system

Abstract

Provide a system. The method includes: providing a user with a series of psychology-based questions; A means for collecting user response data; A means for analyzing the collected response data to generate a user profile; means for generating personalized responses and instructional strategies based on the user profile; A means for providing the generated response and instruction method to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, there has been an increasing demand for individualized support in education and counseling settings. However, conventional systems have had difficulty effectively grasping changes in a user's psychological state and interests and providing appropriate support. Furthermore, providing continuous and timely support to individual users is time-consuming and difficult to do efficiently. Given this background, there is a demand for a system that can automatically provide appropriate support and guidance based on an accurate psychological profile of each user. [Means for solving the problem]

[0005] In order to solve these problems, the present invention provides the following means. First, a means is provided for presenting a series of psychology-based questions to a user and collecting response data. Next, a means is used for analyzing the collected response data and generating a user profile. The system further includes a means for generating individual responses and instruction methods based on the user profile and providing them to the user. In addition, a means is provided for presenting new psychology-based questions to the user at regular intervals, collecting the response data, and comparing and analyzing it with past data. Finally, the system includes a means for updating the user profile based on the collected new response data and generating new individual responses and instruction methods based on the updated user profile. This makes it possible to continuously and efficiently provide appropriate responses and instruction to individual users.

[0006] "Psychologically-based questions" are questions designed based on psychological theories and research findings, and are used to assess a user's personality traits, interests, emotional state, etc.

[0007] "User" refers to an individual or entity using the system and responding to psychologically based questions.

[0008] "Response data" is a collection of response information provided by users to psychologically based questions.

[0009] A "user profile" is a collection of evaluation information such as a user's personality traits, interests, and emotional state, obtained by analyzing collected response data.

[0010] "Individual responses and instruction methods" refer to responses and instruction methods that are generated based on a user profile and are suited to a specific user.

[0011] A "terminal" is an electronic device through which a user accesses the system and has the ability to submit questions and collect response data.

[0012] A "server" is a central processing unit that receives response data, performs analysis, and generates and updates user profiles.

[0013] A "fixed period" refers to a predetermined time interval during which new questions are presented to the user and changes in mood and interests are periodically assessed.

[0014] "Comparative analysis" is an analytical method for identifying changes in a user's psychological state and interests by comparing newly collected response data with past response data.

[0015] "Database" refers to the computer system or storage where collected response data and generated user profiles are recorded and stored. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[0038] System configuration

[0039] server

[0040] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server is also responsible for generating new questionnaires and generating personalized responses and coaching methods.

[0041] Terminal

[0042] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[0043] User

[0044] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[0045] Program processing

[0046] Data Collection Overview

[0047] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[0048] Terminal: Presents a list of questions to the user and collects their answers.

[0049] User: Provides answers to questions posed and sends the data to the device.

[0050] Processing response data

[0051] Terminal: Sends the user's response data to the server.

[0052] Server: Analyzes the received response data and evaluates the user's personality traits, interests, and emotional state to generate a user profile.

[0053] Regular data collection and analysis

[0054] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[0055] Terminal: Presents a new list of questions to the user and collects their answers.

[0056] User: Answers questions and sends the data to the server via the device.

[0057] Server: Compares and analyzes new response data with past data to understand changes in user sentiment and interests.

[0058] Generate and deliver personalized responses

[0059] Server: Generates personalized responses and guidance based on the updated user profile. For example, it suggests relaxation techniques for a user experiencing increased stress.

[0060] Terminal: Displays the response and instruction received from the server to the user.

[0061] User: Review the advice and guidance provided and implement it as needed.

[0062] Specific examples

[0063] Example of first login

[0064] Server: Send the following questions to the terminal of a newly registered user.

[0065] "How are you feeling right now?"

[0066] "What hobbies do you have?"

[0067] "How often do you meet with your friends?"

[0068] Terminal: Display the question to the user.

[0069] User: Answers the questions and sends them to the server from the device.

[0070] Server: Analyzes the response data and generates a user profile.

[0071] Examples of regular follow-up

[0072] Server: After one month, generate a new list of questions for the user and send it to the device.

[0073] Terminal: Display the new question to the user.

[0074] User: Answers questions and sends the data from the device to the server.

[0075] Server: Analyzes new response data and compares it with past data. For example, if a user responds that they are feeling more stressed, the server generates advice accordingly.

[0076] Terminal: Displays the generated advice to the user.

[0077] User: Check out the advice and try yoga.

[0078] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] Server: Once a new user has registered, it generates a series of psychologically based questions and sends them to the device.

[0082] Step 2:

[0083] Terminal: Displays the generated list of questions to the user.

[0084] Step 3:

[0085] User: Answers the questionnaire and enters the answer data into the terminal.

[0086] Step 4:

[0087] Terminal: Sends the answer data entered by the user to the server.

[0088] Step 5:

[0089] Server: Receives the response data and analyzes it using an analytics engine. This analysis reveals the user's personality traits, interests, and current emotional state.

[0090] Step 6:

[0091] Server: Generates a user profile from the analysis results and stores the profile in a database.

[0092] Step 7:

[0093] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[0094] Step 8:

[0095] Terminal: The generated responses and instruction methods are displayed to the user, who then confirms them.

[0096] Step 9:

[0097] Server: After a certain period of time (e.g., one month), send a remote reminder and generate a new list of psychology-based questions for the user and send them to the device.

[0098] Step 10:

[0099] Terminal: Present the new question list to the user.

[0100] Step 11:

[0101] User: Answers a new question and enters the answer data into the device.

[0102] Step 12:

[0103] Device: Sends the user's new answer data to the server.

[0104] Step 13:

[0105] Server: Analyzes new response data and compares it with past response data.

[0106] Step 14:

[0107] Server: Updates the user's profile based on the analysis results, generating an up-to-date profile that reflects changes in the user's mood and interests.

[0108] Step 15:

[0109] Server: Generates new personalized responses and coaching strategies based on the updated user profile, such as stress reduction strategies or new hobby recommendations, if needed.

[0110] Step 16:

[0111] Device: Display the latest updates and guidance to the user.

[0112] Step 17:

[0113] User: Review any new guidance or solutions provided and implement them as needed.

[0114] This series of steps enables the system to flexibly respond to changes in the user's psychological state and interests, and provide appropriate, personalized advice and guidance.

[0115] Example 1

[0116] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0117] Conventional psychology-based data collection systems lack the ability to respond to individual users, making it difficult to accurately grasp the continuous changes in a user's emotions and interests. As a result, the accuracy of individualized instruction methods and advice is low, making it difficult to provide effective support. Furthermore, generating question lists requires a lot of manpower, and the systems lack scalability and flexibility.

[0118] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0119] In this invention, the server includes means for presenting a series of psychology-based questions to the user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, and means for providing the generated responses and instruction methods to the user. This makes it possible to continuously grasp changes in the user's psychological state and interests and provide appropriate responses and instruction.

[0120] A "psychologically based questionnaire" is a series of questions designed based on psychological theory and research to assess a user's psychological state, personality traits, and interests.

[0121] "User response data" is data that includes user-provided responses to the series of psychology-based questions.

[0122] A "user profile" is a collection of information generated based on a user's response data to indicate the user's personality traits, interests, emotional state, etc.

[0123] "Individualized responses and guidance methods" are methods for providing advice and assistance suited to a particular user based on the generated user profile.

[0124] A "generative AI model" is a model that uses artificial intelligence technology to generate text in natural language based on a specified prompt.

[0125] A "prompt" is a piece of text that is input to a generative AI model and provides instructions for the model to generate appropriate output.

[0126] A "machine learning algorithm" is a mathematical method or model that automatically learns from data, recognizes patterns, and makes predictions and classifications.

[0127] "Data analysis library" is a general term for software libraries used to collect, organize, analyze, and visualize data.

[0128] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[0129] System configuration

[0130] server

[0131] The server is a central processing unit that receives user response data, analyzes it, and generates and updates user profiles. The server also generates new question lists and generates personalized responses and instructional methods. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-3®) to generate question lists and analyzes the response data using Python's Pandas and Scikit-learn.

[0132] Terminal

[0133] The terminal is an electronic device accessed by the user, which poses psychological questions, collects the user's answers, and sends them to the server. The terminal can be a PC, smartphone, tablet, etc. The terminal displays the list of questions and sends the answers entered by the user to the server via an HTTP request.

[0134] User

[0135] The user is an individual or an organization that uses this system and is the subject of answering psychological questions. The user answers the questions using a terminal.

[0136] Program processing

[0137] Data Collection Overview

[0138] The server generates a list of psychology-based questions when the user logs in for the first time and sends them to the terminal. The terminal displays the list of questions to the user, collects the answers, and sends them to the server. The user provides answers to the displayed questions and sends the data to the terminal.

[0139] Processing response data

[0140] The device sends the user's response data to the server, which then analyzes the received response data and generates a user profile by evaluating the user's personality traits, interests, and emotional state. This analysis uses data analysis libraries such as Python's Pandas and Scikit-learn.

[0141] Regular data collection and analysis

[0142] The server periodically generates a new list of questions based on psychology for the user and sends it to the terminal. The terminal provides the new list of questions to the user and collects their answers. The user answers the questions and sends the data to the server via the terminal. The server compares and analyzes the new answer data with past data to understand changes in the user's feelings and interests.

[0143] Generate and deliver personalized responses

[0144] The server generates individualized responses and guidance methods based on the updated user profile. For example, it might suggest relaxation methods to a user experiencing increasing stress. The device displays the responses and guidance methods received from the server to the user. The user can then review the provided advice and guidance and implement them as necessary.

[0145] Specific examples

[0146] Example of first login

[0147] The server sends the following questions to the terminal of the newly registered user:

[0148] "How are you feeling right now?"

[0149] "What hobbies do you have?"

[0150] "How often do you meet with your friends?"

[0151] The device displays questions to the user. The user answers the questions and sends them to the server. The server analyzes the answer data and generates a user profile. For example, it uses Scikit-learn, a Python analysis library.

[0152] Examples of regular follow-up

[0153] The server generates a new list of questions for the user one month later and sends it to the device. The device displays the new questions to the user. The user answers the questions and sends the data from the device to the server. The server analyzes the new answer data and compares it with past data. For example, if the user answers "my stress has increased," the server generates advice accordingly. The device displays the generated advice to the user. The user checks the advice and tries yoga.

[0154] Prompt Sentence Examples

[0155] Generate a list of questions to ask users when they first log in: "How are you feeling right now?", "What are your hobbies?", "How often do you meet up with your friends?"

[0156]

[0157] Based on the user's response data, suggest ways to relieve stress, such as yoga, meditation, or walking.

[0158] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1: First login authentication

[0161] The server compares the authentication information (user ID and password) entered by the user with the database and authenticates the login. Specifically, the server receives the user's authentication information and checks whether it matches the information stored in the database. The input to this step is the authentication information entered by the user into the terminal, and the output is whether the login was successful or not.

[0162] Step 2: Generate a questionnaire

[0163] After successful authentication, the server generates a list of psychology-based questions to present to the user. Using a generative AI model, it creates appropriate questions based on the prompt text. Specifically, it inputs the prompt "Generate questions to display when the user logs in for the first time: How are you feeling right now?" and sends the generated text to the terminal as a list of questions. The input for this step is the prompt text, and the output is the generated list of questions.

[0164] Step 3: Question list display

[0165] The terminal displays the question list received from the server to the user. Specifically, the terminal places questions on the terminal's UI so that the user can answer them. The input of this step is the question list sent from the server, and the output is the user's visual confirmation.

[0166] Step 4: Collect response data

[0167] The terminal collects the answers entered by the user. The user enters answers to questions through the terminal. The input of this step is the user's answer, and the output is the collected answer data.

[0168] Step 5: Send response data

[0169] The terminal sends the collected response data to the server. Specifically, the terminal passes data to the server using the POST method of the HTTP request. The input of this step is the response data collected by the terminal, and the output is the response data sent to the server.

[0170] Step 6: Analyze response data

[0171] The server analyzes the received response data. Using Python's Pandas or Scikit-learn, the response data is converted into a data frame and the user's personality traits and interests are evaluated. As a specific example, a machine learning model is run on the converted data frame to extract the user's profile. The input to this step is the response data, and the output is the analysis results.

[0172] Step 7: Create a user profile

[0173] The server generates a user profile from the analysis results. The generated profile contains comprehensive information about the user's personality traits and interests. Specifically, it uses Scikit-learn to create a model and saves it in a database. The input to this step is the analysis results, and the output is the user profile.

[0174] Step 8: Provide feedback

[0175] The server generates initial feedback and advice based on the generated user profile. Specifically, it creates a feedback sentence from the generated profile and sends it to the terminal. The terminal displays the feedback to the user. The input of this step is the user profile, and the output is a feedback sentence.

[0176] Step 9: Generate regular follow-up questions

[0177] The server generates a new list of questions at regular intervals. It uses a generative AI model to create appropriate questions based on the prompt. As a specific example, a prompt such as "Please generate stress check questions as a follow-up in one month" is input to generate new questions. The input for this step is the prompt for follow-up, and the output is a new list of questions.

[0178] Step 10: Display the follow-up questions list

[0179] The terminal displays the newly generated question list to the user. The user checks the questions on the terminal and enters the answers. The input of this step is the new question list sent from the server, and the output is the user's visual confirmation.

[0180] Step 11: Collect new response data

[0181] The terminal collects new answers entered by the user. The user answers questions through the terminal. The input of this step is the user's new answers, and the output is the collected new answer data.

[0182] Step 12: Send new response data

[0183] The terminal sends the collected new response data to the server. Specifically, the terminal sends the data using the POST method of the HTTP request. The input of this step is the collected new response data, and the output is the new response data sent to the server.

[0184] Step 13: New data analysis

[0185] The server compares the newly received response data with past data and analyzes it. Python's Pandas is used to combine the old and new data into a data frame to understand changes in user sentiment and interests. The input for this step is the new response data and past data, and the output is the results of the comparison and analysis.

[0186] Step 14: Update User Profile

[0187] The server updates the user profile based on the analysis results. The updated profile reflects the latest user status. Specifically, it updates the Scikit-learn model and re-stores the information in the database. The input to this step is the comparative analysis results, and the output is an updated user profile.

[0188] Step 15: Providing advice

[0189] The server generates personalized advice based on the updated user profile. Specifically, it sends the generated advice sentence to the terminal, which then displays it to the user. The input of this step is the updated user profile, and the output is the generated advice sentence.

[0190] (Application example 1)

[0191] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0192] Conventional security awareness systems have had the challenge of accurately grasping users' psychological states and behavioral patterns and providing appropriate individual responses based on them. Furthermore, they lacked effective means for continuously monitoring changes in users' security risks and providing corresponding feedback. To address these challenges, advanced analysis based on users' psychological data and flexible responses utilizing generative AI models were required.

[0193] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0194] In this invention, the server includes means for providing a series of questions based on psychology to a user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, means for providing the generated responses and instruction methods to the user, means for generating a question list using a generative AI model, and means for periodically evaluating changes in the user's security awareness and risks. This makes it possible to accurately grasp the user's psychological state and behavioral patterns and reduce security risks through individual responses.

[0195] - A "psychologically based set of questions" is a set of questions based on psychological theories to assess a user's psychological state and behavioral patterns.

[0196] "Answer data" refers to information that answers a series of questions provided by a user.

[0197] A "user profile" is a data set that indicates a user's psychological state and behavioral characteristics, and is constructed based on collected user response data.

[0198] The "individual response and instruction method" refers to a response or instruction content that is generated based on the user profile and is tailored to the situation of each user.

[0199] A "generative AI model" is a model that uses machine learning and artificial intelligence to analyze and predict data, and is used, for example, to automatically generate question lists.

[0200] A "question list" is a set of psychologically generated questions presented to a user.

[0201] "Security awareness" refers to the awareness and attitude that users have toward the protection of information and assets in their daily lives and work.

[0202] A "security risk" is a security threat or danger that a user may face.

[0203] "Means of evaluation" refers to a method for analyzing the user's condition based on collected data and determining changes in risk and awareness.

[0204] This invention is a system that asks users psychological questions, collects and analyzes their answers, creates a psychological profile of the user, and proposes personalized responses based on that profile. An embodiment of this system will be described in detail below.

[0205] System configuration

[0206] server

[0207] The server is the core of data collection, analysis, and profile generation. Specifically, it has the following main functions:

[0208] Generate a list of questions: The server uses a generative AI model to generate a list of questions to assess the user's psychological state.

[0209] Analysis of response data: The collected response data is analyzed to generate user profiles. For the analysis, we use the Python Django framework and the Scikit-learn library.

[0210] Update user profile: New response data is collected periodically, compared with and analyzed against existing profiles, and then updated.

[0211] Generate personalized responses: Based on the user profile, personalized responses and instructional content are generated and sent to the device.

[0212] Terminal

[0213] The terminal provides the interface between the user and the server. It is typically a smartphone or tablet and has the following functions:

[0214] Present the question list: Present the question list sent from the server to the user.

[0215] Collecting response data: Collect user response data and send it to the server. The smartphone app uses Swift (iOS) or Kotlin (ANDROID (registered trademark)).

[0216] Providing individualized solutions: Displaying individual solutions and guidance received from the server to the user.

[0217] User

[0218] Users are individuals or organizations who use this system, answer questions presented by the system, and confirm and implement the guidance provided.

[0219] Operation Sequence

[0220] 1. First time login

[0221] The server uses a generative AI model to generate an initial list of questions and sends them to the terminal.

[0222] The terminal displays a list of initial questions to the user and collects their answers.

[0223] The server analyzes the collected response data and generates a user profile.

[0224] 2. Regular follow-up

[0225] At regular intervals, the server generates a new list of questions and sends it to the terminal.

[0226] The terminal displays new questions to the user and collects their answers.

[0227] The server analyzes the collected new response data, compares it with the existing profile, and updates the user profile.

[0228] 3. Providing personalized attention

[0229] The server generates new personalized treatments and coaching methods based on the updated user profile.

[0230] The terminal displays the generated response and instruction method to the user.

[0231] Specific examples

[0232] Example initial questions: "How often do you currently change your password?" or "How often do you perform backups?"

[0233] Example follow-up question: "Have you clicked on any suspicious links in emails or on social media recently?"

[0234] Prompt Sentence Examples

[0235] Below are some example prompts to input to the generative AI model:

[0236] "Generate the following questions:

[0237] 1. How often do you currently change your password?

[0238] 2. How did you research a new app you recently installed?

[0239] 3. How often do you perform backups?

[0240] According to the above-described embodiment, the present invention can accurately grasp the psychological state and behavioral patterns of users, and reduce security risks through individual responses.

[0241] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0242] Step 1: First login and questionnaire generation

[0243] When a user logs in for the first time, the server uses a generative AI model to generate a list of questions based on psychology. This list of questions is intended to evaluate the user's psychological state and behavioral patterns. The generated list of questions is then sent to the device.

[0244] Input: Information of the user who logged in for the first time

[0245] Data Computation: Automatic generation of question lists using generative AI models

[0246] Output: Generated questionnaire

[0247] Step 2: Present a list of questions and collect answers

[0248] The terminal presents the list of questions received from the server to the user. The user answers the presented questions, and the answer data is collected by the terminal. The collected answer data is then sent from the terminal to the server.

[0249] Input: Question list received from the server

[0250] Data processing: Displaying a list of questions and allowing users to enter answers

[0251] Output: User response data

[0252] Step 3: Analyze response data and generate user profiles

[0253] The server analyzes the response data sent from the device and generates a user profile. This analysis is performed using Python's Django framework and Scikit-learn library. Based on the analysis results, the user's psychological state and behavioral characteristics are evaluated and a profile is constructed.

