System

Abstract

A system is provided.SOLUTION: A system, comprising: means for capturing meeting or document data generated by a user; means for transmitting the captured data to a server; means for analyzing the data received by the server to identify gender-related issues; means for generating revision suggestions for the identified issues; and means for notifying the user of the generated revision suggestions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The present invention aims to address the serious problem of the gender gap, particularly in Japan. In Japan, interest in gender is low, and many people are unaware of or do not understand gender-related issues. This makes it highly likely that companies and individuals will unconsciously commit gender discrimination. The objective of the present invention is to provide a technological means to improve this low level of gender awareness and prevent gender discrimination before it occurs. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. It provides a means for capturing meeting and text data generated by users and includes a means for sending the captured data to a server. It provides a means for the server to analyze the data received and identify gender-related problems. It provides a means for generating correction suggestions for the identified problems and includes a means for notifying the user of the generated correction suggestions, thereby detecting gender-discriminatory language and behavior before they occur and encouraging them to correct them. It also provides a means for collecting feedback data provided by users based on the gender-related problems and correction suggestions identified by the server and updating the learning model. It also provides a means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and periodically notifying the user. In this way, a system is provided that continuously supports the improvement of gender awareness and the prevention of gender discrimination.

[0006] A "user" is an individual or group that generates meeting and text data and uses the system.

[0007] "Meeting and text data" refers to voice data generated by a user during a meeting, and data recorded as text in general.

[0008] A "capture means" is software or hardware for collecting user speech or text data in real time or after the fact.

[0009] A "server" is a computer system that receives and analyzes the captured data.

[0010] "Means for sending" refers to a communication means for transferring the captured data to the server.

[0011] "Means of analysis" refers to algorithms and programs that use AI models to identify gender-related issues in the data received.

[0012] "Gender-related issues" refer to gender-discriminatory expressions and behaviors contained in the data.

[0013] "Means for generating fixes" are algorithms and programs for devising alternatives and fixes for identified problems.

[0014] "Means of notification" refers to the communication means or interface used to communicate the proposed revisions to the user.

[0015] "Feedback data" refers to opinions and reactions regarding system usage provided by users.

[0016] "Learning model" refers to a model trained to perform data analysis using AI.

[0017] The "report generating means" refers to algorithms and programs for creating documents summarizing the occurrence and improvement status of gender issues.

[0018] "Notification means" refers to the communication means or interface used to notify the user of the generated report. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[0041] What the program does

[0042] Initial setup and data reception

[0043] 1. User Initial Settings

[0044] A user accesses the system's website and creates a new account. Registration information such as name, email address, and password are entered. After each piece of information is entered, the device sends it to the server. The server receives this information and generates an initial setting profile.

[0045] Data capture and transmission

[0046] 2. Real-time data capture

[0047] A user starts a conference. The terminal captures the user's voice data in real time and sends it to the server. Similarly, text data is captured as the user composes the text.

[0048] Data analysis and problem detection

[0049] 3. Data analysis and problem detection

[0050] The server analyzes the received audio and text materials and uses AI learning models to identify gender-related bias and discriminatory language. For example, the server will detect if the content includes the phrase "men should play a leadership role."

[0051] Proposed fix generation and notification

[0052] 4. Generate correction suggestions

[0053] The server generates suggested corrections for the identified problems. For example, it generates a suggested correction for the detected expression, such as "Anyone can demonstrate leadership."

[0054] 5. Feedback Notification

[0055] The device will notify the user in real time of suggested revisions, such as "That expression contains gender bias. We recommend changing it to 'Leadership is open to everyone.'"

[0056] Gathering feedback and updating learning models

[0057] 6. Collecting User Feedback

[0058] After the user makes corrections based on the suggested corrections, they send the corrections and feedback to the server, which collects this feedback and stores it in a database to improve the accuracy of analysis in the future.

[0059] 7. Updating the learning model

[0060] The server retrains the AI ​​learning model based on the feedback data collected, improving the accuracy of detecting gender-related issues.

[0061] Report generation and notification

[0062] 8. Generate a status report

[0063] The server then compiles the data analyzed and periodically generates reports detailing the occurrence and improvement of gender issues.

[0064] 9. Report Notification

[0065] The device will notify the user of the generated report and provide a link to download or view it.

[0066] Specific operation example

[0067] Example 1: Analysis of audio data during a meeting

[0068] 1. A user starts a conference

[0069] A user initiates a conference and the terminal captures the audio data.

[0070] 2. Sending and analyzing audio data

[0071] The device sends the captured voice data to a server, which converts the voice data into text and analyzes it using an AI learning model.

[0072] 3. Identifying issues and providing fixes

[0073] The server detects gender-discriminatory expressions such as "products for women" and generates a correction suggestion. The device notifies the user with a message saying, "That expression contains gender bias. We recommend changing it to 'products for all customers.'"

[0074] 4. User Corrections and Feedback

[0075] After users modify the expressions based on the suggestions, they send feedback to the server, which then reflects the improvements in gender bias in subsequent analyses.

