system

Abstract

We provide the system. [Solution] A means of generating individual counseling and guidance content by executing a generative AI model, A means of distributing the generated counseling content to an educational machine, A means of conducting interactive education based on the delivered instructional content and recording responses during the education, A means of analyzing recorded response data to improve the content of the next lesson, A system that includes this.

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 and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional in-prison education and rehabilitation programs, it has been difficult to effectively improve the ability of serious offenders to deeply introspect their own actions from ethical and moral perspectives. There is a lack of an appropriate education process based on individual past behavior histories and psychological evaluation data, and as a result, opportunities to contribute to reducing the recidivism rate have not been fully provided. There is a demand for providing an effective education system that can solve this problem and reduce the recidivism rate after social reintegration.

Means for Solving the Problems

[0005] This invention provides a system for conducting interactive education for individual serious offenders by generating individual counseling and guidance content using a generative AI model and distributing that content to an educational machine. The educational machine recreates the victim's perspective through audio playback based on the guidance content, encouraging introspection. The response data recorded during this process is sent to a server and used to improve the content of the next educational session. Furthermore, the system includes means for collecting and pre-processing the individual information necessary for analysis by the generative AI model, enabling more effective counseling and guidance.

[0006] A "generative AI model" is an artificial intelligence algorithm and system used to generate individualized counseling and guidance content.

[0007] An "educational machine" is a device that provides interactive education to serious offenders based on generated instructional content, facilitating learning through audio playback and dialogue.

[0008] "Counseling content" refers to text or audio information generated based on the offender's past behavioral history and psychological state, in order to encourage appropriate ethical guidance and introspection.

[0009] "Instructional content" refers to educational plans and scenarios identified by a generative AI model, including specific educational goals and tasks that are communicated to serious offenders by educational machines.

[0010] "Interactive education" is an educational process in which users actively participate, and educational machines dynamically adjust the content based on responses and choices.

[0011] "Recorded response data" refers to a dataset containing information such as behavior, statements, and reaction speed exhibited by serious offenders during educational sessions, and is used for feedback analysis.

[0012] "Preprocessing" refers to the process of organizing and processing collected data into a format that is easily analyzed by the generating AI model, and it also refers to the work of ensuring data integrity and quality. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] In one embodiment of the invention, the server first accesses a database within an authenticated prison and collects various data about serious offenders. This includes behavioral history, psychological evaluation results, and personal information. This data is preprocessed and prepared in a format that can be effectively analyzed by the generated AI model.

[0035] Next, the server runs a generative AI model to generate individualized counseling and guidance content based on the collected data. This process sets up scenarios for providing education tailored to each serious offender and includes content that promotes learning about ethics and morality.

[0036] The server transmits the generated instructional content to terminals within the prison. The terminals then transmit the content to educational machines (robots) and prepare for interactive educational sessions.

[0037] The user, a serious offender, physically interacts with the educational machine and receives instruction. The educational machine conducts the education in an interactive format, following generated scenarios and engaging in question-and-answer sessions that encourage the user to reconsider their lacking ethical perspectives and the victim's point of view.

[0038] As a concrete example, regarding a past theft committed by the user, the educational machine asks questions such as, "What did the stolen item mean to the victim?" and uses a resonant voice scenario to convey the victim's feelings. During this process, the user's responses and statements are recorded on the device and sent to the server.

[0039] The recorded response data is analyzed on a server and used to improve the content and methods of future lessons. This strengthens the system for providing more appropriate education while maintaining individuality.

[0040] Through this embodiment, it is possible to enhance ethical reflection and reduce recidivism rates after reintegration into society by providing interactive guidance tailored to individual offenders.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server accesses the prison database and collects behavioral history, psychological evaluation data, and personal data of serious offenders. This data is preprocessed into a format suitable for analysis by generative AI models.

[0044] Step 2:

[0045] The server runs a generative AI model, analyzes pre-processed data, and generates individualized counseling and guidance content. This guidance content includes scenarios incorporating ethical education and the victim's perspective.

[0046] Step 3:

[0047] The server transmits the generated instructional content to terminals within the prison. The terminals review the received instructional content and prepare it for use with educational equipment.

[0048] Step 4:

[0049] The user, a serious offender, interacts with an educational machine to participate in an educational session. The educational machine conducts interactive education based on generated scenarios, presenting the user with questions and playing audio scenarios.

[0050] Step 5:

[0051] The device records the user's responses during the educational session, including the content of the user's answers and their response speed.

[0052] Step 6:

[0053] The device sends recorded response data to the server. The server analyzes this data and generates feedback to be used to improve the next educational session.

[0054] (Example 1)

[0055] 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."

[0056] Traditional education systems have provided a uniform approach to ethical and moral education for serious offenders, making it difficult to provide appropriate feedback based on individual characteristics and past behavioral history. Therefore, there is a need for individualized education that can prevent recidivism.

[0057] 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.

[0058] In this invention, the server includes means for transmitting generated instruction content to a medium via a communication terminal, means for performing interactive instruction based on the transmitted instruction content and saving the actions taken during instruction, means for analyzing the saved action data and using it to improve the content of the next instruction, means for collecting and processing individualized information for information analysis, and means for creating individualized counseling and instruction content using generative AI technology. This makes it possible to provide appropriate ethical and moral education tailored to individual circumstances and contribute to preventing recidivism.

[0059] "Generative AI technology" is a technology that uses artificial intelligence to automatically generate content and data tailored to specific purposes.

[0060] A "communication terminal" is a device used for sending and receiving data, and is a device that enables the transmission of information over a network.

[0061] A "medium" refers to a physical or electronic device or system used as a means of transmitting or storing information.

[0062] "Interactive instruction" is an educational process in which the student and the instructional system communicate with each other as the process progresses.

[0063] "Behavioral data" refers to data that records the reactions and behaviors exhibited by participants during the instruction process.

[0064] "Personalized information" refers to information that includes unique data and attributes related to a specific individual.

[0065] "Counseling" is the act of providing psychological or behavioral support to participants through advice and guidance.

[0066] Modes for carrying out the invention

[0067] In this invention, the server first accesses an authenticated database within the prison to collect various data on serious offenders. This data includes behavioral history, psychological evaluation results, and personal information. A database management system is used for data collection, such as MySQL®. The collected data is preprocessed using the Pandas library and converted into a format that can be effectively analyzed by the generated AI model.

[0068] Next, the server runs a generative AI model to generate individual counseling and guidance content based on the pre-processed data. A large-scale language model (e.g., OpenAI® GPT) is used in this step. By giving the AI ​​model specific instructions such as "Create an ethics education scenario based on the user's individual history" as a prompt, appropriate guidance content is generated.

[0069] The generated instructional content is transmitted from the server to terminals installed within the prison. This communication typically uses protocols such as TCP / IP or HTTP. Upon receiving the instructional content, the terminal transmits the data to an educational medium (e.g., a robot) and prepares for an interactive educational session. The educational medium uses a speech synthesis system and a display to present information, enabling interactive instruction.

[0070] The users, who are serious criminals, interact with an educational medium and receive instruction in an interactive format. For example, they might be asked questions such as, "Consider the impact the theft had on the victim," and the dialogue progresses to deepen their ethical reflection. During this time, the user's responses and statements are recorded on the device, and this data is transmitted to the server in real time.

[0071] The server analyzes the collected response data using tools like Python's Scikit-learn to improve future instruction. This makes it possible to continuously provide instruction optimized for each individual user, and is expected to reduce the recidivism rate of serious offenders.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server connects to an authenticated database within the prison to retrieve behavioral history, psychological evaluation results, and personal information of serious offenders. The input consists of various data from the database, and the output is the collected, unprocessed dataset. In this process, a database management system (e.g., MySQL) is used to execute SQL queries and extract the necessary information.

[0075] Step 2:

[0076] The server preprocesses the collected data, including imputing missing values, standardizing the data, and encoding categorical variables. The input is an unprocessed dataset, and the output is formatted data that can be analyzed by a generative AI model. Specifically, the Python Pandas library is used to clean and format the data.

[0077] Step 3:

[0078] The server runs a generative AI model based on the formatted data. The model used here is a large-scale language model that generates individual instructional content in the form of prompt sentences as input. The input consists of formatted data and prompt sentences (e.g., "Create an ethics education scenario based on the user's personal history"), and the output is the generated instructional content.

[0079] Step 4:

[0080] The server sends the generated instructional content to the prison terminal. The input is the instructional content, and the output is the completion of the data transmission to the terminal. Communication protocols such as TCP / IP and HTTP are used in this stage, and the data is sent to the terminal via the internet.

[0081] Step 5:

[0082] The terminal receives the instructional content and transmits it to the educational media. This initiates the preparation for an interactive educational session. The input is the instructional content from the server, and the output is the setup of the instructional content on the educational media. The educational media uses a speech synthesis system and a display to present information to the user.

[0083] Step 6:

[0084] Users receive instruction through an educational medium. The instruction proceeds in an interactive format, with questions and explanations based on the instructional content. For example, the user might be asked, "Consider the impact the theft had on the victim." The input is the question from the educational medium, and the output is the user's response.

[0085] Step 7:

[0086] The terminal records user responses and statements and sends this data to a server. Input is user response data, and output is the completion of data transmission to the server. Recording functions and text logs are used, and responses are saved in real time.

[0087] Step 8:

[0088] The server analyzes recorded response data to help improve new teaching content. The input is response data, and the output is a plan for improving the next lesson. Tools such as Scikit-learn are used for data analysis to gain insights useful for future lessons.

[0089] (Application Example 1)

[0090] 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."

[0091] In modern organizations, employee ethics education is crucial, but there is a lack of mechanisms to provide appropriate, individualized support. Employees face diverse ethical dilemmas, and uniform educational methods are insufficient. Furthermore, there is a need for means to continuously evaluate changes in employee behavior and flexibly improve educational content.

[0092] 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.

[0093] In this invention, the server includes means for running a generative AI model to generate individual counseling and guidance content, means for distributing the generated counseling content to electronic devices within the organization, means for conducting interactive education based on the distributed guidance content and recording responses during the education, and means for analyzing the recorded response data and using it to improve the content of the next guidance session. This enables flexible ethical education with personalized information.

[0094] A "generative AI model" is an artificial intelligence program that generates content aligned with a specific purpose based on input data.

[0095] An "educational machine" is a device used to conduct interactive education and record user responses.

[0096] "Personalized information" refers to information collected based on the behavioral history and evaluation data of a specific individual.

[0097] "Preprocessing" refers to the process of preparing collected data into a format that can be analyzed by the generating AI model.

[0098] "Ethics education" refers to educational content designed to deepen employees' understanding of ethical situations they may face and to encourage them to make appropriate judgments.

[0099] "Electronic devices" are devices used for distributing information and presenting educational content.

[0100] "Means of recording responses" refers to methods of saving user reactions as data in an interactive educational process.

[0101] The invention will now be described in terms of its implementation. This system aims to provide personalized ethics education to employees within an organization using a generative AI model.

[0102] First, the server collects employee-related information from the organization's database. This information includes employee behavioral history and past performance data. This data is preprocessed and formatted so that it can be effectively analyzed by generative AI models. Data preprocessing libraries such as 'pandas' are used for this preprocessing.

[0103] Next, the server runs a generative AI model and generates individualized ethical education content for each employee based on the collected data. Generative AI models such as OpenAI's GPT-3 (registered trademark) are used for content generation, and the prompt message is in the format of "Employee ID: X, Please create an ethical dilemma scenario."

[0104] The generated training content is delivered to electronic devices deployed within the organization—for example, smartphones and tablets—and presented to employees. This allows employees to participate in interactive training sessions.

[0105] The employee, acting as the user, responds to the presented scenarios in an interactive format, and their responses are recorded. This recording includes methods for saving it to a database and uploading the data to the cloud.

[0106] Finally, the server analyzes the recorded response data and uses it to improve future training methods. Through this analysis, the effectiveness of the training content can be enhanced, and employees' ethical awareness can be deepened.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects employee information from the organization's database. This information includes employee behavioral history and performance data. The input is the database, and the server uses SQL queries to extract the necessary data. The output is raw data for preprocessing.

