system

Abstract

To provide a system that can offer users practical and specific feedback. [Solution] A system comprising: means for receiving authentication information entered by the user; means for comparing the received authentication information with records in a database; means for providing the user with a diagnostic start page when user authentication is successful; means for receiving a diagnostic start request from the user; means for sequentially displaying pre-configured questions for enneagram diagnosis to the user; means for receiving and saving the user's answers; means for analyzing the answer data and identifying the user's enneagram type when all questions have been answered; means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results; and means for providing the generated report to the user.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Self-analysis tools are useful for understanding an individual's personality and aptitude. However, conventional self-analysis tools mainly use a one-way question-and-answer format, and there is a problem that it is difficult to deeply analyze the user's answers. In addition, many of these tools lack the function of analyzing the user's answer data in detail and providing specific feedback. Therefore, it is difficult for users to obtain practical information, and there is a problem that they cannot be fully utilized in job hunting, team building, personnel evaluation, etc.

Means for Solving the Problems

[0005] The present invention solves the above problems with a system that includes means for receiving authentication information entered by a user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-set Enneagram diagnostic questions to the user, means for receiving and saving the user's answers, means for analyzing the answer data and identifying the user's Enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. In particular, by using a machine learning model as a means for analyzing the answer data, it becomes possible to identify the Enneagram type with high accuracy and provide the user with practical and specific feedback.

[0006] User authentication is the process of verifying that a user is a legitimate user when they access a system.

[0007] A "database" is a collection of information that is systematically stored and can be efficiently searched and updated as needed.

[0008] A "diagnosis start page" is a web page or application screen that provides an interface for users to begin the Enneagram diagnosis.

[0009] A "diagnosis initiation request" is an action or signal that a user sends to the system to indicate their intention to begin a diagnosis.

[0010] An "Enneagram diagnostic questionnaire" is a set of specific questions designed to assess a user's personality traits and aptitudes.

[0011] "User responses" refer to the response data selected or entered by the user in response to questions used for the Enneagram assessment.

[0012] "Analysis of response data" is an analytical process that uses user response data to identify Enneagram types and other characteristics.

[0013] "Personality traits" refer to the patterns of behavior and thought that characterize an individual's personality.

[0014] "Job suitability" refers to evaluation information that indicates how well an individual is suited to a particular job or role.

[0015] A "machine learning model" is an algorithm or mathematical model that learns from data and uses the results of that learning to make predictions or classifications about new data.

[0016] A "report" refers to a document or data generated based on the analysis results, and includes specific feedback regarding the user's personality traits and suitability for the job. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be described.

[0020] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Further, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of the arithmetic unit include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[0039] 1. User Registration and Authentication

[0040] 1. User Registration

[0041] Users access the registration page and enter the required information (name, email address, password, etc.).

[0042] The terminal sends the entered information to the server.

[0043] The server validates the received information to ensure it is in the correct format.

[0044] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[0045] 2. User Authentication

[0046] The user enters their email address and password on the login page and attempts to authenticate.

[0047] The terminal sends the entered authentication information to the server.

[0048] The server compares the information with that in the database to determine if authentication was successful.

[0049] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0050] 2. Begin Enneagram assessment

[0051] 1. Preparation for initiating diagnosis

[0052] The user clicks the "Start Diagnosis" button on the homepage.

[0053] The device sends this request to the server.

[0054] The server starts a new diagnostic session and selects the first question to present to the user.

[0055] 2. Display the question

[0056] The server generates the first question for the Enneagram assessment and displays it to the user.

[0057] The device displays the question on the screen and allows the user to select or enter an answer.

[0058] 3. Processing Question Answers

[0059] 1. Collection of responses

[0060] The user selects the appropriate option for each question and clicks the submit button.

[0061] The device sends the user's responses to the server in real time.

[0062] 2. Save your answer

[0063] The server temporarily stores the received response as session data.

[0064] The server selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[0065] 4. Analysis of diagnostic results

[0066] 1. Analysis of response data

[0067] Once all questions have been answered, the server passes the accumulated answer data, which is stored as session data, to the AI ​​engine.

[0068] The server uses a machine learning model to analyze the response data and identify the user's Enneagram type.

[0069] 2. Report generation

[0070] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[0071] The report includes a description of the user's Enneagram type, personality traits, strengths, and advice on suitable job types and roles.

[0072] 5. Results display and feedback

[0073] 1. Providing results

[0074] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0075] The device will display a report on the results screen so that the user can review it.

[0076] 2. User Feedback

[0077] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[0078] Users can use the results to consider their career paths and create plans for self-improvement.

[0079] Specific example

[0080] For example, if a user named "Yamada Taro" creates a new account, the user fills in the required information on the registration form. The server receives this information and stores it in a database, allowing the user to log in later. The user then logs in and clicks the "Start Diagnosis" button. The server generates the first questions of the Enneagram diagnosis and presents them to the user via the terminal. Once the user answers the questions, the answers are sent to the server and temporarily stored. After all questions have been answered, the server uses an AI engine to analyze the data and determine Yamada Taro's Enneagram type. Based on the results, the server creates a report and provides it to Yamada Taro.

[0081] This system allows users to conduct self-analysis and consider their career path based on the results.

[0082] The following describes the processing flow.

[0083] Step 1:

[0084] Users access the registration page and enter the required information (name, email address, password, etc.).

[0085] The terminal sends the information entered by the user to the server as form data.

[0086] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[0087] Step 2:

[0088] If validation is successful, the server saves the information to the database as a new user.

[0089] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[0090] The user confirms the registration completion message and then accesses the login page.

[0091] Step 3:

[0092] The user enters their email address and password on the login page.

[0093] The terminal sends the entered authentication information to the server.

[0094] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[0095] Step 4:

[0096] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0097] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[0098] Step 5:

[0099] The device sends this request to the server.

[0100] The server starts a new diagnostic session, selects the first question, and sends it back to the terminal.

[0101] The device displays the first question on the screen, allowing the user to answer it.

[0102] Step 6:

[0103] The user selects the appropriate option for the displayed question and clicks the submit button.

[0104] The device sends the user's response to the server in real time.

[0105] Step 7:

[0106] The server temporarily stores the received response as session data.

[0107] The server selects the next question and sends it back to the terminal.

[0108] Repeat this process until the entire set of questions is complete.

[0109] Step 8:

[0110] Once the user has finished answering all the questions, the server collects the session data.

[0111] The server passes the response data to the AI ​​engine, which then analyzes the Enneagram type.

[0112] The AI ​​uses machine learning models to analyze user response patterns and identify types.

[0113] Step 9:

[0114] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[0115] The report includes information such as a description of the user's Enneagram type, personality traits, and suitable occupations and jobs.

[0116] Step 10:

[0117] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0118] The device will display a report on the results screen so that the user can review it.

[0119] The above describes the specific processing flow in the system of the present invention.

[0120] (Example 1)

[0121] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0122] Traditional personality assessment systems often suffer from inaccurate results and insufficient feedback, as users simply answer pre-set questions. Furthermore, the lack of machine learning models in the analysis results reduces the reliability of the assessment. Additionally, cumbersome user authentication and session management detract from the user experience.

[0123] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0124] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for starting a user session and providing a diagnostic start page when user authentication is successful, means for sequentially displaying pre-configured personality diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's personality type using a generated AI model when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This enables the provision of highly accurate and reliable diagnostic results to the user and allows for detailed feedback based on individual personality traits. Furthermore, by simplifying user authentication and session management, the overall user experience can be improved.

[0125] "User authentication" refers to the process of verifying that a user is a legitimate user by comparing the authentication information entered by the user with records in a database.

[0126] The "diagnosis start page" is a web page that users access when they begin a diagnosis, and it is a screen for preparing for the diagnosis.

[0127] A "diagnostic session" represents a series of steps a user takes to perform a diagnosis, and is a collection of data that includes the entire process of answering a series of questions.

[0128] "Personality assessment questions" are pre-set questions designed to determine a user's personality traits and suitability for a job.

[0129] "Response data" refers to the data of the answers that a user enters or selects in response to diagnostic questions.

[0130] A "machine learning model" is an artificial intelligence technology that is trained using large amounts of data to perform specific tasks with high accuracy.

[0131] A "generative AI model" is a machine learning algorithm that learns on its own and is used to analyze user diagnostic data.

[0132] "Personality traits" is a concept that describes the unique characteristics and patterns related to a user's personality.

[0133] "Job suitability" is an indicator used to evaluate how well-suited a user is for a particular job or task.

[0134] A "detailed report" is a document generated based on the analysis results that contains specific and detailed information about the user's personality traits and suitability for the job.

[0135] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[0136] 1. User Registration and Authentication

[0137] User Registration

[0138] The user accesses the system's registration page and enters required information such as name, email address, and password. The terminal sends this information to the server. The server validates the received information to ensure it is in the correct format. Information that is successfully validated is stored in the database, and a registration completion message is sent back to the user.

[0139] User Authentication

[0140] The user enters their email address and password on the login page and attempts authentication. The device sends the entered authentication information to the server. The server compares it with the information in the database to confirm whether authentication was successful. If authentication is successful, the server starts a user session and redirects the user to the homepage.

[0141] 2. Begin Enneagram assessment

[0142] Preparation for starting the diagnosis

[0143] The user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnostic session, generates the first question, and provides it to the user.

[0144] Display the question

[0145] The server generates the initial questions for the Enneagram assessment and displays them to the user via the screen. The terminal displays the questions and allows the user to select or enter answers.

[0146] 3. Processing Question Answers

[0147] Collection of responses

[0148] The user selects the appropriate option for each question and clicks the submit button. The device then sends the user's answers to the server.

[0149] Save the answer

[0150] The server temporarily stores the received answers as session data. It then selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[0151] 4. Analysis of diagnostic results

[0152] Analysis of response data

[0153] The server passes the session data to the AI ​​engine once all questions have been answered. The server uses a machine learning model to identify the user's personality type.

[0154] 5. Report generation and results delivery

[0155] Report generation

[0156] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. The report includes an explanation of the Enneagram type, personality traits, strengths, and career advice.

[0157] Providing results

[0158] The server sends the generated report to the device for display on the user's dashboard. The device displays the report on the results screen, allowing the user to review it.

[0159] Specific example

[0160] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information on the registration page. The device sends this information to the server, which validates it and saves it to the database if the information is in the correct format. Once registration is complete, Yamada Taro logs in and clicks the "Start Diagnosis" button. The server generates the first question of the diagnosis and presents it to Yamada Taro through the device. When Yamada Taro answers, the answer is sent to the server and temporarily stored. Once all questions are completed, the server uses an AI engine to analyze and identify Yamada Taro's personality type. A report is generated based on the results and presented on Yamada Taro's dashboard.

[0161] Example of a prompt

[0162] "Please create a new account."

[0163] "Please log in to begin the diagnosis."

[0164] "Please answer all questions and obtain your diagnostic results."

[0165] This system allows users to understand their own personality traits and job suitability with high accuracy, and to receive effective feedback. Furthermore, it simplifies user authentication and session management, improving the overall user experience.

[0166] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0167] Step 1: User Registration

[0168] Input: The user accesses the registration page and enters their name, email address, and password.

[0169] Processing: The terminal sends this information to the server. The server validates the received information to check if it is in the correct format (e.g., email address format and password strength).

[0170] Output: The server saves the information that was successfully validated to the database, generates a registration completion message, and sends it to the terminal.

[0171] Specific operation: The user enters information into a form via a browser and clicks the submit button. The server executes backend validation logic (e.g., email address check using regular expressions).

[0172] Step 2: User Authentication

[0173] Input: The user enters their email address and password on the login page.

[0174] Processing: The terminal sends these authentication credentials to the server. The server compares them with the information in the database, and if they match, it determines that authentication was successful.

[0175] Output: The server initiates a user session and sends instructions to the terminal to redirect to the homepage.

[0176] Specific operation: The user enters information into the login form, and the terminal sends it to the server as an HTTP POST request. The server executes a database query to retrieve the user information and compares it with a hashed password.

[0177] Step 3: Start diagnosis

[0178] Input: The user clicks the "Start Diagnosis" button on the homepage.

[0179] Processing: The terminal sends this request to the server. The server starts a new diagnostic session and generates the first question.

[0180] Output: The server sends the first question to the terminal, and the terminal displays it to the user.

[0181] Specific operation: The server generates a diagnostic session ID and stores the session information in memory. Next, it randomly or sequentially selects the first question from the question list and sends it to the terminal in JSON format.

[0182] Step 4: Question Display

[0183] Input: Question data received from the server by the terminal.

[0184] Processing: The terminal displays the question on the screen and allows the user to select or enter an answer.

[0185] Output: The user enters or selects an answer to the displayed question.

[0186] Specific operation: The terminal analyzes the received question data and displays it on the screen using HTML or other front-end technologies.

[0187] Step 5: Collecting responses

[0188] Input: Response data submitted by the user.

[0189] Processing: The terminal sends the user's response to the server. The server temporarily stores the received response as session data.

[0190] Output: The server generates the following question and sends it to the terminal.

[0191] Specific operation: When the user clicks the submit button, the device sends an HTTP POST request containing the answer data to the server. The server saves the answer data to memory or a database and selects the next question.

[0192] Step 6: Refresh the problem session

[0193] Input: A request from the user to proceed to the next question.

[0194] Processing: The server selects the next question based on the session data and sends it to the terminal.

[0195] Output: The terminal will display the following question on the screen.

[0196] Specific operation: Based on the previous question and answer, the server determines the next question to display, generates a new question, and sends it to the terminal.

[0197] Step 7: Analysis of diagnostic results

[0198] Input: User response data for all questions.

[0199] Processing: The server collects all response data and passes it to the AI ​​engine for analysis.

[0200] Output: The server identifies the user's personality type and retrieves the result.

[0201] Specific operation: The server calls an AI engine (e.g., scikit-learn in Python or TENSORFLOW®), inputs the user's response data into a pre-trained model, and predicts the personality type.

[0202] Step 8: Report Generation

[0203] Input: Analysis results from the AI ​​engine.

[0204] Processing: The server generates a detailed report based on the analysis results.

[0205] Output: The server prepares to send the generated report to the terminal.

[0206] Specific operation: The server uses a template engine (e.g., Jinja2) to create a detailed report based on the analysis results and structure it in JSON format.

[0207] Step 9: Results display and feedback

[0208] Input: Report data sent from the server.

[0209] Processing: The terminal displays the report on the screen for the user to review.

[0210] Output: Users review the report and provide feedback as needed.

[0211] Specific operation: The device parses the received report data and displays it on the screen using HTML or other front-end technologies. Users can review the report and enter feedback.

[0212] This allows users to receive detailed diagnostic results, which can be used for self-understanding and career development.

[0213] (Application Example 1)

[0214] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0215] The goal is to improve operator performance in work environments such as factories by accurately evaluating users' personality traits and job aptitudes through Enneagram assessments, and optimizing work assignments and training content based on individual characteristics.

[0216] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0217] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-configured Enneagram diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's Enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and job suitability based on the analysis results, means for making suggestions to optimize work assignments and training content based on the user's personality traits and job suitability, and means for providing the generated report to the user. This enables optimal work assignments and training to improve operator performance.

[0218] "User" refers to an individual or operator who uses the system.

[0219] "Authentication information" refers to data (e.g., email address and password) that a user uses to access a system.

[0220] A "database" refers to digital storage used to systematically store information used in a system, such as user information and response data.

[0221] A "diagnosis start page" refers to a webpage that provides an interface for users to begin the Enneagram diagnosis.

[0222] "Enneagram diagnostic questions" refer to a set of questions designed to assess a user's personality traits and suitability for a job.

[0223] "Response data" refers to information resulting from users' responses to the Enneagram diagnostic test.

[0224] "Analysis" refers to a series of processes that analyze response data to identify the user's Enneagram type.

[0225] "Enneagram type" refers to the personality classification of a user identified through an Enneagram assessment.

[0226] A "report" refers to a document that compiles detailed information about a user's personality traits and suitability for their job.

[0227] "Task assignment" refers to assigning specific tasks or duties to an operator.

[0228] "Training content" refers to learning and training programs provided to improve operators' skills and suitability for their jobs.

[0229] "Proposal" refers to advice on optimizing task assignments and training content for users based on the analysis results.

[0230] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze data and draw conclusions.

[0231] This invention relates to an Enneagram diagnostic system for evaluating a user's personality traits and job suitability. The system includes a set of functions for user authentication, management of diagnostic sessions, data analysis, and result delivery.

[0232] Hardware and software configuration

[0233] The following hardware and software will be used in the implementation of this system.

[0234] Hardware: Industrial PC or server

[0235] Software: Flask (web application framework), SQLite (database), Scikit-learn (machine learning library)

[0236] System operation

[0237] User registration and authentication

[0238] Users must first register and authenticate with the system. They enter their email address and password as authentication information. The device sends this information to the server, which verifies it against the information in its database. If authentication is successful, the user can access the diagnostic start page.

[0239] Starting the Enneagram assessment

[0240] After successful user authentication, the user accesses the diagnostic start page and clicks the "Start Diagnostics" button. In response to this request, the server starts a new diagnostic session and sequentially displays the user the questions for the Enneagram diagnostic test.

[0241] Question answering process

[0242] As the user answers each question, the answer is sent to the server in real time and temporarily stored as session data. This process is repeated until all questions have been answered.

[0243] Analysis of diagnostic results

[0244] Once all questions have been answered, the server passes the received response data to a generating AI model (machine learning model) for analysis. After analysis, the server identifies the user's Enneagram type and generates a detailed report based on it. This report includes the user's personality traits, job suitability, and suggestions for suitable work assignments and training content.

[0245] Results display and feedback

[0246] The generated reports are provided to the user's dashboard, where they can review them. Based on the report's content, users can then consider self-improvement and their career paths.

[0247] Specific example

[0248] For example, when a factory operator takes an Enneagram assessment, the user first registers with the system and begins the assessment after authentication. As the operator answers questions, the system analyzes the response data to identify the operator's personality traits and job suitability. Based on the analysis results, the system then proposes the most suitable work content and training program for the operator. In this way, performance in the work environment can be improved.

[0249] Examples of prompt statements

[0250] Examples of prompts for generative AI models:

[0251] "Are you good at demonstrating leadership?" Please rate the displayed question on a 5-point scale.

[0252] The above describes the embodiments of the present invention and details of the Enneagram diagnostic system for improving a user's suitability for their work.

[0253] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0254] Step 1:

[0255] The user accesses the system and enters the required information (name, email address, password) on the registration page. The terminal sends this information to the database. The server receives the submitted information and performs format validation. Information that passes validation is stored in the database, and a registration completion message is sent back to the user.

[0256] Input: Username, email address, password

[0257] Output: Registration complete message

[0258] Step 2:

[0259] The user enters their email address and password on the login page and attempts to authenticate. The device sends the entered authentication information to the server. The server compares this information with the information in the database, and if the comparison is successful, it starts a user session and redirects the user to the homepage.

[0260] Input: User's email address, password

[0261] Output: Authentication result, homepage

[0262] Step 3:

[0263] The user clicks the "Start Diagnosis" button. The device sends the request to the server. The server starts a new diagnosis session and displays the user the first questions for the Enneagram diagnosis.

[0264] Input: Diagnostic Initiation Request

[0265] Output: Initial Question

[0266] Step 4:

[0267] The user answers the questions. The device sends the user's answers to the server in real time. The server temporarily stores the received answers as session data, selects the next question, and displays it to the user. This process is repeated until all questions have been answered.

[0268] Input: User's response

[0269] Output: Next question, session data

[0270] Step 5:

[0271] Once all questions have been answered, the server passes the accumulated answer data as session data to a generating AI model for analysis. The server then identifies the user's Enneagram type based on the analysis results.

[0272] Input: All response data

[0273] Output: Enneagram type

[0274] Step 6:

[0275] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. This report includes the user's Enneagram type, personality traits, strengths, and suitable job roles. Furthermore, it also suggests work assignments and training programs.