[0254] Input: Answer data sent from the device

[0255] Data Calculation: Data Analysis and Profile Generation

[0256] Output: Generated user profile

[0257] Step 4: Generate personalized responses

[0258] The server generates individualized responses and instruction methods based on the generated user profile. These responses are suited to the user's psychological state and behavioral characteristics. The generated individualized responses are sent to the terminal.

[0259] Input: Generated user profile

[0260] Data arithmetic: generating personalized responses and instructional strategies

[0261] Output: Generated individual responses

[0262] Step 5: Offer personalized support

[0263] The terminal presents the individual response and instruction methods received from the server to the user, who can then confirm and implement the presented response and instruction methods.

[0264] Input: Specific response received from the server

[0265] Data processing: Display of individual support and instruction content

[0266] Output: Presented to the user

[0267] Step 6: Regular follow-up and generate a new list of questions

[0268] At regular intervals, the server uses the generative AI model to generate a new list of questions based on psychology. This list of questions is sent to the device and presented to the user to detect changes in the user's psychological state and behavior.

[0269] Input: Periodic time lapse

[0270] Data Calculation: Automatic generation of new question lists

[0271] Output: The new questionnaire generated

[0272] Step 7: Collect and analyze new response data

[0273] The device presents the user with a new list of questions, collects new response data, and sends it to the server, which analyzes the new response data, compares it with the existing profile, and updates the user's psychological profile accordingly.

[0274] Input: Newly collected response data

[0275] Data Calculation: Analyze data and update profiles

[0276] Output: Updated user profile

[0277] Through the above processing steps, the system of the present invention can accurately grasp the user's psychological state and behavioral patterns, and reduce security risks through individual responses.

[0278] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0279] The present invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0280] System configuration

[0281] server

[0282] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[0283] Terminal

[0284] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[0285] User

[0286] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[0287] Emotion Engine

[0288] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[0289] Program processing

[0290] Data Collection Overview

[0291] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[0292] Terminal: Presents a list of questions to the user and collects their answers.

[0293] User: Provides answers to questions presented and enters the data into the terminal.

[0294] Processing response data

[0295] Terminal: Sends the user's response data to the server.

[0296] Server: The received response data is analyzed by the analysis engine and emotion engine. The analysis engine evaluates the user's personality traits, interests, and current emotional state, and the emotion engine recognizes the user's emotions.

[0297] Creating and updating user profiles

[0298] Server: Generates a user profile from the analysis results and stores the profile in a database. Emotion data recognized by the emotion engine is also incorporated into the profile.

[0299] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[0300] Terminal: Presents a new list of questions to the user and collects their answers.

[0301] User: Answers questions and sends the data to the server via the device.

[0302] Server: Compares and analyzes new response data with past data to understand changes in the user's mood and interests, and updates the user profile taking into account the newly recognized emotional data by the emotion engine.

[0303] Generate and deliver personalized responses

[0304] Server: Generates personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it will suggest relaxation techniques.

[0305] Terminal: Displays the response and instruction received from the server to the user.

[0306] User: Review the advice and guidance provided and implement it as needed.

[0307] Specific examples

[0308] Example of first login

[0309] Server: Send the following questions to the terminal of a newly registered user.

[0310] "How are you feeling right now?"

[0311] "What hobbies do you have?"

[0312] "How often do you meet with your friends?"

[0313] Terminal: Display the question to the user.

[0314] User: Answers the questions and sends them to the server from the device.

[0315] Server: The response data is analyzed using an analysis engine to generate a user profile, and emotions are recognized using an emotion engine, and this data is also incorporated into the profile.

[0316] Examples of regular follow-up

[0317] Server: After one month, generate a new list of questions for the user and send it to the device.

[0318] Terminal: Display the new question to the user.

[0319] User: Answers questions and sends the data from the device to the server.

[0320] Server: Analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[0321] Terminal: Displays the generated advice to the user.

[0322] Users: Check out the advice and try yoga, meditation, etc.

[0323] In this way, the system further improves the accuracy and effectiveness of individual responses based on emotion recognition using an emotion engine, in addition to changes in the user's psychological state and interests, making it possible to continuously provide appropriate advice and guidance to the user.

[0324] The processing flow will be explained below.

[0325] Step 1:

[0326] Server: Generates a series of psychologically based questions for users who have completed new registration and sends the questions to the device.

[0327] Step 2:

[0328] Terminal: Displays the generated list of questions to the user.

[0329] Step 3:

[0330] User: Answers the displayed questions and enters the answer data into the terminal.

[0331] Step 4:

[0332] Terminal: Sends the user's response data to the server.

[0333] Step 5:

[0334] Server: To analyze the received response data, the emotion engine is started and emotions are recognized from the user's response data.

[0335] Step 6:

[0336] Server: Based on the emotion data recognized by the emotion engine, further detailed analysis is performed to evaluate the user's personality traits, interests, and current emotional state.

[0337] Step 7:

[0338] Server: Generates a user profile from the analysis results, including the recognized emotion data, and stores the profile in a database.

[0339] Step 8:

[0340] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[0341] Step 9:

[0342] Terminal: Displays the generated responses and instruction methods to the user.

[0343] Step 10:

[0344] User: Review the advice and guidance provided and act on it as needed.

[0345] Step 11:

[0346] Server: After a certain period of time (e.g., one month), the server sends a reminder to the user, generates a new psychological questionnaire, and sends it to the device.

[0347] Step 12:

[0348] Terminal: Present the new question list to the user.

[0349] Step 13:

[0350] User: Answers a new question and enters the answer data into the device.

[0351] Step 14:

[0352] Device: Sends the user's new answer data to the server.

[0353] Step 15:

[0354] Server: Receives new response data and recognizes emotions again using the emotion engine.

[0355] Step 16:

[0356] Server: Compares and analyzes new emotion data recognized by the emotion engine with previous response data and emotion data.

[0357] Step 17:

[0358] Server: Updates the user's profile based on the new analysis results, including the new emotional data.

[0359] Step 18:

[0360] Server: Generates new personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it generates relaxation techniques and stress management advice.

[0361] Step 19:

[0362] Terminal: The generated new responses and teaching methods are displayed to the user.

[0363] Step 20:

[0364] User: Review the new advice and guidance provided and implement it as needed.

[0365] This series of steps enables the system to continuously monitor changes in the user's psychological state and emotions and provide flexible and appropriate individual responses.

[0366] Example 2

[0367] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0368] Conventional systems provide basic questions and advice based on the user's psychological state, but they have difficulty recognizing the user's specific emotional state and providing individualized support and guidance based on that. Therefore, there is a need for systems that can quickly and accurately provide appropriate support according to the user's emotional changes and the situation they find themselves in. Another challenge is to improve the accuracy of user profiles and the quality of individualized support through regular follow-up.

[0369] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0370] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for recognizing emotions from the user response data; means for analyzing the emotion data and incorporating it into the user profile; means for periodically presenting new psychology-based questions to the user, collecting the response data, and comparing and analyzing it with past data; means for updating the user profile based on the collected new response data, generating new individual responses and instruction methods based on the updated user profile, and means for providing the generated responses and instruction methods to the user. This enables precise analysis of not only the user's psychological state but also their emotional state, making it possible to provide individual responses and instruction methods based on the analysis. This makes it possible to efficiently provide more appropriate support to the user.

[0371] A "user" is someone who uses this system to answer psychological questions and receive personalized support and guidance.

[0372] A "server" is a central processing unit that receives and analyzes user response data and generates and updates user profiles.

[0373] A "terminal" is an electronic device accessed by a user that presents psychological questions, collects user response data, and transmits it to a server.

[0374] "Psychologically based questions" are questions designed to understand a user's personality traits and emotional state.

[0375] A "user profile" is a data set that includes a user's personality traits, interests, emotional state, etc.

[0376] "Individual responses and guidance methods" are advice and suggestions tailored to the user, generated based on the user's profile.

[0377] The "emotion engine" is a system component that has the function of analyzing the user's response data and recognizing the user's emotional state.

[0378] "Answer data" is a general term for information provided by a user in response to a question.

[0379] The "analysis engine" is a component of the system that analyzes the user's response data and evaluates the user's personality traits, emotional state, and so on.

[0380] A "database" is a storage device for storing generated user profiles and analysis results.

[0381] "Follow-up" refers to the process of periodically checking the user's status, asking new questions, and collecting and analyzing the response data.

[0382] "TensorFlow" is a machine learning framework used to build emotion engines.

[0383] "Natural language processing" is a technology that analyzes the meaning of text data entered by a user and extracts various characteristics.

[0384] This invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. The system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0385] server

[0386] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[0387] The specific technologies used include a server built on the Django framework using Python, a machine learning model using TENSORFLOW (registered trademark) for the emotion engine, and a natural language processing technology for the analysis engine, which extracts personality traits and emotional states from user response data.

[0388] Terminal

[0389] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. The terminal can be a personal computer, smartphone, tablet, or other device.

[0390] A web app is provided to access the device, and the service can be accessed through a browser. The device also temporarily stores the answer data entered by the user and sends it to the server.

[0391] User

[0392] The user is an individual or group who uses this system and answers psychological questions. The user enters answers to the questions displayed on the terminal and sends the data to the server.

[0393] Emotion Engine

[0394] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[0395] Specific examples

[0396] A specific example of system operation is shown below.

[0397] Example of first login

[0398] The server sends the following questions to the terminal of the newly registered user:

[0399] How are you feeling right now?

[0400] What hobbies do you have?

[0401] How often do you meet up with friends?

[0402] The terminal displays the question to the user.

[0403] The user answers the questions and sends them from the terminal to the server.

[0404] The server analyzes the response data using an analysis engine to generate a user profile, and also recognizes emotions using an emotion engine and incorporates that data into the profile.

[0405] Examples of regular follow-up

[0406] After one month, the server generates a new list of questions for the user and sends it to the terminal.

[0407] The terminal displays the new question to the user.

[0408] The user answers the questions and transmits the data from the terminal to the server.

[0409] The server analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[0410] The terminal displays the generated advice to the user.

[0411] Users check out advice and try things like yoga and meditation.

[0412] In this way, the system further improves the accuracy and effectiveness of individual responses based on changes in the user's psychological state and interests, as well as emotion recognition using an emotion engine, making it possible to continuously provide appropriate advice and guidance to users.

[0413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0414] System program processing flow

[0415] Step 1:

[0416] The server creates a new user profile when the user logs in for the first time. The prompt text is generated as follows:

[0417] "How are you feeling right now?"

[0418] "What hobbies do you have?"

[0419] "How often do you meet with your friends?"

[0420] The server generates these questionnaires and sends them to the terminal. The input is the user's login information, and the output is the generated questionnaire.

[0421] Step 2:

[0422] The terminal displays the list of questions received from the server to the user. The user inputs answers to the displayed questions. The input is the list of questions received from the server, and the output is the answer data entered by the user.

[0423] Step 3:

[0424] The user inputs an answer to the displayed question. Specifically, the user inputs text such as "I'm feeling a little anxious right now" into the terminal. The input is the displayed question, and the output is the answer text entered by the user.

[0425] Step 4:

[0426] The terminal collects the user's response data and sends it to the server. The input is the response data entered by the user, and the output is the response data sent to the server.

[0427] Step 5:

[0428] The server analyzes the received response data using an analysis engine and an emotion engine. Specifically, it uses natural language processing technology to evaluate the user's personality traits and emotional state, and recognizes emotions using the emotion engine. The input is the user's response data, and the output is an analyzed user profile and recognized emotion data.

[0429] Step 6:

[0430] The server generates a user profile from the analysis results and stores the profile in a database. The emotion data recognized by the emotion engine is also incorporated into the profile. The input is the analysis results, and the output is the generated user profile.

[0431] Step 7:

[0432] After a certain period of time, the server generates a new list of psychology-based questions and sends it to the terminal. The input is the user profile, and the output is the new list of questions.

[0433] Step 8:

[0434] The terminal provides a new list of questions to the user and collects their answers. The input is the new list of questions received from the server, and the output is the new answer data entered by the user.

[0435] Step 9:

[0436] The user answers a new question and sends the data to the server via the terminal. The input is the new question, and the output is the new answer data.

[0437] Step 10:

[0438] The server compares and analyzes the new response data with past data. It updates the profile, including the emotional data. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly. The input is the new response data and past data, and the output is the updated user profile and generated advice.

[0439] Step 11:

[0440] The server generates individual responses and instruction methods based on the updated user profile and transmits them to the terminal. The input is the updated user profile, and the output is the individual responses and instruction methods.

[0441] Step 12:

[0442] The terminal displays the responses and instruction methods received from the server to the user. The input is the responses and instruction methods received from the server, and the output is the instruction content displayed to the user.

[0443] Step 13:

[0444] The user reviews the advice and guidance provided and implements it as needed. For example, if a relaxation suggestion is displayed, the user tries it. The input is the displayed advice, and the output is the user's behavior.

[0445] Through the above processing steps, this system is able to provide highly accurate individual responses based on the user's psychological and emotional state.

[0446] (Application example 2)

[0447] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0448] In modern brick-and-mortar stores, it is difficult to grasp customers' psychological state and emotions in real time and provide personalized support and product suggestions. Furthermore, conventional systems have difficulty in properly recognizing customers' emotions and providing quick and appropriate responses based on that data. In order to improve customer satisfaction, it is necessary to provide advanced customer service based on customers' emotions.

[0449] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0450] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for capturing the user's facial expressions and voice in real time and recognizing their emotions using an emotion engine; means for transmitting the recognized emotion data to the server and returning analysis results in real time; and means for displaying appropriate customer service methods and product suggestions to the user based on the returned analysis results. This makes it possible to analyze the customer's psychological state and emotions in real time and provide individualized support based on the results. This improves customer satisfaction and enables advanced customer service in physical stores.

[0451] "Psychologically-based Questions" refers to a series of questions based on psychological theory and empirical research designed to assess a user's personality traits, interests, and emotional state.

[0452] "Response data" refers to response information provided by a user to a psychology-based question.

[0453] "User profile" refers to information that indicates a user's personality traits, interests, and emotional state, generated by analyzing collected response data and emotional data.

[0454] "Personalized responses and coaching" refers to specific advice and suggestions provided to a user based on the generated user profile.

[0455] "Capturing facial expressions and voice in real time" refers to instantly capturing the user's facial movements, tone of voice, pitch, etc. and processing them as digital data.

[0456] "Emotion engine" refers to a software or hardware module that analyzes captured facial and voice data to recognize the user's emotional state.

[0457] "Recognized emotion data" refers to data that indicates a particular emotional state of a user that has been analyzed and extracted by an emotion engine.

[0458] "Real-time return of analysis results" refers to the process of instantly sending recognized emotion data and other analysis results from the server to the device.

[0459] "Displaying customer service methods and product suggestions" refers to displaying information on the terminal display that suggests appropriate customer service methods and products to store staff based on the customer's emotional and psychological state.

[0460] "Brick and mortar store" refers to a point of sale that exists in a physical location and where customers can visit in person to purchase goods or services.

[0461] MODE FOR CARRYING OUT THE INVENTION

[0462] The present invention is a system for enhancing customer service in brick-and-mortar stores, which presents a series of psychologically based questions, analyzes the user's response data, and recognizes the user's emotions using an emotion engine. Specific embodiments of the system are described below.

[0463] System Configuration

[0464] The system of the present invention mainly consists of three main components: a server, terminals (smart glasses), and users (store staff and customers). It also includes an emotion engine and a back-end system for data analysis.

[0465] Hardware and software used

[0466] Server: Amazon Web Services (AWS (registered trademark)) is used to perform data analysis and profile generation.

[0467] Devices: Smart glasses (e.g., Google® Glass®, Vuzix Blade) are used to capture data in real time and display information to staff.

[0468] Emotion Engine: Real-time emotion recognition using the Affectiva SDK.

[0469] Analysis engine: Uses TensorFlow to analyze image and audio data.

[0470] Communication: Uses the WebSocket API to send and receive data in real time.

[0471] Program processing and specific examples

[0472] 1. Data Collection:

[0473] Device: The smart glasses have a built-in camera that captures the customer's facial expressions and a microphone that picks up the customer's voice.

[0474] Emotion Engine: Recognize customer emotions based on captured data using the Affectiva SDK.

[0475] 2. Data Transmission and Analysis:

[0476] Terminal: Sends captured and analyzed data to the server.

[0477] Server: Further analyzes the received data using TensorFlow to assess the customer's state of mind and emotions.

[0478] 3. Generate personalized responses:

[0479] Server: Generates appropriate customer service methods and product suggestions based on the analysis results.

[0480] Terminal: The generated information is displayed on the smart glasses display.

[0481] 4. Real-time return:

[0482] Server: Sends back analysis results in real time and displays them on staff's smart glasses.

[0483] Terminal: Staff respond appropriately to customers based on the information displayed.

[0484] Specific examples

[0485] If a customer enters a store and shows an expression that suggests they are "slightly irritated," the emotion engine will recognize this expression and display a message in real time on the staff member's smart glasses saying, "The customer may be feeling dissatisfied. Please suggest products or services that will help them relax."

[0486] Prompt Sentence Examples

[0487] "Analyze the customer's facial expression and display the following instructions to your staff:

[0488] The customer is smiling: 'The customer seems happy. Please suggest new products.'

[0489] Customer in distress: 'The customer seems distressed. Please ask if they need help.'

[0490] Customer is frustrated: 'The customer may be frustrated. Suggest a product or service that will help them relax.'

[0491] In this way, the system of the present invention analyzes the customer's psychological state and emotions in real time and provides appropriate responses based on that analysis, thereby improving customer satisfaction and providing high-quality customer service.

[0492] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0493] Step 1:

[0494] The device captures the customer's facial expressions with a camera built into the smart glasses and picks up the customer's voice with a microphone, thereby inputting video and audio data.

[0495] Input: Customer facial expression video and audio

[0496] Output: Captured video and audio data

[0497] Step 2:

[0498] The device sends the captured video and audio data to the emotion engine, which uses the Affectiva SDK to recognize the customer's emotions from the video and audio data.

[0499] Input: Captured video and audio data

[0500] Output: Recognized emotion data

[0501] Step 3:

[0502] The device sends the recognized emotion data to the server, which then analyzes the received emotion data and previously collected response data using an analysis engine (TensorFlow) to evaluate the user's mental state and emotions.

[0503] Input: Recognized emotion data and previously collected response data

[0504] Output: Analysis results (mental state and emotional evaluation)

[0505] Step 4:

[0506] The server generates appropriate customer service methods and product suggestions based on the analysis results, which are then returned to the terminal in text format.

[0507] Input: Analysis results (mental state and emotional assessment)

[0508] Output: Text data of customer service methods and product recommendations

[0509] Step 5:

[0510] The device then displays the received text data on the smart glasses' display, allowing staff to provide appropriate service to customers based on this information.

[0511] Input: Text data of customer service methods and product recommendations

[0512] Output: Customer service methods and product suggestions displayed on smart glasses

[0513] This series of processing steps enables real-time analysis of the customer's psychological state and emotions, enabling personalized responses. Staff can receive, through the smart glasses, recommendations for optimal customer service methods and product recommendations in real time based on the customer's condition, thereby improving customer satisfaction.

[0514] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0515] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0516] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0517] [Second embodiment]

[0518] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0519] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0520] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0521] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0522] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0523] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0524] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0525] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0526] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0527] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0528] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0529] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0530] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[0531] System configuration

[0532] server

[0533] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server is also responsible for generating new questionnaires and generating personalized responses and coaching methods.