[0110] Step 2:

[0111] The server preprocesses the collected data. Specifically, it uses the pandas library to impute missing values ​​and normalize the data. The input is raw data, and the output is data in a format suitable for analysis. This processing improves the quality of the data.

[0112] Step 3:

[0113] The server runs a generation AI model and generates ethical education scenarios for employees based on pre-processed data. The input is the pre-processed data, which is sent to the AI ​​model along with the prompt "Employee ID: X, please create an ethical dilemma scenario." The output is the generated educational scenario.

[0114] Step 4:

[0115] The server distributes the generated training scenarios to devices within the organization. These devices are smartphones and tablets, and the scenarios are displayed through an application. The input is the generated scenario, and the output is the scenario screen displayed on the device.

[0116] Step 5:

[0117] The employee, acting as the user, responds to scenarios presented on the terminal. The employee's responses are recorded by the terminal; the input is the employee's reaction, and the output is the recorded data.

[0118] Step 6:

[0119] The server analyzes the recorded response data. This analysis utilizes data mining techniques to improve future teaching methods. The input is the recorded data, and the output is data representing proposed improvements. Through this analysis, more effective teaching content is created.

[0120] 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.

[0121] In this embodiment of the invention, the server accesses a prison database to collect detailed profile data of serious offenders. This includes behavioral history, psychological evaluation results, and personal background information. The server preprocesses this data and converts it into a format suitable for analysis by a generative AI model.

[0122] The server runs a generative AI model to create personalized counseling and instruction content. This system then transmits the generated instruction content to terminals installed within the prison. The terminals then transmit the received instruction content to educational equipment for preparation.

[0123] As part of the educational machine, it is equipped with an emotion engine. This emotion engine analyzes the user's, or serious criminal's, facial expressions, tone of voice, and speech patterns to recognize their emotional state in real time.

[0124] During the educational session, the user interacts with the educational machine and receives instruction. Throughout this process, the machine dynamically adjusts interactive questions and scenarios based on the user's emotional responses. For example, if the user shows confusion or discomfort, the machine adjusts its pace and is programmed to deliver ethical lessons in a more easily understandable way.

[0125] For example, if a scenario related to a user's past violent behavior is presented, the emotional engine, upon sensing the user's tension, will slow down the pace of the dialogue and use reassuring language to encourage introspection. In this way, more nuanced guidance is possible.

[0126] The device sends user emotional data recorded during the session to the server. The server analyzes this data and uses it to improve the content and strategy of future sessions based on individual emotional responses.

[0127] Through this embodiment, by incorporating an emotional engine, it is possible to provide flexible guidance tailored to the condition of each serious offender, further promoting introspection and the improvement of ethical awareness.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server accesses the prison database, collects the behavioral history, psychological evaluations, and personal information of serious offenders, and converts this data into a format suitable for analysis using data preprocessing tools.

[0131] Step 2:

[0132] The server runs a generative AI model and uses pre-processed data to generate individual counseling and guidance content. This guidance content includes scenarios that incorporate the victim's perspective, with a focus on ethical education.

[0133] Step 3:

[0134] The server transmits the generated instructional content to terminals within the prison. The terminals receive this content and prepare for the session to be conducted by the educational machine.

[0135] Step 4:

[0136] The user interacts with the educational machine and participates in an interactive educational session. During this session, an emotion engine built into the educational machine analyzes the user's facial expressions and voice in real time to recognize their emotional state.

[0137] Step 5:

[0138] The educational machine adjusts interactive questions and scenarios based on the user's emotional responses to help them reflect more deeply. For example, if the user shows confusion, the educational machine will rephrase the question to aid understanding.

[0139] Step 6:

[0140] The device sends user emotion data and responses recorded during the session to the server.

[0141] Step 7:

[0142] The server analyzes the received data and generates feedback to optimize the content of the next lesson based on the recorded emotions and reactions.

[0143] (Example 2)

[0144] 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".

[0145] Education and counseling for individuals with specific backgrounds or experiences presents a challenge because general approaches often fail to reflect their individual emotions and levels of understanding. Dynamic instruction that considers emotional responses is particularly difficult, highlighting the need for individualized guidance.

[0146] 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.

[0147] In this invention, the server includes means for acquiring and organizing individual person background information from a matching database, means for running a generation AI model to generate individual counseling and guidance content, and means for distributing the generated counseling content to each location for provision. This makes it possible to provide emotionally adapted, interactive education and counseling tailored to each individual and to optimize the content of the next guidance session.

[0148] "Individual person background information" refers to all information related to a specific individual's past actions, behaviors, and background.

[0149] A "matching database" is a system that stores various types of information and provides a collection of information that allows for data retrieval and comparison based on specific conditions.

[0150] A "generative AI model" refers to an artificial intelligence algorithm designed to analyze data and output results or predictions based on a specific task.

[0151] "Counseling and guidance content" refers to programs and activities aimed at providing psychological support and educational intervention to individual people.

[0152] "Distributing to each location for provision" means sending the generated information and instructional content to the locations and devices where it is needed, making it available for use.

[0153] "Interactive education" refers to an educational process that progresses through two-way communication with the recipient, and the content is often adjusted based on the recipient's responses.

[0154] In implementing this invention, the server plays a crucial role. First, the server uses a matching database system to collect and organize individual biographical information. This database system includes software that can store and quickly search and retrieve data in various formats. For example, a business database management system is suitable.

[0155] The server uses a generative AI model based on the compiled history information to create personalized counseling and guidance content. The generative AI model employs a natural language processing-based analysis algorithm, specifically applying common language generation techniques. An example of a prompt is the instruction to "generate personalized counseling content" given to the model.

[0156] The generated instructional content is distributed from the server to terminals at each location via the network. The terminals receive the data accurately through a secure communication protocol and transmit it to the educational implementation device. This educational implementation device includes an audio playback system and an interactive user interface, on which users receive education and counseling.

[0157] As part of the educational implementation device, it is equipped with an emotion analysis engine that analyzes the user's emotional state in real time. The user reacts during the lesson, and their facial expressions, tone of voice, and word choice are recorded as data by the emotion analysis engine. For example, if the user becomes emotionally confused, the educational implementation device adjusts the pace of the conversation and provides instruction in an easily understandable format.

[0158] This allows users to have a flexible educational experience that responds to their own emotions. As an example of a prompt, the AI ​​model is given the instruction, "Suggest the most effective way to communicate in this situation." This mechanism makes it possible to promote more effective introspection and improvement of ethical awareness.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The server retrieves and organizes individual biographical information from a matching database. The input consists of basic identification information about the individual. Based on this, it uses SQL queries to search the database for relevant information. The output is organized profile data. This profile data includes behavioral history and psychological evaluation results, and missing values ​​are imputed and outliers are corrected.

[0162] Step 2:

[0163] The server runs the AI ​​model using the prepared data. The input is the profile data generated in Step 1. This data, along with prompts, is input to the AI ​​model and used to generate counseling and guidance content. The output is counseling guidelines and guidance scenarios tailored to each individual. Natural language processing technology is applied to generate personalized content.

[0164] Step 3:

[0165] The server distributes the generated instructional content to the terminal via the network. The input is the instructional content generated in step 2. This is sent to the terminal using a secure communication protocol (e.g., HTTPS). The output is data converted into a format that the educational implementation device can receive. The terminal checks the received data and performs error checking.

[0166] Step 4:

[0167] The terminal transmits instructional content to the educational implementation device and prepares it to start the user's educational session. The input is the instructional content delivered from the server. The terminal instructs the educational implementation device to configure the interface and prepare media files. The output indicates that the implementation device is ready to successfully start the educational session.

[0168] Step 5:

[0169] The user interacts with the educational device and receives instruction. The emotion analysis engine detects the user's facial expressions, tone of voice, and language use in real time. The input is the user's emotional responses and behaviors, and the analysis engine converts this emotional state into digital data. The output is real-time emotional state information of the user, which is recorded sequentially on the terminal.

[0170] Step 6:

[0171] The terminal sends the recorded user emotion data to the server. The input is a dataset of emotional state information recorded in step 5. This is transferred to the server for analysis. The output is feedback data to optimize the content of the next session. The server uses this to provide a foundation for generating more effective counseling content.

[0172] (Application Example 2)

[0173] 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".

[0174] In typical work environments, there is a challenge in understanding workers' fatigue and stress levels in real time and providing individualized guidance to promote efficient and safe work. Traditional guidance methods have limited the ability to respond promptly to the individual conditions and circumstances of each worker, thus limiting improvements in work efficiency and safety.

[0175] 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.

[0176] In this invention, the server includes means for executing a generation AI model to generate individual instruction content, means for distributing the generated instruction content to educational equipment, means for conducting interactive instruction based on the distributed instruction content and observing the worker's state, means for analyzing the observed state data to improve the next instruction content, means for analyzing the worker's facial expressions and voice in the work environment and evaluating the state in real time, and means for providing individualized instruction based on the evaluation results and visualizing it through a display device. This makes it possible to instantly grasp the worker's state and provide appropriate responses, thereby improving work efficiency and safety.

[0177] A "generative AI model" is a computational model that generates new information based on data, and is a technology that provides output optimized for a specific purpose.

[0178] "Instructional content" refers to the information and procedures provided to achieve specific goals, and is tailored to the individual learner and their environment.

[0179] "Educational equipment" refers to devices and equipment used for learning and training purposes, and is the totality of hardware and software that supports the transmission of information and the development of skills.

[0180] "To distribute" means to send generated information to a specific device or user, with the aim of ensuring that the information reaches its destination accurately and quickly.

[0181] "Interactive" refers to the characteristic where the user and the system interact with each other, and communication takes place through information and actions.

[0182] "Observing" means carefully monitoring the state and changes of an object or environment, acquiring information based on the results, and making judgments and taking actions according to the purpose.

[0183] "Real-time" refers to the instantaneous processing and communication of data, reflecting the current state and situation without delay.

[0184] "Visualization" refers to the process of representing information and data visually and displaying them in a way that users can intuitively understand.

[0185] To implement this invention, a system is needed that can grasp the state of workers in the work environment in real time and provide individualized guidance based on that. The server first runs a generative AI model and generates individual guidance content based on the data. The generative AI model used here is designed to collect and preprocess the worker's facial expressions, voice, and other movement data to create guidance that is suitable for each individual worker.

[0186] The generated instructional content is distributed via a network to educational equipment. This educational equipment includes a display device, such as smart glasses, to allow workers to visually confirm the instruction. This educational equipment observes the worker's state in real time, analyzes their emotions using an emotion engine, and provides appropriate instructional content.

[0187] As a concrete example, let's say there is a worker A working the night shift at a factory. The server evaluates worker A's condition, and if it analyzes that worker A is feeling fatigued or stressed, it generates a message saying, "Take a few minutes' break and rehydrate," and notifies worker A via smart glasses. This message is appropriately adjusted based on data collected in real time by the generating AI model.

[0188] An example of a prompt is, "Design an assistant system that recognizes the emotions of factory workers and improves work efficiency." This prompt is used as input to a generating AI model, which then performs the necessary data processing and generates the instruction content.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server collects facial image and audio data of workers in their work environment from smart glasses. This data is used as input, and preprocessed using facial recognition and speech recognition technologies to extract features from each. During this conversion process, emotional states are identified from the facial data, and voice tone and speech patterns are identified from the audio data.

[0192] Step 2:

[0193] The server inputs pre-processed features into the generating AI model to evaluate the worker's current emotional state. This prompt instructs the AI ​​model to "evaluate the worker's current state and generate necessary guidance." Based on the input data, the AI ​​model calculates the worker's emotional state and generates appropriate guidance.

[0194] Step 3:

[0195] The generated instruction content is delivered from the server to the terminal (smart glasses). The smart glasses visualize the instruction content and display it on the screen so that the worker can check it. For example, if the worker shows signs of fatigue, an alert such as "We recommend taking a short break" is sent.

[0196] Step 4:

[0197] The terminal observes the worker's reactions and sends that data back to the server. For example, data is collected to determine whether the worker took a break as recommended. This includes information monitored in real time again through facial expressions and voice.