[0276] Input: Enneagram type

[0277] Output: Detailed report

[0278] Step 7:

[0279] The server sends the generated report to the user's dashboard, and the terminal displays it to the user. The user checks the displayed report and obtains specific feedback on their personality traits and job suitability.

[0280] Input: Detailed report

[0281] Output: Report display on the dashboard

[0282] Step 8:

[0283] Based on the report content, the user formulates a self-improvement plan and considers a career path. As a result, the user can engage in work that leverages their strengths.

[0284] Input: Report display on the dashboard

[0285] Output: Self-improvement plan, consideration of career path

[0286] Specific examples of prompt sentences

[0287] Example of a prompt for the generation AI model:

[0288] "Are you good at demonstrating leadership?" Please rate the displayed question on a five-point scale.

[0289] The above are the processing steps of the system based on the embodiments of the present invention. Through these steps, a detailed enneagram diagnosis for enhancing the user's job suitability becomes possible.

[0290] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0291] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[0292] 1. User Registration and Authentication

[0293] 1. User Registration

[0294] Users access the registration page and enter their name, email address, password, etc.

[0295] The terminal sends the information entered by the user to the server as form data.

[0296] The server validates the received information to ensure it is in the correct format.

[0297] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[0298] 2. User Authentication

[0299] The user enters their email address and password on the login page.

[0300] The terminal sends the entered authentication information to the server.

[0301] The server compares the information with that in the database to verify that authentication was successful.

[0302] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0303] 2. Begin Enneagram assessment

[0304] 1. Preparation for initiating diagnosis

[0305] The user clicks the "Start Diagnosis" button on the homepage.

[0306] The terminal sends this request to the server.

[0307] The server starts a new diagnosis session, selects the first question, and sends it back to the terminal.

[0308] Before starting the diagnosis, the terminal displays a screen where the emotion engine collects data such as the user's expression, voice, and text input.

[0309] 2. Collection of Emotional Data and Display of Questions

[0310] The terminal captures the user's expression with the camera, collects voice data with the microphone, and receives text input.

[0311] The server sends this data to the emotion engine to recognize the user's emotion.

[0312] Based on the recognized user emotion data, the server generates the first question and presents it to the user.

[0313] The terminal displays the question on the screen to enable the user to answer.

[0314] 3. Processing of Question Responses

[0315] 1. Collection of Answers

[0316] The user selects an appropriate option for the displayed question and clicks the send button.

[0317] The terminal sends this user's answer to the server in real time.

[0318] 2. Saving of Answers and Adaptive Question Presentation

[0319] The server temporarily stores the received response as session data.

[0320] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the user's sentiment data recognized by the sentiment engine.

[0321] The server selects the next adjusted question and sends it back to the terminal.

[0322] Repeat this process until the entire set of questions is complete.

[0323] 4. Analysis of diagnostic results

[0324] 1. Analysis of response data and sentiment data

[0325] Once all questions have been answered, the server passes the answer data, which has been stored as session data, along with the emotion data recognized by the emotion engine, to the AI ​​engine.

[0326] The server uses a machine learning model to analyze response data and sentiment data to identify the user's Enneagram type.

[0327] 2. Report generation

[0328] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[0329] The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable occupations and jobs, and feedback based on emotional data.

[0330] 5. Results display and feedback

[0331] 1. Providing results

[0332] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0333] The device will display a report on the results screen so that the user can review it.

[0334] 2. User Feedback

[0335] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[0336] Users can use the results to consider their career paths and create plans for self-improvement.

[0337] Specific example

[0338] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the device collects emotional data such as the user's facial expressions, voice, and text input and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. When the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on Yamada Taro's Enneagram type and related feedback, and provides it to the user.

[0339] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] Users access the registration page and enter the required information, such as their name, email address, and password.

[0343] The terminal sends the entered information to the server as form data.

[0344] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[0345] Step 2:

[0346] If validation is successful, the server saves the information to the database as a new user.

[0347] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[0348] The user confirms the registration completion message and then accesses the login page.

[0349] Step 3:

[0350] The user enters their email address and password on the login page.

[0351] The terminal sends the entered authentication information to the server.

[0352] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[0353] Step 4:

[0354] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0355] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[0356] Step 5:

[0357] The device sends a "start diagnosis" request to the server.

[0358] The server initiates a new diagnostic session and presents the emotion engine data collection screen to the terminal.

[0359] The device displays a screen to the user and begins collecting facial expressions, voice, and text data.

[0360] Step 6:

[0361] The user provides emotional data (facial expressions, voice, text) in the specified manner.

[0362] The device collects this data in real time and sends it to the server.

[0363] Step 7:

[0364] The server passes the collected emotion data to the emotion engine to recognize the user's emotions.

[0365] The server temporarily stores the recognized emotion data as session data.

[0366] The server generates the initial question based on sentiment data and sends it back to the terminal.

[0367] Step 8:

[0368] The device displays the first question on the screen, allowing the user to answer it.

[0369] The user selects the appropriate option for the presented question and clicks the submit button.

[0370] Step 9:

[0371] The device sends the user's responses to the server in real time.

[0372] The server temporarily stores the received response as session data.

[0373] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the sentiment data recognized by the sentiment engine.

[0374] Step 10:

[0375] The server selects the next adjusted question and sends it back to the terminal.

[0376] Repeat this process until the entire set of questions is complete.

[0377] Step 11:

[0378] Once the user has finished answering all the questions, the server collects all the response data and sentiment data.

[0379] The server passes this data to the AI ​​engine, which then analyzes the user's Enneagram type.

[0380] The AI ​​uses a machine learning model to analyze response data and sentiment data together to identify the user's Enneagram type.

[0381] Step 12:

[0382] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[0383] The report includes information such as a description of the user's Enneagram type, personality traits, strengths, additional feedback based on emotional data, and suitable job types and tasks.

[0384] Step 13:

[0385] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0386] The device will display a report on the results screen so that the user can review it.

[0387] Step 14:

[0388] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[0389] Users can use the results to consider their career paths and create plans for self-improvement.

[0390] The above outlines the specific processing flow of the self-analysis AI system that incorporates an emotion engine.

[0391] (Example 2)

[0392] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0393] When users evaluate their personality traits and job suitability through Enneagram assessments, conventional systems analyze the results based solely on the answers to questions, failing to adequately consider the user's emotional state and psychological factors. Furthermore, there is a need to accurately recognize the user's emotions and provide more precise diagnostic results. To address this challenge, a new system is required that collects user emotional data and utilizes it in its analysis to perform deeper analyses.

[0394] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0395] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for collecting emotional data such as the user's facial expressions, voice, and text input before the diagnostic starts, means for sequentially displaying pre-set questions for enneagram diagnosis to the user, means for receiving and storing the user's answers along with emotional data, means for analyzing the answer data and emotional data to identify the user's enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This makes it possible to provide a more accurate enneagram diagnosis that takes into account the user's emotional state and to obtain detailed insights into the user's personality traits and suitability for work.

[0396] "Authentication information" refers to the information required for a user to log in to a system, and typically includes a username, email address, and password.

[0397] A "database" is a system for efficiently managing, storing, and retrieving data, and it exists in various forms such as SQL and NoSQL.

[0398] The "Enneagram test" is a psychological method that classifies individuals' personality traits and behavioral patterns into nine types.

[0399] "Emotional data" refers to emotional information collected from user facial expressions, voice, text input, etc., and is analyzed using an emotion engine.

[0400] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions, voice, text input, etc., to recognize their emotional state.

[0401] A "machine learning model" is an algorithm that learns patterns from data and uses those patterns to make predictions and classifications.

[0402] The "Start Diagnosis Page" is the webpage that users access to begin the Enneagram diagnosis, and it includes a description of the diagnosis and a start button.

[0403] "Session data" refers to data that is temporarily stored when a user uses the system, and includes information from the start to the end of the session.

[0404] A "report" is a document summarizing the user's Enneagram assessment results, containing detailed information about personality traits and job suitability.

[0405] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[0406] User registration and authentication are performed as follows: The user accesses the registration page and enters information such as name, email address, and password. The terminal sends the entered user information as form data to the server. The server validates the received information to check if the data is in the correct format. If validation is successful, the server saves the user information to a database (e.g., an SQL database), generates a registration completion message, and sends it to the terminal.

[0407] In user authentication, the user accesses the login page and enters their email address and password. The device sends the user's authentication information to the server. The server compares this information with the information in the database and confirms that authentication was successful. If authentication is successful, a user session is started and the user is redirected to the homepage.

[0408] In the preparation phase for starting the diagnosis, the user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnosis session, selects the first question, and sends it back to the device. Before starting the diagnosis, the device displays a screen that collects emotional data such as the user's facial expressions, voice, and text input.

[0409] The collection of emotion data and display of questions are performed as follows: The device captures the user's facial expressions with its camera, collects audio data with its microphone, and receives text input. The server sends this data to an emotion engine to recognize the user's emotions. Based on the recognition results, the first question is generated and presented to the user. The device displays the question on the screen, allowing the user to answer.

[0410] In the question-answering process, the user selects the appropriate option for the displayed question and clicks the submit button. The terminal sends the user's answers to the server in real time. The server temporarily stores the received answers as session data and dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. This process is repeated until the entire set of questions is completed.

[0411] In the analysis of the diagnostic results, once all questions have been answered, the server passes the accumulated response data and sentiment data as session data to the AI ​​engine. Using a machine learning model (e.g., using TensorFlow or PyTorch), the response data and sentiment data are analyzed to identify the user's Enneagram type. Based on the analysis results, a detailed report on the user's personality traits and job suitability is generated. The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable jobs and tasks, and feedback based on the sentiment data.

[0412] As part of the results display and feedback process, the server sends data to the terminal to display the generated report on the user's dashboard. The terminal displays the report on the results screen, allowing the user to review it. The user reviews the displayed report and receives specific feedback regarding their personality traits and suitability for the job. Based on the results, they can consider their career path or plan for self-improvement.

[0413] As a concrete example, if a user named "Yamada Taro" creates a new account, the user enters the necessary information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the terminal collects emotional data such as the user's facial expressions, voice, and text input, and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. After the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on "Yamada Taro's" Enneagram type and related feedback, and provides it to the user. This system allows users to conduct a deeper self-analysis and consider their career path based on the results.

[0414] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[0415] Examples of prompt statements to input into the generative AI model are as follows:

[0416] "Taro Yamada is taking an Enneagram assessment. First, he registered as a user and then clicked the button to start the assessment. Facial expressions, voice, and text input will be collected as emotional data for this user. What is the first question?"

[0417] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0418] User registration and authentication

[0419] Step 1: User Registration

[0420] 1. Input: The user accesses the registration page and enters information such as their name, email address, and password.

[0421] 2. Operation and Data Processing: The terminal sends the entered user information to the server as form data. Specifically, the data in the form is sent to the server as an HTTP POST request.

[0422] 3. Output: The server validates the received information to ensure the data is in the correct format. Specifically, it checks whether the email address is in the correct format and whether the password length is appropriate.

[0423] 4. Operation: If validation is successful, the server saves the user information to the database and generates and sends a registration completion message to the terminal. Specifically, the user information is inserted into the database, and the message "Registration complete" is returned as a response.

[0424] Step 2: User Authentication

[0425] 1. Input: The user accesses the login page and enters their email address and password.

[0426] 2. Operation and Data Processing: The terminal sends the user's authentication information to the server. Specifically, the authentication information is sent to the server as an HTTP POST request.

[0427] 3. Output: The server verifies the authentication success by comparing the information with that in the database. For example, it might run a database query to find a record where the entered email address and password match.

[0428] 4. Operation: If authentication is successful, the server initiates a user session and redirects the user to the homepage. Specifically, a session management token is generated, and the user is redirected to the homepage via a redirect header in the HTTP response.

[0429] Enneagram assessment started.

[0430] Step 3: Preparing to begin diagnosis

[0431] 1. Input: The user clicks the "Start Diagnosis" button on the homepage.

[0432] 2. Operation and Data Processing: The terminal sends this request to the server. Specifically, the request is sent to the server in the background using Ajax.

[0433] 3. Output: The server starts a new diagnostic session, selects the first question, and sends it back to the terminal. Specifically, a diagnostic session ID is generated, and the question data is returned in JSON format.

[0434] 4. Operation: Before starting the diagnosis, the device displays a screen to collect emotional data such as the user's facial expressions, voice, and text input. Specifically, a dialog box confirming access to the camera and microphone will appear on the screen.

[0435] Step 4: Collecting sentiment data and displaying questions

[0436] 1. Input: Collect emotional data such as the user's facial expressions, voice, and text input.

[0437] 2. Operation and Data Processing: The device captures the user's facial expressions with a camera, collects audio data with a microphone, and receives text input. Specifically, the camera and microphone are activated by the browser, and the collected data is processed by JavaScript (registered trademark).

[0438] 3. Output: The server sends this data to the emotion engine to recognize the user's emotions. Specifically, audio data is uploaded to the server as a .wav file and image data as a .jpeg file.

[0439] 4. Operation: Based on the recognition results, the first question is generated and presented to the user. Specifically, based on the output data of the emotion engine, a question such as "How are you feeling right now?" is generated. The question is added to the HTML DOM and displayed on the screen.

[0440] Question answering process

[0441] Step 5: Collecting responses

[0442] 1. Input: The user selects the appropriate option for the displayed question and clicks the submit button.

[0443] 2. Operation and Data Processing: The terminal sends the user's responses to the server in real time. Specifically, the data is sent to the server asynchronously using Ajax.

[0444] 3. Output: The server temporarily stores the received response as session data. Specifically, the response data is stored in a session variable in memory.

[0445] Step 6: Saving responses and presenting adaptive questions

[0446] 1. Input: User response data and sentiment data sent to the server.

[0447] 2. Operation and Data Processing: The server dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. Specifically, the next questions are dynamically fetched from the database using the results of sentiment recognition.

[0448] 3. Output: The next adjusted question is selected and sent to the terminal. Specifically, question data is generated in JSON format and returned as a response.

[0449] 4. Operation: This process is repeated until the entire set of questions is completed. Specifically, responses and sentiment data for each question are collected sequentially and processed on the server.

[0450] Analysis of diagnostic results

[0451] Step 7: Analysis of response data and sentiment data

[0452] 1. Input: Answer data and sentiment data for all questions.

[0453] 2. Operation and Data Processing: The server passes the response data and sentiment data to the AI ​​engine, which then uses a machine learning model for analysis. Specifically, it uses TensorFlow or PyTorch to perform calculations based on the data and identify the user's Enneagram type.

[0454] 3. Output: The results will identify the user's Enneagram type.

[0455] Step 8: Generate the report

[0456] 1. Input: Data on analyzed Enneagram types, personality traits, and job suitability.

[0457] 2. Operation and Data Processing: The server generates detailed reports based on the analysis results. Specifically, it uses an automated generation tool to construct reports in PDF or HTML format.

[0458] 3. Output: The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable job types and tasks, and feedback based on emotional data.

[0459] Results display and feedback

[0460] Step 9: Providing Results

[0461] 1. Input: The generated report.

[0462] 2. Operation and Data Processing: The server sends data to the terminal to display the report on the user's dashboard. Specifically, the report's URL and binary data are sent as a response.

[0463] 3. Output: The terminal displays the report on the results screen for the user to review. Specifically, the report is inserted into the HTML DOM and displayed on the screen.

[0464] Step 10: User Feedback

[0465] 1. Input: The displayed report.

[0466] 2. Operation and Data Processing: Users review the displayed reports and receive specific feedback on their personality traits and job suitability. Based on the results, they consider career paths and plan for self-improvement.

[0467] 3. Output: Users will be able to obtain information to develop concrete action plans.

[0468] (Application Example 2)

[0469] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0470] Conventional personality assessment systems evaluate personality traits and aptitudes based on user responses, but they do not take into account the user's emotional state, making it difficult to provide deeper analysis or personalized feedback. There was a need for a system that could collect and analyze user emotional data and adjust the diagnostic process accordingly to obtain more accurate results.

[0471] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0472] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page if user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-set diagnostic questions to the user, means for receiving and storing the user's answers, means for collecting the user's facial expressions, voice, and text in real time and analyzing them with an emotion engine, means for analyzing the answer data and emotion data to identify the user's characteristics once all questions have been answered, means for generating a detailed report on the user's characteristics based on the analysis results, and means for providing the generated report to the user. By analyzing the user's emotional state and integrating it with the answer data, more accurate personality diagnosis and personalized feedback become possible.

[0473] "Authentication information" refers to the information a user enters to access a system, and typically includes a username and password.

[0474] A "database" is a record system that stores user information and diagnostic data, allowing for easy access and management.

[0475] An "Enneagram diagnostic questionnaire" is a set of questions designed to evaluate a user's personality traits and suitability for a job.

[0476] "Response data" refers to the collection of answers provided by users to questions used for the Enneagram assessment.

[0477] An "emotion engine" is a software or hardware system that analyzes data such as a user's facial expressions, voice, and text input to recognize their emotional state.

[0478] A "generative AI model" is a machine learning algorithm used to analyze user response data and sentiment data to identify personality traits and aptitudes.

[0479] A "report" is a document generated based on analyzed data, providing detailed information about the user's personality traits and suitability for their job.

[0480] A "user session" is a data stream used to track and manage a series of operations a user performs from the time they log in until they log out.

[0481] A "homepage" is a web page that provides an interface for users to begin a diagnostic test.

[0482] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[0483] 1. User Registration and Authentication

[0484] Program processing:

[0485] The terminal first receives authentication information (username, password, etc.) entered by the user. The server compares this authentication information with the records in the database, and if authentication is successful, provides the user with a diagnostic start page. This process uses the user's terminal (smartphone, PC, etc.) and the server as hardware. The software used is a database management system (DBMS) and a web server.

[0486] Specific example:

[0487] The server compares the authentication information entered by the user with the database and, if correct, provides a homepage displaying a "Start Diagnosis" button.

[0488] 2. Starting the Enneagram assessment

[0489] Program processing:

[0490] When the user clicks the "Start Diagnosis" button, the device sends this request to the server, initiating a new diagnostic session. The server selects the first question and displays a screen on the device for collecting emotional data. The camera captures the user's facial expressions and the microphone collects audio data for emotional data collection.

[0491] Specific example:

[0492] The server displays a screen that captures the user's face with a camera and simultaneously collects audio data with a microphone. When the user clicks the "Ready" button, the first question is displayed on the screen.

[0493] 3. Processing Question Answers

[0494] Program processing:

[0495] When a user answers a question, that answer and sentiment data are sent to the server. The server stores this data and analyzes it using a sentiment engine. The next question is dynamically generated based on the analysis results and sent back to the terminal.

[0496] Specific example:

[0497] The server uses sentiment data submitted along with the user's answers to understand the user's emotional state and adjust the questions accordingly.

[0498] 4. Analysis of diagnostic results

[0499] Program processing:

[0500] Once all questions have been answered, the server passes the accumulated answer data and sentiment data to a generating AI model to analyze the user's personality traits and job suitability. The analysis results are then generated as a detailed report.

[0501] Specific example:

[0502] The server inputs user response data and emotional data into a generating AI model to produce a detailed report on the user's personality traits and aptitudes. This report includes the user's Enneagram type and related career aptitudes.

[0503] 5. Results display and feedback

[0504] Program processing:

[0505] The generated reports are displayed on the user's dashboard, allowing the user to review them. Users can receive specific feedback regarding their personality traits and suitability for their work.

[0506] Specific example:

[0507] Users can determine their Enneagram type and then consider their career path based on that type. For example, if the analysis result is "Enneagram Type 5," they will be advised that data analysis or research positions would be suitable for them.

[0508] Example of a prompt

[0509] "Analyze video frames showing the user's joyful expression and recommend comedy videos they should watch next. Input: Facial expression data frame. Output: Titles and links to recommended comedy videos."

[0510] "A procedure to perform emotion recognition and provide appropriate feedback based on audio data collected while the user is making a sad expression."

[0511] This makes it possible to incorporate the user's emotional state, thereby more accurately evaluating the user's personality traits and suitability for the job, and providing personalized feedback.

