: User's emotional state (e.g., impatience, anxiety).

[1650] Step 5:

[1651] The server inputs the data into a trained AI model based on the analyzed information and sentiment data, generating appropriate open-ended questions.

[1652] Input: Analyzed information (contextual information, keywords, sentiment data).

[1653] Operation: The AI ​​model generates appropriate questions based on the data.

[1654] Output: Multiple open-ended questions generated.

[1655] Step 6:

[1656] The server selects the question that best fits the context and sentiment from among the generated questions.

[1657] Input: Multiple questions generated.

[1658] Operation: The server selects questions based on selection criteria (contextual information, keywords, sentiment data).

[1659] Output: The best open-ended question.

[1660] Step 7:

[1661] The server sends the selected question back to the user's terminal, which then displays the question in an interactive interface.

[1662] Input: The best open-ended question.

[1663] Operation: The server sends a question to the terminal, and the terminal displays that question on the interface.

[1664] Output: The question displayed in the user's interactive interface.

[1665] Step 8:

[1666] The user enters an answer to the displayed question, and the interaction continues when that answer is sent back to the server.

[1667] Input: User's response text (e.g., "I will check the status of the project members").

[1668] Action: The user enters their answer and clicks the submit button.

[1669] Output: The terminal sends the response text to the server, and the next analysis process begins.

[1670] keyword:

[1671] Generative AI model, prompt sentence

[1672] (Application Example 2)

[1673] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1674] Traditional food delivery services have problems such as difficulty for users to place orders and make inquiries smoothly, and in particular, insufficient responses tailored to users' emotional states, leading to low service satisfaction. Furthermore, there was a lack of mechanisms to provide users with mental support through continuous dialogue, so there was a need to improve the user experience.

[1675] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes an interactive interface means for the user to input questions or tasks; a means for analyzing the input text using a natural language processing engine and extracting context, emotions, and keywords; a means including a trained AI model for generating relevant open-ended questions based on the extracted information; a means for returning the generated questions to the user; a means for providing an interface for the user to answer the returned questions and supporting continuous dialogue; and a means for running as a food delivery assistant application that provides appropriate suggestions and questions based on the user's emotional state. As a result, the user can receive appropriate responses according to their emotions, improving service satisfaction and enabling the provision of mental support.

[1676] An "interactive interface" is an interactive user interface that allows users to input questions or tasks.

[1677] A "natural language processing engine" refers to algorithms and related technologies used to analyze input text and extract context, sentiment, and keywords.

[1678] A "trained AI model" refers to an artificial intelligence model that has already been trained on data and is capable of producing highly accurate results for a specific task.

[1679] "Emotional state" refers to the psychological state or emotions a user exhibits when typing text.

[1680] A "food delivery assistant application" is a smartphone application that aims to improve food delivery services by providing appropriate suggestions and questions based on the user's emotional state.

[1681] An "open-ended question" is a type of question in which users can freely enter their answers and are not limited to specific choices.

[1682] "User experience" is a general term for the experiences and satisfaction that users gain through using a service or product.

[1683] In order to implement this invention, it is necessary to construct a system comprising the following elements and processes.

[1684] System Configuration

[1685] 1. User Interface

[1686] Users access the assistant using a smartphone app. The app provides an interactive interface, allowing users to input messages via text forms or voice input.

[1687] 2. Receiving user input

[1688] The terminal acquires text and voice data entered by the user and sends it to the server.

[1689] 3. Server Initialization

[1690] The server passes the received text and audio data to a natural language processing (NLP) engine to begin text analysis. Specifically, the NLP engine (for example, Google Cloud Natural Language API) extracts context, sentiment, and keywords from the input text.

[1691] 4. Utilizing the Emotion Engine

[1692] During the process of analyzing text and audio data, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotional state. The emotion engine employs algorithms that evaluate emotions based on words and context in the input text.

[1693] 5. Question generation using AI models

[1694] The server inputs the analyzed information and sentiment data into a pre-trained AI model (for example, OpenAI's generative AI model). The AI ​​model generates appropriate open-end questions based on the user's emotional state.

[1695] 6. Selection and submission of questions

[1696] The server selects the most appropriate question from among the multiple questions generated, based on context and sentiment.