[0076] This system can prevent gender discrimination that companies and individuals unconsciously commit on a daily basis. Through continuous feedback and updates to the learning model, the system evolves over time, enabling more accurate analysis and recommendations.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[0080] Step 2:

[0081] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[0082] Step 3:

[0083] The user starts a meeting or starts writing a document. The device captures the audio data of the meeting in real time and sends it to the server. The text data is also captured in the same way.

[0084] Step 4:

[0085] The server converts the received voice data into text, and then inputs the text and sentence data into an AI learning model to analyze gender-related issues.

[0086] Step 5:

[0087] The server uses the analysis results to identify gender-related issues, such as the phrase "men should take on leadership roles."

[0088] Step 6:

[0089] Based on the problems identified by the server, a correction proposal is generated. As a correction proposal, the server provides the expression "Anyone can demonstrate leadership."

[0090] Step 7:

[0091] The device will notify the user in real time of suggested revisions, specifically displaying a message saying, "That expression contains gender bias. We recommend that you revise it to 'Leadership is open to everyone.'"

[0092] Step 8:

[0093] The user actually makes corrections based on the suggested corrections, checks the corrections, and sends feedback to the server if necessary.

[0094] Step 9:

[0095] The server receives user feedback and stores it in a database. The collected feedback data is used as retraining data for the AI ​​learning model.

[0096] Step 10:

[0097] The server periodically retrains the AI ​​learning model based on the feedback data, thereby improving the accuracy of the analysis.

[0098] Step 11:

[0099] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring problems and their improvement status.

[0100] Step 12:

[0101] The device notifies the user of the generated report, which the user can then download or view on the web.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] Until now, there has been a lack of systems that can instantly detect gender-discriminatory expressions used unconsciously during meetings and document writing and provide appropriate correction suggestions. As a result, expressions containing gender bias are often used as is, hindering the promotion of gender equality. In addition, there has been a lack of a mechanism for continuously improving the system based on feedback data, which has limited improvements in analysis accuracy. Furthermore, there has been a lack of a mechanism for regularly reporting analysis results and correction status to users.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes: means for capturing meeting and text data generated by users in real time; means for transmitting the captured data to the server; means for analyzing the data received by the server and identifying gender-related issues using an AI learning model; means for generating correction suggestions for the identified issues; means for notifying the user of the generated correction suggestions in real time; means for collecting feedback data provided by the user and updating the learning model; and means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user periodically. This makes it possible to instantly detect expressions containing gender bias and provide appropriate correction suggestions. Continuous improvement of the system based on feedback and regular status reports are also realized.

[0107] "User" refers to a user who uses the system to hold meetings or generate text data.

[0108] "Meeting and written data" refers to voice data, text data, and related information generated by the user.

[0109] "Capturing means" refers to devices and software for acquiring and processing user meeting and text data in real time.

[0110] "Server" refers to a computer system that receives data sent by users and analyzes and processes it.

[0111] "Transmitting means" refers to a communication device or network technology for delivering the captured data to the server.

[0112] "Analyzing" refers to the act of analyzing received data to identify specific issues or characteristics.

[0113] "Gender-related issues" refers to content that contains gender bias, prejudice, or discriminatory language based on gender.

[0114] An "AI learning model" refers to an algorithm that uses artificial intelligence technology to analyze data and detect specific patterns or problems.

[0115] "Means of identification" refers to techniques and methods that use AI learning models to identify gender-related issues.

[0116] "Means for generating fixes" refers to technologies and methods for automatically creating improvements or alternative expressions for identified problems.

[0117] "Notification means" refers to a device or method for notifying the user of generated revision suggestions and analysis results in real time.

[0118] "Feedback Data" refers to information about changes made by a user in response to a suggested revision and the results of those changes.

[0119] "Means for updating the learning model" refers to technologies and methods for retraining the AI ​​learning model based on collected feedback data and improving its accuracy.

[0120] "Means for generating reports" refers to the techniques and methods for creating reports summarizing gender-related issues and progress based on the analyzed data.

[0121] "Means for notification" refers to the technology or method for periodically providing the generated report to the user.

[0122] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[0123] This system captures and processes data in real time when users use their devices to hold meetings and generate documents. Specifically, the following hardware and software are used:

[0124] Device: A device used by a user, such as a computer, tablet, or smartphone, that includes a microphone, keyboard, and screen for capturing voice and text data.

[0125] Server: A computer system that receives, analyzes, and processes data, and analyzes the data using AI learning models. Examples of use include cloud services and virtual servers.

[0126] Software: This includes real-time voice recording applications and text editors used for data capture, AI learning models (e.g., GPT-3.5, BERT) used for data analysis, and report generation tools.

[0127] Using this hardware and software, the system operates as follows.

[0128] When a user accesses the system's website and creates a new account, registration information such as name, email address, and password is sent to the server, which then generates an initial setting profile based on the received information.

[0129] When a user starts a conference, the device captures voice data in real time and sends it to the server. When the user writes a sentence, data is also captured and sent to the server.

[0130] The server converts the received voice data into text and analyzes it using an AI learning model (e.g., OpenAI's GPT-3.5 or Google's BERT). This analysis identifies gender-related bias and discriminatory language. The server then generates appropriate correction suggestions for the identified issues. The generated correction suggestions are notified to the user in real time via their device.