[0534] Terminal

[0535] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[0536] User

[0537] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[0538] Program processing

[0539] Data Collection Overview

[0540] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[0541] Terminal: Presents a list of questions to the user and collects their answers.

[0542] User: Provides answers to questions posed and sends the data to the device.

[0543] Processing response data

[0544] Terminal: Sends the user's response data to the server.

[0545] Server: Analyzes the received response data and evaluates the user's personality traits, interests, and emotional state to generate a user profile.

[0546] Regular data collection and analysis

[0547] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[0548] Terminal: Presents a new list of questions to the user and collects their answers.

[0549] User: Answers questions and sends the data to the server via the device.

[0550] Server: Compares and analyzes new response data with past data to understand changes in user sentiment and interests.

[0551] Generate and deliver personalized responses

[0552] Server: Generates personalized responses and guidance based on the updated user profile. For example, it suggests relaxation techniques for a user experiencing increased stress.

[0553] Terminal: Displays the response and instruction received from the server to the user.

[0554] User: Review the advice and guidance provided and implement it as needed.

[0555] Specific examples

[0556] Example of first login

[0557] Server: Send the following questions to the terminal of a newly registered user.

[0558] "How are you feeling right now?"

[0559] "What hobbies do you have?"

[0560] "How often do you meet with your friends?"

[0561] Terminal: Display the question to the user.

[0562] User: Answers the questions and sends them to the server from the device.

[0563] Server: Analyzes the response data and generates a user profile.

[0564] Examples of regular follow-up

[0565] Server: After one month, generate a new list of questions for the user and send it to the device.

[0566] Terminal: Display the new question to the user.

[0567] User: Answers questions and sends the data from the device to the server.

[0568] Server: Analyzes new response data and compares it with past data. For example, if a user responds that they are feeling more stressed, the server generates advice accordingly.

[0569] Terminal: Displays the generated advice to the user.

[0570] User: Check out the advice and try yoga.

[0571] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[0572] The processing flow will be explained below.

[0573] Step 1:

[0574] Server: Once a new user has registered, it generates a series of psychologically based questions and sends them to the device.

[0575] Step 2:

[0576] Terminal: Displays the generated list of questions to the user.

[0577] Step 3:

[0578] User: Answers the questionnaire and enters the answer data into the terminal.

[0579] Step 4:

[0580] Terminal: Sends the answer data entered by the user to the server.

[0581] Step 5:

[0582] Server: Receives the response data and analyzes it using an analytics engine. This analysis reveals the user's personality traits, interests, and current emotional state.

[0583] Step 6:

[0584] Server: Generates a user profile from the analysis results and stores the profile in a database.

[0585] Step 7:

[0586] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[0587] Step 8:

[0588] Terminal: The generated responses and instruction methods are displayed to the user, who then confirms them.

[0589] Step 9:

[0590] Server: After a certain period of time (e.g., one month), send a remote reminder and generate a new list of psychology-based questions for the user and send them to the device.

[0591] Step 10:

[0592] Terminal: Present the new question list to the user.

[0593] Step 11:

[0594] User: Answers a new question and enters the answer data into the device.

[0595] Step 12:

[0596] Device: Sends the user's new answer data to the server.

[0597] Step 13:

[0598] Server: Analyzes new response data and compares it with past response data.

[0599] Step 14:

[0600] Server: Updates the user's profile based on the analysis results, generating an up-to-date profile that reflects changes in the user's mood and interests.

[0601] Step 15:

[0602] Server: Generates new personalized responses and coaching strategies based on the updated user profile, such as stress reduction strategies or new hobby recommendations, if needed.

[0603] Step 16:

[0604] Device: Display the latest updates and guidance to the user.

[0605] Step 17:

[0606] User: Review any new guidance or solutions provided and implement them as needed.

[0607] This series of steps enables the system to flexibly respond to changes in the user's psychological state and interests, and provide appropriate, personalized advice and guidance.

[0608] Example 1

[0609] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0610] Conventional psychology-based data collection systems lack the ability to respond to individual users, making it difficult to accurately grasp the continuous changes in a user's emotions and interests. As a result, the accuracy of individualized instruction methods and advice is low, making it difficult to provide effective support. Furthermore, generating question lists requires a lot of manpower, and the systems lack scalability and flexibility.

[0611] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0612] In this invention, the server includes means for presenting a series of psychology-based questions to the user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, and means for providing the generated responses and instruction methods to the user. This makes it possible to continuously grasp changes in the user's psychological state and interests and provide appropriate responses and instruction.

[0613] A "psychologically based questionnaire" is a series of questions designed based on psychological theory and research to assess a user's psychological state, personality traits, and interests.

[0614] "User response data" is data that includes user-provided responses to the series of psychology-based questions.

[0615] A "user profile" is a collection of information generated based on a user's response data to indicate the user's personality traits, interests, emotional state, etc.

[0616] "Individualized responses and guidance methods" are methods for providing advice and assistance suited to a particular user based on the generated user profile.

[0617] A "generative AI model" is a model that uses artificial intelligence technology to generate text in natural language based on a specified prompt.

[0618] A "prompt" is a piece of text that is input to a generative AI model and provides instructions for the model to generate appropriate output.

[0619] A "machine learning algorithm" is a mathematical method or model that automatically learns from data, recognizes patterns, and makes predictions and classifications.

[0620] "Data analysis library" is a general term for software libraries used to collect, organize, analyze, and visualize data.

[0621] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[0622] System configuration

[0623] server

[0624] The server is a central processing unit that receives user response data, analyzes it, and generates and updates user profiles. The server is also responsible for generating new question lists and generating personalized responses and instructional methods. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-3) to generate question lists and analyzes the response data using Python's Pandas and Scikit-learn.

[0625] Terminal

[0626] The terminal is an electronic device accessed by the user, which poses psychological questions, collects the user's answers, and sends them to the server. The terminal can be a PC, smartphone, tablet, etc. The terminal displays the list of questions and sends the answers entered by the user to the server via an HTTP request.

[0627] User

[0628] The user is an individual or an organization that uses this system and is the subject of answering psychological questions. The user answers the questions using a terminal.

[0629] Program processing

[0630] Data Collection Overview

[0631] The server generates a list of psychology-based questions when the user logs in for the first time and sends them to the terminal. The terminal displays the list of questions to the user, collects the answers, and sends them to the server. The user provides answers to the displayed questions and sends the data to the terminal.

[0632] Processing response data

[0633] The device sends the user's response data to the server, which then analyzes the received response data and generates a user profile by evaluating the user's personality traits, interests, and emotional state. This analysis uses data analysis libraries such as Python's Pandas and Scikit-learn.

[0634] Regular data collection and analysis

[0635] The server periodically generates a new list of questions based on psychology for the user and sends it to the terminal. The terminal provides the new list of questions to the user and collects their answers. The user answers the questions and sends the data to the server via the terminal. The server compares and analyzes the new answer data with past data to understand changes in the user's feelings and interests.

[0636] Generate and deliver personalized responses

[0637] The server generates individualized responses and guidance methods based on the updated user profile. For example, it might suggest relaxation methods to a user experiencing increasing stress. The device displays the responses and guidance methods received from the server to the user. The user can then review the provided advice and guidance and implement them as necessary.

[0638] Specific examples

[0639] Example of first login

[0640] The server sends the following questions to the terminal of the newly registered user:

[0641] "How are you feeling right now?"

[0642] "What hobbies do you have?"

[0643] "How often do you meet with your friends?"

[0644] The device displays questions to the user. The user answers the questions and sends them to the server. The server analyzes the answer data and generates a user profile. For example, it uses Scikit-learn, a Python analysis library.

[0645] Examples of regular follow-up

[0646] The server generates a new list of questions for the user one month later and sends it to the device. The device displays the new questions to the user. The user answers the questions and sends the data from the device to the server. The server analyzes the new answer data and compares it with past data. For example, if the user answers "my stress has increased," the server generates advice accordingly. The device displays the generated advice to the user. The user checks the advice and tries yoga.

[0647] Prompt Sentence Examples

[0648] Generate a list of questions to ask users when they first log in: "How are you feeling right now?", "What are your hobbies?", "How often do you meet up with your friends?"

[0649]

[0650] Based on the user's response data, suggest ways to relieve stress, such as yoga, meditation, or walking.

[0651] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[0652] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0653] Step 1: First login authentication

[0654] The server compares the authentication information (user ID and password) entered by the user with the database and authenticates the login. Specifically, the server receives the user's authentication information and checks whether it matches the information stored in the database. The input to this step is the authentication information entered by the user into the terminal, and the output is whether the login was successful or not.

[0655] Step 2: Generate a questionnaire

[0656] After successful authentication, the server generates a list of psychology-based questions to present to the user. Using a generative AI model, it creates appropriate questions based on the prompt text. Specifically, it inputs the prompt "Generate questions to display when the user logs in for the first time: How are you feeling right now?" and sends the generated text to the terminal as a list of questions. The input for this step is the prompt text, and the output is the generated list of questions.

[0657] Step 3: Question list display

[0658] The terminal displays the question list received from the server to the user. Specifically, the terminal places questions on the terminal's UI so that the user can answer them. The input of this step is the question list sent from the server, and the output is the user's visual confirmation.

[0659] Step 4: Collect response data

[0660] The terminal collects the answers entered by the user. The user enters answers to questions through the terminal. The input of this step is the user's answer, and the output is the collected answer data.

[0661] Step 5: Send response data

[0662] The terminal sends the collected response data to the server. Specifically, the terminal passes data to the server using the POST method of the HTTP request. The input of this step is the response data collected by the terminal, and the output is the response data sent to the server.

[0663] Step 6: Analyze response data

[0664] The server analyzes the received response data. Using Python's Pandas or Scikit-learn, the response data is converted into a data frame and the user's personality traits and interests are evaluated. As a specific example, a machine learning model is run on the converted data frame to extract the user's profile. The input to this step is the response data, and the output is the analysis results.

[0665] Step 7: Create a user profile

[0666] The server generates a user profile from the analysis results. The generated profile contains comprehensive information about the user's personality traits and interests. Specifically, it uses Scikit-learn to create a model and saves it in a database. The input to this step is the analysis results, and the output is the user profile.

[0667] Step 8: Provide feedback

[0668] The server generates initial feedback and advice based on the generated user profile. Specifically, it creates a feedback sentence from the generated profile and sends it to the terminal. The terminal displays the feedback to the user. The input of this step is the user profile, and the output is a feedback sentence.

[0669] Step 9: Generate regular follow-up questions

[0670] The server generates a new list of questions at regular intervals. It uses a generative AI model to create appropriate questions based on the prompt. As a specific example, a prompt such as "Please generate stress check questions as a follow-up in one month" is input to generate new questions. The input for this step is the prompt for follow-up, and the output is a new list of questions.

[0671] Step 10: Display the follow-up questions list

[0672] The terminal displays the newly generated question list to the user. The user checks the questions on the terminal and enters the answers. The input of this step is the new question list sent from the server, and the output is the user's visual confirmation.

[0673] Step 11: Collect new response data

[0674] The terminal collects new answers entered by the user. The user answers questions through the terminal. The input of this step is the user's new answers, and the output is the collected new answer data.

[0675] Step 12: Send new response data

[0676] The terminal sends the collected new response data to the server. Specifically, the terminal sends the data using the POST method of the HTTP request. The input of this step is the collected new response data, and the output is the new response data sent to the server.

[0677] Step 13: New data analysis

[0678] The server compares the newly received response data with past data and analyzes it. Python's Pandas is used to combine the old and new data into a data frame to understand changes in user sentiment and interests. The input for this step is the new response data and past data, and the output is the results of the comparison and analysis.

[0679] Step 14: Update User Profile

[0680] The server updates the user profile based on the analysis results. The updated profile reflects the latest user status. Specifically, it updates the Scikit-learn model and re-stores the information in the database. The input to this step is the comparative analysis results, and the output is an updated user profile.

[0681] Step 15: Providing advice

[0682] The server generates personalized advice based on the updated user profile. Specifically, it sends the generated advice sentence to the terminal, which then displays it to the user. The input of this step is the updated user profile, and the output is the generated advice sentence.

[0683] (Application example 1)

[0684] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0685] Conventional security awareness systems have had the challenge of accurately grasping users' psychological states and behavioral patterns and providing appropriate individual responses based on them. Furthermore, they lacked effective means for continuously monitoring changes in users' security risks and providing corresponding feedback. To address these challenges, advanced analysis based on users' psychological data and flexible responses utilizing generative AI models were required.

[0686] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0687] In this invention, the server includes means for providing a series of questions based on psychology to a user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, means for providing the generated responses and instruction methods to the user, means for generating a question list using a generative AI model, and means for periodically evaluating changes in the user's security awareness and risks. This makes it possible to accurately grasp the user's psychological state and behavioral patterns and reduce security risks through individual responses.

[0688] - A "psychologically based set of questions" is a set of questions based on psychological theories to assess a user's psychological state and behavioral patterns.

[0689] "Answer data" refers to information that answers a series of questions provided by a user.

[0690] A "user profile" is a data set that indicates a user's psychological state and behavioral characteristics, and is constructed based on collected user response data.

[0691] The "individual response and instruction method" refers to a response or instruction content that is generated based on the user profile and is tailored to the situation of each user.

[0692] A "generative AI model" is a model that uses machine learning and artificial intelligence to analyze and predict data, and is used, for example, to automatically generate question lists.

[0693] A "question list" is a set of psychologically generated questions presented to a user.

[0694] "Security awareness" refers to the awareness and attitude that users have toward the protection of information and assets in their daily lives and work.

[0695] A "security risk" is a security threat or danger that a user may face.

[0696] "Means of evaluation" refers to a method for analyzing the user's condition based on collected data and determining changes in risk and awareness.

[0697] This invention is a system that asks users psychological questions, collects and analyzes their answers, creates a psychological profile of the user, and proposes personalized responses based on that profile. An embodiment of this system will be described in detail below.

[0698] System configuration

[0699] server

[0700] The server is the core of data collection, analysis, and profile generation. Specifically, it has the following main functions:

[0701] Generate a list of questions: The server uses a generative AI model to generate a list of questions to assess the user's psychological state.

[0702] Analysis of response data: The collected response data is analyzed to generate user profiles. For the analysis, we use the Python Django framework and the Scikit-learn library.

[0703] Update user profile: New response data is collected periodically, compared with and analyzed against existing profiles, and then updated.

[0704] Generate personalized responses: Based on the user profile, personalized responses and instructional content are generated and sent to the device.

[0705] Terminal

[0706] The terminal provides the interface between the user and the server. It is typically a smartphone or tablet and has the following functions:

[0707] Present the question list: Present the question list sent from the server to the user.

[0708] Collecting response data: Collect user response data and send it to the server. The smartphone app uses Swift (iOS) and Kotlin (Android).

[0709] Providing individualized solutions: Displaying individual solutions and guidance received from the server to the user.

[0710] User

[0711] Users are individuals or organizations who use this system, answer questions presented by the system, and confirm and implement the guidance provided.

[0712] Operation Sequence

[0713] 1. First time login

[0714] The server uses a generative AI model to generate an initial list of questions and sends them to the terminal.

[0715] The terminal displays a list of initial questions to the user and collects their answers.

[0716] The server analyzes the collected response data and generates a user profile.

[0717] 2. Regular follow-up

[0718] At regular intervals, the server generates a new list of questions and sends it to the terminal.

[0719] The terminal displays new questions to the user and collects their answers.

[0720] The server analyzes the collected new response data, compares it with the existing profile, and updates the user profile.

[0721] 3. Providing personalized attention

[0722] The server generates new personalized treatments and coaching methods based on the updated user profile.

[0723] The terminal displays the generated response and instruction method to the user.

[0724] Specific examples

[0725] Example initial questions: "How often do you currently change your password?" or "How often do you perform backups?"

[0726] Example follow-up question: "Have you clicked on any suspicious links in emails or on social media recently?"

[0727] Prompt Sentence Examples

[0728] Below are some example prompts to input to the generative AI model:

[0729] "Generate the following questions:

[0730] 1. How often do you currently change your password?

[0731] 2. How did you research a new app you recently installed?

[0732] 3. How often do you perform backups?

[0733] According to the above-described embodiment, the present invention can accurately grasp the psychological state and behavioral patterns of users, and reduce security risks through individual responses.

[0734] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0735] Step 1: First login and questionnaire generation

[0736] When a user logs in for the first time, the server uses a generative AI model to generate a list of questions based on psychology. This list of questions is intended to evaluate the user's psychological state and behavioral patterns. The generated list of questions is then sent to the device.

[0737] Input: Information of the user who logged in for the first time

[0738] Data Computation: Automatic generation of question lists using generative AI models

[0739] Output: Generated questionnaire

[0740] Step 2: Present a list of questions and collect answers

[0741] The terminal presents the list of questions received from the server to the user. The user answers the presented questions, and the answer data is collected by the terminal. The collected answer data is then sent from the terminal to the server.

[0742] Input: Question list received from the server

[0743] Data processing: Displaying a list of questions and allowing users to enter answers

[0744] Output: User response data

[0745] Step 3: Analyze response data and generate user profiles

[0746] The server analyzes the response data sent from the device and generates a user profile. This analysis is performed using Python's Django framework and Scikit-learn library. Based on the analysis results, the user's psychological state and behavioral characteristics are evaluated and a profile is constructed.

[0747] Input: Answer data sent from the device

[0748] Data Calculation: Data Analysis and Profile Generation

[0749] Output: Generated user profile

[0750] Step 4: Generate personalized responses

[0751] The server generates individualized responses and instruction methods based on the generated user profile. These responses are suited to the user's psychological state and behavioral characteristics. The generated individualized responses are sent to the terminal.

[0752] Input: Generated user profile

[0753] Data arithmetic: generating personalized responses and instructional strategies

[0754] Output: Generated individual responses

[0755] Step 5: Offer personalized support

[0756] The terminal presents the individual response and instruction methods received from the server to the user, who can then confirm and implement the presented response and instruction methods.

[0757] Input: Specific response received from the server

[0758] Data processing: Display of individual support and instruction content

[0759] Output: Presented to the user

[0760] Step 6: Regular follow-up and generate a new list of questions

[0761] At regular intervals, the server uses the generative AI model to generate a new list of questions based on psychology. This list of questions is sent to the device and presented to the user to detect changes in the user's psychological state and behavior.

[0762] Input: Periodic time lapse

[0763] Data Calculation: Automatic generation of new question lists

[0764] Output: The new questionnaire generated

[0765] Step 7: Collect and analyze new response data

[0766] The device presents the user with a new list of questions, collects new response data, and sends it to the server, which analyzes the new response data, compares it with the existing profile, and updates the user's psychological profile accordingly.

[0767] Input: Newly collected response data

[0768] Data Calculation: Analyze data and update profiles

[0769] Output: Updated user profile

[0770] Through the above processing steps, the system of the present invention can accurately grasp the user's psychological state and behavioral patterns, and reduce security risks through individual responses.

[0771] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0772] The present invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0773] System configuration

[0774] server

[0775] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[0776] Terminal

[0777] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[0778] User

[0779] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[0780] Emotion Engine

[0781] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[0782] Program processing

[0783] Data Collection Overview

[0784] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[0785] Terminal: Presents a list of questions to the user and collects their answers.

[0786] User: Provides answers to questions presented and enters the data into the terminal.

[0787] Processing response data

[0788] Terminal: Sends the user's response data to the server.