[0512] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0513] Step 1:

[0514] The user enters authentication information (username, password, etc.) into the terminal. The terminal sends the entered authentication information to the server, which compares it with the records in the database. This comparison verifies that the user is a legitimate registered user.

[0515] Input: Username, Password

[0516] Output: Authentication result (success / failure)

[0517] Specific operation: The server compares the received authentication information with the database, and if authentication is successful, it starts a user session and provides a diagnostic start page.

[0518] Step 2:

[0519] The user clicks the "Start Diagnosis" button. The device sends this request to the server, which starts a new diagnosis session. The server sends the first question back to the device, and the device displays a screen that collects data such as the user's facial expressions, voice, and text input before the diagnosis begins.

[0520] Input: Diagnostic Start Request

[0521] Output: Initial question and sentiment data collection screen

[0522] Specific operation: The device uses the user's camera and microphone to collect facial expressions and voice, and also accepts text input.

[0523] Step 3:

[0524] The device sends the collected user facial expressions, voice, and text data to the server. The server passes the received data to an emotion engine, which analyzes the user's emotional state. Based on the analysis results, the server provides the user with an initial question.

[0525] Input: Facial expression data, audio data, text data

[0526] Output: Emotional state, first question

[0527] Specific operation: The server inputs data into the emotion engine and obtains emotion recognition results. Based on these results, it generates the most appropriate questions and sends them back to the terminal.

[0528] Step 4:

[0529] The user enters their answers to the displayed questions, and the device sends them to the server. The server temporarily stores the collected sentiment data along with the user's answers. Before generating the next question, the server re-analyzes the sentiment data and dynamically adjusts the order and content of the questions.

[0530] Input: User's response

[0531] Output: Next question

[0532] Specific operation: The server re-analyzes the received response using an emotion engine, dynamically determines the next question, and sends it back to the terminal.

[0533] Step 5:

[0534] Once all questions have been answered, the server passes the accumulated answer data and sentiment data to a generating AI model to identify the user's characteristics. Based on this analysis, a detailed report is generated. The server then sends the generated report to the user's device, making it viewable on the dashboard.

[0535] Input: Accumulated response data, sentiment data

[0536] Output: User characteristics, detailed report

[0537] Specific operation: The server inputs data into the generated AI model, compiles the analysis results into a report format, and sends it to the terminal for display on the user's dashboard.

[0538] Example of a prompt:

[0539] "Analyze video frames showing the user's joyful expression and recommend comedy videos they should watch next. Input: Facial expression data frame. Output: Titles and links to recommended comedy videos."

[0540] "A procedure to perform emotion recognition and provide appropriate feedback based on audio data collected while the user is making a sad expression."

[0541] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0542] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0543] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0544] [Second Embodiment]

[0545] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0546] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0547] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0548] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0549] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0550] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0551] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0552] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0553] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0554] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0555] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0556] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0557] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[0558] 1. User Registration and Authentication

[0559] 1. User Registration

[0560] Users access the registration page and enter the required information (name, email address, password, etc.).

[0561] The terminal sends the entered information to the server.

[0562] The server validates the received information to ensure it is in the correct format.

[0563] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[0564] 2. User Authentication

[0565] The user enters their email address and password on the login page and attempts to authenticate.

[0566] The terminal sends the entered authentication information to the server.

[0567] The server compares the information with that in the database to determine if authentication was successful.

[0568] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0569] 2. Begin Enneagram assessment

[0570] 1. Preparation for initiating diagnosis

[0571] The user clicks the "Start Diagnosis" button on the homepage.

[0572] The device sends this request to the server.

[0573] The server starts a new diagnostic session and selects the first question to present to the user.

[0574] 2. Display the question

[0575] The server generates the first question for the Enneagram assessment and displays it to the user.

[0576] The device displays the question on the screen and allows the user to select or enter an answer.

[0577] 3. Processing Question Answers

[0578] 1. Collection of responses

[0579] The user selects the appropriate option for each question and clicks the submit button.

[0580] The device sends the user's responses to the server in real time.

[0581] 2. Save your answer

[0582] The server temporarily stores the received response as session data.

[0583] The server selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[0584] 4. Analysis of diagnostic results

[0585] 1. Analysis of response data

[0586] Once all questions have been answered, the server passes the accumulated answer data, which is stored as session data, to the AI ​​engine.

[0587] The server uses a machine learning model to analyze the response data and identify the user's Enneagram type.

[0588] 2. Report generation

[0589] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[0590] The report includes a description of the user's Enneagram type, personality traits, strengths, and advice on suitable job types and roles.

[0591] 5. Results display and feedback

[0592] 1. Providing results

[0593] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0594] The device will display a report on the results screen so that the user can review it.

[0595] 2. User Feedback

[0596] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[0597] Users can use the results to consider their career paths and create plans for self-improvement.

[0598] Specific example

[0599] For example, if a user named "Yamada Taro" creates a new account, the user fills in the required information on the registration form. The server receives this information and stores it in a database, allowing the user to log in later. The user then logs in and clicks the "Start Diagnosis" button. The server generates the first questions of the Enneagram diagnosis and presents them to the user via the terminal. Once the user answers the questions, the answers are sent to the server and temporarily stored. After all questions have been answered, the server uses an AI engine to analyze the data and determine Yamada Taro's Enneagram type. Based on the results, the server creates a report and provides it to Yamada Taro.

[0600] This system allows users to conduct self-analysis and consider their career path based on the results.

[0601] The following describes the processing flow.

[0602] Step 1:

[0603] Users access the registration page and enter the required information (name, email address, password, etc.).

[0604] The terminal sends the information entered by the user to the server as form data.

[0605] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[0606] Step 2:

[0607] If validation is successful, the server saves the information to the database as a new user.

[0608] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[0609] The user confirms the registration completion message and then accesses the login page.

[0610] Step 3:

[0611] The user enters their email address and password on the login page.

[0612] The terminal sends the entered authentication information to the server.

[0613] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[0614] Step 4:

[0615] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0616] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[0617] Step 5:

[0618] The device sends this request to the server.

[0619] The server starts a new diagnostic session, selects the first question, and sends it back to the terminal.

[0620] The device displays the first question on the screen, allowing the user to answer it.

[0621] Step 6:

[0622] The user selects the appropriate option for the displayed question and clicks the submit button.

[0623] The device sends the user's response to the server in real time.

[0624] Step 7:

[0625] The server temporarily stores the received response as session data.

[0626] The server selects the next question and sends it back to the terminal.

[0627] Repeat this process until the entire set of questions is complete.

[0628] Step 8:

[0629] Once the user has finished answering all the questions, the server collects the session data.

[0630] The server passes the response data to the AI ​​engine, which then analyzes the Enneagram type.

[0631] The AI ​​uses machine learning models to analyze user response patterns and identify types.

[0632] Step 9:

[0633] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[0634] The report includes information such as a description of the user's Enneagram type, personality traits, and suitable occupations and jobs.

[0635] Step 10:

[0636] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0637] The device will display a report on the results screen so that the user can review it.

[0638] The above describes the specific processing flow in the system of the present invention.

[0639] (Example 1)

[0640] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0641] Traditional personality assessment systems often suffer from inaccurate results and insufficient feedback, as users simply answer pre-set questions. Furthermore, the lack of machine learning models in the analysis results reduces the reliability of the assessment. Additionally, cumbersome user authentication and session management detract from the user experience.

[0642] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0643] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for starting a user session and providing a diagnostic start page when user authentication is successful, means for sequentially displaying pre-configured personality diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's personality type using a generated AI model when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This enables the provision of highly accurate and reliable diagnostic results to the user and allows for detailed feedback based on individual personality traits. Furthermore, by simplifying user authentication and session management, the overall user experience can be improved.

[0644] "User authentication" refers to the process of verifying that a user is a legitimate user by comparing the authentication information entered by the user with records in a database.

[0645] The "diagnosis start page" is a web page that users access when they begin a diagnosis, and it is a screen for preparing for the diagnosis.

[0646] A "diagnostic session" represents a series of steps a user takes to perform a diagnosis, and is a collection of data that includes the entire process of answering a series of questions.

[0647] "Personality assessment questions" are pre-set questions designed to determine a user's personality traits and suitability for a job.

[0648] "Response data" refers to the data of the answers that a user enters or selects in response to diagnostic questions.

[0649] A "machine learning model" is an artificial intelligence technology that is trained using large amounts of data to perform specific tasks with high accuracy.

[0650] A "generative AI model" is a machine learning algorithm that learns on its own and is used to analyze user diagnostic data.

[0651] "Personality traits" is a concept that describes the unique characteristics and patterns related to a user's personality.

[0652] "Job suitability" is an indicator used to evaluate how well-suited a user is for a particular job or task.

[0653] A "detailed report" is a document generated based on the analysis results that contains specific and detailed information about the user's personality traits and suitability for the job.

[0654] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[0655] 1. User Registration and Authentication

[0656] User Registration

[0657] The user accesses the system's registration page and enters required information such as name, email address, and password. The terminal sends this information to the server. The server validates the received information to ensure it is in the correct format. Information that is successfully validated is stored in the database, and a registration completion message is sent back to the user.

[0658] User Authentication

[0659] The user enters their email address and password on the login page and attempts authentication. The device sends the entered authentication information to the server. The server compares it with the information in the database to confirm whether authentication was successful. If authentication is successful, the server starts a user session and redirects the user to the homepage.

[0660] 2. Begin Enneagram assessment

[0661] Preparation for starting the diagnosis

[0662] The user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnostic session, generates the first question, and provides it to the user.

[0663] Display the question

[0664] The server generates the initial questions for the Enneagram assessment and displays them to the user via the screen. The terminal displays the questions and allows the user to select or enter answers.

[0665] 3. Processing Question Answers

[0666] Collection of responses

[0667] The user selects the appropriate option for each question and clicks the submit button. The device then sends the user's answers to the server.

[0668] Save the answer

[0669] The server temporarily stores the received answers as session data. It then selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[0670] 4. Analysis of diagnostic results

[0671] Analysis of response data

[0672] The server passes the session data to the AI ​​engine once all questions have been answered. The server uses a machine learning model to identify the user's personality type.

[0673] 5. Report generation and results delivery

[0674] Report generation

[0675] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. The report includes an explanation of the Enneagram type, personality traits, strengths, and career advice.

[0676] Providing results

[0677] The server sends the generated report to the device for display on the user's dashboard. The device displays the report on the results screen, allowing the user to review it.

[0678] Specific example

[0679] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information on the registration page. The device sends this information to the server, which validates it and saves it to the database if the information is in the correct format. Once registration is complete, Yamada Taro logs in and clicks the "Start Diagnosis" button. The server generates the first question of the diagnosis and presents it to Yamada Taro through the device. When Yamada Taro answers, the answer is sent to the server and temporarily stored. Once all questions are completed, the server uses an AI engine to analyze and identify Yamada Taro's personality type. A report is generated based on the results and presented on Yamada Taro's dashboard.

[0680] Example of a prompt

[0681] "Please create a new account."

[0682] "Please log in to begin the diagnosis."

[0683] "Please answer all questions and obtain your diagnostic results."

[0684] This system allows users to understand their own personality traits and job suitability with high accuracy, and to receive effective feedback. Furthermore, it simplifies user authentication and session management, improving the overall user experience.

[0685] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0686] Step 1: User Registration

[0687] Input: The user accesses the registration page and enters their name, email address, and password.

[0688] Processing: The terminal sends this information to the server. The server validates the received information to check if it is in the correct format (e.g., email address format and password strength).

[0689] Output: The server saves the information that was successfully validated to the database, generates a registration completion message, and sends it to the terminal.

[0690] Specific operation: The user enters information into a form via a browser and clicks the submit button. The server executes backend validation logic (e.g., email address check using regular expressions).

[0691] Step 2: User Authentication

[0692] Input: The user enters their email address and password on the login page.

[0693] Processing: The terminal sends these authentication credentials to the server. The server compares them with the information in the database, and if they match, it determines that authentication was successful.

[0694] Output: The server initiates a user session and sends instructions to the terminal to redirect to the homepage.

[0695] Specific operation: The user enters information into the login form, and the terminal sends it to the server as an HTTP POST request. The server executes a database query to retrieve the user information and compares it with a hashed password.

[0696] Step 3: Start diagnosis

[0697] Input: The user clicks the "Start Diagnosis" button on the homepage.

[0698] Processing: The terminal sends this request to the server. The server starts a new diagnostic session and generates the first question.

[0699] Output: The server sends the first question to the terminal, and the terminal displays it to the user.

[0700] Specific operation: The server generates a diagnostic session ID and stores the session information in memory. Next, it randomly or sequentially selects the first question from the question list and sends it to the terminal in JSON format.

[0701] Step 4: Question Display

[0702] Input: Question data received from the server by the terminal.

[0703] Processing: The terminal displays the question on the screen and allows the user to select or enter an answer.

[0704] Output: The user enters or selects an answer to the displayed question.

[0705] Specific operation: The terminal analyzes the received question data and displays it on the screen using HTML or other front-end technologies.

[0706] Step 5: Collecting responses

[0707] Input: Response data submitted by the user.

[0708] Processing: The terminal sends the user's response to the server. The server temporarily stores the received response as session data.

[0709] Output: The server generates the following question and sends it to the terminal.

[0710] Specific operation: When the user clicks the submit button, the device sends an HTTP POST request containing the answer data to the server. The server saves the answer data to memory or a database and selects the next question.

[0711] Step 6: Refresh the problem session

[0712] Input: A request from the user to proceed to the next question.

[0713] Processing: The server selects the next question based on the session data and sends it to the terminal.

[0714] Output: The terminal will display the following question on the screen.

[0715] Specific operation: Based on the previous question and answer, the server determines the next question to display, generates a new question, and sends it to the terminal.

[0716] Step 7: Analysis of diagnostic results

[0717] Input: User response data for all questions.

[0718] Processing: The server collects all response data and passes it to the AI ​​engine for analysis.

[0719] Output: The server identifies the user's personality type and retrieves the result.

[0720] Specific operation: The server calls an AI engine (e.g., scikit-learn or TensorFlow in Python), inputs the user's response data into a pre-trained model, and predicts the personality type.

[0721] Step 8: Report Generation

[0722] Input: Analysis results from the AI ​​engine.

[0723] Processing: The server generates a detailed report based on the analysis results.

[0724] Output: The server prepares to send the generated report to the terminal.

[0725] Specific operation: The server uses a template engine (e.g., Jinja2) to create a detailed report based on the analysis results and structure it in JSON format.

[0726] Step 9: Results display and feedback

[0727] Input: Report data sent from the server.

[0728] Processing: The terminal displays the report on the screen for the user to review.

[0729] Output: Users review the report and provide feedback as needed.

[0730] Specific operation: The device parses the received report data and displays it on the screen using HTML or other front-end technologies. Users can review the report and enter feedback.

[0731] This allows users to receive detailed diagnostic results, which can be used for self-understanding and career development.

[0732] (Application Example 1)

[0733] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0734] The goal is to improve operator performance in work environments such as factories by accurately evaluating users' personality traits and job aptitudes through Enneagram assessments, and optimizing work assignments and training content based on individual characteristics.

[0735] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0736] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-configured Enneagram diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's Enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and job suitability based on the analysis results, means for making suggestions to optimize work assignments and training content based on the user's personality traits and job suitability, and means for providing the generated report to the user. This enables optimal work assignments and training to improve operator performance.

[0737] "User" refers to an individual or operator who uses the system.

[0738] "Authentication information" refers to data (e.g., email address and password) that a user uses to access a system.

[0739] A "database" refers to digital storage used to systematically store information used in a system, such as user information and response data.

[0740] A "diagnosis start page" refers to a webpage that provides an interface for users to begin the Enneagram diagnosis.

[0741] "Enneagram diagnostic questions" refer to a set of questions designed to assess a user's personality traits and suitability for a job.

[0742] "Response data" refers to information resulting from users' responses to the Enneagram diagnostic test.

[0743] "Analysis" refers to a series of processes that analyze response data to identify the user's Enneagram type.

[0744] "Enneagram type" refers to the personality classification of a user identified through an Enneagram assessment.

[0745] A "report" refers to a document that compiles detailed information about a user's personality traits and suitability for their job.

[0746] "Task assignment" refers to assigning specific tasks or duties to an operator.

[0747] "Training content" refers to learning and training programs provided to improve operators' skills and suitability for their jobs.

[0748] "Proposal" refers to advice on optimizing task assignments and training content for users based on the analysis results.

[0749] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze data and draw conclusions.

[0750] This invention relates to an Enneagram diagnostic system for evaluating a user's personality traits and job suitability. The system includes a set of functions for user authentication, management of diagnostic sessions, data analysis, and result delivery.

[0751] Hardware and software configuration

[0752] The following hardware and software will be used in the implementation of this system.

[0753] Hardware: Industrial PC or server

[0754] Software: Flask (web application framework), SQLite (database), Scikit-learn (machine learning library)

[0755] System operation

[0756] User registration and authentication

[0757] Users must first register and authenticate with the system. They enter their email address and password as authentication information. The device sends this information to the server, which verifies it against the information in its database. If authentication is successful, the user can access the diagnostic start page.

[0758] Starting the Enneagram assessment

[0759] After successful user authentication, the user accesses the diagnostic start page and clicks the "Start Diagnostics" button. In response to this request, the server starts a new diagnostic session and sequentially displays the user the questions for the Enneagram diagnostic test.

[0760] Question answering process

[0761] As the user answers each question, the answer is sent to the server in real time and temporarily stored as session data. This process is repeated until all questions have been answered.

[0762] Analysis of diagnostic results

[0763] Once all questions have been answered, the server passes the received response data to a generating AI model (machine learning model) for analysis. After analysis, the server identifies the user's Enneagram type and generates a detailed report based on it. This report includes the user's personality traits, job suitability, and suggestions for suitable work assignments and training content.

[0764] Results display and feedback

[0765] The generated reports are provided to the user's dashboard, where they can review them. Based on the report's content, users can then consider self-improvement and their career paths.

[0766] Specific example

[0767] For example, when a factory operator takes an Enneagram assessment, the user first registers with the system and begins the assessment after authentication. As the operator answers questions, the system analyzes the response data to identify the operator's personality traits and job suitability. Based on the analysis results, the system then proposes the most suitable work content and training program for the operator. In this way, performance in the work environment can be improved.

[0768] Examples of prompt statements

[0769] Examples of prompts for generative AI models:

[0770] "Are you good at demonstrating leadership?" Please rate the displayed question on a 5-point scale.

[0771] The above describes the embodiments of the present invention and details of the Enneagram diagnostic system for improving a user's suitability for their work.

[0772] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0773] Step 1:

[0774] The user accesses the system and enters the required information (name, email address, password) on the registration page. The terminal sends this information to the database. The server receives the submitted information and performs format validation. Information that passes validation is stored in the database, and a registration completion message is sent back to the user.

[0775] Input: Username, email address, password

[0776] Output: Registration complete message

[0777] Step 2:

[0778] The user enters their email address and password on the login page and attempts to authenticate. The device sends the entered authentication information to the server. The server compares this information with the information in the database, and if the comparison is successful, it starts a user session and redirects the user to the homepage.

[0779] Input: User's email address, password

[0780] Output: Authentication result, homepage

[0781] Step 3:

[0782] The user clicks the "Start Diagnosis" button. The device sends the request to the server. The server starts a new diagnosis session and displays the user the first questions for the Enneagram diagnosis.

[0783] Input: Diagnostic Initiation Request

[0784] Output: Initial Question

[0785] Step 4:

[0786] The user answers the questions. The device sends the user's answers to the server in real time. The server temporarily stores the received answers as session data, selects the next question, and displays it to the user. This process is repeated until all questions have been answered.

[0787] Input: User's response

[0788] Output: Next question, session data

[0789] Step 5:

[0790] Once all questions have been answered, the server passes the accumulated answer data as session data to a generating AI model for analysis. The server then identifies the user's Enneagram type based on the analysis results.