[0131] For example, if a phrase such as "Men should demonstrate leadership" is detected, the server will generate a suggested correction such as "Anyone can demonstrate leadership." The device will notify the user and display a message saying, "That phrase contains gender bias. We recommend that you correct it to 'Anyone can demonstrate leadership.'"

[0132] The user corrects the expression based on the suggested corrections and sends the corrections and feedback to the server. The server stores this feedback in a database and uses it to retrain the AI ​​learning model, thereby improving the accuracy of detecting gender-related issues.

[0133] Based on the analyzed data, the server periodically generates reports summarizing the occurrence and improvement of gender issues, and notifies the user via their device. The user can then download and view the generated reports.

[0134] Prompt Sentence Examples

[0135] Here is an example of a prompt to input to a generative AI model:

[0136] Detect whether the following conversation contains gender bias and provide suggestions for correction.

[0137] (Conversation):

[0138] A: "In fact, there are many situations where men demonstrate leadership."

[0139] B: "Market it as a product for women."

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1: Initial User Setup

[0142] Input: A user visits the system's website and enters their name, email address, and password to create a new account.

[0143] Specific operation: The device captures the information entered by the user and sends it to the server.

[0144] Output: The server generates an initial profile based on the received information, which stores the user's basic information.

[0145] Step 2: Real-time data capture

[0146] Input: A user starts a conference and generates voice data.

[0147] Specific operation: The device uses the microphone to capture audio data in real time and sends the data to the server.

[0148] Output: The voice data sent to the server is saved. Similarly, when the user writes a sentence, the device captures the text data and sends it to the server.

[0149] Step 3: Convert and analyze audio data

[0150] Input: The server receives the voice data sent from the device.

[0151] Specific operation: The server converts the voice data into text (e.g., using the Google Speech-to-Text API).

[0152] Output: The server generates the converted text data and prepares it to be passed to the AI ​​learning model.

[0153] Step 4: Analyzing the text data

[0154] Input: The server receives the text data sent from the terminal.

[0155] Specific operation: The server uses an AI learning model (e.g., GPT-3.5 or BERT) to analyze text data.

[0156] Output: The server identifies gender-related issues and stores the information.

[0157] Step 5: Generate correction suggestions

[0158] Input: The server begins processing based on the parsed text data and identified issues.

[0159] Specific Actions: The server generates appropriate fixes for the identified issues.

[0160] Output: The server prepares the generated revision suggestions and creates information to notify the user.

[0161] Step 6: Notification of proposed amendments

[0162] Input: The server holds the generated revision suggestions.

[0163] Specific operation: The server sends the proposed revision to the device, and the device notifies the user. For example, a message such as "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" is displayed.

[0164] Output: The user receives notification of the proposed revision and confirms the contents.

[0165] Step 7: Gather user feedback

[0166] Input: The user corrects the text based on the suggested corrections.

[0167] Specific operation: The user inputs the corrected data and feedback into the terminal, which then transmits this data to the server.

[0168] Output: The server stores the received feedback data in a database.

[0169] Step 8: Update the learning model

[0170] Input: The server retrieves the accumulated feedback data.

[0171] Specific operation: The server retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model based on new data.

[0172] Output: Updated AI learning model.

[0173] Step 9: Generate reports and notifications

[0174] Input: The server receives the parsed data and feedback.

[0175] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues.

[0176] Output: Notifies the user of the generated report and provides a link to download or view it.

[0177] By clarifying the detailed processing and inputs and outputs at each step, it is possible to concretely demonstrate how the system prevents and resolves gender-related issues.

[0178] (Application example 1)

[0179] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0180] During meetings and work instructions within factories, unconsciously gender-biased remarks are often made, resulting in unequal working environments and a worsening atmosphere within the workplace. It is also difficult to immediately correct and improve these remarks, which can have a negative impact on employee morale and the company's reputation in the long term. Therefore, there is a growing need for a system that can identify gender-biased remarks within factories in real time and propose appropriate corrections.

[0181] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0182] In this invention, the server includes means for capturing meeting and text data generated by users, means for transmitting the captured data to the server, means for the server to analyze the data received and identify gender-related issues, means for generating correction proposals for the identified issues, means for notifying the user of the generated correction proposals, and means for capturing voice data in real time during factory meetings, detecting gender issues, and generating appropriate correction proposals. This makes it possible to immediately detect gender-biased remarks in the factory and present appropriate correction proposals.

[0183] "Meeting and text data" refers to text and voice data such as conversations, instructions, and reports that users generate in the factory.

[0184] The "capturing means" refers to a device and software for collecting voice data and text data from a user in real time and transmitting the data to a server.

[0185] "Server" means a central system for analyzing data and generating suggested fixes for identified problems; it is a computer system that communicates with users over a network.

[0186] "Means for analyzing" refers to the method and function by which the server analyzes the data received using an AI learning model to identify gender-related issues.

[0187] "Gender-related issues" are gender-based prejudices or discriminatory expressions contained in users' statements or writings.