[0198] Step 5:

[0199] The server analyzes the collected response data and uses it to improve the content of future lessons and generated prompts. This data is then fed back into the generative AI model and used for training and tuning to improve the model's performance.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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".

[0216] In one embodiment of the invention, the server first accesses a database within an authenticated prison and collects various data about serious offenders. This includes behavioral history, psychological evaluation results, and personal information. This data is preprocessed and prepared in a format that can be effectively analyzed by the generated AI model.

[0217] Next, the server runs a generative AI model to generate individualized counseling and guidance content based on the collected data. This process sets up scenarios for providing education tailored to each serious offender and includes content that promotes learning about ethics and morality.

[0218] The server transmits the generated instructional content to terminals within the prison. The terminals then transmit the content to educational machines (robots) and prepare for interactive educational sessions.

[0219] The user, a serious offender, physically interacts with the educational machine and receives instruction. The educational machine conducts the education in an interactive format, following generated scenarios and engaging in question-and-answer sessions that encourage the user to reconsider their lacking ethical perspectives and the victim's point of view.

[0220] As a concrete example, regarding a past theft committed by the user, the educational machine asks questions such as, "What did the stolen item mean to the victim?" and uses a resonant voice scenario to convey the victim's feelings. During this process, the user's responses and statements are recorded on the device and sent to the server.

[0221] The recorded response data is analyzed on a server and used to improve the content and methods of future lessons. This strengthens the system for providing more appropriate education while maintaining individuality.

[0222] Through this embodiment, it is possible to enhance ethical reflection and reduce recidivism rates after reintegration into society by providing interactive guidance tailored to individual offenders.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The server accesses the prison database and collects behavioral history, psychological evaluation data, and personal data of serious offenders. This data is preprocessed into a format suitable for analysis by generative AI models.

[0226] Step 2:

[0227] The server runs a generative AI model, analyzes pre-processed data, and generates individualized counseling and guidance content. This guidance content includes scenarios incorporating ethical education and the victim's perspective.

[0228] Step 3:

[0229] The server transmits the generated instructional content to terminals within the prison. The terminals review the received instructional content and prepare it for use with educational equipment.

[0230] Step 4:

[0231] The user, a serious offender, interacts with an educational machine to participate in an educational session. The educational machine conducts interactive education based on generated scenarios, presenting the user with questions and playing audio scenarios.

[0232] Step 5:

[0233] The device records the user's responses during the educational session, including the content of the user's answers and their response speed.

[0234] Step 6:

[0235] The device sends recorded response data to the server. The server analyzes this data and generates feedback to be used to improve the next educational session.

[0236] (Example 1)

[0237] 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."

[0238] Traditional education systems have provided a uniform approach to ethical and moral education for serious offenders, making it difficult to provide appropriate feedback based on individual characteristics and past behavioral history. Therefore, there is a need for individualized education that can prevent recidivism.

[0239] 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.

[0240] In this invention, the server includes means for transmitting generated instruction content to a medium via a communication terminal, means for performing interactive instruction based on the transmitted instruction content and saving the actions taken during instruction, means for analyzing the saved action data and using it to improve the content of the next instruction, means for collecting and processing individualized information for information analysis, and means for creating individualized counseling and instruction content using generative AI technology. This makes it possible to provide appropriate ethical and moral education tailored to individual circumstances and contribute to preventing recidivism.

[0241] "Generative AI technology" is a technology that uses artificial intelligence to automatically generate content and data tailored to specific purposes.

[0242] A "communication terminal" is a device used for sending and receiving data, and is a device that enables the transmission of information over a network.

[0243] A "medium" refers to a physical or electronic device or system used as a means of transmitting or storing information.

[0244] "Interactive instruction" is an educational process in which the student and the instructional system communicate with each other as the process progresses.

[0245] "Behavioral data" refers to data that records the reactions and behaviors exhibited by participants during the instruction process.

[0246] "Personalized information" refers to information that includes unique data and attributes related to a specific individual.

[0247] "Counseling" is the act of providing psychological or behavioral support to participants through advice and guidance.

[0248] Modes for carrying out the invention

[0249] In this invention, the server first accesses an authenticated database within the prison to collect various data on serious offenders. This data includes behavioral history, psychological evaluation results, and personal information. A database management system is used for data collection, such as MySQL. The collected data is preprocessed using the Pandas library and converted into a format that can be effectively analyzed by the generative AI model.

[0250] Next, the server runs a generative AI model to generate individual counseling and guidance content based on the pre-processed data. A large-scale language model (e.g., OpenAI GPT) is used in this step. By giving the AI ​​model specific instructions such as "Create an ethics education scenario based on the user's individual history" as a prompt, appropriate guidance content is generated.

[0251] The generated instructional content is transmitted from the server to terminals installed within the prison. This communication typically uses protocols such as TCP / IP or HTTP. Upon receiving the instructional content, the terminal transmits the data to an educational medium (e.g., a robot) and prepares for an interactive educational session. The educational medium uses a speech synthesis system and a display to present information, enabling interactive instruction.

[0252] The users, who are serious criminals, interact with an educational medium and receive instruction in an interactive format. For example, they might be asked questions such as, "Consider the impact the theft had on the victim," and the dialogue progresses to deepen their ethical reflection. During this time, the user's responses and statements are recorded on the device, and this data is transmitted to the server in real time.

[0253] The server analyzes the collected response data using tools like Python's Scikit-learn to improve future instruction. This makes it possible to continuously provide instruction optimized for each individual user, and is expected to reduce the recidivism rate of serious offenders.

[0254] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0255] Step 1:

[0256] The server connects to an authenticated database within the prison to retrieve behavioral history, psychological evaluation results, and personal information of serious offenders. The input consists of various data from the database, and the output is the collected, unprocessed dataset. In this process, a database management system (e.g., MySQL) is used to execute SQL queries and extract the necessary information.

[0257] Step 2:

[0258] The server preprocesses the collected data, including imputing missing values, standardizing the data, and encoding categorical variables. The input is an unprocessed dataset, and the output is formatted data that can be analyzed by a generative AI model. Specifically, the Python Pandas library is used to clean and format the data.

[0259] Step 3:

[0260] The server runs a generative AI model based on the formatted data. The model used here is a large-scale language model that generates individual instructional content in the form of prompt sentences as input. The input consists of formatted data and prompt sentences (e.g., "Create an ethics education scenario based on the user's personal history"), and the output is the generated instructional content.

[0261] Step 4:

[0262] The server sends the generated instructional content to the prison terminal. The input is the instructional content, and the output is the completion of the data transmission to the terminal. Communication protocols such as TCP / IP and HTTP are used in this stage, and the data is sent to the terminal via the internet.

[0263] Step 5:

[0264] The terminal receives the instructional content and transmits it to the educational media. This initiates the preparation for an interactive educational session. The input is the instructional content from the server, and the output is the setup of the instructional content on the educational media. The educational media uses a speech synthesis system and a display to present information to the user.

[0265] Step 6:

[0266] Users receive instruction through an educational medium. The instruction proceeds in an interactive format, with questions and explanations based on the instructional content. For example, the user might be asked, "Consider the impact the theft had on the victim." The input is the question from the educational medium, and the output is the user's response.

[0267] Step 7:

[0268] The terminal records user responses and statements and sends this data to a server. Input is user response data, and output is the completion of data transmission to the server. Recording functions and text logs are used, and responses are saved in real time.

[0269] Step 8:

[0270] The server analyzes recorded response data to help improve new teaching content. The input is response data, and the output is a plan for improving the next lesson. Tools such as Scikit-learn are used for data analysis to gain insights useful for future lessons.

[0271] (Application Example 1)

[0272] 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."

[0273] In modern organizations, employee ethics education is crucial, but there is a lack of mechanisms to provide appropriate, individualized support. Employees face diverse ethical dilemmas, and uniform educational methods are insufficient. Furthermore, there is a need for means to continuously evaluate changes in employee behavior and flexibly improve educational content.

[0274] 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.

[0275] In this invention, the server includes means for running a generative AI model to generate individual counseling and guidance content, means for distributing the generated counseling content to electronic devices within the organization, means for conducting interactive education based on the distributed guidance content and recording responses during the education, and means for analyzing the recorded response data and using it to improve the content of the next guidance session. This enables flexible ethical education with personalized information.

[0276] A "generative AI model" is an artificial intelligence program that generates content aligned with a specific purpose based on input data.

[0277] An "educational machine" is a device used to conduct interactive education and record user responses.

[0278] "Personalized information" refers to information collected based on the behavioral history and evaluation data of a specific individual.

[0279] "Preprocessing" refers to the process of preparing collected data into a format that can be analyzed by the generating AI model.

[0280] "Ethical education" refers to educational content that deepens employees' understanding of potential ethical situations they may face and promotes appropriate judgment.

[0281] "Electronic device" refers to a device used for distributing information and presenting educational content.

[0282] "Means for recording responses" refers to a method of storing users' reactions as data in an interactive educational process.

[0283] The form for implementing the invention will be described. This system aims to provide individualized ethical education to employees within an organization using a generative AI model.

[0284] First, the server collects information related to employees from the organization's database. Information collection includes employees' action histories and past evaluation data, etc. This data is preprocessed and organized into a format that can be effectively analyzed by the generative AI model. For preprocessing, libraries such as 'pandas', a data preprocessing library, are used.

[0285] Next, the server runs the generative AI model and generates individualized ethical education content for each employee based on the collected data. For content generation, generative AI models such as OpenAI's GPT-3 are used, and a format like "Employee ID: X, please create a scenario of an ethical dilemma" is used as the prompt text.

[0286] The generated educational content is distributed to electronic devices deployed within the organization, such as smartphones and tablets, and presented to employees. This enables employees to receive an interactive educational session.

[0287] The employee, who is the user, responds to the presented scenario in an interactive manner, and their reaction is recorded. This recording includes methods of storing in the database and uploading data to the cloud.

[0288] Finally, the server analyzes the recorded response data and uses it to improve future training methods. Through this analysis, the effectiveness of the training content can be enhanced, and employees' ethical awareness can be deepened.

[0289] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0290] Step 1:

[0291] The server collects employee information from the organization's database. This information includes employee behavioral history and performance data. The input is the database, and the server uses SQL queries to extract the necessary data. The output is raw data for preprocessing.

[0292] Step 2:

[0293] The server preprocesses the collected data. Specifically, it uses the pandas library to impute missing values ​​and normalize the data. The input is raw data, and the output is data in a format suitable for analysis. This processing improves the quality of the data.

[0294] Step 3:

[0295] The server runs a generation AI model and generates ethical education scenarios for employees based on pre-processed data. The input is the pre-processed data, which is sent to the AI ​​model along with the prompt "Employee ID: X, please create an ethical dilemma scenario." The output is the generated educational scenario.

[0296] Step 4:

[0297] The server distributes the generated training scenarios to devices within the organization. These devices are smartphones and tablets, and the scenarios are displayed through an application. The input is the generated scenario, and the output is the scenario screen displayed on the device.

[0298] Step 5:

[0299] The employee, acting as the user, responds to scenarios presented on the terminal. The employee's responses are recorded by the terminal; the input is the employee's reaction, and the output is the recorded data.

[0300] Step 6:

[0301] The server analyzes the recorded response data. This analysis utilizes data mining techniques to improve future teaching methods. The input is the recorded data, and the output is data representing proposed improvements. Through this analysis, more effective teaching content is created.

[0302] 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.

[0303] In this embodiment of the invention, the server accesses a prison database to collect detailed profile data of serious offenders. This includes behavioral history, psychological evaluation results, and personal background information. The server preprocesses this data and converts it into a format suitable for analysis by a generative AI model.

[0304] The server runs a generative AI model to create personalized counseling and instruction content. This system then transmits the generated instruction content to terminals installed within the prison. The terminals then transmit the received instruction content to educational equipment for preparation.

[0305] As part of the educational machine, it is equipped with an emotion engine. This emotion engine analyzes the user's, or serious criminal's, facial expressions, tone of voice, and speech patterns to recognize their emotional state in real time.