[0791] Input: All response data

[0792] Output: Enneagram type

[0793] Step 6:

[0794] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. This report includes the user's Enneagram type, personality traits, strengths, and suitable job roles. Furthermore, it also suggests work assignments and training programs.

[0795] Input: Enneagram type

[0796] Output: Detailed report

[0797] Step 7:

[0798] The server sends the generated report to the user's dashboard, and the terminal displays it to the user. The user reviews the displayed report and receives specific feedback on their personality traits and suitability for the job.

[0799] Input: Detailed report

[0800] Output: Displaying reports on the dashboard

[0801] Step 8:

[0802] Based on the report content, users can plan for self-improvement and consider their career paths. This allows users to engage in work that leverages their strengths.

[0803] Input: Displaying reports on the dashboard

[0804] Output: Planning for self-improvement, considering career paths.

[0805] Examples of prompt statements

[0806] Examples of prompts for generative AI models:

[0807] "Are you good at demonstrating leadership?" Please rate the displayed question on a 5-point scale.

[0808] The above describes the processing steps of the system based on an embodiment of the present invention. This step enables a detailed Enneagram diagnosis to improve the user's suitability for their work.

[0809] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0810] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[0811] 1. User Registration and Authentication

[0812] 1. User Registration

[0813] Users access the registration page and enter their name, email address, password, etc.

[0814] The terminal sends the information entered by the user to the server as form data.

[0815] The server validates the received information to ensure it is in the correct format.

[0816] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[0817] 2. User Authentication

[0818] The user enters their email address and password on the login page.

[0819] The terminal sends the entered authentication information to the server.

[0820] The server compares the information with that in the database to verify that authentication was successful.

[0821] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0822] 2. Begin Enneagram assessment

[0823] 1. Preparation for initiating diagnosis

[0824] The user clicks the "Start Diagnosis" button on the homepage.

[0825] The device sends this request to the server.

[0826] The server starts a new diagnostic session, selects the first question, and sends it back to the terminal.

[0827] Before the diagnosis begins, the device displays a screen where the emotion engine collects data such as the user's facial expressions, voice, and text input.

[0828] 2. Collection of sentiment data and presentation of questions

[0829] The device captures the user's facial expressions with a camera, collects audio data with a microphone, and receives text input.

[0830] The server sends this data to the emotion engine to recognize the user's emotions.

[0831] The server generates and presents the first question to the user based on the recognized user sentiment data.

[0832] The device displays the question on the screen, allowing the user to answer it.

[0833] 3. Processing Question Answers

[0834] 1. Collection of responses

[0835] The user selects the appropriate option for the displayed question and clicks the submit button.

[0836] The device sends the user's response to the server in real time.

[0837] 2. Saving responses and presenting adaptive questions

[0838] The server temporarily stores the received response as session data.

[0839] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the user's sentiment data recognized by the sentiment engine.

[0840] The server selects the next adjusted question and sends it back to the terminal.

[0841] Repeat this process until the entire set of questions is complete.

[0842] 4. Analysis of diagnostic results

[0843] 1. Analysis of response data and sentiment data

[0844] Once all questions have been answered, the server passes the answer data, which has been stored as session data, along with the emotion data recognized by the emotion engine, to the AI ​​engine.

[0845] The server uses a machine learning model to analyze response data and sentiment data to identify the user's Enneagram type.

[0846] 2. Report generation

[0847] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[0848] The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable occupations and jobs, and feedback based on emotional data.

[0849] 5. Results display and feedback

[0850] 1. Providing results

[0851] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0852] The device will display a report on the results screen so that the user can review it.

[0853] 2. User Feedback

[0854] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[0855] Users can use the results to consider their career paths and create plans for self-improvement.

[0856] Specific example

[0857] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the device collects emotional data such as the user's facial expressions, voice, and text input and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. When the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on Yamada Taro's Enneagram type and related feedback, and provides it to the user.

[0858] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[0859] The following describes the processing flow.

[0860] Step 1:

[0861] Users access the registration page and enter the required information, such as their name, email address, and password.

[0862] The terminal sends the entered information to the server as form data.

[0863] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[0864] Step 2:

[0865] If validation is successful, the server saves the information to the database as a new user.

[0866] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[0867] The user confirms the registration completion message and then accesses the login page.

[0868] Step 3:

[0869] The user enters their email address and password on the login page.

[0870] The terminal sends the entered authentication information to the server.

[0871] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[0872] Step 4:

[0873] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[0874] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[0875] Step 5:

[0876] The device sends a "start diagnosis" request to the server.

[0877] The server initiates a new diagnostic session and presents the emotion engine data collection screen to the terminal.

[0878] The device displays a screen to the user and begins collecting facial expressions, voice, and text data.

[0879] Step 6:

[0880] The user provides emotional data (facial expressions, voice, text) in the specified manner.

[0881] The device collects this data in real time and sends it to the server.

[0882] Step 7:

[0883] The server passes the collected emotion data to the emotion engine to recognize the user's emotions.

[0884] The server temporarily stores the recognized emotion data as session data.

[0885] The server generates the initial question based on sentiment data and sends it back to the terminal.

[0886] Step 8:

[0887] The device displays the first question on the screen, allowing the user to answer it.

[0888] The user selects the appropriate option for the presented question and clicks the submit button.

[0889] Step 9:

[0890] The device sends the user's responses to the server in real time.

[0891] The server temporarily stores the received response as session data.

[0892] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the sentiment data recognized by the sentiment engine.

[0893] Step 10:

[0894] The server selects the next adjusted question and sends it back to the terminal.

[0895] Repeat this process until the entire set of questions is complete.

[0896] Step 11:

[0897] Once the user has finished answering all the questions, the server collects all the response data and sentiment data.

[0898] The server passes this data to the AI ​​engine, which then analyzes the user's Enneagram type.

[0899] The AI ​​uses a machine learning model to analyze response data and sentiment data together to identify the user's Enneagram type.

[0900] Step 12:

[0901] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[0902] The report includes information such as a description of the user's Enneagram type, personality traits, strengths, additional feedback based on emotional data, and suitable job types and tasks.

[0903] Step 13:

[0904] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[0905] The device will display a report on the results screen so that the user can review it.

[0906] Step 14:

[0907] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[0908] Users can use the results to consider their career paths and create plans for self-improvement.

[0909] The above outlines the specific processing flow of the self-analysis AI system that incorporates an emotion engine.

[0910] (Example 2)

[0911] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0912] When users evaluate their personality traits and job suitability through Enneagram assessments, conventional systems analyze the results based solely on the answers to questions, failing to adequately consider the user's emotional state and psychological factors. Furthermore, there is a need to accurately recognize the user's emotions and provide more precise diagnostic results. To address this challenge, a new system is required that collects user emotional data and utilizes it in its analysis to perform deeper analyses.

[0913] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0914] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for collecting emotional data such as the user's facial expressions, voice, and text input before the diagnostic starts, means for sequentially displaying pre-set questions for enneagram diagnosis to the user, means for receiving and storing the user's answers along with emotional data, means for analyzing the answer data and emotional data to identify the user's enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This makes it possible to provide a more accurate enneagram diagnosis that takes into account the user's emotional state and to obtain detailed insights into the user's personality traits and suitability for work.

[0915] "Authentication information" refers to the information required for a user to log in to a system, and typically includes a username, email address, and password.

[0916] A "database" is a system for efficiently managing, storing, and retrieving data, and it exists in various forms such as SQL and NoSQL.

[0917] The "Enneagram test" is a psychological method that classifies individuals' personality traits and behavioral patterns into nine types.

[0918] "Emotional data" refers to emotional information collected from user facial expressions, voice, text input, etc., and is analyzed using an emotion engine.

[0919] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions, voice, text input, etc., to recognize their emotional state.

[0920] A "machine learning model" is an algorithm that learns patterns from data and uses those patterns to make predictions and classifications.

[0921] The "Start Diagnosis Page" is the webpage that users access to begin the Enneagram diagnosis, and it includes a description of the diagnosis and a start button.

[0922] "Session data" refers to data that is temporarily stored when a user uses the system, and includes information from the start to the end of the session.

[0923] A "report" is a document summarizing the user's Enneagram assessment results, containing detailed information about personality traits and job suitability.

[0924] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[0925] User registration and authentication are performed as follows: The user accesses the registration page and enters information such as name, email address, and password. The terminal sends the entered user information as form data to the server. The server validates the received information to check if the data is in the correct format. If validation is successful, the server saves the user information to a database (e.g., an SQL database), generates a registration completion message, and sends it to the terminal.

[0926] In user authentication, the user accesses the login page and enters their email address and password. The device sends the user's authentication information to the server. The server compares this information with the information in the database and confirms that authentication was successful. If authentication is successful, a user session is started and the user is redirected to the homepage.

[0927] In the preparation phase for starting the diagnosis, the user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnosis session, selects the first question, and sends it back to the device. Before starting the diagnosis, the device displays a screen that collects emotional data such as the user's facial expressions, voice, and text input.

[0928] The collection of emotion data and display of questions are performed as follows: The device captures the user's facial expressions with its camera, collects audio data with its microphone, and receives text input. The server sends this data to an emotion engine to recognize the user's emotions. Based on the recognition results, the first question is generated and presented to the user. The device displays the question on the screen, allowing the user to answer.

[0929] In the question-answering process, the user selects the appropriate option for the displayed question and clicks the submit button. The terminal sends the user's answers to the server in real time. The server temporarily stores the received answers as session data and dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. This process is repeated until the entire set of questions is completed.

[0930] In the analysis of the diagnostic results, once all questions have been answered, the server passes the accumulated response data and sentiment data as session data to the AI ​​engine. Using a machine learning model (e.g., using TensorFlow or PyTorch), the response data and sentiment data are analyzed to identify the user's Enneagram type. Based on the analysis results, a detailed report on the user's personality traits and job suitability is generated. The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable jobs and tasks, and feedback based on the sentiment data.

[0931] As part of the results display and feedback process, the server sends data to the terminal to display the generated report on the user's dashboard. The terminal displays the report on the results screen, allowing the user to review it. The user reviews the displayed report and receives specific feedback regarding their personality traits and suitability for the job. Based on the results, they can consider their career path or plan for self-improvement.

[0932] As a concrete example, if a user named "Yamada Taro" creates a new account, the user enters the necessary information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the terminal collects emotional data such as the user's facial expressions, voice, and text input, and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. After the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on "Yamada Taro's" Enneagram type and related feedback, and provides it to the user. This system allows users to conduct a deeper self-analysis and consider their career path based on the results.

[0933] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[0934] Examples of prompt statements to input into the generative AI model are as follows:

[0935] "Taro Yamada is taking an Enneagram assessment. First, he registered as a user and then clicked the button to start the assessment. Facial expressions, voice, and text input will be collected as emotional data for this user. What is the first question?"

[0936] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0937] User registration and authentication

[0938] Step 1: User Registration

[0939] 1. Input: The user accesses the registration page and enters information such as their name, email address, and password.

[0940] 2. Operation and Data Processing: The terminal sends the entered user information to the server as form data. Specifically, the data in the form is sent to the server as an HTTP POST request.

[0941] 3. Output: The server validates the received information to ensure the data is in the correct format. Specifically, it checks whether the email address is in the correct format and whether the password length is appropriate.

[0942] 4. Operation: If validation is successful, the server saves the user information to the database and generates and sends a registration completion message to the terminal. Specifically, the user information is inserted into the database, and the message "Registration complete" is returned as a response.

[0943] Step 2: User Authentication

[0944] 1. Input: The user accesses the login page and enters their email address and password.

[0945] 2. Operation and Data Processing: The terminal sends the user's authentication information to the server. Specifically, the authentication information is sent to the server as an HTTP POST request.

[0946] 3. Output: The server verifies the authentication success by comparing the information with that in the database. For example, it might run a database query to find a record where the entered email address and password match.

[0947] 4. Operation: If authentication is successful, the server initiates a user session and redirects the user to the homepage. Specifically, a session management token is generated, and the user is redirected to the homepage via a redirect header in the HTTP response.

[0948] Enneagram assessment started.

[0949] Step 3: Preparing to begin diagnosis

[0950] 1. Input: The user clicks the "Start Diagnosis" button on the homepage.

[0951] 2. Operation and Data Processing: The terminal sends this request to the server. Specifically, the request is sent to the server in the background using Ajax.

[0952] 3. Output: The server starts a new diagnostic session, selects the first question, and sends it back to the terminal. Specifically, a diagnostic session ID is generated, and the question data is returned in JSON format.

[0953] 4. Operation: Before starting the diagnosis, the device displays a screen to collect emotional data such as the user's facial expressions, voice, and text input. Specifically, a dialog box confirming access to the camera and microphone will appear on the screen.

[0954] Step 4: Collecting sentiment data and displaying questions

[0955] 1. Input: Collect emotional data such as the user's facial expressions, voice, and text input.

[0956] 2. Operation and Data Processing: The device captures the user's facial expressions with a camera, collects audio data with a microphone, and receives text input. Specifically, the camera and microphone are activated by the browser, and the collected data is processed by JavaScript.

[0957] 3. Output: The server sends this data to the emotion engine to recognize the user's emotions. Specifically, audio data is uploaded to the server as a .wav file and image data as a .jpeg file.

[0958] 4. Operation: Based on the recognition results, the first question is generated and presented to the user. Specifically, based on the output data of the emotion engine, a question such as "How are you feeling right now?" is generated. The question is added to the HTML DOM and displayed on the screen.

[0959] Question answering process

[0960] Step 5: Collecting responses

[0961] 1. Input: The user selects the appropriate option for the displayed question and clicks the submit button.

[0962] 2. Operation and Data Processing: The terminal sends the user's responses to the server in real time. Specifically, the data is sent to the server asynchronously using Ajax.

[0963] 3. Output: The server temporarily stores the received response as session data. Specifically, the response data is stored in a session variable in memory.

[0964] Step 6: Saving responses and presenting adaptive questions

[0965] 1. Input: User response data and sentiment data sent to the server.

[0966] 2. Operation and Data Processing: The server dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. Specifically, the next questions are dynamically fetched from the database using the results of sentiment recognition.

[0967] 3. Output: The next adjusted question is selected and sent to the terminal. Specifically, question data is generated in JSON format and returned as a response.

[0968] 4. Operation: This process is repeated until the entire set of questions is completed. Specifically, responses and sentiment data for each question are collected sequentially and processed on the server.

[0969] Analysis of diagnostic results

[0970] Step 7: Analysis of response data and sentiment data

[0971] 1. Input: Answer data and sentiment data for all questions.

[0972] 2. Operation and Data Processing: The server passes the response data and sentiment data to the AI ​​engine, which then uses a machine learning model for analysis. Specifically, it uses TensorFlow or PyTorch to perform calculations based on the data and identify the user's Enneagram type.

[0973] 3. Output: The results will identify the user's Enneagram type.

[0974] Step 8: Generate the report

[0975] 1. Input: Data on analyzed Enneagram types, personality traits, and job suitability.

[0976] 2. Operation and Data Processing: The server generates detailed reports based on the analysis results. Specifically, it uses an automated generation tool to construct reports in PDF or HTML format.

[0977] 3. Output: The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable job types and tasks, and feedback based on emotional data.

[0978] Results display and feedback

[0979] Step 9: Providing Results

[0980] 1. Input: The generated report.

[0981] 2. Operation and Data Processing: The server sends data to the terminal to display the report on the user's dashboard. Specifically, the report's URL and binary data are sent as a response.

[0982] 3. Output: The terminal displays the report on the results screen for the user to review. Specifically, the report is inserted into the HTML DOM and displayed on the screen.

[0983] Step 10: User Feedback

[0984] 1. Input: The displayed report.

[0985] 2. Operation and Data Processing: Users review the displayed reports and receive specific feedback on their personality traits and job suitability. Based on the results, they consider career paths and plan for self-improvement.

[0986] 3. Output: Users will be able to obtain information to develop concrete action plans.

[0987] (Application Example 2)

[0988] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0989] Conventional personality assessment systems evaluate personality traits and aptitudes based on user responses, but they do not take into account the user's emotional state, making it difficult to provide deeper analysis or personalized feedback. There was a need for a system that could collect and analyze user emotional data and adjust the diagnostic process accordingly to obtain more accurate results.

[0990] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0991] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page if user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-set diagnostic questions to the user, means for receiving and storing the user's answers, means for collecting the user's facial expressions, voice, and text in real time and analyzing them with an emotion engine, means for analyzing the answer data and emotion data to identify the user's characteristics once all questions have been answered, means for generating a detailed report on the user's characteristics based on the analysis results, and means for providing the generated report to the user. By analyzing the user's emotional state and integrating it with the answer data, more accurate personality diagnosis and personalized feedback become possible.

[0992] "Authentication information" refers to the information a user enters to access a system, and typically includes a username and password.

[0993] A "database" is a record system that stores user information and diagnostic data, allowing for easy access and management.

[0994] An "Enneagram diagnostic questionnaire" is a set of questions designed to evaluate a user's personality traits and suitability for a job.

[0995] "Response data" refers to the collection of answers provided by users to questions used for the Enneagram assessment.

[0996] An "emotion engine" is a software or hardware system that analyzes data such as a user's facial expressions, voice, and text input to recognize their emotional state.

[0997] A "generative AI model" is a machine learning algorithm used to analyze user response data and sentiment data to identify personality traits and aptitudes.

[0998] A "report" is a document generated based on analyzed data, providing detailed information about the user's personality traits and suitability for their job.

[0999] A "user session" is a data stream used to track and manage a series of operations a user performs from the time they log in until they log out.

[1000] A "homepage" is a web page that provides an interface for users to begin a diagnostic test.

[1001] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[1002] 1. User Registration and Authentication

[1003] Program processing:

[1004] The terminal first receives authentication information (username, password, etc.) entered by the user. The server compares this authentication information with the records in the database, and if authentication is successful, provides the user with a diagnostic start page. This process uses the user's terminal (smartphone, PC, etc.) and the server as hardware. The software used is a database management system (DBMS) and a web server.

[1005] Specific example:

[1006] The server compares the authentication information entered by the user with the database and, if correct, provides a homepage displaying a "Start Diagnosis" button.

[1007] 2. Starting the Enneagram assessment

[1008] Program processing:

[1009] When the user clicks the "Start Diagnosis" button, the device sends this request to the server, initiating a new diagnostic session. The server selects the first question and displays a screen on the device for collecting emotional data. The camera captures the user's facial expressions and the microphone collects audio data for emotional data collection.

[1010] Specific example:

[1011] The server displays a screen that captures the user's face with a camera and simultaneously collects audio data with a microphone. When the user clicks the "Ready" button, the first question is displayed on the screen.

[1012] 3. Processing Question Answers

[1013] Program processing:

[1014] When a user answers a question, that answer and sentiment data are sent to the server. The server stores this data and analyzes it using a sentiment engine. The next question is dynamically generated based on the analysis results and sent back to the terminal.

[1015] Specific example:

[1016] The server uses sentiment data submitted along with the user's answers to understand the user's emotional state and adjust the questions accordingly.

[1017] 4. Analysis of diagnostic results

[1018] Program processing:

[1019] Once all questions have been answered, the server passes the accumulated answer data and sentiment data to a generating AI model to analyze the user's personality traits and job suitability. The analysis results are then generated as a detailed report.

[1020] Specific example:

[1021] The server inputs user response data and emotional data into a generating AI model to produce a detailed report on the user's personality traits and aptitudes. This report includes the user's Enneagram type and related career aptitudes.

[1022] 5. Results display and feedback

[1023] Program processing:

[1024] The generated reports are displayed on the user's dashboard, allowing the user to review them. Users can receive specific feedback regarding their personality traits and suitability for their work.

[1025] Specific example:

[1026] Users can determine their Enneagram type and then consider their career path based on that type. For example, if the analysis result is "Enneagram Type 5," they will be advised that data analysis or research positions would be suitable for them.

[1027] Example of a prompt

[1028] "Analyze video frames showing the user's joyful expression and recommend comedy videos they should watch next. Input: Facial expression data frame. Output: Titles and links to recommended comedy videos."