[1697] 7. Returning questions and continuing the dialogue

[1698] The server sends the selected question back to the user's terminal, which displays it in an interactive interface. The user answers the displayed question and sends it back to the server, continuing the interaction.

[1699] Hardware and software to use

[1700] Hardware: Smartphone (iOS / Android)

[1701] software:

[1702] Natural Language Processing Engine: Google Cloud Natural Language API

[1703] Emotion Engine: IBM Watson Tone Analyzer

[1704] Pre-trained AI models: Generative AI models from OpenAI

[1705] Specific example

[1706] Specific example 1:

[1707] User: Lately, my cooking has become monotonous...

[1708] AI Assistant: You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?

[1709] Specific example 2:

[1710] User: My ordered food hasn't arrived yet.

[1711] AI Assistant: We apologize for any concern regarding the order delay. We will check the latest shipping status. Have you been busy lately?

[1712] Example of a prompt

[1713] Examples of prompt statements are as follows:

[1714] Prompt: A user has sent a message about "cooking becoming monotonous." Analyze the user's emotional state and generate an appropriate open-end question.

[1715] Example response: "You're having trouble with your cooking becoming monotonous, aren't you? How about trying a new recipe? Is there anything you've been wanting to try lately?"

[1716] This system allows users to receive appropriate responses based on their emotions, improving service satisfaction and enabling the provision of mental support.

[1717] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1718] Step 1:

[1719] The user accesses the interactive interface using a smartphone app. Here, the user enters a message using a text form or voice input. The input data is then generated.

[1720] Step 2:

[1721] The terminal acquires the input text and audio data and sends it to the server. Here, the input data is transferred from the terminal to the server.

[1722] Step 3:

[1723] The server passes the received text and audio data to a natural language processing (NLP) engine. The server uses the NLP engine (e.g., Google Cloud Natural Language API) to analyze the input text and extract context, sentiment, and keywords. Analysis results data is then generated.

[1724] Step 4:

[1725] The server passes the analyzed text data to the sentiment engine to recognize the user's emotional state. The sentiment engine (for example, IBM Watson Tone Analyzer) evaluates the emotions from the words and context in the input text and outputs sentiment data.

[1726] Step 5:

[1727] The server inputs data into a trained AI model (e.g., OpenAI's generative AI model) based on sentiment data and contextual data. The AI ​​model generates appropriate open-end questions according to the user's emotional state. Question data is then generated.

[1728] Step 6:

[1729] The server selects the most appropriate question from the multiple questions generated, based on context and sentiment. The question selection algorithm narrows down the questions according to the selection criteria. The final question data is then generated.

[1730] Step 7:

[1731] The server sends the selected questions back to the user's terminal. The terminal receives the question data and displays it in the interactive interface. The user can then view the questions that have been sent to them.

[1732] Step 8:

[1733] The user enters an answer to the displayed question and sends it back to the server. This continues the interaction. The answer data is sent to the server and proceeds to the next processing step.

[1734] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1735] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1736] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1737] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1738] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1739] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1740] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1741] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1742] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1743] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1744] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1745] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1746] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1747] 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.

[1748] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1749] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1750] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1751] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1752] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1753] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1754] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1755] The following is further disclosed regarding the embodiments described above.

[1756] (Claim 1)

[1757] An interactive interface for users to input questions and tasks,

[1758] A method for analyzing input text using a natural language processing engine and extracting context, sentiment, and keywords,

[1759] A means including a trained AI model for generating relevant open-end questions based on extracted information,

[1760] A means of returning the generated question to the user,

[1761] It provides an interface for users to answer questions returned by others, and a means to support continuous dialogue.

[1762] A system that includes this.

[1763] (Claim 2)

[1764] The system according to claim 1, which analyzes input related to the user's mental state in order to provide mental support and generates appropriate open-ended questions.

[1765] (Claim 3)

[1766] The system according to claim 1, comprising means for receiving new input from a user, re-analyzing it, generating and returning an appropriate open-ended question, and enabling continuous interaction.

[1767] "Example 1"

[1768] (Claim 1)

[1769] An interactive interface for users to input questions and tasks,

[1770] A method for analyzing input text using a natural language processing engine and extracting context, sentiment, and keywords,

[1771] A means including a trained AI model for generating relevant open-end questions based on extracted information,

[1772] A means of returning the generated question to the user,

[1773] It provides an interface for users to answer questions returned by others, and a means to support continuous dialogue.