[0306] During the education session, the user faces the educational machine and receives guidance. In this process, the educational machine dynamically adjusts interactive questions and scenarios based on the user's emotional reactions. For example, if the user shows confusion or discomfort, the educational machine is programmed to adjust the pace and convey ethical lessons in a more understandable form.

[0307] As a specific example, when a scenario related to violent acts committed by the user in the past is presented, if the emotion engine senses the user's state of tension, the educational machine slows down the tempo of the conversation and uses reassuring words to prompt introspection. In this way, more detailed guidance is made possible.

[0308] The terminal sends the user's emotional data recorded during the session to the server. The server analyzes this data and uses it to improve the content and strategies of the next guidance based on individual emotional reactions.

[0309] Through this embodiment, by incorporating an emotion engine, it is possible to provide flexible guidance tailored to the state of each serious offender, and further promote introspection and the improvement of ethics.

[0310] The following describes the processing flow.

[0311] Step 1:

[0312] The server accesses the prison database, collects the action history, psychological evaluation, and personal information of serious offenders, and converts them into a form suitable for analysis using data preprocessing means.

[0313] Step 2:

[0314] The server runs the generative AI model and uses the preprocessed data to generate individual counseling and guidance content. This guidance content includes scenarios that incorporate the victim's perspective with a focus on ethical education.

[0315] Step 3:

[0316] The server transmits the generated instructional content to terminals within the prison. The terminals receive this content and prepare for the session to be conducted by the educational machine.

[0317] Step 4:

[0318] The user interacts with the educational machine and participates in an interactive educational session. During this session, an emotion engine built into the educational machine analyzes the user's facial expressions and voice in real time to recognize their emotional state.

[0319] Step 5:

[0320] The educational machine adjusts interactive questions and scenarios based on the user's emotional responses to help them reflect more deeply. For example, if the user shows confusion, the educational machine will rephrase the question to aid understanding.

[0321] Step 6:

[0322] The device sends user emotion data and responses recorded during the session to the server.

[0323] Step 7:

[0324] The server analyzes the received data and generates feedback to optimize the content of the next lesson based on the recorded emotions and reactions.

[0325] (Example 2)

[0326] 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".

[0327] Education and counseling for individuals with specific backgrounds or experiences presents a challenge because general approaches often fail to reflect their individual emotions and levels of understanding. Dynamic instruction that considers emotional responses is particularly difficult, highlighting the need for individualized guidance.

[0328] 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.

[0329] In this invention, the server includes means for acquiring and organizing individual person background information from a matching database, means for running a generation AI model to generate individual counseling and guidance content, and means for distributing the generated counseling content to each location for provision. This makes it possible to provide emotionally adapted, interactive education and counseling tailored to each individual and to optimize the content of the next guidance session.

[0330] "Individual person background information" refers to all information related to a specific individual's past actions, behaviors, and background.

[0331] A "matching database" is a system that stores various types of information and provides a collection of information that allows for data retrieval and comparison based on specific conditions.

[0332] A "generative AI model" refers to an artificial intelligence algorithm designed to analyze data and output results or predictions based on a specific task.

[0333] "Counseling and guidance content" refers to programs and activities aimed at providing psychological support and educational intervention to individual people.

[0334] "Distributing to each location for provision" means sending the generated information and instructional content to the locations and devices where it is needed, making it available for use.

[0335] "Interactive education" refers to an educational process that progresses through two-way communication with the recipient, and the content is often adjusted based on the recipient's responses.

[0336] In implementing this invention, the server plays a crucial role. First, the server uses a matching database system to collect and organize individual biographical information. This database system includes software that can store and quickly search and retrieve data in various formats. For example, a business database management system is suitable.

[0337] The server uses a generative AI model based on the compiled history information to create personalized counseling and guidance content. The generative AI model employs a natural language processing-based analysis algorithm, specifically applying common language generation techniques. An example of a prompt is the instruction to "generate personalized counseling content" given to the model.

[0338] The generated instructional content is distributed from the server to terminals at each location via the network. The terminals receive the data accurately through a secure communication protocol and transmit it to the educational implementation device. This educational implementation device includes an audio playback system and an interactive user interface, on which users receive education and counseling.

[0339] As part of the educational implementation device, it is equipped with an emotion analysis engine that analyzes the user's emotional state in real time. The user reacts during the lesson, and their facial expressions, tone of voice, and word choice are recorded as data by the emotion analysis engine. For example, if the user becomes emotionally confused, the educational implementation device adjusts the pace of the conversation and provides instruction in an easily understandable format.

[0340] This allows users to have a flexible educational experience that responds to their own emotions. As an example of a prompt, the AI ​​model is given the instruction, "Suggest the most effective way to communicate in this situation." This mechanism makes it possible to promote more effective introspection and improvement of ethical awareness.

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] The server retrieves and organizes individual biographical information from a matching database. The input consists of basic identification information about the individual. Based on this, it uses SQL queries to search the database for relevant information. The output is organized profile data. This profile data includes behavioral history and psychological evaluation results, and missing values ​​are imputed and outliers are corrected.

[0344] Step 2:

[0345] The server runs the AI ​​model using the prepared data. The input is the profile data generated in Step 1. This data, along with prompts, is input to the AI ​​model and used to generate counseling and guidance content. The output is counseling guidelines and guidance scenarios tailored to each individual. Natural language processing technology is applied to generate personalized content.

[0346] Step 3:

[0347] The server distributes the generated instructional content to the terminal via the network. The input is the instructional content generated in step 2. This is sent to the terminal using a secure communication protocol (e.g., HTTPS). The output is data converted into a format that the educational implementation device can receive. The terminal checks the received data and performs error checking.

[0348] Step 4:

[0349] The terminal transmits instructional content to the educational implementation device and prepares it to start the user's educational session. The input is the instructional content delivered from the server. The terminal instructs the educational implementation device to configure the interface and prepare media files. The output indicates that the implementation device is ready to successfully start the educational session.

[0350] Step 5:

[0351] The user interacts with the educational device and receives instruction. The emotion analysis engine detects the user's facial expressions, tone of voice, and language use in real time. The input is the user's emotional responses and behaviors, and the analysis engine converts this emotional state into digital data. The output is real-time emotional state information of the user, which is recorded sequentially on the terminal.

[0352] Step 6:

[0353] The terminal sends the recorded user emotion data to the server. The input is a dataset of emotional state information recorded in step 5. This is transferred to the server for analysis. The output is feedback data to optimize the content of the next session. The server uses this to provide a foundation for generating more effective counseling content.

[0354] (Application Example 2)

[0355] 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."

[0356] In typical work environments, there is a challenge in understanding workers' fatigue and stress levels in real time and providing individualized guidance to promote efficient and safe work. Traditional guidance methods have limited the ability to respond promptly to the individual conditions and circumstances of each worker, thus limiting improvements in work efficiency and safety.

[0357] 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.

[0358] In this invention, the server includes means for executing a generation AI model to generate individual instruction content, means for distributing the generated instruction content to educational equipment, means for conducting interactive instruction based on the distributed instruction content and observing the worker's state, means for analyzing the observed state data to improve the next instruction content, means for analyzing the worker's facial expressions and voice in the work environment and evaluating the state in real time, and means for providing individualized instruction based on the evaluation results and visualizing it through a display device. This makes it possible to instantly grasp the worker's state and provide appropriate responses, thereby improving work efficiency and safety.

[0359] A "generative AI model" is a computational model that generates new information based on data, and is a technology that provides output optimized for a specific purpose.

[0360] "Instructional content" refers to the information and procedures provided to achieve specific goals, and is tailored to the individual learner and their environment.

[0361] "Educational equipment" refers to devices and equipment used for learning and training purposes, and is the totality of hardware and software that supports the transmission of information and the development of skills.

[0362] "To distribute" means to send generated information to a specific device or user, with the aim of ensuring that the information reaches its destination accurately and quickly.

[0363] "Interactive" refers to the characteristic where the user and the system interact with each other, and communication takes place through information and actions.

[0364] "Observing" means carefully monitoring the state and changes of an object or environment, acquiring information based on the results, and making judgments and taking actions according to the purpose.

[0365] "Real-time" refers to the instantaneous processing and communication of data, reflecting the current state and situation without delay.

[0366] "Visualization" refers to the process of representing information and data visually and displaying them in a way that users can intuitively understand.

[0367] To implement this invention, a system is needed that can grasp the state of workers in the work environment in real time and provide individualized guidance based on that. The server first runs a generative AI model and generates individual guidance content based on the data. The generative AI model used here is designed to collect and preprocess the worker's facial expressions, voice, and other movement data to create guidance that is suitable for each individual worker.

[0368] The generated instructional content is distributed via a network to educational equipment. This educational equipment includes a display device, such as smart glasses, to allow workers to visually confirm the instruction. This educational equipment observes the worker's state in real time, analyzes their emotions using an emotion engine, and provides appropriate instructional content.

[0369] As a concrete example, let's say there is a worker A working the night shift at a factory. The server evaluates worker A's condition, and if it analyzes that worker A is feeling fatigued or stressed, it generates a message saying, "Take a few minutes' break and rehydrate," and notifies worker A via smart glasses. This message is appropriately adjusted based on data collected in real time by the generating AI model.

[0370] An example of a prompt is, "Design an assistant system that recognizes the emotions of factory workers and improves work efficiency." This prompt is used as input to a generating AI model, which then performs the necessary data processing and generates the instruction content.

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The server collects facial image and audio data of workers in their work environment from smart glasses. This data is used as input, and preprocessed using facial recognition and speech recognition technologies to extract features from each. During this conversion process, emotional states are identified from the facial data, and voice tone and speech patterns are identified from the audio data.

[0374] Step 2:

[0375] The server inputs pre-processed features into the generating AI model to evaluate the worker's current emotional state. This prompt instructs the AI ​​model to "evaluate the worker's current state and generate necessary guidance." Based on the input data, the AI ​​model calculates the worker's emotional state and generates appropriate guidance.

[0376] Step 3:

[0377] The generated instruction content is delivered from the server to the terminal (smart glasses). The smart glasses visualize the instruction content and display it on the screen so that the worker can check it. For example, if the worker shows signs of fatigue, an alert such as "We recommend taking a short break" is sent.

[0378] Step 4:

[0379] The terminal observes the worker's reactions and sends that data back to the server. For example, data is collected to determine whether the worker took a break as recommended. This includes information monitored in real time again through facial expressions and voice.

[0380] Step 5:

[0381] The server analyzes the collected response data and uses it to improve the content of future lessons and generated prompts. This data is then fed back into the generative AI model and used for training and tuning to improve the model's performance.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] [Third Embodiment]

[0386] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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".

[0398] In one embodiment of the invention, the server first accesses a database within an authenticated prison and collects various data about serious offenders. This includes behavioral history, psychological evaluation results, and personal information. This data is preprocessed and prepared in a format that can be effectively analyzed by the generated AI model.

[0399] Next, the server runs a generative AI model to generate individualized counseling and guidance content based on the collected data. This process sets up scenarios for providing education tailored to each serious offender and includes content that promotes learning about ethics and morality.

[0400] The server transmits the generated instructional content to terminals within the prison. The terminals then transmit the content to educational machines (robots) and prepare for interactive educational sessions.

[0401] The user, a serious offender, physically interacts with the educational machine and receives instruction. The educational machine conducts the education in an interactive format, following generated scenarios and engaging in question-and-answer sessions that encourage the user to reconsider their lacking ethical perspectives and the victim's point of view.

[0402] As a concrete example, regarding a past theft committed by the user, the educational machine asks questions such as, "What did the stolen item mean to the victim?" and uses a resonant voice scenario to convey the victim's feelings. During this process, the user's responses and statements are recorded on the device and sent to the server.

[0403] The recorded response data is analyzed on a server and used to improve the content and methods of future lessons. This strengthens the system for providing more appropriate education while maintaining individuality.

[0404] Through this embodiment, it is possible to enhance ethical reflection and reduce recidivism rates after reintegration into society by providing interactive guidance tailored to individual offenders.

[0405] The following describes the processing flow.