[1029] "A procedure to perform emotion recognition and provide appropriate feedback based on audio data collected while the user is making a sad expression."

[1030] This makes it possible to incorporate the user's emotional state, thereby more accurately evaluating the user's personality traits and suitability for the job, and providing personalized feedback.

[1031] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1032] Step 1:

[1033] The user enters authentication information (username, password, etc.) into the terminal. The terminal sends the entered authentication information to the server, which compares it with the records in the database. This comparison verifies that the user is a legitimate registered user.

[1034] Input: Username, Password

[1035] Output: Authentication result (success / failure)

[1036] Specific operation: The server compares the received authentication information with the database, and if authentication is successful, it starts a user session and provides a diagnostic start page.

[1037] Step 2:

[1038] The user clicks the "Start Diagnosis" button. The device sends this request to the server, which starts a new diagnosis session. The server sends the first question back to the device, and the device displays a screen that collects data such as the user's facial expressions, voice, and text input before the diagnosis begins.

[1039] Input: Diagnostic Start Request

[1040] Output: Initial question and sentiment data collection screen

[1041] Specific operation: The device uses the user's camera and microphone to collect facial expressions and voice, and also accepts text input.

[1042] Step 3:

[1043] The device sends the collected user facial expressions, voice, and text data to the server. The server passes the received data to an emotion engine, which analyzes the user's emotional state. Based on the analysis results, the server provides the user with an initial question.

[1044] Input: Facial expression data, audio data, text data

[1045] Output: Emotional state, first question

[1046] Specific operation: The server inputs data into the emotion engine and obtains emotion recognition results. Based on these results, it generates the most appropriate questions and sends them back to the terminal.

[1047] Step 4:

[1048] The user enters their answers to the displayed questions, and the device sends them to the server. The server temporarily stores the collected sentiment data along with the user's answers. Before generating the next question, the server re-analyzes the sentiment data and dynamically adjusts the order and content of the questions.

[1049] Input: User's response

[1050] Output: Next question

[1051] Specific operation: The server re-analyzes the received response using an emotion engine, dynamically determines the next question, and sends it back to the terminal.

[1052] Step 5:

[1053] Once all questions have been answered, the server passes the accumulated answer data and sentiment data to a generating AI model to identify the user's characteristics. Based on this analysis, a detailed report is generated. The server then sends the generated report to the user's device, making it viewable on the dashboard.

[1054] Input: Accumulated response data, sentiment data

[1055] Output: User characteristics, detailed report

[1056] Specific operation: The server inputs data into the generated AI model, compiles the analysis results into a report format, and sends it to the terminal for display on the user's dashboard.

[1057] Example of a prompt:

[1058] "Analyze video frames showing the user's joyful expression and recommend comedy videos they should watch next. Input: Facial expression data frame. Output: Titles and links to recommended comedy videos."

[1059] "A procedure to perform emotion recognition and provide appropriate feedback based on audio data collected while the user is making a sad expression."

[1060] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1061] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1062] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1063] [Third Embodiment]

[1064] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1065] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1066] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1067] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1068] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1069] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1070] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1071] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1072] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1073] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1074] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1075] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1076] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[1077] 1. User Registration and Authentication

[1078] 1. User Registration

[1079] Users access the registration page and enter the required information (name, email address, password, etc.).

[1080] The terminal sends the entered information to the server.

[1081] The server validates the received information to ensure it is in the correct format.

[1082] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[1083] 2. User Authentication

[1084] The user enters their email address and password on the login page and attempts to authenticate.

[1085] The terminal sends the entered authentication information to the server.

[1086] The server compares the information with that in the database to determine if authentication was successful.

[1087] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1088] 2. Begin Enneagram assessment

[1089] 1. Preparation for initiating diagnosis

[1090] The user clicks the "Start Diagnosis" button on the homepage.

[1091] The device sends this request to the server.

[1092] The server starts a new diagnostic session and selects the first question to present to the user.

[1093] 2. Display the question

[1094] The server generates the first question for the Enneagram assessment and displays it to the user.

[1095] The device displays the question on the screen and allows the user to select or enter an answer.

[1096] 3. Processing Question Answers

[1097] 1. Collection of responses

[1098] The user selects the appropriate option for each question and clicks the submit button.

[1099] The device sends the user's responses to the server in real time.

[1100] 2. Save your answer

[1101] The server temporarily stores the received response as session data.

[1102] The server selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[1103] 4. Analysis of diagnostic results

[1104] 1. Analysis of response data

[1105] Once all questions have been answered, the server passes the accumulated answer data, which is stored as session data, to the AI ​​engine.

[1106] The server uses a machine learning model to analyze the response data and identify the user's Enneagram type.

[1107] 2. Report generation

[1108] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[1109] The report includes a description of the user's Enneagram type, personality traits, strengths, and advice on suitable job types and roles.

[1110] 5. Results display and feedback

[1111] 1. Providing results

[1112] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1113] The device will display a report on the results screen so that the user can review it.

[1114] 2. User Feedback

[1115] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[1116] Users can use the results to consider their career paths and create plans for self-improvement.

[1117] Specific example

[1118] For example, if a user named "Yamada Taro" creates a new account, the user fills in the required information on the registration form. The server receives this information and stores it in a database, allowing the user to log in later. The user then logs in and clicks the "Start Diagnosis" button. The server generates the first questions of the Enneagram diagnosis and presents them to the user via the terminal. Once the user answers the questions, the answers are sent to the server and temporarily stored. After all questions have been answered, the server uses an AI engine to analyze the data and determine Yamada Taro's Enneagram type. Based on the results, the server creates a report and provides it to Yamada Taro.

[1119] This system allows users to conduct self-analysis and consider their career path based on the results.

[1120] The following describes the processing flow.

[1121] Step 1:

[1122] Users access the registration page and enter the required information (name, email address, password, etc.).

[1123] The terminal sends the information entered by the user to the server as form data.

[1124] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[1125] Step 2:

[1126] If validation is successful, the server saves the information to the database as a new user.

[1127] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[1128] The user confirms the registration completion message and then accesses the login page.

[1129] Step 3:

[1130] The user enters their email address and password on the login page.

[1131] The terminal sends the entered authentication information to the server.

[1132] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[1133] Step 4:

[1134] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1135] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[1136] Step 5:

[1137] The device sends this request to the server.

[1138] The server starts a new diagnostic session, selects the first question, and sends it back to the terminal.

[1139] The device displays the first question on the screen, allowing the user to answer it.

[1140] Step 6:

[1141] The user selects the appropriate option for the displayed question and clicks the submit button.

[1142] The device sends the user's response to the server in real time.

[1143] Step 7:

[1144] The server temporarily stores the received response as session data.

[1145] The server selects the next question and sends it back to the terminal.

[1146] Repeat this process until the entire set of questions is complete.

[1147] Step 8:

[1148] Once the user has finished answering all the questions, the server collects the session data.

[1149] The server passes the response data to the AI ​​engine, which then analyzes the Enneagram type.

[1150] The AI ​​uses machine learning models to analyze user response patterns and identify types.

[1151] Step 9:

[1152] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[1153] The report includes information such as a description of the user's Enneagram type, personality traits, and suitable occupations and jobs.

[1154] Step 10:

[1155] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1156] The device will display a report on the results screen so that the user can review it.

[1157] The above describes the specific processing flow in the system of the present invention.

[1158] (Example 1)

[1159] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1160] Traditional personality assessment systems often suffer from inaccurate results and insufficient feedback, as users simply answer pre-set questions. Furthermore, the lack of machine learning models in the analysis results reduces the reliability of the assessment. Additionally, cumbersome user authentication and session management detract from the user experience.

[1161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1162] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for starting a user session and providing a diagnostic start page when user authentication is successful, means for sequentially displaying pre-configured personality diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's personality type using a generated AI model when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This enables the provision of highly accurate and reliable diagnostic results to the user and allows for detailed feedback based on individual personality traits. Furthermore, by simplifying user authentication and session management, the overall user experience can be improved.

[1163] "User authentication" refers to the process of verifying that a user is a legitimate user by comparing the authentication information entered by the user with records in a database.

[1164] The "diagnosis start page" is a web page that users access when they begin a diagnosis, and it is a screen for preparing for the diagnosis.

[1165] A "diagnostic session" represents a series of steps a user takes to perform a diagnosis, and is a collection of data that includes the entire process of answering a series of questions.

[1166] "Personality assessment questions" are pre-set questions designed to determine a user's personality traits and suitability for a job.

[1167] "Response data" refers to the data of the answers that a user enters or selects in response to diagnostic questions.

[1168] A "machine learning model" is an artificial intelligence technology that is trained using large amounts of data to perform specific tasks with high accuracy.

[1169] A "generative AI model" is a machine learning algorithm that learns on its own and is used to analyze user diagnostic data.

[1170] "Personality traits" is a concept that describes the unique characteristics and patterns related to a user's personality.

[1171] "Job suitability" is an indicator used to evaluate how well-suited a user is for a particular job or task.

[1172] A "detailed report" is a document generated based on the analysis results that contains specific and detailed information about the user's personality traits and suitability for the job.

[1173] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[1174] 1. User Registration and Authentication

[1175] User Registration

[1176] The user accesses the system's registration page and enters required information such as name, email address, and password. The terminal sends this information to the server. The server validates the received information to ensure it is in the correct format. Information that is successfully validated is stored in the database, and a registration completion message is sent back to the user.

[1177] User Authentication

[1178] The user enters their email address and password on the login page and attempts authentication. The device sends the entered authentication information to the server. The server compares it with the information in the database to confirm whether authentication was successful. If authentication is successful, the server starts a user session and redirects the user to the homepage.

[1179] 2. Begin Enneagram assessment

[1180] Preparation for starting the diagnosis

[1181] The user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnostic session, generates the first question, and provides it to the user.

[1182] Display the question

[1183] The server generates the initial questions for the Enneagram assessment and displays them to the user via the screen. The terminal displays the questions and allows the user to select or enter answers.

[1184] 3. Processing Question Answers

[1185] Collection of responses

[1186] The user selects the appropriate option for each question and clicks the submit button. The device then sends the user's answers to the server.

[1187] Save the answer

[1188] The server temporarily stores the received answers as session data. It then selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[1189] 4. Analysis of diagnostic results

[1190] Analysis of response data

[1191] The server passes the session data to the AI ​​engine once all questions have been answered. The server uses a machine learning model to identify the user's personality type.

[1192] 5. Report generation and results delivery

[1193] Report generation

[1194] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. The report includes an explanation of the Enneagram type, personality traits, strengths, and career advice.

[1195] Providing results

[1196] The server sends the generated report to the device for display on the user's dashboard. The device displays the report on the results screen, allowing the user to review it.

[1197] Specific example

[1198] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information on the registration page. The device sends this information to the server, which validates it and saves it to the database if the information is in the correct format. Once registration is complete, Yamada Taro logs in and clicks the "Start Diagnosis" button. The server generates the first question of the diagnosis and presents it to Yamada Taro through the device. When Yamada Taro answers, the answer is sent to the server and temporarily stored. Once all questions are completed, the server uses an AI engine to analyze and identify Yamada Taro's personality type. A report is generated based on the results and presented on Yamada Taro's dashboard.

[1199] Example of a prompt

[1200] "Please create a new account."

[1201] "Please log in to begin the diagnosis."

[1202] "Please answer all questions and obtain your diagnostic results."

[1203] This system allows users to understand their own personality traits and job suitability with high accuracy, and to receive effective feedback. Furthermore, it simplifies user authentication and session management, improving the overall user experience.

[1204] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1205] Step 1: User Registration

[1206] Input: The user accesses the registration page and enters their name, email address, and password.

[1207] Processing: The terminal sends this information to the server. The server validates the received information to check if it is in the correct format (e.g., email address format and password strength).

[1208] Output: The server saves the information that was successfully validated to the database, generates a registration completion message, and sends it to the terminal.

[1209] Specific operation: The user enters information into a form via a browser and clicks the submit button. The server executes backend validation logic (e.g., email address check using regular expressions).

[1210] Step 2: User Authentication

[1211] Input: The user enters their email address and password on the login page.

[1212] Processing: The terminal sends these authentication credentials to the server. The server compares them with the information in the database, and if they match, it determines that authentication was successful.

[1213] Output: The server initiates a user session and sends instructions to the terminal to redirect to the homepage.

[1214] Specific operation: The user enters information into the login form, and the terminal sends it to the server as an HTTP POST request. The server executes a database query to retrieve the user information and compares it with a hashed password.

[1215] Step 3: Start diagnosis

[1216] Input: The user clicks the "Start Diagnosis" button on the homepage.

[1217] Processing: The terminal sends this request to the server. The server starts a new diagnostic session and generates the first question.

[1218] Output: The server sends the first question to the terminal, and the terminal displays it to the user.

[1219] Specific operation: The server generates a diagnostic session ID and stores the session information in memory. Next, it randomly or sequentially selects the first question from the question list and sends it to the terminal in JSON format.

[1220] Step 4: Question Display

[1221] Input: Question data received from the server by the terminal.

[1222] Processing: The terminal displays the question on the screen and allows the user to select or enter an answer.

[1223] Output: The user enters or selects an answer to the displayed question.

[1224] Specific operation: The terminal analyzes the received question data and displays it on the screen using HTML or other front-end technologies.

[1225] Step 5: Collecting responses

[1226] Input: Response data submitted by the user.

[1227] Processing: The terminal sends the user's response to the server. The server temporarily stores the received response as session data.

[1228] Output: The server generates the following question and sends it to the terminal.

[1229] Specific operation: When the user clicks the submit button, the device sends an HTTP POST request containing the answer data to the server. The server saves the answer data to memory or a database and selects the next question.

[1230] Step 6: Refresh the problem session

[1231] Input: A request from the user to proceed to the next question.

[1232] Processing: The server selects the next question based on the session data and sends it to the terminal.

[1233] Output: The terminal will display the following question on the screen.

[1234] Specific operation: Based on the previous question and answer, the server determines the next question to display, generates a new question, and sends it to the terminal.

[1235] Step 7: Analysis of diagnostic results

[1236] Input: User response data for all questions.

[1237] Processing: The server collects all response data and passes it to the AI ​​engine for analysis.

[1238] Output: The server identifies the user's personality type and retrieves the result.

[1239] Specific operation: The server calls an AI engine (e.g., scikit-learn or TensorFlow in Python), inputs the user's response data into a pre-trained model, and predicts the personality type.

[1240] Step 8: Report Generation

[1241] Input: Analysis results from the AI ​​engine.

[1242] Processing: The server generates a detailed report based on the analysis results.

[1243] Output: The server prepares to send the generated report to the terminal.

[1244] Specific operation: The server uses a template engine (e.g., Jinja2) to create a detailed report based on the analysis results and structure it in JSON format.

[1245] Step 9: Results display and feedback

[1246] Input: Report data sent from the server.

[1247] Processing: The terminal displays the report on the screen for the user to review.

[1248] Output: Users review the report and provide feedback as needed.

[1249] Specific operation: The device parses the received report data and displays it on the screen using HTML or other front-end technologies. Users can review the report and enter feedback.

[1250] This allows users to receive detailed diagnostic results, which can be used for self-understanding and career development.

[1251] (Application Example 1)

[1252] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1253] The goal is to improve operator performance in work environments such as factories by accurately evaluating users' personality traits and job aptitudes through Enneagram assessments, and optimizing work assignments and training content based on individual characteristics.

[1254] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1255] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-configured Enneagram diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's Enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and job suitability based on the analysis results, means for making suggestions to optimize work assignments and training content based on the user's personality traits and job suitability, and means for providing the generated report to the user. This enables optimal work assignments and training to improve operator performance.

[1256] "User" refers to an individual or operator who uses the system.

[1257] "Authentication information" refers to data (e.g., email address and password) that a user uses to access a system.

[1258] A "database" refers to digital storage used to systematically store information used in a system, such as user information and response data.

[1259] A "diagnosis start page" refers to a webpage that provides an interface for users to begin the Enneagram diagnosis.

[1260] "Enneagram diagnostic questions" refer to a set of questions designed to assess a user's personality traits and suitability for a job.

[1261] "Response data" refers to information resulting from users' responses to the Enneagram diagnostic test.

[1262] "Analysis" refers to a series of processes that analyze response data to identify the user's Enneagram type.

[1263] "Enneagram type" refers to the personality classification of a user identified through an Enneagram assessment.

[1264] A "report" refers to a document that compiles detailed information about a user's personality traits and suitability for their job.

[1265] "Task assignment" refers to assigning specific tasks or duties to an operator.

[1266] "Training content" refers to learning and training programs provided to improve operators' skills and suitability for their jobs.

[1267] "Proposal" refers to advice on optimizing task assignments and training content for users based on the analysis results.

[1268] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze data and draw conclusions.

[1269] This invention relates to an Enneagram diagnostic system for evaluating a user's personality traits and job suitability. The system includes a set of functions for user authentication, management of diagnostic sessions, data analysis, and result delivery.

[1270] Hardware and software configuration

[1271] The following hardware and software will be used in the implementation of this system.

[1272] Hardware: Industrial PC or server

[1273] Software: Flask (web application framework), SQLite (database), Scikit-learn (machine learning library)

[1274] System operation

[1275] User registration and authentication

[1276] Users must first register and authenticate with the system. They enter their email address and password as authentication information. The device sends this information to the server, which verifies it against the information in its database. If authentication is successful, the user can access the diagnostic start page.

[1277] Starting the Enneagram assessment

[1278] After successful user authentication, the user accesses the diagnostic start page and clicks the "Start Diagnostics" button. In response to this request, the server starts a new diagnostic session and sequentially displays the user the questions for the Enneagram diagnostic test.

[1279] Question answering process

[1280] As the user answers each question, the answer is sent to the server in real time and temporarily stored as session data. This process is repeated until all questions have been answered.

[1281] Analysis of diagnostic results

[1282] Once all questions have been answered, the server passes the received response data to a generating AI model (machine learning model) for analysis. After analysis, the server identifies the user's Enneagram type and generates a detailed report based on it. This report includes the user's personality traits, job suitability, and suggestions for suitable work assignments and training content.

[1283] Results display and feedback

[1284] The generated reports are provided to the user's dashboard, where they can review them. Based on the report's content, users can then consider self-improvement and their career paths.

[1285] Specific example

[1286] For example, when a factory operator takes an Enneagram assessment, the user first registers with the system and begins the assessment after authentication. As the operator answers questions, the system analyzes the response data to identify the operator's personality traits and job suitability. Based on the analysis results, the system then proposes the most suitable work content and training program for the operator. In this way, performance in the work environment can be improved.

[1287] Examples of prompt statements

[1288] Examples of prompts for generative AI models:

[1289] "Are you good at demonstrating leadership?" Please rate the displayed question on a 5-point scale.

[1290] The above describes the embodiments of the present invention and details of the Enneagram diagnostic system for improving a user's suitability for their work.

[1291] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1292] Step 1:

[1293] The user accesses the system and enters the required information (name, email address, password) on the registration page. The terminal sends this information to the database. The server receives the submitted information and performs format validation. Information that passes validation is stored in the database, and a registration completion message is sent back to the user.

[1294] Input: Username, email address, password

[1295] Output: Registration complete message

[1296] Step 2:

[1297] The user enters their email address and password on the login page and attempts to authenticate. The device sends the entered authentication information to the server. The server compares this information with the information in the database, and if the comparison is successful, it starts a user session and redirects the user to the homepage.

[1298] Input: User's email address, password

[1299] Output: Authentication result, homepage

[1300] Step 3:

[1301] The user clicks the "Start Diagnosis" button. The device sends the request to the server. The server starts a new diagnosis session and displays the user the first questions for the Enneagram diagnosis.

[1302] Input: Diagnostic Initiation Request

[1303] Output: Initial Question

[1304] Step 4:

[1305] The user answers the questions. The device sends the user's answers to the server in real time. The server temporarily stores the received answers as session data, selects the next question, and displays it to the user. This process is repeated until all questions have been answered.