[0188] The "means for generating suggested modifications" refers to the algorithms and processes for generating suggested modifications to appropriate expressions for the issues identified by the server.

[0189] The "means for notifying the generated revision proposal" is a device or software that displays or sounds the revision proposal generated by the server to the user in real time.

[0190] "Means of capturing and detecting gender issues in real time" refers to a function that collects audio data on the spot during meetings within the factory and instantly analyzes it to identify gender issues.

[0191] The system of the present invention is designed to improve fairness in the work environment by detecting gender bias in factory meetings and work instructions and suggesting appropriate corrections. The system has the function of capturing voice data and text data generated by users in real time and transmitting them to a server. Specific embodiments of the present invention will be described below.

[0192] Main features of the program

[0193] 1. User registration and initial setup:

[0194] Users create a new account through the system's website or through the smart glasses or robot, where they enter information such as name, email address, and password, which is then sent to the server, which generates an initial setup profile.

[0195] 2. Real-time voice / text data capture:

[0196] During meetings or work instructions in factories, smart glasses or robots capture users' voice data in real time, and use the SpeechRecognition library to convert the captured voice data into text data.

[0197] 3. Data analysis and gender issue detection:

[0198] The server analyzes the received voice and text data using AI learning models to detect specific keywords and expressions to identify gender-related issues.

[0199] 4. Proposed amendment generation and notification:

[0200] The server generates appropriate corrections for identified gender-related issues. For example, it generates a correction for the statement "men should demonstrate leadership" such as "anyone can demonstrate leadership." The server notifies the user of the corrections in real time.

[0201] Hardware and software used

[0202] Smart glasses or robots:

[0203] A device that captures voice data in real time within the factory and notifies the user of suggested corrections.

[0204] server:

[0205] A central computer system that analyzes data and generates corrections, with AI learning models installed to perform the analysis.

[0206] SpeechRecognition library:

[0207] A software library for converting audio data into text data.

[0208] Specific examples

[0209] Example of operation

[0210] During a factory meeting:

[0211] 1. A user starts a meeting and the smart glasses capture the audio data.

[0212] 2. The captured audio data is sent to the server in real time.

[0213] 3. The server analyzes statements containing gender bias, such as "I think men are better at this task than women," and detects problems.

[0214] 4. The server generates appropriate correction suggestions, such as "Anyone can be good at this task," and notifies the smart glasses.

[0215] 5. The user corrects the statement based on the suggested corrections and sends feedback to the robot.

[0216] Prompt Sentence Examples

[0217] Analyzes statements made during meetings in real time to detect gender bias. If a statement such as "men should take on leadership roles" is made, the system will suggest appropriate corrections.

[0218] effect

[0219] This makes it possible to immediately detect gender-biased remarks in factories and propose appropriate corrections, creating a fairer work environment and ensuring that all employees are evaluated equally, thereby improving the company's reputation and work efficiency.

[0220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0221] Step 1:

[0222] A user creates a new account via a website, smart glasses, or a robot, entering information such as name, email address, and password, which is then sent to a server.

[0223] Input: User enters name, email address, and password.

[0224] Data processing / calculation: The input data is processed on the server to generate an initial setting profile.

[0225] Output: The default profile generated on the server.

[0226] Specific action: The user enters the required information to create an account and clicks the submit button.

[0227] Step 2:

[0228] Smart glasses or robots capture audio data of meetings and work instructions within the factory in real time and transmit the audio data to a server.

[0229] Input: User's speaking voice.

[0230] Data processing / calculation: Capture audio data and convert it to text data using the SpeechRecognition library. Send the converted text data to the server.

[0231] Output: The text data sent to the server.

[0232] How it works: Smart glasses or a robot senses and captures sound in real time.

[0233] Step 3:

[0234] The server analyzes the received text data and uses an AI learning model to identify gender-related issues.

[0235] Input: Text data.

[0236] Data processing / calculation: The received text data is input into an AI learning model, and calculations are performed to identify expressions with gender bias.

[0237] Output: Outcome data identifying gender-related issues.

[0238] Specific operation: The server receives the text data, analyzes it, and identifies expressions.

[0239] Step 4:

[0240] For identified gender-related issues, the server generates appropriate correction suggestions.

[0241] Input: Identified issue.

[0242] Data processing / calculation: Based on the problem, we run an algorithm to generate appropriate fixes.

[0243] Output: Revision proposal data.

[0244] What it does: The server analyzes the problem and algorithmically generates suggested fixes.

[0245] Step 5:

[0246] The generated revision suggestions are notified to the user using smart glasses or a robot.

[0247] Input: Revision proposal data.

[0248] Data processing / calculation: The proposed revision data is formatted for notification to the user and sent to the smart glasses or robot.

[0249] Output: Suggested revision notification displayed on smart glasses or robot.

[0250] Specific behavior: Smart glasses or robot receives the notification and displays it to the user.

[0251] Step 6:

[0252] The user corrects the comment based on the suggested corrections and transmits the feedback to the server.

[0253] Input: Corrected sentences and feedback data.