[0406] Step 1:

[0407] The server accesses the prison database and collects behavioral history, psychological evaluation data, and personal data of serious offenders. This data is preprocessed into a format suitable for analysis by generative AI models.

[0408] Step 2:

[0409] The server runs a generative AI model, analyzes pre-processed data, and generates individualized counseling and guidance content. This guidance content includes scenarios incorporating ethical education and the victim's perspective.

[0410] Step 3:

[0411] The server transmits the generated instructional content to terminals within the prison. The terminals review the received instructional content and prepare it for use with educational equipment.

[0412] Step 4:

[0413] The user, a serious offender, interacts with an educational machine to participate in an educational session. The educational machine conducts interactive education based on generated scenarios, presenting the user with questions and playing audio scenarios.

[0414] Step 5:

[0415] The device records the user's responses during the educational session, including the content of the user's answers and their response speed.

[0416] Step 6:

[0417] The device sends recorded response data to the server. The server analyzes this data and generates feedback to be used to improve the next educational session.

[0418] (Example 1)

[0419] 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."

[0420] Traditional education systems have provided a uniform approach to ethical and moral education for serious offenders, making it difficult to provide appropriate feedback based on individual characteristics and past behavioral history. Therefore, there is a need for individualized education that can prevent recidivism.

[0421] 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.

[0422] In this invention, the server includes means for transmitting generated instruction content to a medium via a communication terminal, means for performing interactive instruction based on the transmitted instruction content and saving the actions taken during instruction, means for analyzing the saved action data and using it to improve the content of the next instruction, means for collecting and processing individualized information for information analysis, and means for creating individualized counseling and instruction content using generative AI technology. This makes it possible to provide appropriate ethical and moral education tailored to individual circumstances and contribute to preventing recidivism.

[0423] "Generative AI technology" is a technology that uses artificial intelligence to automatically generate content and data tailored to specific purposes.

[0424] A "communication terminal" is a device used for sending and receiving data, and is a device that enables the transmission of information over a network.

[0425] A "medium" refers to a physical or electronic device or system used as a means of transmitting or storing information.

[0426] "Interactive instruction" is an educational process in which the student and the instructional system communicate with each other as the process progresses.

[0427] "Behavioral data" refers to data that records the reactions and behaviors exhibited by participants during the instruction process.

[0428] "Personalized information" refers to information that includes unique data and attributes related to a specific individual.

[0429] "Counseling" is the act of providing psychological or behavioral support to participants through advice and guidance.

[0430] Modes for carrying out the invention

[0431] In this invention, the server first accesses an authenticated database within the prison to collect various data on serious offenders. This data includes behavioral history, psychological evaluation results, and personal information. A database management system is used for data collection, such as MySQL. The collected data is preprocessed using the Pandas library and converted into a format that can be effectively analyzed by the generative AI model.

[0432] Next, the server runs a generative AI model to generate individual counseling and guidance content based on the pre-processed data. A large-scale language model (e.g., OpenAI GPT) is used in this step. By giving the AI ​​model specific instructions such as "Create an ethics education scenario based on the user's individual history" as a prompt, appropriate guidance content is generated.

[0433] The generated instructional content is transmitted from the server to terminals installed within the prison. This communication typically uses protocols such as TCP / IP or HTTP. Upon receiving the instructional content, the terminal transmits the data to an educational medium (e.g., a robot) and prepares for an interactive educational session. The educational medium uses a speech synthesis system and a display to present information, enabling interactive instruction.

[0434] The users, who are serious criminals, interact with an educational medium and receive instruction in an interactive format. For example, they might be asked questions such as, "Consider the impact the theft had on the victim," and the dialogue progresses to deepen their ethical reflection. During this time, the user's responses and statements are recorded on the device, and this data is transmitted to the server in real time.

[0435] The server analyzes the collected response data using tools like Python's Scikit-learn to improve future instruction. This makes it possible to continuously provide instruction optimized for each individual user, and is expected to reduce the recidivism rate of serious offenders.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The server connects to an authenticated database within the prison to retrieve behavioral history, psychological evaluation results, and personal information of serious offenders. The input consists of various data from the database, and the output is the collected, unprocessed dataset. In this process, a database management system (e.g., MySQL) is used to execute SQL queries and extract the necessary information.

[0439] Step 2:

[0440] The server preprocesses the collected data, including imputing missing values, standardizing the data, and encoding categorical variables. The input is an unprocessed dataset, and the output is formatted data that can be analyzed by a generative AI model. Specifically, the Python Pandas library is used to clean and format the data.

[0441] Step 3:

[0442] The server runs a generative AI model based on the formatted data. The model used here is a large-scale language model that generates individual instructional content in the form of prompt sentences as input. The input consists of formatted data and prompt sentences (e.g., "Create an ethics education scenario based on the user's personal history"), and the output is the generated instructional content.

[0443] Step 4:

[0444] The server sends the generated instructional content to the prison terminal. The input is the instructional content, and the output is the completion of the data transmission to the terminal. Communication protocols such as TCP / IP and HTTP are used in this stage, and the data is sent to the terminal via the internet.

[0445] Step 5:

[0446] The terminal receives the instructional content and transmits it to the educational media. This initiates the preparation for an interactive educational session. The input is the instructional content from the server, and the output is the setup of the instructional content on the educational media. The educational media uses a speech synthesis system and a display to present information to the user.

[0447] Step 6:

[0448] Users receive instruction through an educational medium. The instruction proceeds in an interactive format, with questions and explanations based on the instructional content. For example, the user might be asked, "Consider the impact the theft had on the victim." The input is the question from the educational medium, and the output is the user's response.

[0449] Step 7:

[0450] The terminal records user responses and statements and sends this data to a server. Input is user response data, and output is the completion of data transmission to the server. Recording functions and text logs are used, and responses are saved in real time.

[0451] Step 8:

[0452] The server analyzes recorded response data to help improve new teaching content. The input is response data, and the output is a plan for improving the next lesson. Tools such as Scikit-learn are used for data analysis to gain insights useful for future lessons.

[0453] (Application Example 1)

[0454] 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."

[0455] In modern organizations, employee ethics education is crucial, but there is a lack of mechanisms to provide appropriate, individualized support. Employees face diverse ethical dilemmas, and uniform educational methods are insufficient. Furthermore, there is a need for means to continuously evaluate changes in employee behavior and flexibly improve educational content.

[0456] 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.

[0457] In this invention, the server includes means for running a generative AI model to generate individual counseling and guidance content, means for distributing the generated counseling content to electronic devices within the organization, means for conducting interactive education based on the distributed guidance content and recording responses during the education, and means for analyzing the recorded response data and using it to improve the content of the next guidance session. This enables flexible ethical education with personalized information.

[0458] A "generative AI model" is an artificial intelligence program that generates content aligned with a specific purpose based on input data.

[0459] An "educational machine" is a device used to conduct interactive education and record user responses.

[0460] "Personalized information" refers to information collected based on the behavioral history and evaluation data of a specific individual.

[0461] "Preprocessing" refers to the process of preparing collected data into a format that can be analyzed by the generating AI model.

[0462] "Ethics education" refers to educational content designed to deepen employees' understanding of ethical situations they may face and to encourage them to make appropriate judgments.

[0463] "Electronic devices" are devices used for distributing information and presenting educational content.

[0464] "Means of recording responses" refers to methods of saving user reactions as data in an interactive educational process.

[0465] The invention will now be described in terms of its implementation. This system aims to provide personalized ethics education to employees within an organization using a generative AI model.

[0466] First, the server collects employee-related information from the organization's database. This information includes employee behavioral history and past performance data. This data is preprocessed and formatted so that it can be effectively analyzed by generative AI models. Data preprocessing libraries such as 'pandas' are used for this preprocessing.

[0467] Next, the server runs a generative AI model and generates individualized ethical education content for each employee based on the collected data. Generative AI models such as OpenAI's GPT-3 are used for content generation, and the prompt message is in the format of "Employee ID: X, Please create an ethical dilemma scenario."

[0468] The generated training content is delivered to electronic devices deployed within the organization—for example, smartphones and tablets—and presented to employees. This allows employees to participate in interactive training sessions.

[0469] The employee, acting as the user, responds to the presented scenarios in an interactive format, and their responses are recorded. This recording includes methods for saving it to a database and uploading the data to the cloud.

[0470] Finally, the server analyzes the recorded response data and uses it to improve future training methods. Through this analysis, the effectiveness of the training content can be enhanced, and employees' ethical awareness can be deepened.

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The server collects employee information from the organization's database. This information includes employee behavioral history and performance data. The input is the database, and the server uses SQL queries to extract the necessary data. The output is raw data for preprocessing.

[0474] Step 2:

[0475] The server preprocesses the collected data. Specifically, it uses the pandas library to impute missing values ​​and normalize the data. The input is raw data, and the output is data in a format suitable for analysis. This processing improves the quality of the data.

[0476] Step 3:

[0477] The server runs a generation AI model and generates ethical education scenarios for employees based on pre-processed data. The input is the pre-processed data, which is sent to the AI ​​model along with the prompt "Employee ID: X, please create an ethical dilemma scenario." The output is the generated educational scenario.

[0478] Step 4:

[0479] The server distributes the generated training scenarios to devices within the organization. These devices are smartphones and tablets, and the scenarios are displayed through an application. The input is the generated scenario, and the output is the scenario screen displayed on the device.

[0480] Step 5:

[0481] The employee, acting as the user, responds to scenarios presented on the terminal. The employee's responses are recorded by the terminal; the input is the employee's reaction, and the output is the recorded data.

[0482] Step 6:

[0483] The server analyzes the recorded response data. This analysis utilizes data mining techniques to improve future teaching methods. The input is the recorded data, and the output is data representing proposed improvements. Through this analysis, more effective teaching content is created.

[0484] 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.

[0485] In this embodiment of the invention, the server accesses a prison database to collect detailed profile data of serious offenders. This includes behavioral history, psychological evaluation results, and personal background information. The server preprocesses this data and converts it into a format suitable for analysis by a generative AI model.

[0486] The server runs a generative AI model to create personalized counseling and instruction content. This system then transmits the generated instruction content to terminals installed within the prison. The terminals then transmit the received instruction content to educational equipment for preparation.

[0487] As part of the educational machine, it is equipped with an emotion engine. This emotion engine analyzes the user's, or serious criminal's, facial expressions, tone of voice, and speech patterns to recognize their emotional state in real time.

[0488] During the educational session, the user interacts with the educational machine and receives instruction. Throughout this process, the machine dynamically adjusts interactive questions and scenarios based on the user's emotional responses. For example, if the user shows confusion or discomfort, the machine adjusts its pace and is programmed to deliver ethical lessons in a more easily understandable way.

[0489] For example, if a scenario related to a user's past violent behavior is presented, the emotional engine, upon sensing the user's tension, will slow down the pace of the dialogue and use reassuring language to encourage introspection. In this way, more nuanced guidance is possible.

[0490] The device sends user emotional data recorded during the session to the server. The server analyzes this data and uses it to improve the content and strategy of future sessions based on individual emotional responses.

[0491] Through this embodiment, by incorporating an emotional engine, it is possible to provide flexible guidance tailored to the condition of each serious offender, further promoting introspection and the improvement of ethical awareness.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] The server accesses the prison database, collects the behavioral history, psychological evaluations, and personal information of serious offenders, and converts this data into a format suitable for analysis using data preprocessing tools.

[0495] Step 2:

[0496] The server runs a generative AI model and uses pre-processed data to generate individual counseling and guidance content. This guidance content includes scenarios that incorporate the victim's perspective, with a focus on ethical education.

[0497] Step 3:

[0498] The server transmits the generated instructional content to terminals within the prison. The terminals receive this content and prepare for the session to be conducted by the educational machine.

[0499] Step 4:

[0500] The user interacts with the educational machine and participates in an interactive educational session. During this session, an emotion engine built into the educational machine analyzes the user's facial expressions and voice in real time to recognize their emotional state.

[0501] Step 5:

[0502] The educational machine adjusts interactive questions and scenarios based on the user's emotional responses to help them reflect more deeply. For example, if the user shows confusion, the educational machine will rephrase the question to aid understanding.