[1306] Input: User's response

[1307] Output: Next question, session data

[1308] Step 5:

[1309] Once all questions have been answered, the server passes the accumulated answer data as session data to a generating AI model for analysis. The server then identifies the user's Enneagram type based on the analysis results.

[1310] Input: All response data

[1311] Output: Enneagram type

[1312] Step 6:

[1313] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. This report includes the user's Enneagram type, personality traits, strengths, and suitable job roles. Furthermore, it also suggests work assignments and training programs.

[1314] Input: Enneagram type

[1315] Output: Detailed report

[1316] Step 7:

[1317] The server sends the generated report to the user's dashboard, and the terminal displays it to the user. The user reviews the displayed report and receives specific feedback on their personality traits and suitability for the job.

[1318] Input: Detailed report

[1319] Output: Displaying reports on the dashboard

[1320] Step 8:

[1321] Based on the report content, users can plan for self-improvement and consider their career paths. This allows users to engage in work that leverages their strengths.

[1322] Input: Displaying reports on the dashboard

[1323] Output: Planning for self-improvement, considering career paths.

[1324] Examples of prompt statements

[1325] Examples of prompts for generative AI models:

[1326] "Are you good at demonstrating leadership?" Please rate the displayed question on a 5-point scale.

[1327] The above describes the processing steps of the system based on an embodiment of the present invention. This step enables a detailed Enneagram diagnosis to improve the user's suitability for their work.

[1328] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1329] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[1330] 1. User Registration and Authentication

[1331] 1. User Registration

[1332] Users access the registration page and enter their name, email address, password, etc.

[1333] The terminal sends the information entered by the user to the server as form data.

[1334] The server validates the received information to ensure it is in the correct format.

[1335] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[1336] 2. User Authentication

[1337] The user enters their email address and password on the login page.

[1338] The terminal sends the entered authentication information to the server.

[1339] The server compares the information with that in the database to verify that authentication was successful.

[1340] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1341] 2. Begin Enneagram assessment

[1342] 1. Preparation for initiating diagnosis

[1343] The user clicks the "Start Diagnosis" button on the homepage.

[1344] The device sends this request to the server.

[1345] The server starts a new diagnostic session, selects the first question, and sends it back to the terminal.

[1346] Before the diagnosis begins, the device displays a screen where the emotion engine collects data such as the user's facial expressions, voice, and text input.

[1347] 2. Collection of sentiment data and presentation of questions

[1348] The device captures the user's facial expressions with a camera, collects audio data with a microphone, and receives text input.

[1349] The server sends this data to the emotion engine to recognize the user's emotions.

[1350] The server generates and presents the first question to the user based on the recognized user sentiment data.

[1351] The device displays the question on the screen, allowing the user to answer it.

[1352] 3. Processing Question Answers

[1353] 1. Collection of responses

[1354] The user selects the appropriate option for the displayed question and clicks the submit button.

[1355] The device sends the user's response to the server in real time.

[1356] 2. Saving responses and presenting adaptive questions

[1357] The server temporarily stores the received response as session data.

[1358] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the user's sentiment data recognized by the sentiment engine.

[1359] The server selects the next adjusted question and sends it back to the terminal.

[1360] Repeat this process until the entire set of questions is complete.

[1361] 4. Analysis of diagnostic results

[1362] 1. Analysis of response data and sentiment data

[1363] Once all questions have been answered, the server passes the answer data, which has been stored as session data, along with the emotion data recognized by the emotion engine, to the AI ​​engine.

[1364] The server uses a machine learning model to analyze response data and sentiment data to identify the user's Enneagram type.

[1365] 2. Report generation

[1366] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[1367] The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable occupations and jobs, and feedback based on emotional data.

[1368] 5. Results display and feedback

[1369] 1. Providing results

[1370] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1371] The device will display a report on the results screen so that the user can review it.

[1372] 2. User Feedback

[1373] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[1374] Users can use the results to consider their career paths and create plans for self-improvement.

[1375] Specific example

[1376] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the device collects emotional data such as the user's facial expressions, voice, and text input and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. When the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on Yamada Taro's Enneagram type and related feedback, and provides it to the user.

[1377] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[1378] The following describes the processing flow.

[1379] Step 1:

[1380] Users access the registration page and enter the required information, such as their name, email address, and password.

[1381] The terminal sends the entered information to the server as form data.

[1382] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[1383] Step 2:

[1384] If validation is successful, the server saves the information to the database as a new user.

[1385] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[1386] The user confirms the registration completion message and then accesses the login page.

[1387] Step 3:

[1388] The user enters their email address and password on the login page.

[1389] The terminal sends the entered authentication information to the server.

[1390] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[1391] Step 4:

[1392] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1393] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[1394] Step 5:

[1395] The device sends a "start diagnosis" request to the server.

[1396] The server initiates a new diagnostic session and presents the emotion engine data collection screen to the terminal.

[1397] The device displays a screen to the user and begins collecting facial expressions, voice, and text data.

[1398] Step 6:

[1399] The user provides emotional data (facial expressions, voice, text) in the specified manner.

[1400] The device collects this data in real time and sends it to the server.

[1401] Step 7:

[1402] The server passes the collected emotion data to the emotion engine to recognize the user's emotions.

[1403] The server temporarily stores the recognized emotion data as session data.

[1404] The server generates the initial question based on sentiment data and sends it back to the terminal.

[1405] Step 8:

[1406] The device displays the first question on the screen, allowing the user to answer it.

[1407] The user selects the appropriate option for the presented question and clicks the submit button.

[1408] Step 9:

[1409] The device sends the user's responses to the server in real time.

[1410] The server temporarily stores the received response as session data.

[1411] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the sentiment data recognized by the sentiment engine.

[1412] Step 10:

[1413] The server selects the next adjusted question and sends it back to the terminal.

[1414] Repeat this process until the entire set of questions is complete.

[1415] Step 11:

[1416] Once the user has finished answering all the questions, the server collects all the response data and sentiment data.

[1417] The server passes this data to the AI ​​engine, which then analyzes the user's Enneagram type.

[1418] The AI ​​uses a machine learning model to analyze response data and sentiment data together to identify the user's Enneagram type.

[1419] Step 12:

[1420] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[1421] The report includes information such as a description of the user's Enneagram type, personality traits, strengths, additional feedback based on emotional data, and suitable job types and tasks.

[1422] Step 13:

[1423] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1424] The device will display a report on the results screen so that the user can review it.

[1425] Step 14:

[1426] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[1427] Users can use the results to consider their career paths and create plans for self-improvement.

[1428] The above outlines the specific processing flow of the self-analysis AI system that incorporates an emotion engine.

[1429] (Example 2)

[1430] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1431] When users evaluate their personality traits and job suitability through Enneagram assessments, conventional systems analyze the results based solely on the answers to questions, failing to adequately consider the user's emotional state and psychological factors. Furthermore, there is a need to accurately recognize the user's emotions and provide more precise diagnostic results. To address this challenge, a new system is required that collects user emotional data and utilizes it in its analysis to perform deeper analyses.

[1432] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1433] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for collecting emotional data such as the user's facial expressions, voice, and text input before the diagnostic starts, means for sequentially displaying pre-set questions for enneagram diagnosis to the user, means for receiving and storing the user's answers along with emotional data, means for analyzing the answer data and emotional data to identify the user's enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This makes it possible to provide a more accurate enneagram diagnosis that takes into account the user's emotional state and to obtain detailed insights into the user's personality traits and suitability for work.

[1434] "Authentication information" refers to the information required for a user to log in to a system, and typically includes a username, email address, and password.

[1435] A "database" is a system for efficiently managing, storing, and retrieving data, and it exists in various forms such as SQL and NoSQL.

[1436] The "Enneagram test" is a psychological method that classifies individuals' personality traits and behavioral patterns into nine types.

[1437] "Emotional data" refers to emotional information collected from user facial expressions, voice, text input, etc., and is analyzed using an emotion engine.

[1438] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions, voice, text input, etc., to recognize their emotional state.

[1439] A "machine learning model" is an algorithm that learns patterns from data and uses those patterns to make predictions and classifications.

[1440] The "Start Diagnosis Page" is the webpage that users access to begin the Enneagram diagnosis, and it includes a description of the diagnosis and a start button.

[1441] "Session data" refers to data that is temporarily stored when a user uses the system, and includes information from the start to the end of the session.

[1442] A "report" is a document summarizing the user's Enneagram assessment results, containing detailed information about personality traits and job suitability.

[1443] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[1444] User registration and authentication are performed as follows: The user accesses the registration page and enters information such as name, email address, and password. The terminal sends the entered user information as form data to the server. The server validates the received information to check if the data is in the correct format. If validation is successful, the server saves the user information to a database (e.g., an SQL database), generates a registration completion message, and sends it to the terminal.

[1445] In user authentication, the user accesses the login page and enters their email address and password. The device sends the user's authentication information to the server. The server compares this information with the information in the database and confirms that authentication was successful. If authentication is successful, a user session is started and the user is redirected to the homepage.

[1446] In the preparation phase for starting the diagnosis, the user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnosis session, selects the first question, and sends it back to the device. Before starting the diagnosis, the device displays a screen that collects emotional data such as the user's facial expressions, voice, and text input.

[1447] The collection of emotion data and display of questions are performed as follows: The device captures the user's facial expressions with its camera, collects audio data with its microphone, and receives text input. The server sends this data to an emotion engine to recognize the user's emotions. Based on the recognition results, the first question is generated and presented to the user. The device displays the question on the screen, allowing the user to answer.

[1448] In the question-answering process, the user selects the appropriate option for the displayed question and clicks the submit button. The terminal sends the user's answers to the server in real time. The server temporarily stores the received answers as session data and dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. This process is repeated until the entire set of questions is completed.

[1449] In the analysis of the diagnostic results, once all questions have been answered, the server passes the accumulated response data and sentiment data as session data to the AI ​​engine. Using a machine learning model (e.g., using TensorFlow or PyTorch), the response data and sentiment data are analyzed to identify the user's Enneagram type. Based on the analysis results, a detailed report on the user's personality traits and job suitability is generated. The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable jobs and tasks, and feedback based on the sentiment data.

[1450] As part of the results display and feedback process, the server sends data to the terminal to display the generated report on the user's dashboard. The terminal displays the report on the results screen, allowing the user to review it. The user reviews the displayed report and receives specific feedback regarding their personality traits and suitability for the job. Based on the results, they can consider their career path or plan for self-improvement.

[1451] As a concrete example, if a user named "Yamada Taro" creates a new account, the user enters the necessary information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the terminal collects emotional data such as the user's facial expressions, voice, and text input, and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. After the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on "Yamada Taro's" Enneagram type and related feedback, and provides it to the user. This system allows users to conduct a deeper self-analysis and consider their career path based on the results.

[1452] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[1453] Examples of prompt statements to input into the generative AI model are as follows:

[1454] "Taro Yamada is taking an Enneagram assessment. First, he registered as a user and then clicked the button to start the assessment. Facial expressions, voice, and text input will be collected as emotional data for this user. What is the first question?"

[1455] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1456] User registration and authentication

[1457] Step 1: User Registration

[1458] 1. Input: The user accesses the registration page and enters information such as their name, email address, and password.

[1459] 2. Operation and Data Processing: The terminal sends the entered user information to the server as form data. Specifically, the data in the form is sent to the server as an HTTP POST request.

[1460] 3. Output: The server validates the received information to ensure the data is in the correct format. Specifically, it checks whether the email address is in the correct format and whether the password length is appropriate.

[1461] 4. Operation: If validation is successful, the server saves the user information to the database and generates and sends a registration completion message to the terminal. Specifically, the user information is inserted into the database, and the message "Registration complete" is returned as a response.

[1462] Step 2: User Authentication

[1463] 1. Input: The user accesses the login page and enters their email address and password.

[1464] 2. Operation and Data Processing: The terminal sends the user's authentication information to the server. Specifically, the authentication information is sent to the server as an HTTP POST request.

[1465] 3. Output: The server verifies the authentication success by comparing the information with that in the database. For example, it might run a database query to find a record where the entered email address and password match.

[1466] 4. Operation: If authentication is successful, the server initiates a user session and redirects the user to the homepage. Specifically, a session management token is generated, and the user is redirected to the homepage via a redirect header in the HTTP response.

[1467] Enneagram assessment started.

[1468] Step 3: Preparing to begin diagnosis

[1469] 1. Input: The user clicks the "Start Diagnosis" button on the homepage.

[1470] 2. Operation and Data Processing: The terminal sends this request to the server. Specifically, the request is sent to the server in the background using Ajax.

[1471] 3. Output: The server starts a new diagnostic session, selects the first question, and sends it back to the terminal. Specifically, a diagnostic session ID is generated, and the question data is returned in JSON format.

[1472] 4. Operation: Before starting the diagnosis, the device displays a screen to collect emotional data such as the user's facial expressions, voice, and text input. Specifically, a dialog box confirming access to the camera and microphone will appear on the screen.

[1473] Step 4: Collecting sentiment data and displaying questions

[1474] 1. Input: Collect emotional data such as the user's facial expressions, voice, and text input.

[1475] 2. Operation and Data Processing: The device captures the user's facial expressions with a camera, collects audio data with a microphone, and receives text input. Specifically, the camera and microphone are activated by the browser, and the collected data is processed by JavaScript.

[1476] 3. Output: The server sends this data to the emotion engine to recognize the user's emotions. Specifically, audio data is uploaded to the server as a .wav file and image data as a .jpeg file.

[1477] 4. Operation: Based on the recognition results, the first question is generated and presented to the user. Specifically, based on the output data of the emotion engine, a question such as "How are you feeling right now?" is generated. The question is added to the HTML DOM and displayed on the screen.

[1478] Question answering process

[1479] Step 5: Collecting responses

[1480] 1. Input: The user selects the appropriate option for the displayed question and clicks the submit button.

[1481] 2. Operation and Data Processing: The terminal sends the user's responses to the server in real time. Specifically, the data is sent to the server asynchronously using Ajax.

[1482] 3. Output: The server temporarily stores the received response as session data. Specifically, the response data is stored in a session variable in memory.

[1483] Step 6: Saving responses and presenting adaptive questions

[1484] 1. Input: User response data and sentiment data sent to the server.

[1485] 2. Operation and Data Processing: The server dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. Specifically, the next questions are dynamically fetched from the database using the results of sentiment recognition.

[1486] 3. Output: The next adjusted question is selected and sent to the terminal. Specifically, question data is generated in JSON format and returned as a response.

[1487] 4. Operation: This process is repeated until the entire set of questions is completed. Specifically, responses and sentiment data for each question are collected sequentially and processed on the server.

[1488] Analysis of diagnostic results

[1489] Step 7: Analysis of response data and sentiment data

[1490] 1. Input: Answer data and sentiment data for all questions.

[1491] 2. Operation and Data Processing: The server passes the response data and sentiment data to the AI ​​engine, which then uses a machine learning model for analysis. Specifically, it uses TensorFlow or PyTorch to perform calculations based on the data and identify the user's Enneagram type.

[1492] 3. Output: The results will identify the user's Enneagram type.

[1493] Step 8: Generate the report

[1494] 1. Input: Data on analyzed Enneagram types, personality traits, and job suitability.

[1495] 2. Operation and Data Processing: The server generates detailed reports based on the analysis results. Specifically, it uses an automated generation tool to construct reports in PDF or HTML format.

[1496] 3. Output: The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable job types and tasks, and feedback based on emotional data.

[1497] Results display and feedback

[1498] Step 9: Providing Results

[1499] 1. Input: The generated report.

[1500] 2. Operation and Data Processing: The server sends data to the terminal to display the report on the user's dashboard. Specifically, the report's URL and binary data are sent as a response.

[1501] 3. Output: The terminal displays the report on the results screen for the user to review. Specifically, the report is inserted into the HTML DOM and displayed on the screen.

[1502] Step 10: User Feedback

[1503] 1. Input: The displayed report.

[1504] 2. Operation and Data Processing: Users review the displayed reports and receive specific feedback on their personality traits and job suitability. Based on the results, they consider career paths and plan for self-improvement.

[1505] 3. Output: Users will be able to obtain information to develop concrete action plans.

[1506] (Application Example 2)

[1507] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1508] Conventional personality assessment systems evaluate personality traits and aptitudes based on user responses, but they do not take into account the user's emotional state, making it difficult to provide deeper analysis or personalized feedback. There was a need for a system that could collect and analyze user emotional data and adjust the diagnostic process accordingly to obtain more accurate results.

[1509] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1510] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page if user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-set diagnostic questions to the user, means for receiving and storing the user's answers, means for collecting the user's facial expressions, voice, and text in real time and analyzing them with an emotion engine, means for analyzing the answer data and emotion data to identify the user's characteristics once all questions have been answered, means for generating a detailed report on the user's characteristics based on the analysis results, and means for providing the generated report to the user. By analyzing the user's emotional state and integrating it with the answer data, more accurate personality diagnosis and personalized feedback become possible.

[1511] "Authentication information" refers to the information a user enters to access a system, and typically includes a username and password.

[1512] A "database" is a record system that stores user information and diagnostic data, allowing for easy access and management.

[1513] An "Enneagram diagnostic questionnaire" is a set of questions designed to evaluate a user's personality traits and suitability for a job.

[1514] "Response data" refers to the collection of answers provided by users to questions used for the Enneagram assessment.

[1515] An "emotion engine" is a software or hardware system that analyzes data such as a user's facial expressions, voice, and text input to recognize their emotional state.

[1516] A "generative AI model" is a machine learning algorithm used to analyze user response data and sentiment data to identify personality traits and aptitudes.

[1517] A "report" is a document generated based on analyzed data, providing detailed information about the user's personality traits and suitability for their job.

[1518] A "user session" is a data stream used to track and manage a series of operations a user performs from the time they log in until they log out.

[1519] A "homepage" is a web page that provides an interface for users to begin a diagnostic test.

[1520] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[1521] 1. User Registration and Authentication

[1522] Program processing:

[1523] The terminal first receives authentication information (username, password, etc.) entered by the user. The server compares this authentication information with the records in the database, and if authentication is successful, provides the user with a diagnostic start page. This process uses the user's terminal (smartphone, PC, etc.) and the server as hardware. The software used is a database management system (DBMS) and a web server.

[1524] Specific example:

[1525] The server compares the authentication information entered by the user with the database and, if correct, provides a homepage displaying a "Start Diagnosis" button.

[1526] 2. Starting the Enneagram assessment

[1527] Program processing:

[1528] When the user clicks the "Start Diagnosis" button, the device sends this request to the server, initiating a new diagnostic session. The server selects the first question and displays a screen on the device for collecting emotional data. The camera captures the user's facial expressions and the microphone collects audio data for emotional data collection.

[1529] Specific example:

[1530] The server displays a screen that captures the user's face with a camera and simultaneously collects audio data with a microphone. When the user clicks the "Ready" button, the first question is displayed on the screen.

[1531] 3. Processing Question Answers

[1532] Program processing:

[1533] When a user answers a question, that answer and sentiment data are sent to the server. The server stores this data and analyzes it using a sentiment engine. The next question is dynamically generated based on the analysis results and sent back to the terminal.

[1534] Specific example:

[1535] The server uses sentiment data submitted along with the user's answers to understand the user's emotional state and adjust the questions accordingly.

[1536] 4. Analysis of diagnostic results

[1537] Program processing:

[1538] Once all questions have been answered, the server passes the accumulated answer data and sentiment data to a generating AI model to analyze the user's personality traits and job suitability. The analysis results are then generated as a detailed report.

[1539] Specific example:

[1540] The server inputs user response data and emotional data into a generating AI model to produce a detailed report on the user's personality traits and aptitudes. This report includes the user's Enneagram type and related career aptitudes.

[1541] 5. Results display and feedback

[1542] Program processing:

[1543] The generated reports are displayed on the user's dashboard, allowing the user to review them. Users can receive specific feedback regarding their personality traits and suitability for their work.