[0254] Data processing / calculation: The corrected sentences and feedback data are processed on the server and used to retrain the AI ​​model.

[0255] Output: Feedback data sent to the server.

[0256] Specific behavior: The user corrects their statement based on the suggested corrections, enters their feedback, and presses the submit button.

[0257] Step 7:

[0258] The server collects user feedback data and updates the AI ​​learning model.

[0259] Input: Feedback data.

[0260] Data processing / calculation: Retraining the AI ​​learning model based on feedback data.

[0261] Output: An updated AI learning model.

[0262] What happens: The server processes the feedback data and retrains the learning model.

[0263] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0264] The system of the present invention captures user-generated meeting and text data in real time, and combines this with an emotion engine that recognizes user emotions in real time to more effectively identify gender-related issues and provide appropriate correction suggestions.

[0265] What the program does

[0266] Initial setup and data reception

[0267] 1. User Initial Settings

[0268] A user accesses the system's website and creates a new account. They enter their name, email address, and password, then click the registration button. The device sends the entered information to the server, which receives the information and creates and saves the user profile.

[0269] Data capture and transmission

[0270] 2. Real-time data capture

[0271] A user starts a conference. The device captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server. Text data is also captured in the same way.

[0272] Data analysis and problem detection

[0273] 3. Data analysis and problem detection

[0274] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis. For example, if the expression "men should demonstrate leadership" is detected and the user simultaneously expresses negative feelings toward that statement, the issue will be set as a high priority.

[0275] Proposed fix generation and notification

[0276] 4. Generate correction suggestions

[0277] The server generates suggested corrections based on the identified problems and the user's emotional response to them. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentle explanation that reflects the user's emotions.

[0278] 5. Feedback Notification

[0279] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[0280] Gathering feedback and updating learning models

[0281] 6. Collecting User Feedback

[0282] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[0283] 7. Updating the learning model

[0284] The AI ​​learning model is retrained based on the feedback data collected by the server. The feedback also includes user emotional data, which further improves the accuracy of analysis.

[0285] Report generation and notification

[0286] 8. Generate a status report

[0287] The server then periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues, their improvement status, and insights based on user sentiment data.

[0288] 9. Report Notification

[0289] The device notifies the user of the generated report, which the user can then download or view on the web.

[0290] Specific operation example

[0291] Example 1: Analysis of speech and emotion data during a meeting

[0292] 1. A user starts a conference

[0293] A user initiates a conference and the terminal captures voice data and emotion data.

[0294] 2. Transmission and analysis of voice and emotion data

[0295] The device sends the captured voice and emotion data to a server. The server converts the voice data into text and analyzes it using an emotion engine. For example, if a user says "products for women" and expresses negative emotion, this will be identified as a high-priority issue.

[0296] 3. Identifying issues and providing fixes

[0297] The server determines that the expression "products for women" is gender discriminatory and generates a correction suggestion of "products for all customers." Using emotional data, the server confirms that the user has little resistance to this correction suggestion and notifies the user of the suggestion in a gentler way.

[0298] 4. User Corrections and Feedback

[0299] The user then modifies the expression based on the suggestions and provides feedback to the server. This feedback is collected along with the user's emotional data and is reflected in subsequent analyses.

[0300] This system not only identifies gender-discriminatory expressions, but also provides appropriate correction suggestions that take the user's feelings into consideration, allowing for more effective gender bias reduction. This allows users to make corrections without any resistance, and continuous feedback and updates to the learning model improve the accuracy and effectiveness of the entire system.

[0301] The processing flow will be explained below.

[0302] Step 1:

[0303] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[0304] Step 2:

[0305] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[0306] Step 3:

[0307] The user starts a meeting or starts writing a document. The device captures the meeting's audio data in real time, and simultaneously captures the user's emotional data using the emotion engine. The captured data is sent to the server.

[0308] Step 4:

[0309] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis.

[0310] Step 5:

[0311] The server uses the analysis results to identify gender-related issues, such as the expression "men should play a leadership role," and detects the user's negative emotional state in response to it.

[0312] Step 6:

[0313] The server generates correction suggestions for identified problems that take into account the user's emotional data. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentler suggestion that takes into account the user's emotional state.

[0314] Step 7:

[0315] The device notifies the user in real time of suggested revisions, specifically, "That expression is gender biased. We recommend that you revise it to 'Leadership is something everyone can demonstrate,'" and displays a gentler message tailored to the user's emotional state.

[0316] Step 8:

[0317] The user corrects the expression based on the suggested corrections, and the results of the corrections and the emotions at that time are fed back to the server.

[0318] Step 9:

[0319] The server receives user feedback and stores it in a database. The feedback data collected by the server is used to retrain the AI ​​learning model.

[0320] Step 10:

[0321] The server periodically retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model.

[0322] Step 11:

[0323] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring issues and their improvement status, as well as insights based on user sentiment data.

[0324] Step 12:

[0325] The device notifies the user of the generated report, which the user can then download or view on the web.