[0503] Step 6:

[0504] The device sends user emotion data and responses recorded during the session to the server.

[0505] Step 7:

[0506] The server analyzes the received data and generates feedback to optimize the content of the next lesson based on the recorded emotions and reactions.

[0507] (Example 2)

[0508] 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."

[0509] Education and counseling for individuals with specific backgrounds or experiences presents a challenge because general approaches often fail to reflect their individual emotions and levels of understanding. Dynamic instruction that considers emotional responses is particularly difficult, highlighting the need for individualized guidance.

[0510] 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.

[0511] In this invention, the server includes means for acquiring and organizing individual person background information from a matching database, means for running a generation AI model to generate individual counseling and guidance content, and means for distributing the generated counseling content to each location for provision. This makes it possible to provide emotionally adapted, interactive education and counseling tailored to each individual and to optimize the content of the next guidance session.

[0512] "Individual person background information" refers to all information related to a specific individual's past actions, behaviors, and background.

[0513] A "matching database" is a system that stores various types of information and provides a collection of information that allows for data retrieval and comparison based on specific conditions.

[0514] A "generative AI model" refers to an artificial intelligence algorithm designed to analyze data and output results or predictions based on a specific task.

[0515] "Counseling and guidance content" refers to programs and activities aimed at providing psychological support and educational intervention to individual people.

[0516] "Distributing to each location for provision" means sending the generated information and instructional content to the locations and devices where it is needed, making it available for use.

[0517] "Interactive education" refers to an educational process that progresses through two-way communication with the recipient, and the content is often adjusted based on the recipient's responses.

[0518] In implementing this invention, the server plays a crucial role. First, the server uses a matching database system to collect and organize individual biographical information. This database system includes software that can store and quickly search and retrieve data in various formats. For example, a business database management system is suitable.

[0519] The server uses a generative AI model based on the compiled history information to create personalized counseling and guidance content. The generative AI model employs a natural language processing-based analysis algorithm, specifically applying common language generation techniques. An example of a prompt is the instruction to "generate personalized counseling content" given to the model.

[0520] The generated instructional content is distributed from the server to terminals at each location via the network. The terminals receive the data accurately through a secure communication protocol and transmit it to the educational implementation device. This educational implementation device includes an audio playback system and an interactive user interface, on which users receive education and counseling.

[0521] As part of the educational implementation device, it is equipped with an emotion analysis engine that analyzes the user's emotional state in real time. The user reacts during the lesson, and their facial expressions, tone of voice, and word choice are recorded as data by the emotion analysis engine. For example, if the user becomes emotionally confused, the educational implementation device adjusts the pace of the conversation and provides instruction in an easily understandable format.

[0522] This allows users to have a flexible educational experience that responds to their own emotions. As an example of a prompt, the AI ​​model is given the instruction, "Suggest the most effective way to communicate in this situation." This mechanism makes it possible to promote more effective introspection and improvement of ethical awareness.

[0523] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0524] Step 1:

[0525] The server retrieves and organizes individual biographical information from a matching database. The input consists of basic identification information about the individual. Based on this, it uses SQL queries to search the database for relevant information. The output is organized profile data. This profile data includes behavioral history and psychological evaluation results, and missing values ​​are imputed and outliers are corrected.

[0526] Step 2:

[0527] The server runs the AI ​​model using the prepared data. The input is the profile data generated in Step 1. This data, along with prompts, is input to the AI ​​model and used to generate counseling and guidance content. The output is counseling guidelines and guidance scenarios tailored to each individual. Natural language processing technology is applied to generate personalized content.

[0528] Step 3:

[0529] The server distributes the generated instructional content to the terminal via the network. The input is the instructional content generated in step 2. This is sent to the terminal using a secure communication protocol (e.g., HTTPS). The output is data converted into a format that the educational implementation device can receive. The terminal checks the received data and performs error checking.

[0530] Step 4:

[0531] The terminal transmits instructional content to the educational implementation device and prepares it to start the user's educational session. The input is the instructional content delivered from the server. The terminal instructs the educational implementation device to configure the interface and prepare media files. The output indicates that the implementation device is ready to successfully start the educational session.

[0532] Step 5:

[0533] The user interacts with the educational device and receives instruction. The emotion analysis engine detects the user's facial expressions, tone of voice, and language use in real time. The input is the user's emotional responses and behaviors, and the analysis engine converts this emotional state into digital data. The output is real-time emotional state information of the user, which is recorded sequentially on the terminal.

[0534] Step 6:

[0535] The terminal sends the recorded user emotion data to the server. The input is a dataset of emotional state information recorded in step 5. This is transferred to the server for analysis. The output is feedback data to optimize the content of the next session. The server uses this to provide a foundation for generating more effective counseling content.

[0536] (Application Example 2)

[0537] 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."

[0538] In typical work environments, there is a challenge in understanding workers' fatigue and stress levels in real time and providing individualized guidance to promote efficient and safe work. Traditional guidance methods have limited the ability to respond promptly to the individual conditions and circumstances of each worker, thus limiting improvements in work efficiency and safety.

[0539] 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.

[0540] In this invention, the server includes means for executing a generation AI model to generate individual instruction content, means for distributing the generated instruction content to educational equipment, means for conducting interactive instruction based on the distributed instruction content and observing the worker's state, means for analyzing the observed state data to improve the next instruction content, means for analyzing the worker's facial expressions and voice in the work environment and evaluating the state in real time, and means for providing individualized instruction based on the evaluation results and visualizing it through a display device. This makes it possible to instantly grasp the worker's state and provide appropriate responses, thereby improving work efficiency and safety.

[0541] A "generative AI model" is a computational model that generates new information based on data, and is a technology that provides output optimized for a specific purpose.

[0542] "Instructional content" refers to the information and procedures provided to achieve specific goals, and is tailored to the individual learner and their environment.

[0543] "Educational equipment" refers to devices and equipment used for learning and training purposes, and is the totality of hardware and software that supports the transmission of information and the development of skills.

[0544] "To distribute" means to send generated information to a specific device or user, with the aim of ensuring that the information reaches its destination accurately and quickly.

[0545] "Interactive" refers to the characteristic where the user and the system interact with each other, and communication takes place through information and actions.

[0546] "Observing" means carefully monitoring the state and changes of an object or environment, acquiring information based on the results, and making judgments and taking actions according to the purpose.

[0547] "Real-time" refers to the instantaneous processing and communication of data, reflecting the current state and situation without delay.

[0548] "Visualization" refers to the process of representing information and data visually and displaying them in a way that users can intuitively understand.

[0549] To implement this invention, a system is needed that can grasp the state of workers in the work environment in real time and provide individualized guidance based on that. The server first runs a generative AI model and generates individual guidance content based on the data. The generative AI model used here is designed to collect and preprocess the worker's facial expressions, voice, and other movement data to create guidance that is suitable for each individual worker.

[0550] The generated instructional content is distributed via a network to educational equipment. This educational equipment includes a display device, such as smart glasses, to allow workers to visually confirm the instruction. This educational equipment observes the worker's state in real time, analyzes their emotions using an emotion engine, and provides appropriate instructional content.

[0551] As a concrete example, let's say there is a worker A working the night shift at a factory. The server evaluates worker A's condition, and if it analyzes that worker A is feeling fatigued or stressed, it generates a message saying, "Take a few minutes' break and rehydrate," and notifies worker A via smart glasses. This message is appropriately adjusted based on data collected in real time by the generating AI model.

[0552] An example of a prompt is, "Design an assistant system that recognizes the emotions of factory workers and improves work efficiency." This prompt is used as input to a generating AI model, which then performs the necessary data processing and generates the instruction content.

[0553] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0554] Step 1:

[0555] The server collects facial image and audio data of workers in their work environment from smart glasses. This data is used as input, and preprocessed using facial recognition and speech recognition technologies to extract features from each. During this conversion process, emotional states are identified from the facial data, and voice tone and speech patterns are identified from the audio data.

[0556] Step 2:

[0557] The server inputs pre-processed features into the generating AI model to evaluate the worker's current emotional state. This prompt instructs the AI ​​model to "evaluate the worker's current state and generate necessary guidance." Based on the input data, the AI ​​model calculates the worker's emotional state and generates appropriate guidance.

[0558] Step 3:

[0559] The generated instruction content is delivered from the server to the terminal (smart glasses). The smart glasses visualize the instruction content and display it on the screen so that the worker can check it. For example, if the worker shows signs of fatigue, an alert such as "We recommend taking a short break" is sent.

[0560] Step 4:

[0561] The terminal observes the worker's reactions and sends that data back to the server. For example, data is collected to determine whether the worker took a break as recommended. This includes information monitored in real time again through facial expressions and voice.

[0562] Step 5:

[0563] The server analyzes the collected response data and uses it to improve the content of future lessons and generated prompts. This data is then fed back into the generative AI model and used for training and tuning to improve the model's performance.

[0564] 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.

[0565] 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.

[0566] 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.

[0567] [Fourth Embodiment]

[0568] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0569] 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.

[0570] 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).

[0571] 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.

[0572] 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.

[0573] 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).

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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".

[0581] In one embodiment of the invention, the server first accesses a database within an authenticated prison and collects various data about serious offenders. This includes behavioral history, psychological evaluation results, and personal information. This data is preprocessed and prepared in a format that can be effectively analyzed by the generated AI model.

[0582] Next, the server runs a generative AI model to generate individualized counseling and guidance content based on the collected data. This process sets up scenarios for providing education tailored to each serious offender and includes content that promotes learning about ethics and morality.

[0583] The server transmits the generated instructional content to terminals within the prison. The terminals then transmit the content to educational machines (robots) and prepare for interactive educational sessions.

[0584] The user, a serious offender, physically interacts with the educational machine and receives instruction. The educational machine conducts the education in an interactive format, following generated scenarios and engaging in question-and-answer sessions that encourage the user to reconsider their lacking ethical perspectives and the victim's point of view.

[0585] As a concrete example, regarding a past theft committed by the user, the educational machine asks questions such as, "What did the stolen item mean to the victim?" and uses a resonant voice scenario to convey the victim's feelings. During this process, the user's responses and statements are recorded on the device and sent to the server.

[0586] The recorded response data is analyzed on a server and used to improve the content and methods of future lessons. This strengthens the system for providing more appropriate education while maintaining individuality.

[0587] Through this embodiment, it is possible to enhance ethical reflection and reduce recidivism rates after reintegration into society by providing interactive guidance tailored to individual offenders.

[0588] The following describes the processing flow.

[0589] Step 1:

[0590] The server accesses the prison database and collects behavioral history, psychological evaluation data, and personal data of serious offenders. This data is preprocessed into a format suitable for analysis by generative AI models.

[0591] Step 2:

[0592] The server runs a generative AI model, analyzes pre-processed data, and generates individualized counseling and guidance content. This guidance content includes scenarios incorporating ethical education and the victim's perspective.

[0593] Step 3:

[0594] The server transmits the generated instructional content to terminals within the prison. The terminals review the received instructional content and prepare it for use with educational equipment.

[0595] Step 4:

[0596] The user, a serious offender, interacts with an educational machine to participate in an educational session. The educational machine conducts interactive education based on generated scenarios, presenting the user with questions and playing audio scenarios.

[0597] Step 5:

[0598] The device records the user's responses during the educational session, including the content of the user's answers and their response speed.

[0599] Step 6:

[0600] The device sends recorded response data to the server. The server analyzes this data and generates feedback to be used to improve the next educational session.

[0601] (Example 1)

[0602] 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".

[0603] Traditional education systems have provided a uniform approach to ethical and moral education for serious offenders, making it difficult to provide appropriate feedback based on individual characteristics and past behavioral history. Therefore, there is a need for individualized education that can prevent recidivism.

[0604] 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.

[0605] In this invention, the server includes means for transmitting generated instruction content to a medium via a communication terminal, means for performing interactive instruction based on the transmitted instruction content and saving the actions taken during instruction, means for analyzing the saved action data and using it to improve the content of the next instruction, means for collecting and processing individualized information for information analysis, and means for creating individualized counseling and instruction content using generative AI technology. This makes it possible to provide appropriate ethical and moral education tailored to individual circumstances and contribute to preventing recidivism.