[1544] Specific example:

[1545] Users can determine their Enneagram type and then consider their career path based on that type. For example, if the analysis result is "Enneagram Type 5," they will be advised that data analysis or research positions would be suitable for them.

[1546] Example of a prompt

[1547] "Analyze video frames showing the user's joyful expression and recommend comedy videos they should watch next. Input: Facial expression data frame. Output: Titles and links to recommended comedy videos."

[1548] "A procedure to perform emotion recognition and provide appropriate feedback based on audio data collected while the user is making a sad expression."

[1549] This makes it possible to incorporate the user's emotional state, thereby more accurately evaluating the user's personality traits and suitability for the job, and providing personalized feedback.

[1550] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1551] Step 1:

[1552] The user enters authentication information (username, password, etc.) into the terminal. The terminal sends the entered authentication information to the server, which compares it with the records in the database. This comparison verifies that the user is a legitimate registered user.

[1553] Input: Username, Password

[1554] Output: Authentication result (success / failure)

[1555] Specific operation: The server compares the received authentication information with the database, and if authentication is successful, it starts a user session and provides a diagnostic start page.

[1556] Step 2:

[1557] The user clicks the "Start Diagnosis" button. The device sends this request to the server, which starts a new diagnosis session. The server sends the first question back to the device, and the device displays a screen that collects data such as the user's facial expressions, voice, and text input before the diagnosis begins.

[1558] Input: Diagnostic Start Request

[1559] Output: Initial question and sentiment data collection screen

[1560] Specific operation: The device uses the user's camera and microphone to collect facial expressions and voice, and also accepts text input.

[1561] Step 3:

[1562] The device sends the collected user facial expressions, voice, and text data to the server. The server passes the received data to an emotion engine, which analyzes the user's emotional state. Based on the analysis results, the server provides the user with an initial question.

[1563] Input: Facial expression data, audio data, text data

[1564] Output: Emotional state, first question

[1565] Specific operation: The server inputs data into the emotion engine and obtains emotion recognition results. Based on these results, it generates the most appropriate questions and sends them back to the terminal.

[1566] Step 4:

[1567] The user enters their answers to the displayed questions, and the device sends them to the server. The server temporarily stores the collected sentiment data along with the user's answers. Before generating the next question, the server re-analyzes the sentiment data and dynamically adjusts the order and content of the questions.

[1568] Input: User's response

[1569] Output: Next question

[1570] Specific operation: The server re-analyzes the received response using an emotion engine, dynamically determines the next question, and sends it back to the terminal.

[1571] Step 5:

[1572] Once all questions have been answered, the server passes the accumulated answer data and sentiment data to a generating AI model to identify the user's characteristics. Based on this analysis, a detailed report is generated. The server then sends the generated report to the user's device, making it viewable on the dashboard.

[1573] Input: Accumulated response data, sentiment data

[1574] Output: User characteristics, detailed report

[1575] Specific operation: The server inputs data into the generated AI model, compiles the analysis results into a report format, and sends it to the terminal for display on the user's dashboard.

[1576] Example of a prompt:

[1577] "Analyze video frames showing the user's joyful expression and recommend comedy videos they should watch next. Input: Facial expression data frame. Output: Titles and links to recommended comedy videos."

[1578] "A procedure to perform emotion recognition and provide appropriate feedback based on audio data collected while the user is making a sad expression."

[1579] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1580] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1581] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1582] [Fourth Embodiment]

[1583] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1584] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1585] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1586] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1587] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1588] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1589] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1590] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1591] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1592] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1593] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1594] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1595] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1596] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[1597] 1. User Registration and Authentication

[1598] 1. User Registration

[1599] Users access the registration page and enter the required information (name, email address, password, etc.).

[1600] The terminal sends the entered information to the server.

[1601] The server validates the received information to ensure it is in the correct format.

[1602] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[1603] 2. User Authentication

[1604] The user enters their email address and password on the login page and attempts to authenticate.

[1605] The terminal sends the entered authentication information to the server.

[1606] The server compares the information with that in the database to determine if authentication was successful.

[1607] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1608] 2. Begin Enneagram assessment

[1609] 1. Preparation for initiating diagnosis

[1610] The user clicks the "Start Diagnosis" button on the homepage.

[1611] The device sends this request to the server.

[1612] The server starts a new diagnostic session and selects the first question to present to the user.

[1613] 2. Display the question

[1614] The server generates the first question for the Enneagram assessment and displays it to the user.

[1615] The device displays the question on the screen and allows the user to select or enter an answer.

[1616] 3. Processing Question Answers

[1617] 1. Collection of responses

[1618] The user selects the appropriate option for each question and clicks the submit button.

[1619] The device sends the user's responses to the server in real time.

[1620] 2. Save your answer

[1621] The server temporarily stores the received response as session data.

[1622] The server selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[1623] 4. Analysis of diagnostic results

[1624] 1. Analysis of response data

[1625] Once all questions have been answered, the server passes the accumulated answer data, which is stored as session data, to the AI ​​engine.

[1626] The server uses a machine learning model to analyze the response data and identify the user's Enneagram type.

[1627] 2. Report generation

[1628] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[1629] The report includes a description of the user's Enneagram type, personality traits, strengths, and advice on suitable job types and roles.

[1630] 5. Results display and feedback

[1631] 1. Providing results

[1632] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1633] The device will display a report on the results screen so that the user can review it.

[1634] 2. User Feedback

[1635] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[1636] Users can use the results to consider their career paths and create plans for self-improvement.

[1637] Specific example

[1638] For example, if a user named "Yamada Taro" creates a new account, the user fills in the required information on the registration form. The server receives this information and stores it in a database, allowing the user to log in later. The user then logs in and clicks the "Start Diagnosis" button. The server generates the first questions of the Enneagram diagnosis and presents them to the user via the terminal. Once the user answers the questions, the answers are sent to the server and temporarily stored. After all questions have been answered, the server uses an AI engine to analyze the data and determine Yamada Taro's Enneagram type. Based on the results, the server creates a report and provides it to Yamada Taro.

[1639] This system allows users to conduct self-analysis and consider their career path based on the results.

[1640] The following describes the processing flow.

[1641] Step 1:

[1642] Users access the registration page and enter the required information (name, email address, password, etc.).

[1643] The terminal sends the information entered by the user to the server as form data.

[1644] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[1645] Step 2:

[1646] If validation is successful, the server saves the information to the database as a new user.

[1647] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[1648] The user confirms the registration completion message and then accesses the login page.

[1649] Step 3:

[1650] The user enters their email address and password on the login page.

[1651] The terminal sends the entered authentication information to the server.

[1652] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[1653] Step 4:

[1654] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1655] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[1656] Step 5:

[1657] The device sends this request to the server.

[1658] The server starts a new diagnostic session, selects the first question, and sends it back to the terminal.

[1659] The device displays the first question on the screen, allowing the user to answer it.

[1660] Step 6:

[1661] The user selects the appropriate option for the displayed question and clicks the submit button.

[1662] The device sends the user's response to the server in real time.

[1663] Step 7:

[1664] The server temporarily stores the received response as session data.

[1665] The server selects the next question and sends it back to the terminal.

[1666] Repeat this process until the entire set of questions is complete.

[1667] Step 8:

[1668] Once the user has finished answering all the questions, the server collects the session data.

[1669] The server passes the response data to the AI ​​engine, which then analyzes the Enneagram type.

[1670] The AI ​​uses machine learning models to analyze user response patterns and identify types.

[1671] Step 9:

[1672] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[1673] The report includes information such as a description of the user's Enneagram type, personality traits, and suitable occupations and jobs.

[1674] Step 10:

[1675] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1676] The device will display a report on the results screen so that the user can review it.

[1677] The above describes the specific processing flow in the system of the present invention.

[1678] (Example 1)

[1679] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1680] Traditional personality assessment systems often suffer from inaccurate results and insufficient feedback, as users simply answer pre-set questions. Furthermore, the lack of machine learning models in the analysis results reduces the reliability of the assessment. Additionally, cumbersome user authentication and session management detract from the user experience.

[1681] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1682] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for starting a user session and providing a diagnostic start page when user authentication is successful, means for sequentially displaying pre-configured personality diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's personality type using a generated AI model when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This enables the provision of highly accurate and reliable diagnostic results to the user and allows for detailed feedback based on individual personality traits. Furthermore, by simplifying user authentication and session management, the overall user experience can be improved.

[1683] "User authentication" refers to the process of verifying that a user is a legitimate user by comparing the authentication information entered by the user with records in a database.

[1684] The "diagnosis start page" is a web page that users access when they begin a diagnosis, and it is a screen for preparing for the diagnosis.

[1685] A "diagnostic session" represents a series of steps a user takes to perform a diagnosis, and is a collection of data that includes the entire process of answering a series of questions.

[1686] "Personality assessment questions" are pre-set questions designed to determine a user's personality traits and suitability for a job.

[1687] "Response data" refers to the data of the answers that a user enters or selects in response to diagnostic questions.

[1688] A "machine learning model" is an artificial intelligence technology that is trained using large amounts of data to perform specific tasks with high accuracy.

[1689] A "generative AI model" is a machine learning algorithm that learns on its own and is used to analyze user diagnostic data.

[1690] "Personality traits" is a concept that describes the unique characteristics and patterns related to a user's personality.

[1691] "Job suitability" is an indicator used to evaluate how well-suited a user is for a particular job or task.

[1692] A "detailed report" is a document generated based on the analysis results that contains specific and detailed information about the user's personality traits and suitability for the job.

[1693] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. The system includes functions for user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results.

[1694] 1. User Registration and Authentication

[1695] User Registration

[1696] The user accesses the system's registration page and enters required information such as name, email address, and password. The terminal sends this information to the server. The server validates the received information to ensure it is in the correct format. Information that is successfully validated is stored in the database, and a registration completion message is sent back to the user.

[1697] User Authentication

[1698] The user enters their email address and password on the login page and attempts authentication. The device sends the entered authentication information to the server. The server compares it with the information in the database to confirm whether authentication was successful. If authentication is successful, the server starts a user session and redirects the user to the homepage.

[1699] 2. Begin Enneagram assessment

[1700] Preparation for starting the diagnosis

[1701] The user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnostic session, generates the first question, and provides it to the user.

[1702] Display the question

[1703] The server generates the initial questions for the Enneagram assessment and displays them to the user via the screen. The terminal displays the questions and allows the user to select or enter answers.

[1704] 3. Processing Question Answers

[1705] Collection of responses

[1706] The user selects the appropriate option for each question and clicks the submit button. The device then sends the user's answers to the server.

[1707] Save the answer

[1708] The server temporarily stores the received answers as session data. It then selects the next question and presents it to the user again. This process is repeated until all questions have been answered.

[1709] 4. Analysis of diagnostic results

[1710] Analysis of response data

[1711] The server passes the session data to the AI ​​engine once all questions have been answered. The server uses a machine learning model to identify the user's personality type.

[1712] 5. Report generation and results delivery

[1713] Report generation

[1714] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. The report includes an explanation of the Enneagram type, personality traits, strengths, and career advice.

[1715] Providing results

[1716] The server sends the generated report to the device for display on the user's dashboard. The device displays the report on the results screen, allowing the user to review it.

[1717] Specific example

[1718] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information on the registration page. The device sends this information to the server, which validates it and saves it to the database if the information is in the correct format. Once registration is complete, Yamada Taro logs in and clicks the "Start Diagnosis" button. The server generates the first question of the diagnosis and presents it to Yamada Taro through the device. When Yamada Taro answers, the answer is sent to the server and temporarily stored. Once all questions are completed, the server uses an AI engine to analyze and identify Yamada Taro's personality type. A report is generated based on the results and presented on Yamada Taro's dashboard.

[1719] Example of a prompt

[1720] "Please create a new account."

[1721] "Please log in to begin the diagnosis."

[1722] "Please answer all questions and obtain your diagnostic results."

[1723] This system allows users to understand their own personality traits and job suitability with high accuracy, and to receive effective feedback. Furthermore, it simplifies user authentication and session management, improving the overall user experience.

[1724] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1725] Step 1: User Registration

[1726] Input: The user accesses the registration page and enters their name, email address, and password.

[1727] Processing: The terminal sends this information to the server. The server validates the received information to check if it is in the correct format (e.g., email address format and password strength).

[1728] Output: The server saves the information that was successfully validated to the database, generates a registration completion message, and sends it to the terminal.

[1729] Specific operation: The user enters information into a form via a browser and clicks the submit button. The server executes backend validation logic (e.g., email address check using regular expressions).

[1730] Step 2: User Authentication

[1731] Input: The user enters their email address and password on the login page.

[1732] Processing: The terminal sends these authentication credentials to the server. The server compares them with the information in the database, and if they match, it determines that authentication was successful.

[1733] Output: The server initiates a user session and sends instructions to the terminal to redirect to the homepage.

[1734] Specific operation: The user enters information into the login form, and the terminal sends it to the server as an HTTP POST request. The server executes a database query to retrieve the user information and compares it with a hashed password.

[1735] Step 3: Start diagnosis

[1736] Input: The user clicks the "Start Diagnosis" button on the homepage.

[1737] Processing: The terminal sends this request to the server. The server starts a new diagnostic session and generates the first question.

[1738] Output: The server sends the first question to the terminal, and the terminal displays it to the user.

[1739] Specific operation: The server generates a diagnostic session ID and stores the session information in memory. Next, it randomly or sequentially selects the first question from the question list and sends it to the terminal in JSON format.

[1740] Step 4: Question Display

[1741] Input: Question data received from the server by the terminal.

[1742] Processing: The terminal displays the question on the screen and allows the user to select or enter an answer.

[1743] Output: The user enters or selects an answer to the displayed question.

[1744] Specific operation: The terminal analyzes the received question data and displays it on the screen using HTML or other front-end technologies.

[1745] Step 5: Collecting responses

[1746] Input: Response data submitted by the user.

[1747] Processing: The terminal sends the user's response to the server. The server temporarily stores the received response as session data.

[1748] Output: The server generates the following question and sends it to the terminal.

[1749] Specific operation: When the user clicks the submit button, the device sends an HTTP POST request containing the answer data to the server. The server saves the answer data to memory or a database and selects the next question.

[1750] Step 6: Refresh the problem session

[1751] Input: A request from the user to proceed to the next question.

[1752] Processing: The server selects the next question based on the session data and sends it to the terminal.

[1753] Output: The terminal will display the following question on the screen.

[1754] Specific operation: Based on the previous question and answer, the server determines the next question to display, generates a new question, and sends it to the terminal.

[1755] Step 7: Analysis of diagnostic results

[1756] Input: User response data for all questions.

[1757] Processing: The server collects all response data and passes it to the AI ​​engine for analysis.

[1758] Output: The server identifies the user's personality type and retrieves the result.

[1759] Specific operation: The server calls an AI engine (e.g., scikit-learn or TensorFlow in Python), inputs the user's response data into a pre-trained model, and predicts the personality type.

[1760] Step 8: Report Generation

[1761] Input: Analysis results from the AI ​​engine.

[1762] Processing: The server generates a detailed report based on the analysis results.

[1763] Output: The server prepares to send the generated report to the terminal.

[1764] Specific operation: The server uses a template engine (e.g., Jinja2) to create a detailed report based on the analysis results and structure it in JSON format.

[1765] Step 9: Results display and feedback

[1766] Input: Report data sent from the server.

[1767] Processing: The terminal displays the report on the screen for the user to review.

[1768] Output: Users review the report and provide feedback as needed.

[1769] Specific operation: The device parses the received report data and displays it on the screen using HTML or other front-end technologies. Users can review the report and enter feedback.

[1770] This allows users to receive detailed diagnostic results, which can be used for self-understanding and career development.

[1771] (Application Example 1)

[1772] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1773] The goal is to improve operator performance in work environments such as factories by accurately evaluating users' personality traits and job aptitudes through Enneagram assessments, and optimizing work assignments and training content based on individual characteristics.

[1774] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1775] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for sequentially displaying pre-configured Enneagram diagnostic questions to the user, means for receiving and storing the user's answers, means for analyzing the answer data and identifying the user's Enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and job suitability based on the analysis results, means for making suggestions to optimize work assignments and training content based on the user's personality traits and job suitability, and means for providing the generated report to the user. This enables optimal work assignments and training to improve operator performance.

[1776] "User" refers to an individual or operator who uses the system.

[1777] "Authentication information" refers to data (e.g., email address and password) that a user uses to access a system.

[1778] A "database" refers to digital storage used to systematically store information used in a system, such as user information and response data.

[1779] A "diagnosis start page" refers to a webpage that provides an interface for users to begin the Enneagram diagnosis.

[1780] "Enneagram diagnostic questions" refer to a set of questions designed to assess a user's personality traits and suitability for a job.

[1781] "Response data" refers to information resulting from users' responses to the Enneagram diagnostic test.

[1782] "Analysis" refers to a series of processes that analyze response data to identify the user's Enneagram type.

[1783] "Enneagram type" refers to the personality classification of a user identified through an Enneagram assessment.

[1784] A "report" refers to a document that compiles detailed information about a user's personality traits and suitability for their job.

[1785] "Task assignment" refers to assigning specific tasks or duties to an operator.

[1786] "Training content" refers to learning and training programs provided to improve operators' skills and suitability for their jobs.

[1787] "Proposal" refers to advice on optimizing task assignments and training content for users based on the analysis results.

[1788] A "generative AI model" refers to an algorithm that uses machine learning techniques to analyze data and draw conclusions.

[1789] This invention relates to an Enneagram diagnostic system for evaluating a user's personality traits and job suitability. The system includes a set of functions for user authentication, management of diagnostic sessions, data analysis, and result delivery.

[1790] Hardware and software configuration

[1791] The following hardware and software will be used in the implementation of this system.

[1792] Hardware: Industrial PC or server

[1793] Software: Flask (web application framework), SQLite (database), Scikit-learn (machine learning library)

[1794] System operation

[1795] User registration and authentication

[1796] Users must first register and authenticate with the system. They enter their email address and password as authentication information. The device sends this information to the server, which verifies it against the information in its database. If authentication is successful, the user can access the diagnostic start page.

[1797] Starting the Enneagram assessment

[1798] After successful user authentication, the user accesses the diagnostic start page and clicks the "Start Diagnostics" button. In response to this request, the server starts a new diagnostic session and sequentially displays the user the questions for the Enneagram diagnostic test.

[1799] Question answering process

[1800] As the user answers each question, the answer is sent to the server in real time and temporarily stored as session data. This process is repeated until all questions have been answered.

[1801] Analysis of diagnostic results

[1802] Once all questions have been answered, the server passes the received response data to a generating AI model (machine learning model) for analysis. After analysis, the server identifies the user's Enneagram type and generates a detailed report based on it. This report includes the user's personality traits, job suitability, and suggestions for suitable work assignments and training content.

[1803] Results display and feedback

[1804] The generated reports are provided to the user's dashboard, where they can review them. Based on the report's content, users can then consider self-improvement and their career paths.

[1805] Specific example

[1806] For example, when a factory operator takes an Enneagram assessment, the user first registers with the system and begins the assessment after authentication. As the operator answers questions, the system analyzes the response data to identify the operator's personality traits and job suitability. Based on the analysis results, the system then proposes the most suitable work content and training program for the operator. In this way, performance in the work environment can be improved.

[1807] Examples of prompt statements

[1808] Examples of prompts for generative AI models:

[1809] "Are you good at demonstrating leadership?" Please rate the displayed question on a 5-point scale.

[1810] The above describes the embodiments of the present invention and details of the Enneagram diagnostic system for improving a user's suitability for their work.

[1811] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1812] Step 1:

[1813] The user accesses the system and enters the required information (name, email address, password) on the registration page. The terminal sends this information to the database. The server receives the submitted information and performs format validation. Information that passes validation is stored in the database, and a registration completion message is sent back to the user.

[1814] Input: Username, email address, password

[1815] Output: Registration complete message

[1816] Step 2:

[1817] The user enters their email address and password on the login page and attempts to authenticate. The device sends the entered authentication information to the server. The server compares this information with the information in the database, and if the comparison is successful, it starts a user session and redirects the user to the homepage.