[0789] Server: The received response data is analyzed by the analysis engine and emotion engine. The analysis engine evaluates the user's personality traits, interests, and current emotional state, and the emotion engine recognizes the user's emotions.

[0790] Creating and updating user profiles

[0791] Server: Generates a user profile from the analysis results and stores the profile in a database. Emotion data recognized by the emotion engine is also incorporated into the profile.

[0792] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[0793] Terminal: Presents a new list of questions to the user and collects their answers.

[0794] User: Answers questions and sends the data to the server via the device.

[0795] Server: Compares and analyzes new response data with past data to understand changes in the user's mood and interests, and updates the user profile taking into account the newly recognized emotional data by the emotion engine.

[0796] Generate and deliver personalized responses

[0797] Server: Generates personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it will suggest relaxation techniques.

[0798] Terminal: Displays the response and instruction received from the server to the user.

[0799] User: Review the advice and guidance provided and implement it as needed.

[0800] Specific examples

[0801] Example of first login

[0802] Server: Send the following questions to the terminal of a newly registered user.

[0803] "How are you feeling right now?"

[0804] "What hobbies do you have?"

[0805] "How often do you meet with your friends?"

[0806] Terminal: Display the question to the user.

[0807] User: Answers the questions and sends them to the server from the device.

[0808] Server: The response data is analyzed using an analysis engine to generate a user profile, and emotions are recognized using an emotion engine, and this data is also incorporated into the profile.

[0809] Examples of regular follow-up

[0810] Server: After one month, generate a new list of questions for the user and send it to the device.

[0811] Terminal: Display the new question to the user.

[0812] User: Answers questions and sends the data from the device to the server.

[0813] Server: Analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[0814] Terminal: Displays the generated advice to the user.

[0815] Users: Check out the advice and try yoga, meditation, etc.

[0816] In this way, the system further improves the accuracy and effectiveness of individual responses based on emotion recognition using an emotion engine, in addition to changes in the user's psychological state and interests, making it possible to continuously provide appropriate advice and guidance to the user.

[0817] The processing flow will be explained below.

[0818] Step 1:

[0819] Server: Generates a series of psychologically based questions for users who have completed new registration and sends the questions to the device.

[0820] Step 2:

[0821] Terminal: Displays the generated list of questions to the user.

[0822] Step 3:

[0823] User: Answers the displayed questions and enters the answer data into the terminal.

[0824] Step 4:

[0825] Terminal: Sends the user's response data to the server.

[0826] Step 5:

[0827] Server: To analyze the received response data, the emotion engine is started and emotions are recognized from the user's response data.

[0828] Step 6:

[0829] Server: Based on the emotion data recognized by the emotion engine, further detailed analysis is performed to evaluate the user's personality traits, interests, and current emotional state.

[0830] Step 7:

[0831] Server: Generates a user profile from the analysis results, including the recognized emotion data, and stores the profile in a database.

[0832] Step 8:

[0833] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[0834] Step 9:

[0835] Terminal: Displays the generated responses and instruction methods to the user.

[0836] Step 10:

[0837] User: Review the advice and guidance provided and act on it as needed.

[0838] Step 11:

[0839] Server: After a certain period of time (e.g., one month), the server sends a reminder to the user, generates a new psychological questionnaire, and sends it to the device.

[0840] Step 12:

[0841] Terminal: Present the new question list to the user.

[0842] Step 13:

[0843] User: Answers a new question and enters the answer data into the device.

[0844] Step 14:

[0845] Device: Sends the user's new answer data to the server.

[0846] Step 15:

[0847] Server: Receives new response data and recognizes emotions again using the emotion engine.

[0848] Step 16:

[0849] Server: Compares and analyzes new emotion data recognized by the emotion engine with previous response data and emotion data.

[0850] Step 17:

[0851] Server: Updates the user's profile based on the new analysis results, including the new emotional data.

[0852] Step 18:

[0853] Server: Generates new personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it generates relaxation techniques and stress management advice.

[0854] Step 19:

[0855] Terminal: The generated new responses and teaching methods are displayed to the user.

[0856] Step 20:

[0857] User: Review the new advice and guidance provided and implement it as needed.

[0858] This series of steps enables the system to continuously monitor changes in the user's psychological state and emotions and provide flexible and appropriate individual responses.

[0859] Example 2

[0860] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0861] Conventional systems provide basic questions and advice based on the user's psychological state, but they have difficulty recognizing the user's specific emotional state and providing individualized support and guidance based on that. Therefore, there is a need for systems that can quickly and accurately provide appropriate support according to the user's emotional changes and the situation they find themselves in. Another challenge is to improve the accuracy of user profiles and the quality of individualized support through regular follow-up.

[0862] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0863] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for recognizing emotions from the user response data; means for analyzing the emotion data and incorporating it into the user profile; means for periodically presenting new psychology-based questions to the user, collecting the response data, and comparing and analyzing it with past data; means for updating the user profile based on the collected new response data, generating new individual responses and instruction methods based on the updated user profile, and means for providing the generated responses and instruction methods to the user. This enables precise analysis of not only the user's psychological state but also their emotional state, making it possible to provide individual responses and instruction methods based on the analysis. This makes it possible to efficiently provide more appropriate support to the user.

[0864] A "user" is someone who uses this system to answer psychological questions and receive personalized support and guidance.

[0865] A "server" is a central processing unit that receives and analyzes user response data and generates and updates user profiles.

[0866] A "terminal" is an electronic device accessed by a user that presents psychological questions, collects user response data, and transmits it to a server.

[0867] "Psychologically based questions" are questions designed to understand a user's personality traits and emotional state.

[0868] A "user profile" is a data set that includes a user's personality traits, interests, emotional state, etc.

[0869] "Individual responses and guidance methods" are advice and suggestions tailored to the user, generated based on the user's profile.

[0870] The "emotion engine" is a system component that has the function of analyzing the user's response data and recognizing the user's emotional state.

[0871] "Answer data" is a general term for information provided by a user in response to a question.

[0872] The "analysis engine" is a component of the system that analyzes the user's response data and evaluates the user's personality traits, emotional state, and so on.

[0873] A "database" is a storage device for storing generated user profiles and analysis results.

[0874] "Follow-up" refers to the process of periodically checking the user's status, asking new questions, and collecting and analyzing the response data.

[0875] "TensorFlow" is a machine learning framework used to build emotion engines.

[0876] "Natural language processing" is a technology that analyzes the meaning of text data entered by a user and extracts various characteristics.

[0877] This invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. The system consists of four main components: a server, a terminal, a user, and an emotion engine.

[0878] server

[0879] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[0880] The server is built on the Django framework using Python, and the emotion engine uses a machine learning model with TensorFlow. The analysis engine uses natural language processing technology to extract personality traits and emotional states from user response data.

[0881] Terminal

[0882] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. The terminal can be a personal computer, smartphone, tablet, or other device.

[0883] A web app is provided to access the device, and the service can be accessed through a browser. The device also temporarily stores the answer data entered by the user and sends it to the server.

[0884] User

[0885] The user is an individual or group who uses this system and answers psychological questions. The user enters answers to the questions displayed on the terminal and sends the data to the server.

[0886] Emotion Engine

[0887] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[0888] Specific examples

[0889] A specific example of system operation is shown below.

[0890] Example of first login

[0891] The server sends the following questions to the terminal of the newly registered user:

[0892] How are you feeling right now?

[0893] What hobbies do you have?

[0894] How often do you meet up with friends?

[0895] The terminal displays the question to the user.

[0896] The user answers the questions and sends them from the terminal to the server.

[0897] The server analyzes the response data using an analysis engine to generate a user profile, and also recognizes emotions using an emotion engine and incorporates that data into the profile.

[0898] Examples of regular follow-up

[0899] After one month, the server generates a new list of questions for the user and sends it to the terminal.

[0900] The terminal displays the new question to the user.

[0901] The user answers the questions and transmits the data from the terminal to the server.

[0902] The server analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[0903] The terminal displays the generated advice to the user.

[0904] Users check out advice and try things like yoga and meditation.

[0905] In this way, the system further improves the accuracy and effectiveness of individual responses based on changes in the user's psychological state and interests, as well as emotion recognition using an emotion engine, making it possible to continuously provide appropriate advice and guidance to users.

[0906] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0907] System program processing flow

[0908] Step 1:

[0909] The server creates a new user profile when the user logs in for the first time. The prompt text is generated as follows:

[0910] "How are you feeling right now?"

[0911] "What hobbies do you have?"

[0912] "How often do you meet with your friends?"

[0913] The server generates these questionnaires and sends them to the terminal. The input is the user's login information, and the output is the generated questionnaire.

[0914] Step 2:

[0915] The terminal displays the list of questions received from the server to the user. The user inputs answers to the displayed questions. The input is the list of questions received from the server, and the output is the answer data entered by the user.

[0916] Step 3:

[0917] The user inputs an answer to the displayed question. Specifically, the user inputs text such as "I'm feeling a little anxious right now" into the terminal. The input is the displayed question, and the output is the answer text entered by the user.

[0918] Step 4:

[0919] The terminal collects the user's response data and sends it to the server. The input is the response data entered by the user, and the output is the response data sent to the server.

[0920] Step 5:

[0921] The server analyzes the received response data using an analysis engine and an emotion engine. Specifically, it uses natural language processing technology to evaluate the user's personality traits and emotional state, and recognizes emotions using the emotion engine. The input is the user's response data, and the output is an analyzed user profile and recognized emotion data.

[0922] Step 6:

[0923] The server generates a user profile from the analysis results and stores the profile in a database. The emotion data recognized by the emotion engine is also incorporated into the profile. The input is the analysis results, and the output is the generated user profile.

[0924] Step 7:

[0925] After a certain period of time, the server generates a new list of psychology-based questions and sends it to the terminal. The input is the user profile, and the output is the new list of questions.

[0926] Step 8:

[0927] The terminal provides a new list of questions to the user and collects their answers. The input is the new list of questions received from the server, and the output is the new answer data entered by the user.

[0928] Step 9:

[0929] The user answers a new question and sends the data to the server via the terminal. The input is the new question, and the output is the new answer data.

[0930] Step 10:

[0931] The server compares and analyzes the new response data with past data. It updates the profile, including the emotional data. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly. The input is the new response data and past data, and the output is the updated user profile and generated advice.

[0932] Step 11:

[0933] The server generates individual responses and instruction methods based on the updated user profile and transmits them to the terminal. The input is the updated user profile, and the output is the individual responses and instruction methods.

[0934] Step 12:

[0935] The terminal displays the responses and instruction methods received from the server to the user. The input is the responses and instruction methods received from the server, and the output is the instruction content displayed to the user.

[0936] Step 13:

[0937] The user reviews the advice and guidance provided and implements it as needed. For example, if a relaxation suggestion is displayed, the user tries it. The input is the displayed advice, and the output is the user's behavior.

[0938] Through the above processing steps, this system is able to provide highly accurate individual responses based on the user's psychological and emotional state.

[0939] (Application example 2)

[0940] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0941] In modern brick-and-mortar stores, it is difficult to grasp customers' psychological state and emotions in real time and provide personalized support and product suggestions. Furthermore, conventional systems have difficulty in properly recognizing customers' emotions and providing quick and appropriate responses based on that data. In order to improve customer satisfaction, it is necessary to provide advanced customer service based on customers' emotions.

[0942] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0943] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for capturing the user's facial expressions and voice in real time and recognizing their emotions using an emotion engine; means for transmitting the recognized emotion data to the server and returning analysis results in real time; and means for displaying appropriate customer service methods and product suggestions to the user based on the returned analysis results. This makes it possible to analyze the customer's psychological state and emotions in real time and provide individualized support based on the results. This improves customer satisfaction and enables advanced customer service in physical stores.

[0944] "Psychologically-based Questions" refers to a series of questions based on psychological theory and empirical research designed to assess a user's personality traits, interests, and emotional state.

[0945] "Response data" refers to response information provided by a user to a psychology-based question.

[0946] "User profile" refers to information that indicates a user's personality traits, interests, and emotional state, generated by analyzing collected response data and emotional data.

[0947] "Personalized responses and coaching" refers to specific advice and suggestions provided to a user based on the generated user profile.

[0948] "Capturing facial expressions and voice in real time" refers to instantly capturing the user's facial movements, tone of voice, pitch, etc. and processing them as digital data.

[0949] "Emotion engine" refers to a software or hardware module that analyzes captured facial and voice data to recognize the user's emotional state.

[0950] "Recognized emotion data" refers to data that indicates a particular emotional state of a user that has been analyzed and extracted by an emotion engine.

[0951] "Real-time return of analysis results" refers to the process of instantly sending recognized emotion data and other analysis results from the server to the device.

[0952] "Displaying customer service methods and product suggestions" refers to displaying information on the terminal display that suggests appropriate customer service methods and products to store staff based on the customer's emotional and psychological state.

[0953] "Brick and mortar store" refers to a point of sale that exists in a physical location and where customers can visit in person to purchase goods or services.

[0954] MODE FOR CARRYING OUT THE INVENTION

[0955] The present invention is a system for enhancing customer service in brick-and-mortar stores, which presents a series of psychologically based questions, analyzes the user's response data, and recognizes the user's emotions using an emotion engine. Specific embodiments of the system are described below.

[0956] System Configuration

[0957] The system of the present invention mainly consists of three main components: a server, terminals (smart glasses), and users (store staff and customers). It also includes an emotion engine and a back-end system for data analysis.

[0958] Hardware and software used

[0959] Server: Amazon Web Services (AWS) is used for data analysis and profile generation.

[0960] Devices: Smart glasses (e.g., Google Glass, Vuzix Blade) are used to capture data in real time and display information to staff.

[0961] Emotion Engine: Real-time emotion recognition using the Affectiva SDK.

[0962] Analysis engine: Uses TensorFlow to analyze image and audio data.

[0963] Communication: Uses the WebSocket API to send and receive data in real time.

[0964] Program processing and specific examples

[0965] 1. Data Collection:

[0966] Device: The smart glasses have a built-in camera that captures the customer's facial expressions and a microphone that picks up the customer's voice.

[0967] Emotion Engine: Recognize customer emotions based on captured data using the Affectiva SDK.

[0968] 2. Data Transmission and Analysis:

[0969] Terminal: Sends captured and analyzed data to the server.

[0970] Server: Further analyzes the received data using TensorFlow to assess the customer's state of mind and emotions.

[0971] 3. Generate personalized responses:

[0972] Server: Generates appropriate customer service methods and product suggestions based on the analysis results.

[0973] Terminal: The generated information is displayed on the smart glasses display.

[0974] 4. Real-time return:

[0975] Server: Sends back analysis results in real time and displays them on staff's smart glasses.

[0976] Terminal: Staff respond appropriately to customers based on the information displayed.

[0977] Specific examples

[0978] If a customer enters a store and shows an expression that suggests they are "slightly irritated," the emotion engine will recognize this expression and display a message in real time on the staff member's smart glasses saying, "The customer may be feeling dissatisfied. Please suggest products or services that will help them relax."

[0979] Prompt Sentence Examples

[0980] "Analyze the customer's facial expression and display the following instructions to your staff:

[0981] The customer is smiling: 'The customer seems happy. Please suggest new products.'

[0982] Customer in distress: 'The customer seems distressed. Please ask if they need help.'

[0983] Customer is frustrated: 'The customer may be frustrated. Suggest a product or service that will help them relax.'

[0984] In this way, the system of the present invention analyzes the customer's psychological state and emotions in real time and provides appropriate responses based on that analysis, thereby improving customer satisfaction and providing high-quality customer service.

[0985] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0986] Step 1:

[0987] The device captures the customer's facial expressions with a camera built into the smart glasses and picks up the customer's voice with a microphone, thereby inputting video and audio data.

[0988] Input: Customer facial expression video and audio

[0989] Output: Captured video and audio data

[0990] Step 2:

[0991] The device sends the captured video and audio data to the emotion engine, which uses the Affectiva SDK to recognize the customer's emotions from the video and audio data.

[0992] Input: Captured video and audio data

[0993] Output: Recognized emotion data

[0994] Step 3:

[0995] The device sends the recognized emotion data to the server, which then analyzes the received emotion data and previously collected response data using an analysis engine (TensorFlow) to evaluate the user's mental state and emotions.

[0996] Input: Recognized emotion data and previously collected response data

[0997] Output: Analysis results (mental state and emotional evaluation)

[0998] Step 4:

[0999] The server generates appropriate customer service methods and product suggestions based on the analysis results, which are then returned to the terminal in text format.

[1000] Input: Analysis results (mental state and emotional assessment)

[1001] Output: Text data of customer service methods and product recommendations

[1002] Step 5:

[1003] The device then displays the received text data on the smart glasses' display, allowing staff to provide appropriate service to customers based on this information.

[1004] Input: Text data of customer service methods and product recommendations

[1005] Output: Customer service methods and product suggestions displayed on smart glasses

[1006] This series of processing steps enables real-time analysis of the customer's psychological state and emotions, enabling personalized responses. Staff can receive, through the smart glasses, recommendations for optimal customer service methods and product recommendations in real time based on the customer's condition, thereby improving customer satisfaction.

[1007] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1008] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1009] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1010] [Third embodiment]

[1011] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1012] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1013] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1014] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1015] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1016] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1017] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1018] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1019] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1020] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1021] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1022] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1023] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[1024] System configuration

[1025] server

[1026] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server is also responsible for generating new questionnaires and generating personalized responses and coaching methods.

[1027] Terminal

[1028] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[1029] User

[1030] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[1031] Program processing

[1032] Data Collection Overview

[1033] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[1034] Terminal: Presents a list of questions to the user and collects their answers.

[1035] User: Provides answers to questions posed and sends the data to the device.

[1036] Processing response data

[1037] Terminal: Sends the user's response data to the server.

[1038] Server: Analyzes the received response data and evaluates the user's personality traits, interests, and emotional state to generate a user profile.

[1039] Regular data collection and analysis

[1040] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[1041] Terminal: Presents a new list of questions to the user and collects their answers.

[1042] User: Answers questions and sends the data to the server via the device.

[1043] Server: Compares and analyzes new response data with past data to understand changes in user sentiment and interests.

[1044] Generate and deliver personalized responses

[1045] Server: Generates personalized responses and guidance based on the updated user profile. For example, it suggests relaxation techniques for a user experiencing increased stress.

[1046] Terminal: Displays the response and instruction received from the server to the user.

[1047] User: Review the advice and guidance provided and implement it as needed.

[1048] Specific examples

[1049] Example of first login

[1050] Server: Send the following questions to the terminal of a newly registered user.

[1051] "How are you feeling right now?"

[1052] "What hobbies do you have?"

[1053] "How often do you meet with your friends?"

[1054] Terminal: Display the question to the user.

[1055] User: Answers the questions and sends them to the server from the device.

[1056] Server: Analyzes the response data and generates a user profile.

[1057] Examples of regular follow-up

[1058] Server: After one month, generate a new list of questions for the user and send it to the device.

[1059] Terminal: Display the new question to the user.

[1060] User: Answers questions and sends the data from the device to the server.

[1061] Server: Analyzes new response data and compares it with past data. For example, if a user responds that they are feeling more stressed, the server generates advice accordingly.

[1062] Terminal: Displays the generated advice to the user.

[1063] User: Check out the advice and try yoga.

[1064] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[1065] The processing flow will be explained below.

[1066] Step 1:

[1067] Server: Once a new user has registered, it generates a series of psychologically based questions and sends them to the device.

[1068] Step 2:

[1069] Terminal: Displays the generated list of questions to the user.