[0326] Example 2

[0327] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0328] Conventional meeting and text data analysis systems do not take users' feelings into account when identifying gender-related issues, which can lead to reluctance to accept suggested revisions. Furthermore, the learning model is not updated properly based on feedback, which reduces the system's analytical accuracy and effectiveness. Furthermore, it is difficult to continuously monitor the occurrence and improvement status of gender issues.

[0329] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0330] In this invention, the server includes means for capturing meeting and text data generated by a user, means for transmitting the captured data and emotional data to the server, means for converting voice data into text, means for analyzing the converted text data and emotional data to identify gender-related issues, means for generating suggested revisions using a generative AI model, and means for notifying the user of the generated suggested revisions while taking the user's emotional state into consideration. This makes it possible to identify and correct gender-related issues while taking the user's emotions into consideration, and to continuously improve the analysis accuracy and effectiveness of the entire system through feedback.

[0331] A "user" is an entity that uses the system to generate meeting and text data and receives analysis results and suggested revisions.

[0332] "Conference data" refers to voice data and text data generated by users during a conference.

[0333] "Text data" refers to text data such as documents and reports generated by users.

[0334] "Means of capture" refers to the hardware and software capabilities for collecting meeting and text data in real time.

[0335] "Emotional data" refers to data for identifying and recording a user's emotional state.

[0336] "Server" refers to a computer system that performs central data processing, analyzes received data, and outputs results.

[0337] "Means for converting to text" refers to technology or devices that convert voice data into text information.

[0338] "Means of analysis" refers to the algorithms and AI models used to process data and identify gender-related issues.

[0339] "Gender-related issues" refer to elements in meetings or written data that indicate gender bias or discrimination.

[0340] A "generative AI model" refers to a machine learning model that generates corrections and predictions from given data.

[0341] "Means for generating correction proposals" refers to technologies and functions for creating improvement proposals for identified problems.

[0342] "Notification means that take into account the emotional state" refers to a method or technology that takes the user's emotions into account and conveys information in an appropriate format.

[0343] "Feedback data" refers to information such as improvement suggestions provided by users and their impressions after use.

[0344] "Means for updating learning models" refers to techniques and methods for retraining AI models using collected feedback data to improve their accuracy.

[0345] The means for generating "reports" refers to the function for creating reports summarizing the results of analysis and the occurrence and improvement status of gender issues.

[0346] "Means of periodic notification" refers to techniques or methods that provide reports or information to users at regular intervals.

[0347] The system of the present invention captures user-generated meeting and text data, identifies gender-related issues in real time, and provides suggested corrections. A specific embodiment of the system is described below.

[0348] Hardware and software used

[0349] Hardware

[0350] Device: The device that a user uses to conduct a meeting. For example, a PC, tablet, or smartphone.

[0351] Server: A central computer system that analyzes and stores data.

[0352] software

[0353] Conferencing applications: Tools for capturing audio data. Examples: Zoom, Microsoft Teams.

[0354] Emotion engine: Software for capturing user emotional data. Example: Affectiva SDK.

[0355] Speech Recognition API: A service for converting voice data into text data. Example: Google Speech-to-Text API.

[0356] Generative AI models: Models that generate fixes for gender-related issues. Example: GPT-3.

[0357] System Operation

[0358] 1. User Initial Settings

[0359] A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button. The device sends the entered information to the server, which receives the information and creates and stores the user profile.

[0360] 2. Real-time data capture

[0361] A user starts a conference. The terminal captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server in real time.

[0362] 3. Data analysis and problem detection

[0363] The server converts the received voice data into text using a speech recognition API. The server then inputs the converted text and sentence data into a generative AI model to analyze gender-related issues. Emotion data recognized by the emotion engine is also incorporated into the analysis.

[0364] 4. Generate correction suggestions

[0365] Based on the problems identified by the server and the user's emotional response, the generative AI model generates suggested corrections. For example, it might recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions.

[0366] 5. Feedback Notification

[0367] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[0368] 6. Collecting User Feedback

[0369] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[0370] 7. Updating the learning model

[0371] The AI ​​learning model is retrained based on the feedback data collected by the server, which further improves the accuracy of analysis.

[0372] 8. Report Generation and Notification

[0373] The server periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues and their improvement status, as well as insights based on the user's emotional data. The device notifies the user of the generated report. The user can download the report or view it online.

[0374] Prompt Sentence Examples

[0375] For example, if the following audio data is captured:

[0376] "This product is for women."

[0377] For this audio data, the system generates the following correction suggestions:

[0378] This product is for all customers.

[0379] Based on this suggested fix, the system will notify the user with the following message:

[0380] "The wording has gender bias. We recommend amending it to say, 'This product is for all customers.'"

[0381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0382] Step 1:

[0383] A user accesses the system's website and creates a new account. As input, the user enters their name, email address, and password, and presses the register button. The terminal sends this input data to the server. The server processes the received information, generates a new user profile, and stores it in the database. As output, a user profile is generated, and the user receives a notification that the account creation has been completed.

[0384] Step 2:

[0385] A user starts a conference. The user launches a conference application and communicates with conference participants via voice. As input, the user's voice data and emotion data are captured on the device. The device transmits this data to the server in real time. As output, the voice data and emotion data of the conference are stored on the server.