[1818] Input: User's email address, password

[1819] Output: Authentication result, homepage

[1820] Step 3:

[1821] The user clicks the "Start Diagnosis" button. The device sends the request to the server. The server starts a new diagnosis session and displays the user the first questions for the Enneagram diagnosis.

[1822] Input: Diagnostic Initiation Request

[1823] Output: Initial Question

[1824] Step 4:

[1825] The user answers the questions. The device sends the user's answers to the server in real time. The server temporarily stores the received answers as session data, selects the next question, and displays it to the user. This process is repeated until all questions have been answered.

[1826] Input: User's response

[1827] Output: Next question, session data

[1828] Step 5:

[1829] Once all questions have been answered, the server passes the accumulated answer data as session data to a generating AI model for analysis. The server then identifies the user's Enneagram type based on the analysis results.

[1830] Input: All response data

[1831] Output: Enneagram type

[1832] Step 6:

[1833] The server generates a detailed report on the user's personality traits and job suitability based on the analysis results. This report includes the user's Enneagram type, personality traits, strengths, and suitable job roles. Furthermore, it also suggests work assignments and training programs.

[1834] Input: Enneagram type

[1835] Output: Detailed report

[1836] Step 7:

[1837] The server sends the generated report to the user's dashboard, and the terminal displays it to the user. The user reviews the displayed report and receives specific feedback on their personality traits and suitability for the job.

[1838] Input: Detailed report

[1839] Output: Displaying reports on the dashboard

[1840] Step 8:

[1841] Based on the report content, users can plan for self-improvement and consider their career paths. This allows users to engage in work that leverages their strengths.

[1842] Input: Displaying reports on the dashboard

[1843] Output: Planning for self-improvement, considering career paths.

[1844] Examples of prompt statements

[1845] Examples of prompts for generative AI models:

[1846] "Are you good at demonstrating leadership?" Please rate the displayed question on a 5-point scale.

[1847] The above describes the processing steps of the system based on an embodiment of the present invention. This step enables a detailed Enneagram diagnosis to improve the user's suitability for their work.

[1848] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1849] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[1850] 1. User Registration and Authentication

[1851] 1. User Registration

[1852] Users access the registration page and enter their name, email address, password, etc.

[1853] The terminal sends the information entered by the user to the server as form data.

[1854] The server validates the received information to ensure it is in the correct format.

[1855] If validation is successful, the server saves the user information to the database and sends a registration completion message back to the user.

[1856] 2. User Authentication

[1857] The user enters their email address and password on the login page.

[1858] The terminal sends the entered authentication information to the server.

[1859] The server compares the information with that in the database to verify that authentication was successful.

[1860] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1861] 2. Begin Enneagram assessment

[1862] 1. Preparation for initiating diagnosis

[1863] The user clicks the "Start Diagnosis" button on the homepage.

[1864] The device sends this request to the server.

[1865] The server starts a new diagnostic session, selects the first question, and sends it back to the terminal.

[1866] Before the diagnosis begins, the device displays a screen where the emotion engine collects data such as the user's facial expressions, voice, and text input.

[1867] 2. Collection of sentiment data and presentation of questions

[1868] The device captures the user's facial expressions with a camera, collects audio data with a microphone, and receives text input.

[1869] The server sends this data to the emotion engine to recognize the user's emotions.

[1870] The server generates and presents the first question to the user based on the recognized user sentiment data.

[1871] The device displays the question on the screen, allowing the user to answer it.

[1872] 3. Processing Question Answers

[1873] 1. Collection of responses

[1874] The user selects the appropriate option for the displayed question and clicks the submit button.

[1875] The device sends the user's response to the server in real time.

[1876] 2. Saving responses and presenting adaptive questions

[1877] The server temporarily stores the received response as session data.

[1878] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the user's sentiment data recognized by the sentiment engine.

[1879] The server selects the next adjusted question and sends it back to the terminal.

[1880] Repeat this process until the entire set of questions is complete.

[1881] 4. Analysis of diagnostic results

[1882] 1. Analysis of response data and sentiment data

[1883] Once all questions have been answered, the server passes the answer data, which has been stored as session data, along with the emotion data recognized by the emotion engine, to the AI ​​engine.

[1884] The server uses a machine learning model to analyze response data and sentiment data to identify the user's Enneagram type.

[1885] 2. Report generation

[1886] The server generates a detailed report on the user's personality traits and suitability for their job based on the analysis results.

[1887] The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable occupations and jobs, and feedback based on emotional data.

[1888] 5. Results display and feedback

[1889] 1. Providing results

[1890] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1891] The device will display a report on the results screen so that the user can review it.

[1892] 2. User Feedback

[1893] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[1894] Users can use the results to consider their career paths and create plans for self-improvement.

[1895] Specific example

[1896] For example, if a user named "Yamada Taro" creates a new account, the user enters the required information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the device collects emotional data such as the user's facial expressions, voice, and text input and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. When the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on Yamada Taro's Enneagram type and related feedback, and provides it to the user.

[1897] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[1898] The following describes the processing flow.

[1899] Step 1:

[1900] Users access the registration page and enter the required information, such as their name, email address, and password.

[1901] The terminal sends the entered information to the server as form data.

[1902] The server receives this data and performs validation. For example, it checks the format of the email address and the strength of the password.

[1903] Step 2:

[1904] If validation is successful, the server saves the information to the database as a new user.

[1905] Once the saving process is complete, the server generates a registration success message and sends it back to the user.

[1906] The user confirms the registration completion message and then accesses the login page.

[1907] Step 3:

[1908] The user enters their email address and password on the login page.

[1909] The terminal sends the entered authentication information to the server.

[1910] The server compares the received authentication information with the records in the database. If there is a mismatch, it returns an error message.

[1911] Step 4:

[1912] If authentication is successful, the server initiates a user session and redirects the user to the homepage.

[1913] The user accesses the homepage and clicks the button to start the Enneagram assessment.

[1914] Step 5:

[1915] The device sends a "start diagnosis" request to the server.

[1916] The server initiates a new diagnostic session and presents the emotion engine data collection screen to the terminal.

[1917] The device displays a screen to the user and begins collecting facial expressions, voice, and text data.

[1918] Step 6:

[1919] The user provides emotional data (facial expressions, voice, text) in the specified manner.

[1920] The device collects this data in real time and sends it to the server.

[1921] Step 7:

[1922] The server passes the collected emotion data to the emotion engine to recognize the user's emotions.

[1923] The server temporarily stores the recognized emotion data as session data.

[1924] The server generates the initial question based on sentiment data and sends it back to the terminal.

[1925] Step 8:

[1926] The device displays the first question on the screen, allowing the user to answer it.

[1927] The user selects the appropriate option for the presented question and clicks the submit button.

[1928] Step 9:

[1929] The device sends the user's responses to the server in real time.

[1930] The server temporarily stores the received response as session data.

[1931] Before selecting the next question, the server dynamically adjusts the order and content of the questions based on the sentiment data recognized by the sentiment engine.

[1932] Step 10:

[1933] The server selects the next adjusted question and sends it back to the terminal.

[1934] Repeat this process until the entire set of questions is complete.

[1935] Step 11:

[1936] Once the user has finished answering all the questions, the server collects all the response data and sentiment data.

[1937] The server passes this data to the AI ​​engine, which then analyzes the user's Enneagram type.

[1938] The AI ​​uses a machine learning model to analyze response data and sentiment data together to identify the user's Enneagram type.

[1939] Step 12:

[1940] Based on the analysis results, the server generates a detailed report on the user's personality traits and suitability for the job.

[1941] The report includes information such as a description of the user's Enneagram type, personality traits, strengths, additional feedback based on emotional data, and suitable job types and tasks.

[1942] Step 13:

[1943] The server sends the generated report data to the user's device so that it can be displayed on the user's dashboard.

[1944] The device will display a report on the results screen so that the user can review it.

[1945] Step 14:

[1946] Users review the displayed report and receive specific feedback regarding their personality traits and suitability for the job.

[1947] Users can use the results to consider their career paths and create plans for self-improvement.

[1948] The above outlines the specific processing flow of the self-analysis AI system that incorporates an emotion engine.

[1949] (Example 2)

[1950] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1951] When users evaluate their personality traits and job suitability through Enneagram assessments, conventional systems analyze the results based solely on the answers to questions, failing to adequately consider the user's emotional state and psychological factors. Furthermore, there is a need to accurately recognize the user's emotions and provide more precise diagnostic results. To address this challenge, a new system is required that collects user emotional data and utilizes it in its analysis to perform deeper analyses.

[1952] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1953] In this invention, the server includes means for receiving authentication information entered by the user, means for comparing the received authentication information with records in a database, means for providing the user with a diagnostic start page when user authentication is successful, means for receiving a diagnostic start request from the user, means for collecting emotional data such as the user's facial expressions, voice, and text input before the diagnostic starts, means for sequentially displaying pre-set questions for enneagram diagnosis to the user, means for receiving and storing the user's answers along with emotional data, means for analyzing the answer data and emotional data to identify the user's enneagram type when all questions have been answered, means for generating a detailed report on the user's personality traits and suitability for work based on the analysis results, and means for providing the generated report to the user. This makes it possible to provide a more accurate enneagram diagnosis that takes into account the user's emotional state and to obtain detailed insights into the user's personality traits and suitability for work.

[1954] "Authentication information" refers to the information required for a user to log in to a system, and typically includes a username, email address, and password.

[1955] A "database" is a system for efficiently managing, storing, and retrieving data, and it exists in various forms such as SQL and NoSQL.

[1956] The "Enneagram test" is a psychological method that classifies individuals' personality traits and behavioral patterns into nine types.

[1957] "Emotional data" refers to emotional information collected from user facial expressions, voice, text input, etc., and is analyzed using an emotion engine.

[1958] An "emotion engine" is software or an algorithm that analyzes a user's facial expressions, voice, text input, etc., to recognize their emotional state.

[1959] A "machine learning model" is an algorithm that learns patterns from data and uses those patterns to make predictions and classifications.

[1960] The "Start Diagnosis Page" is the webpage that users access to begin the Enneagram diagnosis, and it includes a description of the diagnosis and a start button.

[1961] "Session data" refers to data that is temporarily stored when a user uses the system, and includes information from the start to the end of the session.

[1962] A "report" is a document summarizing the user's Enneagram assessment results, containing detailed information about personality traits and job suitability.

[1963] This invention relates to a system that allows users to evaluate their own personality traits and job suitability through an Enneagram assessment. In addition to user registration and authentication, presentation of diagnostic questions, collection and analysis of responses, and provision of results, this system incorporates an emotion engine that recognizes the user's emotions, enabling deeper analysis.

[1964] User registration and authentication are performed as follows: The user accesses the registration page and enters information such as name, email address, and password. The terminal sends the entered user information as form data to the server. The server validates the received information to check if the data is in the correct format. If validation is successful, the server saves the user information to a database (e.g., an SQL database), generates a registration completion message, and sends it to the terminal.

[1965] In user authentication, the user accesses the login page and enters their email address and password. The device sends the user's authentication information to the server. The server compares this information with the information in the database and confirms that authentication was successful. If authentication is successful, a user session is started and the user is redirected to the homepage.

[1966] In the preparation phase for starting the diagnosis, the user clicks the "Start Diagnosis" button on the homepage. The device sends this request to the server. The server starts a new diagnosis session, selects the first question, and sends it back to the device. Before starting the diagnosis, the device displays a screen that collects emotional data such as the user's facial expressions, voice, and text input.

[1967] The collection of emotion data and display of questions are performed as follows: The device captures the user's facial expressions with its camera, collects audio data with its microphone, and receives text input. The server sends this data to an emotion engine to recognize the user's emotions. Based on the recognition results, the first question is generated and presented to the user. The device displays the question on the screen, allowing the user to answer.

[1968] In the question-answering process, the user selects the appropriate option for the displayed question and clicks the submit button. The terminal sends the user's answers to the server in real time. The server temporarily stores the received answers as session data and dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. This process is repeated until the entire set of questions is completed.

[1969] In the analysis of the diagnostic results, once all questions have been answered, the server passes the accumulated response data and sentiment data as session data to the AI ​​engine. Using a machine learning model (e.g., using TensorFlow or PyTorch), the response data and sentiment data are analyzed to identify the user's Enneagram type. Based on the analysis results, a detailed report on the user's personality traits and job suitability is generated. The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable jobs and tasks, and feedback based on the sentiment data.

[1970] As part of the results display and feedback process, the server sends data to the terminal to display the generated report on the user's dashboard. The terminal displays the report on the results screen, allowing the user to review it. The user reviews the displayed report and receives specific feedback regarding their personality traits and suitability for the job. Based on the results, they can consider their career path or plan for self-improvement.

[1971] As a concrete example, if a user named "Yamada Taro" creates a new account, the user enters the necessary information into the registration form. The server validates this information and saves it to the database. The user then logs in and clicks the "Start Diagnosis" button. Before starting the diagnosis, the terminal collects emotional data such as the user's facial expressions, voice, and text input, and sends it to the server. The server's emotion engine analyzes this data. The server then presents the user with the first question. After the user answers the question, they send their answer and emotional data to the server. Once all questions are completed, the server passes the answer data and emotional data to the AI ​​engine for analysis. The AI ​​then generates a report based on "Yamada Taro's" Enneagram type and related feedback, and provides it to the user. This system allows users to conduct a deeper self-analysis and consider their career path based on the results.

[1972] This system allows users to conduct deeper self-analysis and consider their career paths based on the results.

[1973] Examples of prompt statements to input into the generative AI model are as follows:

[1974] "Taro Yamada is taking an Enneagram assessment. First, he registered as a user and then clicked the button to start the assessment. Facial expressions, voice, and text input will be collected as emotional data for this user. What is the first question?"

[1975] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1976] User registration and authentication

[1977] Step 1: User Registration

[1978] 1. Input: The user accesses the registration page and enters information such as their name, email address, and password.

[1979] 2. Operation and Data Processing: The terminal sends the entered user information to the server as form data. Specifically, the data in the form is sent to the server as an HTTP POST request.

[1980] 3. Output: The server validates the received information to ensure the data is in the correct format. Specifically, it checks whether the email address is in the correct format and whether the password length is appropriate.

[1981] 4. Operation: If validation is successful, the server saves the user information to the database and generates and sends a registration completion message to the terminal. Specifically, the user information is inserted into the database, and the message "Registration complete" is returned as a response.

[1982] Step 2: User Authentication

[1983] 1. Input: The user accesses the login page and enters their email address and password.

[1984] 2. Operation and Data Processing: The terminal sends the user's authentication information to the server. Specifically, the authentication information is sent to the server as an HTTP POST request.

[1985] 3. Output: The server verifies the authentication success by comparing the information with that in the database. For example, it might run a database query to find a record where the entered email address and password match.

[1986] 4. Operation: If authentication is successful, the server initiates a user session and redirects the user to the homepage. Specifically, a session management token is generated, and the user is redirected to the homepage via a redirect header in the HTTP response.

[1987] Enneagram assessment started.

[1988] Step 3: Preparing to begin diagnosis

[1989] 1. Input: The user clicks the "Start Diagnosis" button on the homepage.

[1990] 2. Operation and Data Processing: The terminal sends this request to the server. Specifically, the request is sent to the server in the background using Ajax.

[1991] 3. Output: The server starts a new diagnostic session, selects the first question, and sends it back to the terminal. Specifically, a diagnostic session ID is generated, and the question data is returned in JSON format.

[1992] 4. Operation: Before starting the diagnosis, the device displays a screen to collect emotional data such as the user's facial expressions, voice, and text input. Specifically, a dialog box confirming access to the camera and microphone will appear on the screen.

[1993] Step 4: Collecting sentiment data and displaying questions

[1994] 1. Input: Collect emotional data such as the user's facial expressions, voice, and text input.

[1995] 2. Operation and Data Processing: The device captures the user's facial expressions with a camera, collects audio data with a microphone, and receives text input. Specifically, the camera and microphone are activated by the browser, and the collected data is processed by JavaScript.

[1996] 3. Output: The server sends this data to the emotion engine to recognize the user's emotions. Specifically, audio data is uploaded to the server as a .wav file and image data as a .jpeg file.

[1997] 4. Operation: Based on the recognition results, the first question is generated and presented to the user. Specifically, based on the output data of the emotion engine, a question such as "How are you feeling right now?" is generated. The question is added to the HTML DOM and displayed on the screen.

[1998] Question answering process

[1999] Step 5: Collecting responses

[2000] 1. Input: The user selects the appropriate option for the displayed question and clicks the submit button.

[2001] 2. Operation and Data Processing: The terminal sends the user's responses to the server in real time. Specifically, the data is sent to the server asynchronously using Ajax.

[2002] 3. Output: The server temporarily stores the received response as session data. Specifically, the response data is stored in a session variable in memory.

[2003] Step 6: Saving responses and presenting adaptive questions

[2004] 1. Input: User response data and sentiment data sent to the server.

[2005] 2. Operation and Data Processing: The server dynamically adjusts the order and content of the next questions based on the user's sentiment data recognized by the sentiment engine. Specifically, the next questions are dynamically fetched from the database using the results of sentiment recognition.

[2006] 3. Output: The next adjusted question is selected and sent to the terminal. Specifically, question data is generated in JSON format and returned as a response.

[2007] 4. Operation: This process is repeated until the entire set of questions is completed. Specifically, responses and sentiment data for each question are collected sequentially and processed on the server.

[2008] Analysis of diagnostic results

[2009] Step 7: Analysis of response data and sentiment data

[2010] 1. Input: Answer data and sentiment data for all questions.

[2011] 2. Operation and Data Processing: The server passes the response data and sentiment data to the AI ​​engine, which then uses a machine learning model for analysis. Specifically, it uses TensorFlow or PyTorch to perform calculations based on the data and identify the user's Enneagram type.

[2012] 3. Output: The results will identify the user's Enneagram type.

[2013] Step 8: Generate the report

[2014] 1. Input: Data on analyzed Enneagram types, personality traits, and job suitability.

[2015] 2. Operation and Data Processing: The server generates detailed reports based on the analysis results. Specifically, it uses an automated generation tool to construct reports in PDF or HTML format.

[2016] 3. Output: The report includes a description of the user's Enneagram type, personality traits, strengths, advice on suitable job types and tasks, and feedback based on emotional data.

[2017] Results display and feedback

[2018] Step 9: Providing Results

[2019] 1. Input: The generated report.

[2020] 2. Operation and Data Processing: The server sends data to the terminal to display the report on the user's dashboard. Specifically, the report's URL and binary data are sent as a response.

[2021] 3. Output: The terminal displays the report on the results screen for the user to review. Specifically, the report is inserted into the HTML DOM and displayed on the screen.

[2022] Step 10: User Feedback

[2023] 1. Input: The displayed report.

[2024] 2. Operation and Data Processing: Users review the displayed reports and receive specific feedback on their personality traits and job suitability. Based on the results, they consider career paths and plan for self-improvement.

[2025] 3. Output: Users will be able to obtain information to develop concrete action plans.

[2026] (Application Example 2)

[2027] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2028] Conventional personality assessment systems evaluate personality traits and aptitudes based on user responses, but they do not take into account the user's emotional state, making it difficult to provide deeper analysis or personalized feedback. There was a need for a system that cou...

Claims

1. A means of receiving authentication information entered by the user, A means of comparing the received authentication information with the records in the database, A means of providing the user with a diagnostic start page upon successful user authentication, A means of receiving diagnostic start requests from users, A means of sequentially displaying pre-set questions for Enneagram diagnosis to the user, A means of receiving and saving user responses, Once all questions have been answered, the response data will be analyzed to identify the user's Enneagram type. A means of generating a detailed report on the user's personality traits and suitability for work based on the analysis results, Means of providing the generated report to the user, A system that includes this.

2. The system according to claim 1, characterized in that the means for analyzing the response data identifies the user's enneagram type using a machine learning model.

3. The system according to claim 1, characterized in that, upon successful user authentication, it initiates a user session and provides the user with a homepage.

Images