[1070] Step 3:

[1071] User: Answers the questionnaire and enters the answer data into the terminal.

[1072] Step 4:

[1073] Terminal: Sends the answer data entered by the user to the server.

[1074] Step 5:

[1075] Server: Receives the response data and analyzes it using an analytics engine. This analysis reveals the user's personality traits, interests, and current emotional state.

[1076] Step 6:

[1077] Server: Generates a user profile from the analysis results and stores the profile in a database.

[1078] Step 7:

[1079] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[1080] Step 8:

[1081] Terminal: The generated responses and instruction methods are displayed to the user, who then confirms them.

[1082] Step 9:

[1083] Server: After a certain period of time (e.g., one month), send a remote reminder and generate a new list of psychology-based questions for the user and send them to the device.

[1084] Step 10:

[1085] Terminal: Present the new question list to the user.

[1086] Step 11:

[1087] User: Answers a new question and enters the answer data into the device.

[1088] Step 12:

[1089] Device: Sends the user's new answer data to the server.

[1090] Step 13:

[1091] Server: Analyzes new response data and compares it with past response data.

[1092] Step 14:

[1093] Server: Updates the user's profile based on the analysis results, generating an up-to-date profile that reflects changes in the user's mood and interests.

[1094] Step 15:

[1095] Server: Generates new personalized responses and coaching strategies based on the updated user profile, such as stress reduction strategies or new hobby recommendations, if needed.

[1096] Step 16:

[1097] Device: Display the latest updates and guidance to the user.

[1098] Step 17:

[1099] User: Review any new guidance or solutions provided and implement them as needed.

[1100] This series of steps enables the system to flexibly respond to changes in the user's psychological state and interests, and provide appropriate, personalized advice and guidance.

[1101] Example 1

[1102] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1103] Conventional psychology-based data collection systems lack the ability to respond to individual users, making it difficult to accurately grasp the continuous changes in a user's emotions and interests. As a result, the accuracy of individualized instruction methods and advice is low, making it difficult to provide effective support. Furthermore, generating question lists requires a lot of manpower, and the systems lack scalability and flexibility.

[1104] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1105] In this invention, the server includes means for presenting a series of psychology-based questions to the user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, and means for providing the generated responses and instruction methods to the user. This makes it possible to continuously grasp changes in the user's psychological state and interests and provide appropriate responses and instruction.

[1106] A "psychologically based questionnaire" is a series of questions designed based on psychological theory and research to assess a user's psychological state, personality traits, and interests.

[1107] "User response data" is data that includes user-provided responses to the series of psychology-based questions.

[1108] A "user profile" is a collection of information generated based on a user's response data to indicate the user's personality traits, interests, emotional state, etc.

[1109] "Individualized responses and guidance methods" are methods for providing advice and assistance suited to a particular user based on the generated user profile.

[1110] A "generative AI model" is a model that uses artificial intelligence technology to generate text in natural language based on a specified prompt.

[1111] A "prompt" is a piece of text that is input to a generative AI model and provides instructions for the model to generate appropriate output.

[1112] A "machine learning algorithm" is a mathematical method or model that automatically learns from data, recognizes patterns, and makes predictions and classifications.

[1113] "Data analysis library" is a general term for software libraries used to collect, organize, analyze, and visualize data.

[1114] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[1115] System configuration

[1116] server

[1117] The server is a central processing unit that receives user response data, analyzes it, and generates and updates user profiles. The server is also responsible for generating new question lists and generating personalized responses and instructional methods. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-3) to generate question lists and analyzes the response data using Python's Pandas and Scikit-learn.

[1118] Terminal

[1119] The terminal is an electronic device accessed by the user, which poses psychological questions, collects the user's answers, and sends them to the server. The terminal can be a PC, smartphone, tablet, etc. The terminal displays the list of questions and sends the answers entered by the user to the server via an HTTP request.

[1120] User

[1121] The user is an individual or an organization that uses this system and is the subject of answering psychological questions. The user answers the questions using a terminal.

[1122] Program processing

[1123] Data Collection Overview

[1124] The server generates a list of psychology-based questions when the user logs in for the first time and sends them to the terminal. The terminal displays the list of questions to the user, collects the answers, and sends them to the server. The user provides answers to the displayed questions and sends the data to the terminal.

[1125] Processing response data

[1126] The device sends the user's response data to the server, which then analyzes the received response data and generates a user profile by evaluating the user's personality traits, interests, and emotional state. This analysis uses data analysis libraries such as Python's Pandas and Scikit-learn.

[1127] Regular data collection and analysis

[1128] The server periodically generates a new list of questions based on psychology for the user and sends it to the terminal. The terminal provides the new list of questions to the user and collects their answers. The user answers the questions and sends the data to the server via the terminal. The server compares and analyzes the new answer data with past data to understand changes in the user's feelings and interests.

[1129] Generate and deliver personalized responses

[1130] The server generates individualized responses and guidance methods based on the updated user profile. For example, it might suggest relaxation methods to a user experiencing increasing stress. The device displays the responses and guidance methods received from the server to the user. The user can then review the provided advice and guidance and implement them as necessary.

[1131] Specific examples

[1132] Example of first login

[1133] The server sends the following questions to the terminal of the newly registered user:

[1134] "How are you feeling right now?"

[1135] "What hobbies do you have?"

[1136] "How often do you meet with your friends?"

[1137] The device displays questions to the user. The user answers the questions and sends them to the server. The server analyzes the answer data and generates a user profile. For example, it uses Scikit-learn, a Python analysis library.

[1138] Examples of regular follow-up

[1139] The server generates a new list of questions for the user one month later and sends it to the device. The device displays the new questions to the user. The user answers the questions and sends the data from the device to the server. The server analyzes the new answer data and compares it with past data. For example, if the user answers "my stress has increased," the server generates advice accordingly. The device displays the generated advice to the user. The user checks the advice and tries yoga.

[1140] Prompt Sentence Examples

[1141] Generate a list of questions to ask users when they first log in: "How are you feeling right now?", "What are your hobbies?", "How often do you meet up with your friends?"

[1142]

[1143] Based on the user's response data, suggest ways to relieve stress, such as yoga, meditation, or walking.

[1144] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[1145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1146] Step 1: First login authentication

[1147] The server compares the authentication information (user ID and password) entered by the user with the database and authenticates the login. Specifically, the server receives the user's authentication information and checks whether it matches the information stored in the database. The input to this step is the authentication information entered by the user into the terminal, and the output is whether the login was successful or not.

[1148] Step 2: Generate a questionnaire

[1149] After successful authentication, the server generates a list of psychology-based questions to present to the user. Using a generative AI model, it creates appropriate questions based on the prompt text. Specifically, it inputs the prompt "Generate questions to display when the user logs in for the first time: How are you feeling right now?" and sends the generated text to the terminal as a list of questions. The input for this step is the prompt text, and the output is the generated list of questions.

[1150] Step 3: Question list display

[1151] The terminal displays the question list received from the server to the user. Specifically, the terminal places questions on the terminal's UI so that the user can answer them. The input of this step is the question list sent from the server, and the output is the user's visual confirmation.

[1152] Step 4: Collect response data

[1153] The terminal collects the answers entered by the user. The user enters answers to questions through the terminal. The input of this step is the user's answer, and the output is the collected answer data.

[1154] Step 5: Send response data

[1155] The terminal sends the collected response data to the server. Specifically, the terminal passes data to the server using the POST method of the HTTP request. The input of this step is the response data collected by the terminal, and the output is the response data sent to the server.

[1156] Step 6: Analyze response data

[1157] The server analyzes the received response data. Using Python's Pandas or Scikit-learn, the response data is converted into a data frame and the user's personality traits and interests are evaluated. As a specific example, a machine learning model is run on the converted data frame to extract the user's profile. The input to this step is the response data, and the output is the analysis results.

[1158] Step 7: Create a user profile

[1159] The server generates a user profile from the analysis results. The generated profile contains comprehensive information about the user's personality traits and interests. Specifically, it uses Scikit-learn to create a model and saves it in a database. The input to this step is the analysis results, and the output is the user profile.

[1160] Step 8: Provide feedback

[1161] The server generates initial feedback and advice based on the generated user profile. Specifically, it creates a feedback sentence from the generated profile and sends it to the terminal. The terminal displays the feedback to the user. The input of this step is the user profile, and the output is a feedback sentence.

[1162] Step 9: Generate regular follow-up questions

[1163] The server generates a new list of questions at regular intervals. It uses a generative AI model to create appropriate questions based on the prompt. As a specific example, a prompt such as "Please generate stress check questions as a follow-up in one month" is input to generate new questions. The input for this step is the prompt for follow-up, and the output is a new list of questions.

[1164] Step 10: Display the follow-up questions list

[1165] The terminal displays the newly generated question list to the user. The user checks the questions on the terminal and enters the answers. The input of this step is the new question list sent from the server, and the output is the user's visual confirmation.

[1166] Step 11: Collect new response data

[1167] The terminal collects new answers entered by the user. The user answers questions through the terminal. The input of this step is the user's new answers, and the output is the collected new answer data.

[1168] Step 12: Send new response data

[1169] The terminal sends the collected new response data to the server. Specifically, the terminal sends the data using the POST method of the HTTP request. The input of this step is the collected new response data, and the output is the new response data sent to the server.

[1170] Step 13: New data analysis

[1171] The server compares the newly received response data with past data and analyzes it. Python's Pandas is used to combine the old and new data into a data frame to understand changes in user sentiment and interests. The input for this step is the new response data and past data, and the output is the results of the comparison and analysis.

[1172] Step 14: Update User Profile

[1173] The server updates the user profile based on the analysis results. The updated profile reflects the latest user status. Specifically, it updates the Scikit-learn model and re-stores the information in the database. The input to this step is the comparative analysis results, and the output is an updated user profile.

[1174] Step 15: Providing advice

[1175] The server generates personalized advice based on the updated user profile. Specifically, it sends the generated advice sentence to the terminal, which then displays it to the user. The input of this step is the updated user profile, and the output is the generated advice sentence.

[1176] (Application example 1)

[1177] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1178] Conventional security awareness systems have had the challenge of accurately grasping users' psychological states and behavioral patterns and providing appropriate individual responses based on them. Furthermore, they lacked effective means for continuously monitoring changes in users' security risks and providing corresponding feedback. To address these challenges, advanced analysis based on users' psychological data and flexible responses utilizing generative AI models were required.

[1179] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1180] In this invention, the server includes means for providing a series of questions based on psychology to a user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, means for providing the generated responses and instruction methods to the user, means for generating a question list using a generative AI model, and means for periodically evaluating changes in the user's security awareness and risks. This makes it possible to accurately grasp the user's psychological state and behavioral patterns and reduce security risks through individual responses.

[1181] - A "psychologically based set of questions" is a set of questions based on psychological theories to assess a user's psychological state and behavioral patterns.

[1182] "Answer data" refers to information that answers a series of questions provided by a user.

[1183] A "user profile" is a data set that indicates a user's psychological state and behavioral characteristics, and is constructed based on collected user response data.

[1184] The "individual response and instruction method" refers to a response or instruction content that is generated based on the user profile and is tailored to the situation of each user.

[1185] A "generative AI model" is a model that uses machine learning and artificial intelligence to analyze and predict data, and is used, for example, to automatically generate question lists.

[1186] A "question list" is a set of psychologically generated questions presented to a user.

[1187] "Security awareness" refers to the awareness and attitude that users have toward the protection of information and assets in their daily lives and work.

[1188] A "security risk" is a security threat or danger that a user may face.

[1189] "Means of evaluation" refers to a method for analyzing the user's condition based on collected data and determining changes in risk and awareness.

[1190] This invention is a system that asks users psychological questions, collects and analyzes their answers, creates a psychological profile of the user, and proposes personalized responses based on that profile. An embodiment of this system will be described in detail below.

[1191] System configuration

[1192] server

[1193] The server is the core of data collection, analysis, and profile generation. Specifically, it has the following main functions:

[1194] Generate a list of questions: The server uses a generative AI model to generate a list of questions to assess the user's psychological state.

[1195] Analysis of response data: The collected response data is analyzed to generate user profiles. For the analysis, we use the Python Django framework and the Scikit-learn library.

[1196] Update user profile: New response data is collected periodically, compared with and analyzed against existing profiles, and then updated.

[1197] Generate personalized responses: Based on the user profile, personalized responses and instructional content are generated and sent to the device.

[1198] Terminal

[1199] The terminal provides the interface between the user and the server. It is typically a smartphone or tablet and has the following functions:

[1200] Present the question list: Present the question list sent from the server to the user.

[1201] Collecting response data: Collect user response data and send it to the server. The smartphone app uses Swift (iOS) and Kotlin (Android).

[1202] Providing individualized solutions: Displaying individual solutions and guidance received from the server to the user.

[1203] User

[1204] Users are individuals or organizations who use this system, answer questions presented by the system, and confirm and implement the guidance provided.

[1205] Operation Sequence

[1206] 1. First time login

[1207] The server uses a generative AI model to generate an initial list of questions and sends them to the terminal.

[1208] The terminal displays a list of initial questions to the user and collects their answers.

[1209] The server analyzes the collected response data and generates a user profile.

[1210] 2. Regular follow-up

[1211] At regular intervals, the server generates a new list of questions and sends it to the terminal.

[1212] The terminal displays new questions to the user and collects their answers.

[1213] The server analyzes the collected new response data, compares it with the existing profile, and updates the user profile.

[1214] 3. Providing personalized attention

[1215] The server generates new personalized treatments and coaching methods based on the updated user profile.

[1216] The terminal displays the generated response and instruction method to the user.

[1217] Specific examples

[1218] Example initial questions: "How often do you currently change your password?" or "How often do you perform backups?"

[1219] Example follow-up question: "Have you clicked on any suspicious links in emails or on social media recently?"

[1220] Prompt Sentence Examples

[1221] Below are some example prompts to input to the generative AI model:

[1222] "Generate the following questions:

[1223] 1. How often do you currently change your password?

[1224] 2. How did you research a new app you recently installed?

[1225] 3. How often do you perform backups?

[1226] According to the above-described embodiment, the present invention can accurately grasp the psychological state and behavioral patterns of users, and reduce security risks through individual responses.

[1227] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1228] Step 1: First login and questionnaire generation

[1229] When a user logs in for the first time, the server uses a generative AI model to generate a list of questions based on psychology. This list of questions is intended to evaluate the user's psychological state and behavioral patterns. The generated list of questions is then sent to the device.

[1230] Input: Information of the user who logged in for the first time

[1231] Data Computation: Automatic generation of question lists using generative AI models

[1232] Output: Generated questionnaire

[1233] Step 2: Present a list of questions and collect answers

[1234] The terminal presents the list of questions received from the server to the user. The user answers the presented questions, and the answer data is collected by the terminal. The collected answer data is then sent from the terminal to the server.

[1235] Input: Question list received from the server

[1236] Data processing: Displaying a list of questions and allowing users to enter answers

[1237] Output: User response data

[1238] Step 3: Analyze response data and generate user profiles

[1239] The server analyzes the response data sent from the device and generates a user profile. This analysis is performed using Python's Django framework and Scikit-learn library. Based on the analysis results, the user's psychological state and behavioral characteristics are evaluated and a profile is constructed.

[1240] Input: Answer data sent from the device

[1241] Data Calculation: Data Analysis and Profile Generation

[1242] Output: Generated user profile

[1243] Step 4: Generate personalized responses

[1244] The server generates individualized responses and instruction methods based on the generated user profile. These responses are suited to the user's psychological state and behavioral characteristics. The generated individualized responses are sent to the terminal.

[1245] Input: Generated user profile

[1246] Data arithmetic: generating personalized responses and instructional strategies

[1247] Output: Generated individual responses

[1248] Step 5: Offer personalized support

[1249] The terminal presents the individual response and instruction methods received from the server to the user, who can then confirm and implement the presented response and instruction methods.

[1250] Input: Specific response received from the server

[1251] Data processing: Display of individual support and instruction content

[1252] Output: Presented to the user

[1253] Step 6: Regular follow-up and generate a new list of questions

[1254] At regular intervals, the server uses the generative AI model to generate a new list of questions based on psychology. This list of questions is sent to the device and presented to the user to detect changes in the user's psychological state and behavior.

[1255] Input: Periodic time lapse

[1256] Data Calculation: Automatic generation of new question lists

[1257] Output: The new questionnaire generated

[1258] Step 7: Collect and analyze new response data

[1259] The device presents the user with a new list of questions, collects new response data, and sends it to the server, which analyzes the new response data, compares it with the existing profile, and updates the user's psychological profile accordingly.

[1260] Input: Newly collected response data

[1261] Data Calculation: Analyze data and update profiles

[1262] Output: Updated user profile

[1263] Through the above processing steps, the system of the present invention can accurately grasp the user's psychological state and behavioral patterns, and reduce security risks through individual responses.

[1264] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1265] The present invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1266] System configuration

[1267] server

[1268] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[1269] Terminal

[1270] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[1271] User

[1272] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[1273] Emotion Engine

[1274] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[1275] Program processing

[1276] Data Collection Overview

[1277] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[1278] Terminal: Presents a list of questions to the user and collects their answers.

[1279] User: Provides answers to questions presented and enters the data into the terminal.

[1280] Processing response data

[1281] Terminal: Sends the user's response data to the server.

[1282] Server: The received response data is analyzed by the analysis engine and emotion engine. The analysis engine evaluates the user's personality traits, interests, and current emotional state, and the emotion engine recognizes the user's emotions.

[1283] Creating and updating user profiles

[1284] Server: Generates a user profile from the analysis results and stores the profile in a database. Emotion data recognized by the emotion engine is also incorporated into the profile.

[1285] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[1286] Terminal: Presents a new list of questions to the user and collects their answers.

[1287] User: Answers questions and sends the data to the server via the device.

[1288] Server: Compares and analyzes new response data with past data to understand changes in the user's mood and interests, and updates the user profile taking into account the newly recognized emotional data by the emotion engine.

[1289] Generate and deliver personalized responses

[1290] Server: Generates personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it will suggest relaxation techniques.

[1291] Terminal: Displays the response and instruction received from the server to the user.

[1292] User: Review the advice and guidance provided and implement it as needed.

[1293] Specific examples

[1294] Example of first login

[1295] Server: Send the following questions to the terminal of a newly registered user.

[1296] "How are you feeling right now?"

[1297] "What hobbies do you have?"

[1298] "How often do you meet with your friends?"

[1299] Terminal: Display the question to the user.

[1300] User: Answers the questions and sends them to the server from the device.

[1301] Server: The response data is analyzed using an analysis engine to generate a user profile, and emotions are recognized using an emotion engine, and this data is also incorporated into the profile.

[1302] Examples of regular follow-up

[1303] Server: After one month, generate a new list of questions for the user and send it to the device.

[1304] Terminal: Display the new question to the user.

[1305] User: Answers questions and sends the data from the device to the server.

[1306] Server: Analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[1307] Terminal: Displays the generated advice to the user.

[1308] Users: Check out the advice and try yoga, meditation, etc.

[1309] In this way, the system further improves the accuracy and effectiveness of individual responses based on emotion recognition using an emotion engine, in addition to changes in the user's psychological state and interests, making it possible to continuously provide appropriate advice and guidance to the user.

[1310] The processing flow will be explained below.

[1311] Step 1:

[1312] Server: Generates a series of psychologically based questions for users who have completed new registration and sends the questions to the device.

[1313] Step 2:

[1314] Terminal: Displays the generated list of questions to the user.