[1774] The means provided to allow users to delve deeper into their own challenges and problems,

[1775] A means for analyzing problems related to stress and pressure and generating questions to support the user's mental state,

[1776] A system that includes this.

[1777] (Claim 2)

[1778] The system according to claim 1, which analyzes input related to the user's mental state in order to provide mental support and generates appropriate open-ended questions.

[1779] (Claim 3)

[1780] The system according to claim 1, comprising means for receiving new input from a user, re-analyzing it, generating and returning an appropriate open-ended question, and enabling continuous interaction.

[1781] "Application Example 1"

[1782] (Claim 1)

[1783] An interactive interface for users to input questions and tasks,

[1784] A method for analyzing input text using a natural language processing engine and extracting context, sentiment, and keywords,

[1785] A means including a trained AI model for generating relevant open-end questions based on extracted information,

[1786] A means of returning the generated question to the user,

[1787] It provides an interface for users to answer questions returned by others, and a means to support continuous dialogue.

[1788] A means by which an AI model adapts the content of questions generated to raise security awareness based on user input,

[1789] A means to provide feedback functionality to support the improvement of user security behavior,

[1790] A system that includes this.

[1791] (Claim 2)

[1792] The system according to claim 1, which analyzes input related to the user's mental state in order to provide mental support and generates appropriate open-ended questions.

[1793] (Claim 3)

[1794] The system according to claim 1, comprising means for receiving new input from a user, re-analyzing it, and generating and returning an open-ended question to enable a continuous security dialogue.

[1795] "Example 2 of combining an emotion engine"

[1796] (Claim 1)

[1797] An interactive interface for users to input questions and tasks,

[1798] A method for analyzing input text using a natural language processing engine and extracting context, sentiment, and keywords,

[1799] A means including a trained AI model for generating relevant open-end questions based on extracted information and sentiment data,

[1800] A means including an emotion recognition engine that evaluates the user's emotional state,

[1801] A means of selecting the most suitable question from the generated questions,

[1802] A means of returning the selected questions to the user,

[1803] It provides an interface for users to answer questions returned by others, and a means to support continuous dialogue.

[1804] A system that includes this.

[1805] (Claim 2)

[1806] The system according to claim 1, which analyzes input related to the user's mental state in order to provide mental support and generates appropriate open-ended questions.

[1807] (Claim 3)

[1808] The system according to claim 1, comprising means for receiving new input from a user, re-analyzing it, generating and returning an appropriate open-ended question, and enabling continuous interaction.

[1809] "Application example 2 when combining with an emotional engine"

[1810] (Claim 1)

[1811] An interactive interface for users to input questions and tasks,

[1812] A method for analyzing input text using a natural language processing engine and extracting context, sentiment, and keywords,

[1813] A means including a trained AI model for generating relevant open-end questions based on extracted information,

[1814] A means of returning the generated question to the user,

[1815] It provides an interface for users to answer questions returned by others, and a means to support continuous dialogue.

[1816] A means of implementing a food delivery assistant application that provides appropriate suggestions and questions based on the user's emotional state,

[1817] A system that includes this.

[1818] (Claim 2)

[1819] The system according to claim 1, which analyzes input related to the user's mental state in order to provide mental support and generates appropriate open-ended questions.

[1820] (Claim 3)

[1821] The system according to claim 1, comprising means for generating prompt statements and providing dialogue regarding food delivery according to the user's emotional state. [Explanation of Symbols]

[1822] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An interactive interface for users to input questions and tasks, A method for analyzing input text using a natural language processing engine and extracting context, sentiment, and keywords, A means including a trained AI model for generating relevant open-end questions based on extracted information, A means of returning the generated question to the user, It provides an interface for users to answer questions returned by others, and a means to support continuous dialogue. A system that includes this.

2. The system according to claim 1, which analyzes input related to the user's mental state in order to provide mental support and generates appropriate open-ended questions.

3. The system according to claim 1, comprising means for receiving new input from a user, re-analyzing it, generating and returning an appropriate open-ended question, and enabling continuous dialogue.

Images