[0606] "Generative AI technology" is a technology that uses artificial intelligence to automatically generate content and data tailored to specific purposes.

[0607] A "communication terminal" is a device used for sending and receiving data, and is a device that enables the transmission of information over a network.

[0608] A "medium" refers to a physical or electronic device or system used as a means of transmitting or storing information.

[0609] "Interactive instruction" is an educational process in which the student and the instructional system communicate with each other as the process progresses.

[0610] "Behavioral data" refers to data that records the reactions and behaviors exhibited by participants during the instruction process.

[0611] "Personalized information" refers to information that includes unique data and attributes related to a specific individual.

[0612] "Counseling" is the act of providing psychological or behavioral support to participants through advice and guidance.

[0613] Modes for carrying out the invention

[0614] In this invention, the server first accesses an authenticated database within the prison to collect various data on serious offenders. This data includes behavioral history, psychological evaluation results, and personal information. A database management system is used for data collection, such as MySQL. The collected data is preprocessed using the Pandas library and converted into a format that can be effectively analyzed by the generative AI model.

[0615] Next, the server runs a generative AI model to generate individual counseling and guidance content based on the pre-processed data. A large-scale language model (e.g., OpenAI GPT) is used in this step. By giving the AI ​​model specific instructions such as "Create an ethics education scenario based on the user's individual history" as a prompt, appropriate guidance content is generated.

[0616] The generated instructional content is transmitted from the server to terminals installed within the prison. This communication typically uses protocols such as TCP / IP or HTTP. Upon receiving the instructional content, the terminal transmits the data to an educational medium (e.g., a robot) and prepares for an interactive educational session. The educational medium uses a speech synthesis system and a display to present information, enabling interactive instruction.

[0617] The users, who are serious criminals, interact with an educational medium and receive instruction in an interactive format. For example, they might be asked questions such as, "Consider the impact the theft had on the victim," and the dialogue progresses to deepen their ethical reflection. During this time, the user's responses and statements are recorded on the device, and this data is transmitted to the server in real time.

[0618] The server analyzes the collected response data using tools like Python's Scikit-learn to improve future instruction. This makes it possible to continuously provide instruction optimized for each individual user, and is expected to reduce the recidivism rate of serious offenders.

[0619] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0620] Step 1:

[0621] The server connects to an authenticated database within the prison to retrieve behavioral history, psychological evaluation results, and personal information of serious offenders. The input consists of various data from the database, and the output is the collected, unprocessed dataset. In this process, a database management system (e.g., MySQL) is used to execute SQL queries and extract the necessary information.

[0622] Step 2:

[0623] The server preprocesses the collected data, including imputing missing values, standardizing the data, and encoding categorical variables. The input is an unprocessed dataset, and the output is formatted data that can be analyzed by a generative AI model. Specifically, the Python Pandas library is used to clean and format the data.

[0624] Step 3:

[0625] The server runs a generative AI model based on the formatted data. The model used here is a large-scale language model that generates individual instructional content in the form of prompt sentences as input. The input consists of formatted data and prompt sentences (e.g., "Create an ethics education scenario based on the user's personal history"), and the output is the generated instructional content.

[0626] Step 4:

[0627] The server sends the generated instructional content to the prison terminal. The input is the instructional content, and the output is the completion of the data transmission to the terminal. Communication protocols such as TCP / IP and HTTP are used in this stage, and the data is sent to the terminal via the internet.

[0628] Step 5:

[0629] The terminal receives the instructional content and transmits it to the educational media. This initiates the preparation for an interactive educational session. The input is the instructional content from the server, and the output is the setup of the instructional content on the educational media. The educational media uses a speech synthesis system and a display to present information to the user.

[0630] Step 6:

[0631] Users receive instruction through an educational medium. The instruction proceeds in an interactive format, with questions and explanations based on the instructional content. For example, the user might be asked, "Consider the impact the theft had on the victim." The input is the question from the educational medium, and the output is the user's response.

[0632] Step 7:

[0633] The terminal records user responses and statements and sends this data to a server. Input is user response data, and output is the completion of data transmission to the server. Recording functions and text logs are used, and responses are saved in real time.

[0634] Step 8:

[0635] The server analyzes recorded response data to help improve new teaching content. The input is response data, and the output is a plan for improving the next lesson. Tools such as Scikit-learn are used for data analysis to gain insights useful for future lessons.

[0636] (Application Example 1)

[0637] 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".

[0638] In modern organizations, employee ethics education is crucial, but there is a lack of mechanisms to provide appropriate, individualized support. Employees face diverse ethical dilemmas, and uniform educational methods are insufficient. Furthermore, there is a need for means to continuously evaluate changes in employee behavior and flexibly improve educational content.

[0639] 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.

[0640] In this invention, the server includes means for running a generative AI model to generate individual counseling and guidance content, means for distributing the generated counseling content to electronic devices within the organization, means for conducting interactive education based on the distributed guidance content and recording responses during the education, and means for analyzing the recorded response data and using it to improve the content of the next guidance session. This enables flexible ethical education with personalized information.

[0641] A "generative AI model" is an artificial intelligence program that generates content aligned with a specific purpose based on input data.

[0642] An "educational machine" is a device used to conduct interactive education and record user responses.

[0643] "Personalized information" refers to information collected based on the behavioral history and evaluation data of a specific individual.

[0644] "Preprocessing" refers to the process of preparing collected data into a format that can be analyzed by the generating AI model.

[0645] "Ethics education" refers to educational content designed to deepen employees' understanding of ethical situations they may face and to encourage them to make appropriate judgments.

[0646] "Electronic devices" are devices used for distributing information and presenting educational content.

[0647] "Means of recording responses" refers to methods of saving user reactions as data in an interactive educational process.

[0648] The invention will now be described in terms of its implementation. This system aims to provide personalized ethics education to employees within an organization using a generative AI model.

[0649] First, the server collects employee-related information from the organization's database. This information includes employee behavioral history and past performance data. This data is preprocessed and formatted so that it can be effectively analyzed by generative AI models. Data preprocessing libraries such as 'pandas' are used for this preprocessing.

[0650] Next, the server runs a generative AI model and generates individualized ethical education content for each employee based on the collected data. Generative AI models such as OpenAI's GPT-3 are used for content generation, and the prompt message is in the format of "Employee ID: X, Please create an ethical dilemma scenario."

[0651] The generated training content is delivered to electronic devices deployed within the organization—for example, smartphones and tablets—and presented to employees. This allows employees to participate in interactive training sessions.

[0652] The employee, acting as the user, responds to the presented scenarios in an interactive format, and their responses are recorded. This recording includes methods for saving it to a database and uploading the data to the cloud.

[0653] Finally, the server analyzes the recorded response data and uses it to improve future training methods. Through this analysis, the effectiveness of the training content can be enhanced, and employees' ethical awareness can be deepened.

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

[0655] Step 1:

[0656] The server collects employee information from the organization's database. This information includes employee behavioral history and performance data. The input is the database, and the server uses SQL queries to extract the necessary data. The output is raw data for preprocessing.

[0657] Step 2:

[0658] The server preprocesses the collected data. Specifically, it uses the pandas library to impute missing values ​​and normalize the data. The input is raw data, and the output is data in a format suitable for analysis. This processing improves the quality of the data.

[0659] Step 3:

[0660] The server runs a generation AI model and generates ethical education scenarios for employees based on pre-processed data. The input is the pre-processed data, which is sent to the AI ​​model along with the prompt "Employee ID: X, please create an ethical dilemma scenario." The output is the generated educational scenario.

[0661] Step 4:

[0662] The server distributes the generated training scenarios to devices within the organization. These devices are smartphones and tablets, and the scenarios are displayed through an application. The input is the generated scenario, and the output is the scenario screen displayed on the device.

[0663] Step 5:

[0664] The employee, acting as the user, responds to scenarios presented on the terminal. The employee's responses are recorded by the terminal; the input is the employee's reaction, and the output is the recorded data.

[0665] Step 6:

[0666] The server analyzes the recorded response data. This analysis utilizes data mining techniques to improve future teaching methods. The input is the recorded data, and the output is data representing proposed improvements. Through this analysis, more effective teaching content is created.

[0667] 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.

[0668] In this embodiment of the invention, the server accesses a prison database to collect detailed profile data of serious offenders. This includes behavioral history, psychological evaluation results, and personal background information. The server preprocesses this data and converts it into a format suitable for analysis by a generative AI model.

[0669] The server runs a generative AI model to create personalized counseling and instruction content. This system then transmits the generated instruction content to terminals installed within the prison. The terminals then transmit the received instruction content to educational equipment for preparation.

[0670] As part of the educational machine, it is equipped with an emotion engine. This emotion engine analyzes the user's, or serious criminal's, facial expressions, tone of voice, and speech patterns to recognize their emotional state in real time.

[0671] During the educational session, the user interacts with the educational machine and receives instruction. Throughout this process, the machine dynamically adjusts interactive questions and scenarios based on the user's emotional responses. For example, if the user shows confusion or discomfort, the machine adjusts its pace and is programmed to deliver ethical lessons in a more easily understandable way.

[0672] For example, if a scenario related to a user's past violent behavior is presented, the emotional engine, upon sensing the user's tension, will slow down the pace of the dialogue and use reassuring language to encourage introspection. In this way, more nuanced guidance is possible.

[0673] The device sends user emotional data recorded during the session to the server. The server analyzes this data and uses it to improve the content and strategy of future sessions based on individual emotional responses.

[0674] Through this embodiment, by incorporating an emotional engine, it is possible to provide flexible guidance tailored to the condition of each serious offender, further promoting introspection and the improvement of ethical awareness.

[0675] The following describes the processing flow.

[0676] Step 1:

[0677] The server accesses the prison database, collects the behavioral history, psychological evaluations, and personal information of serious offenders, and converts this data into a format suitable for analysis using data preprocessing tools.

[0678] Step 2:

[0679] The server runs a generative AI model and uses pre-processed data to generate individual counseling and guidance content. This guidance content includes scenarios that incorporate the victim's perspective, with a focus on ethical education.

[0680] Step 3:

[0681] The server transmits the generated instructional content to terminals within the prison. The terminals receive this content and prepare for the session to be conducted by the educational machine.

[0682] Step 4:

[0683] The user interacts with the educational machine and participates in an interactive educational session. During this session, an emotion engine built into the educational machine analyzes the user's facial expressions and voice in real time to recognize their emotional state.

[0684] Step 5:

[0685] The educational machine adjusts interactive questions and scenarios based on the user's emotional responses to help them reflect more deeply. For example, if the user shows confusion, the educational machine will rephrase the question to aid understanding.

[0686] Step 6:

[0687] The device sends user emotion data and responses recorded during the session to the server.

[0688] Step 7:

[0689] The server analyzes the received data and generates feedback to optimize the content of the next lesson based on the recorded emotions and reactions.

[0690] (Example 2)

[0691] 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".

[0692] Education and counseling for individuals with specific backgrounds or experiences presents a challenge because general approaches often fail to reflect their individual emotions and levels of understanding. Dynamic instruction that considers emotional responses is particularly difficult, highlighting the need for individualized guidance.

[0693] 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.

[0694] In this invention, the server includes means for acquiring and organizing individual person background information from a matching database, means for running a generation AI model to generate individual counseling and guidance content, and means for distributing the generated counseling content to each location for provision. This makes it possible to provide emotionally adapted, interactive education and counseling tailored to each individual and to optimize the content of the next guidance session.

[0695] "Individual person background information" refers to all information related to a specific individual's past actions, behaviors, and background.

[0696] A "matching database" is a system that stores various types of information and provides a collection of information that allows for data retrieval and comparison based on specific conditions.

[0697] A "generative AI model" refers to an artificial intelligence algorithm designed to analyze data and output results or predictions based on a specific task.

[0698] "Counseling and guidance content" refers to programs and activities aimed at providing psychological support and educational intervention to individual people.