[1315] Step 3:

[1316] User: Answers the displayed questions and enters the answer data into the terminal.

[1317] Step 4:

[1318] Terminal: Sends the user's response data to the server.

[1319] Step 5:

[1320] Server: To analyze the received response data, the emotion engine is started and emotions are recognized from the user's response data.

[1321] Step 6:

[1322] Server: Based on the emotion data recognized by the emotion engine, further detailed analysis is performed to evaluate the user's personality traits, interests, and current emotional state.

[1323] Step 7:

[1324] Server: Generates a user profile from the analysis results, including the recognized emotion data, and stores the profile in a database.

[1325] Step 8:

[1326] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[1327] Step 9:

[1328] Terminal: Displays the generated responses and instruction methods to the user.

[1329] Step 10:

[1330] User: Review the advice and guidance provided and act on it as needed.

[1331] Step 11:

[1332] Server: After a certain period of time (e.g., one month), the server sends a reminder to the user, generates a new psychological questionnaire, and sends it to the device.

[1333] Step 12:

[1334] Terminal: Present the new question list to the user.

[1335] Step 13:

[1336] User: Answers a new question and enters the answer data into the device.

[1337] Step 14:

[1338] Device: Sends the user's new answer data to the server.

[1339] Step 15:

[1340] Server: Receives new response data and recognizes emotions again using the emotion engine.

[1341] Step 16:

[1342] Server: Compares and analyzes new emotion data recognized by the emotion engine with previous response data and emotion data.

[1343] Step 17:

[1344] Server: Updates the user's profile based on the new analysis results, including the new emotional data.

[1345] Step 18:

[1346] Server: Generates new personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it generates relaxation techniques and stress management advice.

[1347] Step 19:

[1348] Terminal: The generated new responses and teaching methods are displayed to the user.

[1349] Step 20:

[1350] User: Review the new advice and guidance provided and implement it as needed.

[1351] This series of steps enables the system to continuously monitor changes in the user's psychological state and emotions and provide flexible and appropriate individual responses.

[1352] Example 2

[1353] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1354] Conventional systems provide basic questions and advice based on the user's psychological state, but they have difficulty recognizing the user's specific emotional state and providing individualized support and guidance based on that. Therefore, there is a need for systems that can quickly and accurately provide appropriate support according to the user's emotional changes and the situation they find themselves in. Another challenge is to improve the accuracy of user profiles and the quality of individualized support through regular follow-up.

[1355] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1356] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for recognizing emotions from the user response data; means for analyzing the emotion data and incorporating it into the user profile; means for periodically presenting new psychology-based questions to the user, collecting the response data, and comparing and analyzing it with past data; means for updating the user profile based on the collected new response data, generating new individual responses and instruction methods based on the updated user profile, and means for providing the generated responses and instruction methods to the user. This enables precise analysis of not only the user's psychological state but also their emotional state, making it possible to provide individual responses and instruction methods based on the analysis. This makes it possible to efficiently provide more appropriate support to the user.

[1357] A "user" is someone who uses this system to answer psychological questions and receive personalized support and guidance.

[1358] A "server" is a central processing unit that receives and analyzes user response data and generates and updates user profiles.

[1359] A "terminal" is an electronic device accessed by a user that presents psychological questions, collects user response data, and transmits it to a server.

[1360] "Psychologically based questions" are questions designed to understand a user's personality traits and emotional state.

[1361] A "user profile" is a data set that includes a user's personality traits, interests, emotional state, etc.

[1362] "Individual responses and guidance methods" are advice and suggestions tailored to the user, generated based on the user's profile.

[1363] The "emotion engine" is a system component that has the function of analyzing the user's response data and recognizing the user's emotional state.

[1364] "Answer data" is a general term for information provided by a user in response to a question.

[1365] The "analysis engine" is a component of the system that analyzes the user's response data and evaluates the user's personality traits, emotional state, and so on.

[1366] A "database" is a storage device for storing generated user profiles and analysis results.

[1367] "Follow-up" refers to the process of periodically checking the user's status, asking new questions, and collecting and analyzing the response data.

[1368] "TensorFlow" is a machine learning framework used to build emotion engines.

[1369] "Natural language processing" is a technology that analyzes the meaning of text data entered by a user and extracts various characteristics.

[1370] This invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. The system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1371] server

[1372] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[1373] The server is built on the Django framework using Python, and the emotion engine uses a machine learning model with TensorFlow. The analysis engine uses natural language processing technology to extract personality traits and emotional states from user response data.

[1374] Terminal

[1375] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. The terminal can be a personal computer, smartphone, tablet, or other device.

[1376] A web app is provided to access the device, and the service can be accessed through a browser. The device also temporarily stores the answer data entered by the user and sends it to the server.

[1377] User

[1378] The user is an individual or group who uses this system and answers psychological questions. The user enters answers to the questions displayed on the terminal and sends the data to the server.

[1379] Emotion Engine

[1380] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[1381] Specific examples

[1382] A specific example of system operation is shown below.

[1383] Example of first login

[1384] The server sends the following questions to the terminal of the newly registered user:

[1385] How are you feeling right now?

[1386] What hobbies do you have?

[1387] How often do you meet up with friends?

[1388] The terminal displays the question to the user.

[1389] The user answers the questions and sends them from the terminal to the server.

[1390] The server analyzes the response data using an analysis engine to generate a user profile, and also recognizes emotions using an emotion engine and incorporates that data into the profile.

[1391] Examples of regular follow-up

[1392] After one month, the server generates a new list of questions for the user and sends it to the terminal.

[1393] The terminal displays the new question to the user.

[1394] The user answers the questions and transmits the data from the terminal to the server.

[1395] The server analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[1396] The terminal displays the generated advice to the user.

[1397] Users check out advice and try things like yoga and meditation.

[1398] In this way, the system further improves the accuracy and effectiveness of individual responses based on changes in the user's psychological state and interests, as well as emotion recognition using an emotion engine, making it possible to continuously provide appropriate advice and guidance to users.

[1399] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1400] System program processing flow

[1401] Step 1:

[1402] The server creates a new user profile when the user logs in for the first time. The prompt text is generated as follows:

[1403] "How are you feeling right now?"

[1404] "What hobbies do you have?"

[1405] "How often do you meet with your friends?"

[1406] The server generates these questionnaires and sends them to the terminal. The input is the user's login information, and the output is the generated questionnaire.

[1407] Step 2:

[1408] The terminal displays the list of questions received from the server to the user. The user inputs answers to the displayed questions. The input is the list of questions received from the server, and the output is the answer data entered by the user.

[1409] Step 3:

[1410] The user inputs an answer to the displayed question. Specifically, the user inputs text such as "I'm feeling a little anxious right now" into the terminal. The input is the displayed question, and the output is the answer text entered by the user.

[1411] Step 4:

[1412] The terminal collects the user's response data and sends it to the server. The input is the response data entered by the user, and the output is the response data sent to the server.

[1413] Step 5:

[1414] The server analyzes the received response data using an analysis engine and an emotion engine. Specifically, it uses natural language processing technology to evaluate the user's personality traits and emotional state, and recognizes emotions using the emotion engine. The input is the user's response data, and the output is an analyzed user profile and recognized emotion data.

[1415] Step 6:

[1416] The server generates a user profile from the analysis results and stores the profile in a database. The emotion data recognized by the emotion engine is also incorporated into the profile. The input is the analysis results, and the output is the generated user profile.

[1417] Step 7:

[1418] After a certain period of time, the server generates a new list of psychology-based questions and sends it to the terminal. The input is the user profile, and the output is the new list of questions.

[1419] Step 8:

[1420] The terminal provides a new list of questions to the user and collects their answers. The input is the new list of questions received from the server, and the output is the new answer data entered by the user.

[1421] Step 9:

[1422] The user answers a new question and sends the data to the server via the terminal. The input is the new question, and the output is the new answer data.

[1423] Step 10:

[1424] The server compares and analyzes the new response data with past data. It updates the profile, including the emotional data. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly. The input is the new response data and past data, and the output is the updated user profile and generated advice.

[1425] Step 11:

[1426] The server generates individual responses and instruction methods based on the updated user profile and transmits them to the terminal. The input is the updated user profile, and the output is the individual responses and instruction methods.

[1427] Step 12:

[1428] The terminal displays the responses and instruction methods received from the server to the user. The input is the responses and instruction methods received from the server, and the output is the instruction content displayed to the user.

[1429] Step 13:

[1430] The user reviews the advice and guidance provided and implements it as needed. For example, if a relaxation suggestion is displayed, the user tries it. The input is the displayed advice, and the output is the user's behavior.

[1431] Through the above processing steps, this system is able to provide highly accurate individual responses based on the user's psychological and emotional state.

[1432] (Application example 2)

[1433] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1434] In modern brick-and-mortar stores, it is difficult to grasp customers' psychological state and emotions in real time and provide personalized support and product suggestions. Furthermore, conventional systems have difficulty in properly recognizing customers' emotions and providing quick and appropriate responses based on that data. In order to improve customer satisfaction, it is necessary to provide advanced customer service based on customers' emotions.

[1435] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1436] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for capturing the user's facial expressions and voice in real time and recognizing their emotions using an emotion engine; means for transmitting the recognized emotion data to the server and returning analysis results in real time; and means for displaying appropriate customer service methods and product suggestions to the user based on the returned analysis results. This makes it possible to analyze the customer's psychological state and emotions in real time and provide individualized support based on the results. This improves customer satisfaction and enables advanced customer service in physical stores.

[1437] "Psychologically-based Questions" refers to a series of questions based on psychological theory and empirical research designed to assess a user's personality traits, interests, and emotional state.

[1438] "Response data" refers to response information provided by a user to a psychology-based question.

[1439] "User profile" refers to information that indicates a user's personality traits, interests, and emotional state, generated by analyzing collected response data and emotional data.

[1440] "Personalized responses and coaching" refers to specific advice and suggestions provided to a user based on the generated user profile.

[1441] "Capturing facial expressions and voice in real time" refers to instantly capturing the user's facial movements, tone of voice, pitch, etc. and processing them as digital data.

[1442] "Emotion engine" refers to a software or hardware module that analyzes captured facial and voice data to recognize the user's emotional state.

[1443] "Recognized emotion data" refers to data that indicates a particular emotional state of a user that has been analyzed and extracted by an emotion engine.

[1444] "Real-time return of analysis results" refers to the process of instantly sending recognized emotion data and other analysis results from the server to the device.

[1445] "Displaying customer service methods and product suggestions" refers to displaying information on the terminal display that suggests appropriate customer service methods and products to store staff based on the customer's emotional and psychological state.

[1446] "Brick and mortar store" refers to a point of sale that exists in a physical location and where customers can visit in person to purchase goods or services.

[1447] MODE FOR CARRYING OUT THE INVENTION

[1448] The present invention is a system for enhancing customer service in brick-and-mortar stores, which presents a series of psychologically based questions, analyzes the user's response data, and recognizes the user's emotions using an emotion engine. Specific embodiments of the system are described below.

[1449] System Configuration

[1450] The system of the present invention mainly consists of three main components: a server, terminals (smart glasses), and users (store staff and customers). It also includes an emotion engine and a back-end system for data analysis.

[1451] Hardware and software used

[1452] Server: Amazon Web Services (AWS) is used for data analysis and profile generation.

[1453] Devices: Smart glasses (e.g., Google Glass, Vuzix Blade) are used to capture data in real time and display information to staff.

[1454] Emotion Engine: Real-time emotion recognition using the Affectiva SDK.

[1455] Analysis engine: Uses TensorFlow to analyze image and audio data.

[1456] Communication: Uses the WebSocket API to send and receive data in real time.

[1457] Program processing and specific examples

[1458] 1. Data Collection:

[1459] Device: The smart glasses have a built-in camera that captures the customer's facial expressions and a microphone that picks up the customer's voice.

[1460] Emotion Engine: Recognize customer emotions based on captured data using the Affectiva SDK.

[1461] 2. Data Transmission and Analysis:

[1462] Terminal: Sends captured and analyzed data to the server.

[1463] Server: Further analyzes the received data using TensorFlow to assess the customer's state of mind and emotions.

[1464] 3. Generate personalized responses:

[1465] Server: Generates appropriate customer service methods and product suggestions based on the analysis results.

[1466] Terminal: The generated information is displayed on the smart glasses display.

[1467] 4. Real-time return:

[1468] Server: Sends back analysis results in real time and displays them on staff's smart glasses.

[1469] Terminal: Staff respond appropriately to customers based on the information displayed.

[1470] Specific examples

[1471] If a customer enters a store and shows an expression that suggests they are "slightly irritated," the emotion engine will recognize this expression and display a message in real time on the staff member's smart glasses saying, "The customer may be feeling dissatisfied. Please suggest products or services that will help them relax."

[1472] Prompt Sentence Examples

[1473] "Analyze the customer's facial expression and display the following instructions to your staff:

[1474] The customer is smiling: 'The customer seems happy. Please suggest new products.'

[1475] Customer in distress: 'The customer seems distressed. Please ask if they need help.'

[1476] Customer is frustrated: 'The customer may be frustrated. Suggest a product or service that will help them relax.'

[1477] In this way, the system of the present invention analyzes the customer's psychological state and emotions in real time and provides appropriate responses based on that analysis, thereby improving customer satisfaction and providing high-quality customer service.

[1478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1479] Step 1:

[1480] The device captures the customer's facial expressions with a camera built into the smart glasses and picks up the customer's voice with a microphone, thereby inputting video and audio data.

[1481] Input: Customer facial expression video and audio

[1482] Output: Captured video and audio data

[1483] Step 2:

[1484] The device sends the captured video and audio data to the emotion engine, which uses the Affectiva SDK to recognize the customer's emotions from the video and audio data.

[1485] Input: Captured video and audio data

[1486] Output: Recognized emotion data

[1487] Step 3:

[1488] The device sends the recognized emotion data to the server, which then analyzes the received emotion data and previously collected response data using an analysis engine (TensorFlow) to evaluate the user's mental state and emotions.

[1489] Input: Recognized emotion data and previously collected response data

[1490] Output: Analysis results (mental state and emotional evaluation)

[1491] Step 4:

[1492] The server generates appropriate customer service methods and product suggestions based on the analysis results, which are then returned to the terminal in text format.

[1493] Input: Analysis results (mental state and emotional assessment)

[1494] Output: Text data of customer service methods and product recommendations

[1495] Step 5:

[1496] The device then displays the received text data on the smart glasses' display, allowing staff to provide appropriate service to customers based on this information.

[1497] Input: Text data of customer service methods and product recommendations

[1498] Output: Customer service methods and product suggestions displayed on smart glasses

[1499] This series of processing steps enables real-time analysis of the customer's psychological state and emotions, enabling personalized responses. Staff can receive, through the smart glasses, recommendations for optimal customer service methods and product recommendations in real time based on the customer's condition, thereby improving customer satisfaction.

[1500] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1501] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1502] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1503] [Fourth embodiment]

[1504] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1505] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1506] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1507] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1508] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1509] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1510] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1511] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1512] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1513] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1514] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1515] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1516] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1517] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[1518] System configuration

[1519] server

[1520] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server is also responsible for generating new questionnaires and generating personalized responses and coaching methods.

[1521] Terminal

[1522] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[1523] User

[1524] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[1525] Program processing

[1526] Data Collection Overview

[1527] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[1528] Terminal: Presents a list of questions to the user and collects their answers.

[1529] User: Provides answers to questions posed and sends the data to the device.

[1530] Processing response data

[1531] Terminal: Sends the user's response data to the server.

[1532] Server: Analyzes the received response data and evaluates the user's personality traits, interests, and emotional state to generate a user profile.

[1533] Regular data collection and analysis

[1534] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[1535] Terminal: Presents a new list of questions to the user and collects their answers.

[1536] User: Answers questions and sends the data to the server via the device.

[1537] Server: Compares and analyzes new response data with past data to understand changes in user sentiment and interests.

[1538] Generate and deliver personalized responses

[1539] Server: Generates personalized responses and guidance based on the updated user profile. For example, it suggests relaxation techniques for a user experiencing increased stress.

[1540] Terminal: Displays the response and instruction received from the server to the user.

[1541] User: Review the advice and guidance provided and implement it as needed.

[1542] Specific examples

[1543] Example of first login

[1544] Server: Send the following questions to the terminal of a newly registered user.

[1545] "How are you feeling right now?"

[1546] "What hobbies do you have?"

[1547] "How often do you meet with your friends?"

[1548] Terminal: Display the question to the user.

[1549] User: Answers the questions and sends them to the server from the device.

[1550] Server: Analyzes the response data and generates a user profile.

[1551] Examples of regular follow-up

[1552] Server: After one month, generate a new list of questions for the user and send it to the device.

[1553] Terminal: Display the new question to the user.

[1554] User: Answers questions and sends the data from the device to the server.

[1555] Server: Analyzes new response data and compares it with past data. For example, if a user responds that they are feeling more stressed, the server generates advice accordingly.

[1556] Terminal: Displays the generated advice to the user.

[1557] User: Check out the advice and try yoga.

[1558] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[1559] The processing flow will be explained below.

[1560] Step 1:

[1561] Server: Once a new user has registered, it generates a series of psychologically based questions and sends them to the device.

[1562] Step 2:

[1563] Terminal: Displays the generated list of questions to the user.

[1564] Step 3:

[1565] User: Answers the questionnaire and enters the answer data into the terminal.

[1566] Step 4:

[1567] Terminal: Sends the answer data entered by the user to the server.

[1568] Step 5:

[1569] Server: Receives the response data and analyzes it using an analytics engine. This analysis reveals the user's personality traits, interests, and current emotional state.

[1570] Step 6:

[1571] Server: Generates a user profile from the analysis results and stores the profile in a database.

[1572] Step 7:

[1573] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[1574] Step 8:

[1575] Terminal: The generated responses and instruction methods are displayed to the user, who then confirms them.

[1576] Step 9:

[1577] Server: After a certain period of time (e.g., one month), send a remote reminder and generate a new list of psychology-based questions for the user and send them to the device.

[1578] Step 10:

[1579] Terminal: Present the new question list to the user.

[1580] Step 11:

[1581] User: Answers a new question and enters the answer data into the device.

[1582] Step 12:

[1583] Device: Sends the user's new answer data to the server.

[1584] Step 13:

[1585] Server: Analyzes new response data and compares it with past response data.

[1586] Step 14:

[1587] Server: Updates the user's profile based on the analysis results, generating an up-to-date profile that reflects changes in the user's mood and interests.

[1588] Step 15:

[1589] Server: Generates new personalized responses and coaching strategies based on the updated user profile, such as stress reduction strategies or new hobby recommendations, if needed.

[1590] Step 16:

[1591] Device: Display the latest updates and guidance to the user.

[1592] Step 17:

[1593] User: Review any new guidance or solutions provided and implement them as needed.

[1594] This series of steps enables the system to flexibly respond to changes in the user's psychological state and interests, and provide appropriate, personalized advice and guidance.

[1595] Example 1

[1596] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1597] Conventional psychology-based data collection systems lack the ability to respond to individual users, making it difficult to accurately grasp the continuous changes in a user's emotions and interests. As a result, the accuracy of individualized instruction methods and advice is low, making it difficult to provide effective support. Furthermore, generating question lists requires a lot of manpower, and the systems lack scalability and flexibility.

[1598] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1599] In this invention, the server includes means for presenting a series of psychology-based questions to the user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, and means for providing the generated responses and instruction methods to the user. This makes it possible to continuously grasp changes in the user's psychological state and interests and provide appropriate responses and instruction.