[0386] Step 3:

[0387] The server converts the received voice data into text data using a voice recognition API. The voice data is passed to the voice recognition API as input, and data processing is performed. The converted text data is generated as output.

[0388] Step 4:

[0389] The server analyzes the converted text data and emotion data. As input, the text data and emotion data are passed to the analysis algorithm. The server uses these data to identify gender-related issues. As output, gender-related issues are detected.

[0390] Step 5:

[0391] The server generates suggested corrections for the identified issues. As input, gender-related issues and emotional data are entered into the generative AI model. Based on this, the server generates appropriate suggested corrections. For example, it recommends the expression "Anyone can demonstrate leadership." As output, an appropriate suggested correction is generated.

[0392] Step 6:

[0393] The device notifies the user of the proposed revision in real time. As input, the generated revision proposal is sent from the server to the device. The device displays a notification message in a gentle manner that takes into account the user's emotional state. As output, the user receives a notification based on the proposed revision.

[0394] Step 7:

[0395] The user modifies the expression based on the suggested modifications and feeds the results back to the server. As input, the modified content and emotional state are sent from the device to the server. The server stores them in a database. As output, the user's feedback data is collected.

[0396] Step 8:

[0397] The server retrains the learning model based on the collected feedback data. As input, the feedback data and emotion data are passed to the AI ​​model retraining process. This allows the server to improve the analysis accuracy. As output, an updated AI model is generated.

[0398] Step 9:

[0399] The server periodically generates reports on the occurrence and improvement status of gender issues based on the analyzed data. The analyzed data is processed within the server as input. The server compiles a report on frequently occurring issues, their improvement status, and insights based on user sentiment data. A report is generated as output.

[0400] Step 10:

[0401] The terminal notifies the user of the generated report. As input, the generated report is sent from the server to the terminal. The user receives a notification and can download the report or view it on the web. As output, the report is provided to the user.

[0402] (Application example 2)

[0403] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0404] Gender bias and harassment remain serious issues in modern workplaces and online communities. In particular, unconsciously discriminatory gender remarks in meetings and written texts can have a negative impact on the work environment and interpersonal relationships. Furthermore, some users find it difficult to make corrections without feeling uncomfortable, making it difficult to take appropriate measures. Therefore, a system that can effectively detect gender bias and harassment and provide appropriate correction suggestions is needed.

[0405] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0406] In this invention, the server includes a means incorporating an emotion engine that recognizes a user's emotion data in real time, a means for providing suggested revisions in a gentle tone based on the emotion data, and a means for notifying the user of the generated suggested revisions. This allows the user to make corrections without feeling any resistance. Furthermore, by effectively identifying gender bias issues and quickly providing suggested improvements, the system can contribute to improving the workplace and community environment.

[0407] A "user" is a subject who uses this system and is a person who holds meetings and generates text data.

[0408] "Meeting and written data" refers to the content of communication generated by users, and includes voice data and text data.

[0409] "Capture" refers to the act of collecting and storing user-generated meeting and text data in real time.

[0410] "Server" refers to the computer and system that receives and analyzes the captured data.

[0411] "Gender-related issues" refer to elements of gender bias and harassment contained in meetings and written data.

[0412] "Amendment" refers to alternative language or courses of action proposed to remedy a gender-related shortcoming.

[0413] "Notification" is the act of informing the user of the generated revision proposal.

[0414] "Emotion data" refers to data that indicates the emotional state detected from the user's statements and actions.

[0415] "Emotion Engine" refers to algorithms and systems that recognize and analyze a user's emotional state in real time.

[0416] "Feedback" is the act of a user returning their reaction or opinion to the server regarding a proposed revision.

[0417] "Learning model" refers to a machine learning algorithm that is retrained based on collected data to improve analysis accuracy.

[0418] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0419] 1. Initial Setup

[0420] A user accesses the system's website and creates a new account. By entering information such as name, email address, and password and pressing the registration button, a user profile is created. This information is sent from the client terminal to the server, and then received by the server.

[0421] 2. Data Capture

[0422] When a user starts a conference, the client device (smartphone, computer, tablet, etc.) captures the conference audio data in real time. The emotion engine also recognizes the user's emotion data in real time. This data is then sent to the server in real time.

[0423] 3. Data Analysis

[0424] The server uses speech recognition software to convert the received voice data into text. The converted text and sentence data are then input into an AI learning model to analyze gender-related issues. Emotional data recognized by an emotion engine is also incorporated into the analysis, and issues are prioritized based on the user's emotions. For example, if the expression "men should take on leadership roles" is detected and the user is expressing negative emotions, this issue is set as a high priority.

[0425] 4. Proposed amendment generation and notification

[0426] The server generates suggested revisions based on the identified issues and the user's emotional data. For example, it may recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions. The generated revisions are notified to the user in real time. Specifically, the message displayed is gentle and takes into account the user's emotional state: "That expression contains gender bias. We recommend revising it to 'Anyone can demonstrate leadership.'"