[0699] "Distributing to each location for provision" means sending the generated information and instructional content to the locations and devices where it is needed, making it available for use.

[0700] "Interactive education" refers to an educational process that progresses through two-way communication with the recipient, and the content is often adjusted based on the recipient's responses.

[0701] In implementing this invention, the server plays a crucial role. First, the server uses a matching database system to collect and organize individual biographical information. This database system includes software that can store and quickly search and retrieve data in various formats. For example, a business database management system is suitable.

[0702] The server uses a generative AI model based on the compiled history information to create personalized counseling and guidance content. The generative AI model employs a natural language processing-based analysis algorithm, specifically applying common language generation techniques. An example of a prompt is the instruction to "generate personalized counseling content" given to the model.

[0703] The generated instructional content is distributed from the server to terminals at each location via the network. The terminals receive the data accurately through a secure communication protocol and transmit it to the educational implementation device. This educational implementation device includes an audio playback system and an interactive user interface, on which users receive education and counseling.

[0704] As part of the educational implementation device, it is equipped with an emotion analysis engine that analyzes the user's emotional state in real time. The user reacts during the lesson, and their facial expressions, tone of voice, and word choice are recorded as data by the emotion analysis engine. For example, if the user becomes emotionally confused, the educational implementation device adjusts the pace of the conversation and provides instruction in an easily understandable format.

[0705] This allows users to have a flexible educational experience that responds to their own emotions. As an example of a prompt, the AI ​​model is given the instruction, "Suggest the most effective way to communicate in this situation." This mechanism makes it possible to promote more effective introspection and improvement of ethical awareness.

[0706] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0707] Step 1:

[0708] The server retrieves and organizes individual biographical information from a matching database. The input consists of basic identification information about the individual. Based on this, it uses SQL queries to search the database for relevant information. The output is organized profile data. This profile data includes behavioral history and psychological evaluation results, and missing values ​​are imputed and outliers are corrected.

[0709] Step 2:

[0710] The server runs the AI ​​model using the prepared data. The input is the profile data generated in Step 1. This data, along with prompts, is input to the AI ​​model and used to generate counseling and guidance content. The output is counseling guidelines and guidance scenarios tailored to each individual. Natural language processing technology is applied to generate personalized content.

[0711] Step 3:

[0712] The server distributes the generated instructional content to the terminal via the network. The input is the instructional content generated in step 2. This is sent to the terminal using a secure communication protocol (e.g., HTTPS). The output is data converted into a format that the educational implementation device can receive. The terminal checks the received data and performs error checking.

[0713] Step 4:

[0714] The terminal transmits instructional content to the educational implementation device and prepares it to start the user's educational session. The input is the instructional content delivered from the server. The terminal instructs the educational implementation device to configure the interface and prepare media files. The output indicates that the implementation device is ready to successfully start the educational session.

[0715] Step 5:

[0716] The user interacts with the educational device and receives instruction. The emotion analysis engine detects the user's facial expressions, tone of voice, and language use in real time. The input is the user's emotional responses and behaviors, and the analysis engine converts this emotional state into digital data. The output is real-time emotional state information of the user, which is recorded sequentially on the terminal.

[0717] Step 6:

[0718] The terminal sends the recorded user emotion data to the server. The input is a dataset of emotional state information recorded in step 5. This is transferred to the server for analysis. The output is feedback data to optimize the content of the next session. The server uses this to provide a foundation for generating more effective counseling content.

[0719] (Application Example 2)

[0720] 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".

[0721] In typical work environments, there is a challenge in understanding workers' fatigue and stress levels in real time and providing individualized guidance to promote efficient and safe work. Traditional guidance methods have limited the ability to respond promptly to the individual conditions and circumstances of each worker, thus limiting improvements in work efficiency and safety.

[0722] 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.

[0723] In this invention, the server includes means for executing a generation AI model to generate individual instruction content, means for distributing the generated instruction content to educational equipment, means for conducting interactive instruction based on the distributed instruction content and observing the worker's state, means for analyzing the observed state data to improve the next instruction content, means for analyzing the worker's facial expressions and voice in the work environment and evaluating the state in real time, and means for providing individualized instruction based on the evaluation results and visualizing it through a display device. This makes it possible to instantly grasp the worker's state and provide appropriate responses, thereby improving work efficiency and safety.

[0724] A "generative AI model" is a computational model that generates new information based on data, and is a technology that provides output optimized for a specific purpose.

[0725] "Instructional content" refers to the information and procedures provided to achieve specific goals, and is tailored to the individual learner and their environment.

[0726] "Educational equipment" refers to devices and equipment used for learning and training purposes, and is the totality of hardware and software that supports the transmission of information and the development of skills.

[0727] "To distribute" means to send generated information to a specific device or user, with the aim of ensuring that the information reaches its destination accurately and quickly.

[0728] "Interactive" refers to the characteristic where the user and the system interact with each other, and communication takes place through information and actions.

[0729] "Observing" means carefully monitoring the state and changes of an object or environment, acquiring information based on the results, and making judgments and taking actions according to the purpose.

[0730] "Real-time" refers to the instantaneous processing and communication of data, reflecting the current state and situation without delay.

[0731] "Visualization" refers to the process of representing information and data visually and displaying them in a way that users can intuitively understand.

[0732] To implement this invention, a system is needed that can grasp the state of workers in the work environment in real time and provide individualized guidance based on that. The server first runs a generative AI model and generates individual guidance content based on the data. The generative AI model used here is designed to collect and preprocess the worker's facial expressions, voice, and other movement data to create guidance that is suitable for each individual worker.

[0733] The generated instructional content is distributed via a network to educational equipment. This educational equipment includes a display device, such as smart glasses, to allow workers to visually confirm the instruction. This educational equipment observes the worker's state in real time, analyzes their emotions using an emotion engine, and provides appropriate instructional content.

[0734] As a concrete example, let's say there is a worker A working the night shift at a factory. The server evaluates worker A's condition, and if it analyzes that worker A is feeling fatigued or stressed, it generates a message saying, "Take a few minutes' break and rehydrate," and notifies worker A via smart glasses. This message is appropriately adjusted based on data collected in real time by the generating AI model.

[0735] An example of a prompt is, "Design an assistant system that recognizes the emotions of factory workers and improves work efficiency." This prompt is used as input to a generating AI model, which then performs the necessary data processing and generates the instruction content.

[0736] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0737] Step 1:

[0738] The server collects facial image and audio data of workers in their work environment from smart glasses. This data is used as input, and preprocessed using facial recognition and speech recognition technologies to extract features from each. During this conversion process, emotional states are identified from the facial data, and voice tone and speech patterns are identified from the audio data.

[0739] Step 2:

[0740] The server inputs pre-processed features into the generating AI model to evaluate the worker's current emotional state. This prompt instructs the AI ​​model to "evaluate the worker's current state and generate necessary guidance." Based on the input data, the AI ​​model calculates the worker's emotional state and generates appropriate guidance.

[0741] Step 3:

[0742] The generated instruction content is delivered from the server to the terminal (smart glasses). The smart glasses visualize the instruction content and display it on the screen so that the worker can check it. For example, if the worker shows signs of fatigue, an alert such as "We recommend taking a short break" is sent.

[0743] Step 4:

[0744] The terminal observes the worker's reactions and sends that data back to the server. For example, data is collected to determine whether the worker took a break as recommended. This includes information monitored in real time again through facial expressions and voice.

[0745] Step 5:

[0746] The server analyzes the collected response data and uses it to improve the content of future lessons and generated prompts. This data is then fed back into the generative AI model and used for training and tuning to improve the model's performance.

[0747] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0748] 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.

[0749] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0750] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0751] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0752] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0753] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0754] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0755] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0756] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0757] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0758] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0759] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0760] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0761] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0762] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0763] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0764] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0765] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0766] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0767] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0768] The following is further disclosed regarding the embodiments described above.

[0769] (Claim 1)

[0770] A means of generating individual counseling and guidance content by executing a generative AI model,

[0771] A means of distributing the generated counseling content to an educational machine,

[0772] A means of conducting interactive education based on the delivered instructional content and recording responses during the education,

[0773] A means of analyzing recorded response data to improve the content of the next lesson,

[0774] A system that includes this.

[0775] (Claim 2)

[0776] The system according to claim 1, wherein the educational machine includes means for recreating the victim's perspective through audio playback and prompting individual introspection.

[0777] (Claim 3)

[0778] The system according to claim 1, comprising means for collecting and preprocessing individualized information for analysis by a generative AI model.

[0779] "Example 1"

[0780] (Claim 1)

[0781] A means of transmitting the generated instruction content to a medium via a communication terminal,

[0782] A means of conducting interactive instruction based on the transmitted instruction content and preserving the actions taken during instruction,

[0783] A means of analyzing saved behavioral data to improve the content of future instruction,

[0784] In order to analyze the information, means of collecting and processing individualized information,

[0785] A means of creating individualized counseling and guidance content using generative AI technology,

[0786] A system that includes this.

[0787] (Claim 2)

[0788] The system according to claim 1, wherein the educational medium includes means for recreating the victim's perspective through sound reproduction and promoting individual introspection.

[0789] (Claim 3)

[0790] The system according to claim 1, comprising means for collecting and processing individualized information for processing by generative AI technology.

[0791] "Application Example 1"

[0792] (Claim 1)

[0793] A means of generating individual counseling and guidance content by executing a generative AI model,

[0794] A means of distributing the generated counseling content to an educational machine,

[0795] A means of conducting interactive education based on the delivered instructional content and recording responses during the education,

[0796] A means of analyzing recorded response data to improve the content of the next lesson,

[0797] Means for collecting and pre-processing information related to employees within an organization,

[0798] A means of providing ethics education content generated for employees based on pre-processed information via electronic devices,

[0799] A means of recording responses that arise during the process of providing ethics education content and analyzing them for future educational improvement,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, wherein the educational machine includes means for recreating the perspective of a victim or related party through audio playback and for prompting individual introspection.

[0803] (Claim 3)

[0804] The system according to claim 1, comprising means for collecting and preprocessing individualized information for analysis by a generative AI model.

[0805] "Example 2 of combining an emotion engine"

[0806] (Claim 1)

[0807] A means of obtaining and organizing individual people's career information from a matching database,

[0808] A means of generating individual counseling and guidance content by executing a generative AI model,

[0809] A means of distributing the generated counseling content to each location,

[0810] A means of conducting interactive education based on the delivered instructional content and recognizing emotional responses during education,

[0811] A means to record recognized responses and use them to optimize the content of the next lesson,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, wherein the educational implementation device includes means for presenting different perspectives of individuals using sound reproduction and promoting individual introspection.

[0815] (Claim 3)

[0816] The system according to claim 1, further comprising means for acquiring and preprocessing individualized history information in order for the generating AI model to perform analysis.

[0817] "Application example 2 when combining with an emotional engine"

[0818] (Claim 1)

[0819] A means of generating individual instruction content by executing a generative AI model,

[0820] A means of distributing the generated instructional content to educational devices,

[0821] A means of conducting interactive instruction based on the distributed instruction content and observing the worker's condition,

[0822] A means to analyze observed state data and use it to improve the content of the next lesson,

[0823] A means of analyzing the facial expressions and voices of workers in the work environment and evaluating their condition in real time,

[0824] A means of providing individualized instruction based on evaluation results and visualizing them through a display device,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the educational device includes means for providing instruction to improve worker safety and efficiency through audio playback.

[0828] (Claim 3)

[0829] The system according to claim 1, comprising means for collecting and preprocessing individualized information for analysis by a generative AI model. [Explanation of Symbols]

[0830] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of generating individual counseling and guidance content by executing a generative AI model, A means of distributing the generated counseling content to an educational machine, A means of conducting interactive education based on the delivered instructional content and recording responses during the education, A means of analyzing recorded response data to improve the content of the next lesson, A system that includes this.

2. The system according to claim 1, wherein the educational machine includes means for recreating the victim's perspective through audio playback and prompting individual introspection.

3. The system according to claim 1, comprising means for collecting and preprocessing individualized information for analysis by a generative AI model.

Images