[1600] A "psychologically based questionnaire" is a series of questions designed based on psychological theory and research to assess a user's psychological state, personality traits, and interests.

[1601] "User response data" is data that includes user-provided responses to the series of psychology-based questions.

[1602] A "user profile" is a collection of information generated based on a user's response data to indicate the user's personality traits, interests, emotional state, etc.

[1603] "Individualized responses and guidance methods" are methods for providing advice and assistance suited to a particular user based on the generated user profile.

[1604] A "generative AI model" is a model that uses artificial intelligence technology to generate text in natural language based on a specified prompt.

[1605] A "prompt" is a piece of text that is input to a generative AI model and provides instructions for the model to generate appropriate output.

[1606] A "machine learning algorithm" is a mathematical method or model that automatically learns from data, recognizes patterns, and makes predictions and classifications.

[1607] "Data analysis library" is a general term for software libraries used to collect, organize, analyze, and visualize data.

[1608] The present invention is a psychology-based data collection and analysis system for personalized user responses. The system consists of three main components: a server, a terminal, and a user.

[1609] System configuration

[1610] server

[1611] The server is a central processing unit that receives user response data, analyzes it, and generates and updates user profiles. The server is also responsible for generating new question lists and generating personalized responses and instructional methods. Specifically, the server uses a generative AI model (e.g., OpenAI's GPT-3) to generate question lists and analyzes the response data using Python's Pandas and Scikit-learn.

[1612] Terminal

[1613] The terminal is an electronic device accessed by the user, which poses psychological questions, collects the user's answers, and sends them to the server. The terminal can be a PC, smartphone, tablet, etc. The terminal displays the list of questions and sends the answers entered by the user to the server via an HTTP request.

[1614] User

[1615] The user is an individual or an organization that uses this system and is the subject of answering psychological questions. The user answers the questions using a terminal.

[1616] Program processing

[1617] Data Collection Overview

[1618] The server generates a list of psychology-based questions when the user logs in for the first time and sends them to the terminal. The terminal displays the list of questions to the user, collects the answers, and sends them to the server. The user provides answers to the displayed questions and sends the data to the terminal.

[1619] Processing response data

[1620] The device sends the user's response data to the server, which then analyzes the received response data and generates a user profile by evaluating the user's personality traits, interests, and emotional state. This analysis uses data analysis libraries such as Python's Pandas and Scikit-learn.

[1621] Regular data collection and analysis

[1622] The server periodically generates a new list of questions based on psychology for the user and sends it to the terminal. The terminal provides the new list of questions to the user and collects their answers. The user answers the questions and sends the data to the server via the terminal. The server compares and analyzes the new answer data with past data to understand changes in the user's feelings and interests.

[1623] Generate and deliver personalized responses

[1624] The server generates individualized responses and guidance methods based on the updated user profile. For example, it might suggest relaxation methods to a user experiencing increasing stress. The device displays the responses and guidance methods received from the server to the user. The user can then review the provided advice and guidance and implement them as necessary.

[1625] Specific examples

[1626] Example of first login

[1627] The server sends the following questions to the terminal of the newly registered user:

[1628] "How are you feeling right now?"

[1629] "What hobbies do you have?"

[1630] "How often do you meet with your friends?"

[1631] The device displays questions to the user. The user answers the questions and sends them to the server. The server analyzes the answer data and generates a user profile. For example, it uses Scikit-learn, a Python analysis library.

[1632] Examples of regular follow-up

[1633] The server generates a new list of questions for the user one month later and sends it to the device. The device displays the new questions to the user. The user answers the questions and sends the data from the device to the server. The server analyzes the new answer data and compares it with past data. For example, if the user answers "my stress has increased," the server generates advice accordingly. The device displays the generated advice to the user. The user checks the advice and tries yoga.

[1634] Prompt Sentence Examples

[1635] Generate a list of questions to ask users when they first log in: "How are you feeling right now?", "What are your hobbies?", "How often do you meet up with your friends?"

[1636]

[1637] Based on the user's response data, suggest ways to relieve stress, such as yoga, meditation, or walking.

[1638] In this way, the system can continuously monitor changes in the user's state of mind and interests and provide appropriate responses and guidance, improving the accuracy and effectiveness of personalized responses to users.

[1639] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1640] Step 1: First login authentication

[1641] The server compares the authentication information (user ID and password) entered by the user with the database and authenticates the login. Specifically, the server receives the user's authentication information and checks whether it matches the information stored in the database. The input to this step is the authentication information entered by the user into the terminal, and the output is whether the login was successful or not.

[1642] Step 2: Generate a questionnaire

[1643] After successful authentication, the server generates a list of psychology-based questions to present to the user. Using a generative AI model, it creates appropriate questions based on the prompt text. Specifically, it inputs the prompt "Generate questions to display when the user logs in for the first time: How are you feeling right now?" and sends the generated text to the terminal as a list of questions. The input for this step is the prompt text, and the output is the generated list of questions.

[1644] Step 3: Question list display

[1645] The terminal displays the question list received from the server to the user. Specifically, the terminal places questions on the terminal's UI so that the user can answer them. The input of this step is the question list sent from the server, and the output is the user's visual confirmation.

[1646] Step 4: Collect response data

[1647] The terminal collects the answers entered by the user. The user enters answers to questions through the terminal. The input of this step is the user's answer, and the output is the collected answer data.

[1648] Step 5: Send response data

[1649] The terminal sends the collected response data to the server. Specifically, the terminal passes data to the server using the POST method of the HTTP request. The input of this step is the response data collected by the terminal, and the output is the response data sent to the server.

[1650] Step 6: Analyze response data

[1651] The server analyzes the received response data. Using Python's Pandas or Scikit-learn, the response data is converted into a data frame and the user's personality traits and interests are evaluated. As a specific example, a machine learning model is run on the converted data frame to extract the user's profile. The input to this step is the response data, and the output is the analysis results.

[1652] Step 7: Create a user profile

[1653] The server generates a user profile from the analysis results. The generated profile contains comprehensive information about the user's personality traits and interests. Specifically, it uses Scikit-learn to create a model and saves it in a database. The input to this step is the analysis results, and the output is the user profile.

[1654] Step 8: Provide feedback

[1655] The server generates initial feedback and advice based on the generated user profile. Specifically, it creates a feedback sentence from the generated profile and sends it to the terminal. The terminal displays the feedback to the user. The input of this step is the user profile, and the output is a feedback sentence.

[1656] Step 9: Generate regular follow-up questions

[1657] The server generates a new list of questions at regular intervals. It uses a generative AI model to create appropriate questions based on the prompt. As a specific example, a prompt such as "Please generate stress check questions as a follow-up in one month" is input to generate new questions. The input for this step is the prompt for follow-up, and the output is a new list of questions.

[1658] Step 10: Display the follow-up questions list

[1659] The terminal displays the newly generated question list to the user. The user checks the questions on the terminal and enters the answers. The input of this step is the new question list sent from the server, and the output is the user's visual confirmation.

[1660] Step 11: Collect new response data

[1661] The terminal collects new answers entered by the user. The user answers questions through the terminal. The input of this step is the user's new answers, and the output is the collected new answer data.

[1662] Step 12: Send new response data

[1663] The terminal sends the collected new response data to the server. Specifically, the terminal sends the data using the POST method of the HTTP request. The input of this step is the collected new response data, and the output is the new response data sent to the server.

[1664] Step 13: New data analysis

[1665] The server compares the newly received response data with past data and analyzes it. Python's Pandas is used to combine the old and new data into a data frame to understand changes in user sentiment and interests. The input for this step is the new response data and past data, and the output is the results of the comparison and analysis.

[1666] Step 14: Update User Profile

[1667] The server updates the user profile based on the analysis results. The updated profile reflects the latest user status. Specifically, it updates the Scikit-learn model and re-stores the information in the database. The input to this step is the comparative analysis results, and the output is an updated user profile.

[1668] Step 15: Providing advice

[1669] The server generates personalized advice based on the updated user profile. Specifically, it sends the generated advice sentence to the terminal, which then displays it to the user. The input of this step is the updated user profile, and the output is the generated advice sentence.

[1670] (Application example 1)

[1671] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1672] Conventional security awareness systems have had the challenge of accurately grasping users' psychological states and behavioral patterns and providing appropriate individual responses based on them. Furthermore, they lacked effective means for continuously monitoring changes in users' security risks and providing corresponding feedback. To address these challenges, advanced analysis based on users' psychological data and flexible responses utilizing generative AI models were required.

[1673] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1674] In this invention, the server includes means for providing a series of questions based on psychology to a user, means for collecting user response data, means for analyzing the collected response data to generate a user profile, means for generating individual responses and instruction methods based on the user profile, means for providing the generated responses and instruction methods to the user, means for generating a question list using a generative AI model, and means for periodically evaluating changes in the user's security awareness and risks. This makes it possible to accurately grasp the user's psychological state and behavioral patterns and reduce security risks through individual responses.

[1675] - A "psychologically based set of questions" is a set of questions based on psychological theories to assess a user's psychological state and behavioral patterns.

[1676] "Answer data" refers to information that answers a series of questions provided by a user.

[1677] A "user profile" is a data set that indicates a user's psychological state and behavioral characteristics, and is constructed based on collected user response data.

[1678] The "individual response and instruction method" refers to a response or instruction content that is generated based on the user profile and is tailored to the situation of each user.

[1679] A "generative AI model" is a model that uses machine learning and artificial intelligence to analyze and predict data, and is used, for example, to automatically generate question lists.

[1680] A "question list" is a set of psychologically generated questions presented to a user.

[1681] "Security awareness" refers to the awareness and attitude that users have toward the protection of information and assets in their daily lives and work.

[1682] A "security risk" is a security threat or danger that a user may face.

[1683] "Means of evaluation" refers to a method for analyzing the user's condition based on collected data and determining changes in risk and awareness.

[1684] This invention is a system that asks users psychological questions, collects and analyzes their answers, creates a psychological profile of the user, and proposes personalized responses based on that profile. An embodiment of this system will be described in detail below.

[1685] System configuration

[1686] server

[1687] The server is the core of data collection, analysis, and profile generation. Specifically, it has the following main functions:

[1688] Generate a list of questions: The server uses a generative AI model to generate a list of questions to assess the user's psychological state.

[1689] Analysis of response data: The collected response data is analyzed to generate user profiles. For the analysis, we use the Python Django framework and the Scikit-learn library.

[1690] Update user profile: New response data is collected periodically, compared with and analyzed against existing profiles, and then updated.

[1691] Generate personalized responses: Based on the user profile, personalized responses and instructional content are generated and sent to the device.

[1692] Terminal

[1693] The terminal provides the interface between the user and the server. It is typically a smartphone or tablet and has the following functions:

[1694] Present the question list: Present the question list sent from the server to the user.

[1695] Collecting response data: Collect user response data and send it to the server. The smartphone app uses Swift (iOS) and Kotlin (Android).

[1696] Providing individualized solutions: Displaying individual solutions and guidance received from the server to the user.

[1697] User

[1698] Users are individuals or organizations who use this system, answer questions presented by the system, and confirm and implement the guidance provided.

[1699] Operation Sequence

[1700] 1. First time login

[1701] The server uses a generative AI model to generate an initial list of questions and sends them to the terminal.

[1702] The terminal displays a list of initial questions to the user and collects their answers.

[1703] The server analyzes the collected response data and generates a user profile.

[1704] 2. Regular follow-up

[1705] At regular intervals, the server generates a new list of questions and sends it to the terminal.

[1706] The terminal displays new questions to the user and collects their answers.

[1707] The server analyzes the collected new response data, compares it with the existing profile, and updates the user profile.

[1708] 3. Providing personalized attention

[1709] The server generates new personalized treatments and coaching methods based on the updated user profile.

[1710] The terminal displays the generated response and instruction method to the user.

[1711] Specific examples

[1712] Example initial questions: "How often do you currently change your password?" or "How often do you perform backups?"

[1713] Example follow-up question: "Have you clicked on any suspicious links in emails or on social media recently?"

[1714] Prompt Sentence Examples

[1715] Below are some example prompts to input to the generative AI model:

[1716] "Generate the following questions:

[1717] 1. How often do you currently change your password?

[1718] 2. How did you research a new app you recently installed?

[1719] 3. How often do you perform backups?

[1720] According to the above-described embodiment, the present invention can accurately grasp the psychological state and behavioral patterns of users, and reduce security risks through individual responses.

[1721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1722] Step 1: First login and questionnaire generation

[1723] When a user logs in for the first time, the server uses a generative AI model to generate a list of questions based on psychology. This list of questions is intended to evaluate the user's psychological state and behavioral patterns. The generated list of questions is then sent to the device.

[1724] Input: Information of the user who logged in for the first time

[1725] Data Computation: Automatic generation of question lists using generative AI models

[1726] Output: Generated questionnaire

[1727] Step 2: Present a list of questions and collect answers

[1728] The terminal presents the list of questions received from the server to the user. The user answers the presented questions, and the answer data is collected by the terminal. The collected answer data is then sent from the terminal to the server.

[1729] Input: Question list received from the server

[1730] Data processing: Displaying a list of questions and allowing users to enter answers

[1731] Output: User response data

[1732] Step 3: Analyze response data and generate user profiles

[1733] The server analyzes the response data sent from the device and generates a user profile. This analysis is performed using Python's Django framework and Scikit-learn library. Based on the analysis results, the user's psychological state and behavioral characteristics are evaluated and a profile is constructed.

[1734] Input: Answer data sent from the device

[1735] Data Calculation: Data Analysis and Profile Generation

[1736] Output: Generated user profile

[1737] Step 4: Generate personalized responses

[1738] The server generates individualized responses and instruction methods based on the generated user profile. These responses are suited to the user's psychological state and behavioral characteristics. The generated individualized responses are sent to the terminal.

[1739] Input: Generated user profile

[1740] Data arithmetic: generating personalized responses and instructional strategies

[1741] Output: Generated individual responses

[1742] Step 5: Offer personalized support

[1743] The terminal presents the individual response and instruction methods received from the server to the user, who can then confirm and implement the presented response and instruction methods.

[1744] Input: Specific response received from the server

[1745] Data processing: Display of individual support and instruction content

[1746] Output: Presented to the user

[1747] Step 6: Regular follow-up and generate a new list of questions

[1748] At regular intervals, the server uses the generative AI model to generate a new list of questions based on psychology. This list of questions is sent to the device and presented to the user to detect changes in the user's psychological state and behavior.

[1749] Input: Periodic time lapse

[1750] Data Calculation: Automatic generation of new question lists

[1751] Output: The new questionnaire generated

[1752] Step 7: Collect and analyze new response data

[1753] The device presents the user with a new list of questions, collects new response data, and sends it to the server, which analyzes the new response data, compares it with the existing profile, and updates the user's psychological profile accordingly.

[1754] Input: Newly collected response data

[1755] Data Calculation: Analyze data and update profiles

[1756] Output: Updated user profile

[1757] Through the above processing steps, the system of the present invention can accurately grasp the user's psychological state and behavioral patterns, and reduce security risks through individual responses.

[1758] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1759] The present invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. This system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1760] System configuration

[1761] server

[1762] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[1763] Terminal

[1764] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. Terminals can be PCs, smartphones, tablets, etc.

[1765] User

[1766] A user is an individual or organization that utilizes the system and is the subject of answering psychological questions.

[1767] Emotion Engine

[1768] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[1769] Program processing

[1770] Data Collection Overview

[1771] Server: When a user logs in for the first time, it generates a series of psychologically based questions and sends them to the device.

[1772] Terminal: Presents a list of questions to the user and collects their answers.

[1773] User: Provides answers to questions presented and enters the data into the terminal.

[1774] Processing response data

[1775] Terminal: Sends the user's response data to the server.

[1776] Server: The received response data is analyzed by the analysis engine and emotion engine. The analysis engine evaluates the user's personality traits, interests, and current emotional state, and the emotion engine recognizes the user's emotions.

[1777] Creating and updating user profiles

[1778] Server: Generates a user profile from the analysis results and stores the profile in a database. Emotion data recognized by the emotion engine is also incorporated into the profile.

[1779] Server: Generates a new list of psychological questions for the user at regular intervals and sends them to the terminal.

[1780] Terminal: Presents a new list of questions to the user and collects their answers.

[1781] User: Answers questions and sends the data to the server via the device.

[1782] Server: Compares and analyzes new response data with past data to understand changes in the user's mood and interests, and updates the user profile taking into account the newly recognized emotional data by the emotion engine.

[1783] Generate and deliver personalized responses

[1784] Server: Generates personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it will suggest relaxation techniques.

[1785] Terminal: Displays the response and instruction received from the server to the user.

[1786] User: Review the advice and guidance provided and implement it as needed.

[1787] Specific examples

[1788] Example of first login

[1789] Server: Send the following questions to the terminal of a newly registered user.

[1790] "How are you feeling right now?"

[1791] "What hobbies do you have?"

[1792] "How often do you meet with your friends?"

[1793] Terminal: Display the question to the user.

[1794] User: Answers the questions and sends them to the server from the device.

[1795] Server: The response data is analyzed using an analysis engine to generate a user profile, and emotions are recognized using an emotion engine, and this data is also incorporated into the profile.

[1796] Examples of regular follow-up

[1797] Server: After one month, generate a new list of questions for the user and send it to the device.

[1798] Terminal: Display the new question to the user.

[1799] User: Answers questions and sends the data from the device to the server.

[1800] Server: Analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[1801] Terminal: Displays the generated advice to the user.

[1802] Users: Check out the advice and try yoga, meditation, etc.

[1803] In this way, the system further improves the accuracy and effectiveness of individual responses based on emotion recognition using an emotion engine, in addition to changes in the user's psychological state and interests, making it possible to continuously provide appropriate advice and guidance to the user.

[1804] The processing flow will be explained below.

[1805] Step 1:

[1806] Server: Generates a series of psychologically based questions for users who have completed new registration and sends the questions to the device.

[1807] Step 2:

[1808] Terminal: Displays the generated list of questions to the user.

[1809] Step 3:

[1810] User: Answers the displayed questions and enters the answer data into the terminal.

[1811] Step 4:

[1812] Terminal: Sends the user's response data to the server.

[1813] Step 5:

[1814] Server: To analyze the received response data, the emotion engine is started and emotions are recognized from the user's response data.

[1815] Step 6:

[1816] Server: Based on the emotion data recognized by the emotion engine, further detailed analysis is performed to evaluate the user's personality traits, interests, and current emotional state.

[1817] Step 7:

[1818] Server: Generates a user profile from the analysis results, including the recognized emotion data, and stores the profile in a database.

[1819] Step 8:

[1820] Server: Based on the user profile, it generates an initial personalized response and instruction method appropriate for the user and sends the content to the device.

[1821] Step 9:

[1822] Terminal: Displays the generated responses and instruction methods to the user.

[1823] Step 10:

[1824] User: Review the advice and guidance provided and act on it as needed.

[1825] Step 11:

[1826] Server: After a certain period of time (e.g., one month), the server sends a reminder to the user, generates a new psychological questionnaire, and sends it to the device.

[1827] Step 12:

[1828] Terminal: Present the new question list to the user.

[1829] Step 13:

[1830] User: Answers a new question and enters the answer data into the device.

[1831] Step 14:

[1832] Device: Sends the user's new answer data to the server.

[1833] Step 15:

[1834] Server: Receives new response data and recognizes emotions again using the emotion engine.

[1835] Step 16:

[1836] Server: Compares and analyzes new emotion data recognized by the emotion engine with previous response data and emotion data.

[1837] Step 17:

[1838] Server: Updates the user's profile based on the new analysis results, including the new emotional data.

[1839] Step 18:

[1840] Server: Generates new personalized responses and guidance based on the updated user profile. For example, if the emotion engine recognizes that the user is stressed, it generates relaxation techniques and stress management advice.

[1841] Step 19:

[1842] Terminal: The generated new responses and teaching methods are displayed to the user.

[1843] Step 20:

[1844] User: Review the new advice and guidance provided and implement it as needed.

[1845] This series of steps enables the system to continuously monitor changes in the user's psychological state and emotions and provide flexible and appropriate individual responses.

[1846] Example 2

[1847] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1848] Conventional systems provide basic questions and advice based on the user's psychological state, but they have difficulty recognizing the user's specific emotional state and providing individualized support and guidance based on that. Therefore, there is a need for systems that can quickly and accurately provide appropriate support according to the user's emotional changes and the situation they find themselves in. Another challenge is to improve the accuracy of user profiles and the quality of individualized support through regular follow-up.

[1849] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1850] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for recognizing emotions from the user response data; means for analyzing the emotion data and incorporating it into the user profile; means for periodically presenting new psychology-based questions to the user, collecting the response data, and comparing and analyzing it with past data; means for updating the user profile based on the collected new response data, generating new individual responses and instruction methods based on the updated user profile, and means for providing the generated responses and instruction methods to the user. This enables precise analysis of not only the user's psychological state but also their emotional state, making it possible to provide individual responses and instruction methods based on the analysis. This makes it possible to efficiently provide more appropriate support to the user.

[1851] A "user" is someone who uses this system to answer psychological questions and receive personalized support and guidance.

[1852] A "server" is a central processing unit that receives and analyzes user response data and generates and updates user profiles.

[1853] A "terminal" is an electronic device accessed by a user that presents psychological questions, collects user response data, and transmits it to a server.

[1854] "Psychologically based questions" are questions designed to understand a user's personality traits and emotional state.

[1855] A "user profile" is a data set that includes a user's personality traits, interests, emotional state, etc.

[1856] "Individual responses and guidance methods" are advice and suggestions tailored to the user, generated based on the user's profile.

[1857] The "emotion engine" is a system component that has the function of analyzing the user's response data and recognizing the user's emotional state.

[1858] "Answer data" is a general term for information provided by a user in response to a question.

[1859] The "analysis engine" is a component of the system that analyzes the user's response data and evaluates the user's personality traits, emotional state, and so on.

[1860] A "database" is a storage device for storing generated user profiles and analysis results.

[1861] "Follow-up" refers to the process of periodically checking the user's status, asking new questions, and collecting and analyzing the response data.

[1862] "TensorFlow" is a machine learning framework used to build emotion engines.

[1863] "Natural language processing" is a technology that analyzes the meaning of text data entered by a user and extracts various characteristics.

[1864] This invention combines a psychology-based data collection and analysis system for providing personalized responses to users with an emotion engine that recognizes the user's emotions. The system consists of four main components: a server, a terminal, a user, and an emotion engine.

[1865] server

[1866] The server is a central processing unit that receives and analyzes user response data to generate and update user profiles. The server also generates new questionnaires and generates personalized responses and coaching. It also uses an emotion engine to recognize emotions from user response data and incorporates them into the analysis.

[1867] The server is built on the Django framework using Python, and the emotion engine uses a machine learning model with TensorFlow. The analysis engine uses natural language processing technology to extract personality traits and emotional states from user response data.

[1868] Terminal

[1869] The terminal is an electronic device that users access and has the function of asking psychological questions, collecting user response data, and sending it to the server. The terminal can be a personal computer, smartphone, tablet, or other device.

[1870] A web app is provided to access the device, and the service can be accessed through a browser. The device also temporarily stores the answer data entered by the user and sends it to the server.

[1871] User

[1872] The user is an individual or group who uses this system and answers psychological questions. The user enters answers to the questions displayed on the terminal and sends the data to the server.

[1873] Emotion Engine

[1874] The emotion engine analyzes user response data and has the ability to recognize the user's emotions, enabling more personalized responses and guidance based on the user's emotional state.

[1875] Specific examples

[1876] A specific example of system operation is shown below.

[1877] Example of first login

[1878] The server sends the following questions to the terminal of the newly registered user:

[1879] How are you feeling right now?

[1880] What hobbies do you have?

[1881] How often do you meet up with friends?

[1882] The terminal displays the question to the user.

[1883] The user answers the questions and sends them from the terminal to the server.

[1884] The server analyzes the response data using an analysis engine to generate a user profile, and also recognizes emotions using an emotion engine and incorporates that data into the profile.

[1885] Examples of regular follow-up

[1886] After one month, the server generates a new list of questions for the user and sends it to the terminal.

[1887] The terminal displays the new question to the user.

[1888] The user answers the questions and transmits the data from the terminal to the server.

[1889] The server analyzes the new response data using the analysis engine and emotion engine, compares it with past data, and updates the user profile. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly.

[1890] The terminal displays the generated advice to the user.

[1891] Users check out advice and try things like yoga and meditation.

[1892] In this way, the system further improves the accuracy and effectiveness of individual responses based on changes in the user's psychological state and interests, as well as emotion recognition using an emotion engine, making it possible to continuously provide appropriate advice and guidance to users.

[1893] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1894] System program processing flow

[1895] Step 1:

[1896] The server creates a new user profile when the user logs in for the first time. The prompt text is generated as follows:

[1897] "How are you feeling right now?"

[1898] "What hobbies do you have?"

[1899] "How often do you meet with your friends?"

[1900] The server generates these questionnaires and sends them to the terminal. The input is the user's login information, and the output is the generated questionnaire.

[1901] Step 2:

[1902] The terminal displays the list of questions received from the server to the user. The user inputs answers to the displayed questions. The input is the list of questions received from the server, and the output is the answer data entered by the user.

[1903] Step 3:

[1904] The user inputs an answer to the displayed question. Specifically, the user inputs text such as "I'm feeling a little anxious right now" into the terminal. The input is the displayed question, and the output is the answer text entered by the user.

[1905] Step 4:

[1906] The terminal collects the user's response data and sends it to the server. The input is the response data entered by the user, and the output is the response data sent to the server.

[1907] Step 5:

[1908] The server analyzes the received response data using an analysis engine and an emotion engine. Specifically, it uses natural language processing technology to evaluate the user's personality traits and emotional state, and recognizes emotions using the emotion engine. The input is the user's response data, and the output is an analyzed user profile and recognized emotion data.

[1909] Step 6:

[1910] The server generates a user profile from the analysis results and stores the profile in a database. The emotion data recognized by the emotion engine is also incorporated into the profile. The input is the analysis results, and the output is the generated user profile.

[1911] Step 7:

[1912] After a certain period of time, the server generates a new list of psychology-based questions and sends it to the terminal. The input is the user profile, and the output is the new list of questions.

[1913] Step 8:

[1914] The terminal provides a new list of questions to the user and collects their answers. The input is the new list of questions received from the server, and the output is the new answer data entered by the user.

[1915] Step 9:

[1916] The user answers a new question and sends the data to the server via the terminal. The input is the new question, and the output is the new answer data.

[1917] Step 10:

[1918] The server compares and analyzes the new response data with past data. It updates the profile, including the emotional data. For example, if the emotion engine recognizes that "stress has increased," it generates advice accordingly. The input is the new response data and past data, and the output is the updated user profile and generated advice.

[1919] Step 11:

[1920] The server generates individual responses and instruction methods based on the updated user profile and transmits them to the terminal. The input is the updated user profile, and the output is the individual responses and instruction methods.

[1921] Step 12:

[1922] The terminal displays the responses and instruction methods received from the server to the user. The input is the responses and instruction methods received from the server, and the output is the instruction content displayed to the user.

[1923] Step 13:

[1924] The user reviews the advice and guidance provided and implements it as needed. For example, if a relaxation suggestion is displayed, the user tries it. The input is the displayed advice, and the output is the user's behavior.

[1925] Through the above processing steps, this system is able to provide highly accurate individual responses based on the user's psychological and emotional state.

[1926] (Application example 2)

[1927] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1928] In modern brick-and-mortar stores, it is difficult to grasp customers' psychological state and emotions in real time and provide personalized support and product suggestions. Furthermore, conventional systems have difficulty in properly recognizing customers' emotions and providing quick and appropriate responses based on that data. In order to improve customer satisfaction, it is necessary to provide advanced customer service based on customers' emotions.

[1929] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1930] In this invention, the server includes: means for presenting a series of psychology-based questions to the user; means for collecting user response data; means for analyzing the collected response data to generate a user profile; means for capturing the user's facial expressions and voice in real time and recognizing their emotions using an emotion engine; means for transmitting the recognized emotion data to the server and returning analysis results in real time; and means for displaying appropriate customer service methods and product suggestions to the user based on the returned analysis results. This makes it possible to analyze the customer's psychological state and emotions in real time and provide individualized support based on the results. This improves customer satisfaction and enables advanced customer service in physical stores.

[1931] "Psychologically-based Questions" refers to a series of questions based on psychological theory and empirical research designed to assess a user's personality traits, interests, and emotional state.

[1932] "Response data" refers to response information provided by a user to a psychology-based question.

[1933] "User profile" refers to information that indicates a user's personality traits, interests, and emotional state, generated by analyzing collected response data and emotional data.

[1934] "Personalized responses and coaching" refers to specific advice and suggestions provided to a user based on the generated user profile.

[1935] "Capturing facial expressions and voice in real time" refers to instantly capturing the user's facial movements, tone of voice, pitch, etc. and processing them as digital data.

[1936] "Emotion engine" refers to a software or hardware module that analyzes captured facial and voice data to recognize the user's emotional state.

[1937] "Recognized emotion data" refers to data that indicates a particular emotional state of a user that has been analyzed and extracted by an emotion engine.

[1938] "Real-time return of analysis results" refers to the process of instantly sending recognized emotion data and other analysis results from the server to the device.

[1939] "Displaying customer service methods and product suggestions" refers to displaying information on the terminal display that suggests appropriate customer service methods and products to store staff based on the customer's emotional and psychological state.

[1940] "Brick and mortar store" refers to a point of sale that exists in a physical location and where customers can visit in person to purchase goods or services.

[1941] MODE FOR CARRYING OUT THE INVENTION

[1942] The present invention is a system for enhancing customer service in brick-and-mortar stores, which presents a series of psychologically based questions, analyzes the user's response data, and recognizes the user's emotions using an emotion engine. Specific embodiments of the system are described below.

[1943] System Configuration

[1944] The system of the present invention mainly consists of three main components: a server, terminals (smart glasses), and users (store staff and customers). It also includes an emotion engine and a back-end system for data analysis.

[1945] Hardware and software used

[1946] Server: Amazon Web Services (AWS) is used for data analysis and profile generation.

[1947] Devices: Smart glasses (e.g., Google Glass, Vuzix Blade) are used to capture data in real time and display information to staff.

[1948] Emotion Engine: Real-time emotion recognition using the Affectiva SDK.

[1949] Analysis engine: Uses TensorFlow to analyze image and audio data.

[1950] Communication: Uses the WebSocket API to send and receive data in real time.

[1951] Program processing and specific examples

[1952] 1. Data Collection:

[1953] Device: The smart glasses have a built-in camera that captures the customer's facial expressions and a microphone that picks up the customer's voice.

[1954] Emotion Engine: Recognize customer emotions based on captured data using the Affectiva SDK.

[1955] 2. Data Transmission and Analysis:

[1956] Terminal: Sends captured and analyzed data to the server.

[1957] Server: Further analyzes the received data using TensorFlow to assess the customer's state of mind and emotions.

[1958] 3. Generate personalized responses:

[1959] Server: Generates appropriate customer service methods and product suggestions based on the analysis results.

[1960] Terminal: The generated information is displayed on the smart glasses display.

[1961] 4. Real-time return:

[1962] Server: Sends back analysis results in real time and displays them on staff's smart glasses.

[1963] Terminal: Staff respond appropriately to customers based on the information displayed.

[1964] Specific examples

[1965] If a customer enters a store and shows an expression that suggests they are "slightly irritated," the emotion engine will recognize this expression and display a message in real time on the staff member's smart glasses saying, "The customer may be feeling dissatisfied. Please suggest products or services that will help them relax."

[1966] Prompt Sentence Examples

[1967] "Analyze the customer's facial expression and display the following instructions to your staff:

[1968] The customer is smiling: 'The customer seems happy. Please suggest new products.'

[1969] Customer in distress: 'The customer seems distressed. Please ask if they need help.'

[1970] Customer is frustrated: 'The customer may be frustrated. Suggest a product or service that will help them relax.'

[1971] In this way, the system of the present invention analyzes the customer's psychological state and emotions in real time and provides appropriate responses based on that analysis, thereby improving customer satisfaction and providing high-quality customer service.

[1972] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1973] Step 1:

[1974] The device captures the customer's facial expressions with a camera built into the smart glasses and picks up the customer's voice with a microphone, thereby inputting video and audio data.

[1975] Input: Customer facial expression video and audio

[1976] Output: Captured video and audio data

[1977] Step 2:

[1978] The device sends the captured video and audio data to the emotion engine, which uses the Affectiva SDK to recognize the customer's emotions from the video and audio data.

[1979] Input: Captured video and audio data

[1980] Output: Recognized emotion data

[1981] Step 3:

[1982] The device sends the recognized emotion data to the server, which then analyzes the received emotion data and previously collected response data using an analysis engine (TensorFlow) to evaluate the user's mental state and emotions.

[1983] Input: Recognized emotion data and previously collected response data

[1984] Output: Analysis results (mental state and emotional evaluation)

[1985] Step 4:

[1986] The server generates appropriate customer service methods and product suggestions based on the analysis results, which are then returned to the terminal in text format.

[1987] Input: Analysis results (mental state and emotional assessment)

[1988] Output: Text data of customer service methods and product recommendations

[1989] Step 5:

[1990] The device then displays the received text data on the smart glasses' display, allowing staff to provide appropriate service to customers based on this information.

[1991] Input: Text data of customer service methods and product recommendations

[1992] Output: Customer service methods and product suggestions displayed on smart glasses

[1993] This series of processing steps enables real-time analysis of the customer's psychological state and emotions, enabling personalized responses. Staff can receive, through the smart glasses, recommendations for optimal customer service methods and product recommendations in real time based on the customer's condition, thereby improving customer satisfaction.

[1994] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1995] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1996] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1997] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1998] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1999] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2000] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2001] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2002] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2003] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2004] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2005] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2006] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2007] 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.

[2008] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2009] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2010] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2011] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2012] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2013] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2014] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2015] The following is further disclosed regarding the above embodiment.

[2016] (Claim 1)

[2017] means for providing a series of psychology-based questions to a user;

[2018] A means for collecting user response data;

[2019] A means for analyzing the collected response data to generate a user profile;

[2020] means for generating personalized responses and instructional strategies based on the user profile;

[2021] A means for providing the generated response and instruction method to a user;

[2022] A system including:

[2023] (Claim 2)

[2024] 10. The system of claim 1, further comprising means for periodically presenting new psychological questions to the user, collecting response data, and comparing and analyzing the data with past data.

[2025] (Claim 3)

[2026] 10. The system of claim 1, further comprising means for updating the user profile based on the collected new response data and generating new personalized responses and coaching strategies based on the updated user profile.

[2027] "Example 1"

[2028] (Claim 1)

[2029] means for providing a series of psychology-based questions to a user;

[2030] A means for collecting user response data;

[2031] A means for analyzing the collected response data to generate a user profile;

[2032] means for generating personalized responses and instructional strategies based on the user profile;

[2033] A means for providing the generated response and instruction method to a user;

[2034] A system including:

[2035] (Claim 2)

[2036] A means for periodically providing new psychological questions to users, collecting response data, and comparing and analyzing the data with past data;

[2037] a means for generating new questions based on the prompt using a generative AI model;

[2038] and means for using a machine learning algorithm in analyzing the user response data.

[2039] 10. The system of claim 1.

[2040] (Claim 3)

[2041] Update user profiles based on new response data collected,

[2042] means for generating new personalized responses and instructional strategies based on the updated user profile;

[2043] further comprising means for using the data analysis library to generate and update the user profile;

[2044] 10. The system of claim 1.

[2045] "Application Example 1"

[2046] (Claim 1)

[2047] means for providing a series of psychology-based questions to a user;

[2048] A means for collecting user response data;

[2049] A means for analyzing the collected response data to generate a user profile;

[2050] means for generating personalized responses and instructional strategies based on the user profile;

[2051] A means for providing the generated response and instruction method to a user;

[2052] a means for generating a list of questions using a generative AI model;

[2053] A means of periodically evaluating changes in users' security awareness and risks;

[2054] A system including:

[2055] (Claim 2)

[2056] 10. The system of claim 1, further comprising means for periodically presenting new psychological questions to the user, collecting response data, and comparing and analyzing the data with past data.

[2057] (Claim 3)

[2058] 10. The system of claim 1, further comprising means for updating the user profile based on the collected new response data and generating new personalized responses and coaching strategies based on the updated user profile.

[2059] "Example 2: Combining Emotion Engines"

[2060] (Claim 1)

[2061] means for providing a series of psychology-based questions to a user;

[2062] A means for collecting user response data;

[2063] A means for analyzing the collected response data to generate a user profile;

[2064] means for generating personalized responses and instructional strategies based on the user profile;

[2065] A means for providing the generated response and instruction method to a user;

[2066] A means for recognizing emotions from user response data;

[2067] means for analyzing the emotion data and incorporating it into a user profile;

[2068] A system including:

[2069] (Claim 2)

[2070] 10. The system of claim 1, further comprising means for periodically presenting new psychological questions to the user, collecting response data, and comparing and analyzing the data with past data.

[2071] (Claim 3)

[2072] 10. The system of claim 1, further comprising means for updating the user profile based on the collected new response data and generating new personalized responses and coaching strategies based on the updated user profile.

[2073] "Application example 2 when combining emotion engines"

[2074] (Claim 1)

[2075] means for providing a series of psychology-based questions to a user;

[2076] A means for collecting user response data;

[2077] A means for analyzing the collected response data to generate a user profile;

[2078] means for generating personalized responses and instructional strategies based on the user profile;

[2079] A means for providing the generated response and instruction method to a user;

[2080] A means for capturing a user's facial expressions and voice in real time and recognizing emotions using an emotion engine;

[2081] means for transmitting the recognized emotion data to a server and returning analysis results in real time;

[2082] A means for displaying appropriate customer service methods and product suggestions to the user based on the returned analysis results;

[2083] A system including:

[2084] (Claim 2)

[2085] 10. The system of claim 1, further comprising means for periodically presenting new psychological questions to the user, collecting response data, and comparing and analyzing the data with past data.

[2086] (Claim 3)

[2087] 10. The system of claim 1, further comprising means for updating the user profile based on the collected new response data and emotion data, and generating new personalized responses and coaching strategies based on the updated user profile. [Explanation of symbols]

[2088] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for providing a series of psychology-based questions to a user; A means for collecting user response data; A means for analyzing the collected response data to generate a user profile; means for generating personalized responses and instructional strategies based on the user profile; A means for providing the generated response and instruction method to a user; A system including:

2. 2. The system according to claim 1, further comprising means for periodically presenting new psychological questions to the user, collecting response data, and comparing and analyzing the data with past data.

3. 10. The system of claim 1, further comprising means for updating the user profile based on the collected new response data and generating new personalized responses and coaching strategies based on the updated user profile.

Images