[0427] 5. Gather feedback and update the learning model

[0428] The user makes corrections based on the suggested corrections and then provides feedback on the content and emotional state of the corrections to the server. This feedback data is stored in a database and later used to retrain the AI ​​learning model. This improves the system's analysis accuracy and allows it to provide more effective corrections.

[0429] 6. Report Generation and Notifications

[0430] The server generates a report on the occurrence and improvement status of gender issues based on the analyzed data. The report details frequently occurring problems and their improvement status, as well as insights based on the user's emotional data. The generated report is periodically notified to the user, who can download the report or view it online.

[0431] Specific examples

[0432] For example, if a user says "a product for women" during a meeting, the system will detect this statement as gender bias and suggest the expression "a product for all customers." At the same time, the system will analyze the user's negative sentiment toward the statement and notify them of appropriate revisions in a gentler tone.

[0433] Example prompts for generative AI models

[0434] Analyze the following text to determine whether it contains gender bias:

[0435] "Products for women"

[0436] Also, determine whether this text evokes negative emotions.

[0437] In this way, the present invention provides a system that effectively detects gender bias and harassment and provides appropriate correction suggestions.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1: Initial User Setup

[0440] Specific operation: A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button.

[0441] Input: Name, email address, and password entered by the user

[0442] Data processing: The terminal formats the input information and sends it to the server.

[0443] Output: The server generates and stores a user profile based on the information received.

[0444] Step 2: Real-time data capture

[0445] Specific operation: A user starts a conference, and the terminal captures the voice data and emotion data of the conference.

[0446] Input: Voice data and user emotion data obtained from the meeting

[0447] Data processing: Voice data is captured in real time, and emotion data is collected simultaneously.

[0448] Output: Captured data is sent to the server

[0449] Step 3: Data analysis and problem detection

[0450] What it does: The server uses speech recognition software to convert the received voice data into text. It also inputs the text and sentence data into an AI learning model to analyze gender-related issues. The emotion engine also incorporates emotional data into the analysis.

[0451] Input: Voice data and emotion data received by the server

[0452] Data processing: Converting voice data into text and inputting it into an AI learning model for analysis. Emotional data is also incorporated into the analysis.

[0453] Output: Gender-related issues are identified and prioritized.

[0454] Step 4: Generate correction suggestions

[0455] Specific operation: The server generates a correction suggestion based on the identified problem and the user's sentiment data. For example, it recommends the expression "Anyone can demonstrate leadership."

[0456] Input: Identified issues and sentiment data

[0457] Data processing: Generate correction suggestions based on problem and sentiment data

[0458] Output: Generated revision suggestions are generated

[0459] Step 5: Notification of proposed amendments

[0460] Specific behavior: The generated revision suggestions are notified to the user in real time, with a message saying, "That expression contains gender bias. We recommend changing it to 'Leadership is open to everyone.'"

[0461] Input: Generated correction suggestions

[0462] Data processing: Converting data into the appropriate notification format

[0463] Output: The user is notified of the proposed fix

[0464] Step 6: Gather feedback

[0465] Specific operation: The user makes corrections based on the suggested corrections and feeds back the results and emotional state to the server.

[0466] Input: Feedback data and revised content provided by the user

[0467] Data processing: Format the feedback data and store it in a database

[0468] Output: Feedback data is saved in a database

[0469] Step 7: Update the learning model

[0470] Specific operation: The AI ​​learning model is retrained using the feedback data collected by the server.

[0471] Input: Feedback data stored in the database

[0472] Data processing: Retraining the AI ​​learning model with feedback data

[0473] Output: Updated training model is completed.

[0474] Step 8: Generate a status report

[0475] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues based on the analyzed data.

[0476] Input: Parsed data

[0477] Data processing: Collect and analyze the occurrence and improvement status and generate reports

[0478] Output: A report is generated

[0479] Step 9: Report Notification

[0480] Specific Behavior: Notifies the user of the generated report. The user can download the report or view it on the web.

[0481] Input: Generated report

[0482] Data processing: Converting data into the appropriate notification format

[0483] Output: The user is notified of the report

[0484] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0485] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0486] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0487] [Second embodiment]

[0488] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0489] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0490] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0491] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0492] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0493] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0494] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0495] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0496] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0497] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0498] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0499] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0500] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[0501] What the program does

[0502] Initial setup and data reception

[0503] 1. User Initial Settings

[0504] A user accesses the system's website and creates a new account. Registration information such as name, email address, and password are entered. After each piece of information is entered, the device sends it to the server. The server receives this information and generates an initial setting profile.

[0505] Data capture and transmission

[0506] 2. Real-time data capture

[0507] A user starts a conference. The terminal captures the user's voice data in real time and sends it to the server. Similarly, text data is captured as the user composes the text.

[0508] Data analysis and problem detection

[0509] 3. Data analysis and problem detection

[0510] The server analyzes the received audio and text materials and uses AI learning models to identify gender-related bias and discriminatory language. For example, the server will detect if the content contains the phrase "men should play a leadership role."

[0511] Proposed fix generation and notification

[0512] 4. Generate correction suggestions

[0513] The server generates suggested corrections for the identified problems. For example, it generates a suggested correction for the detected expression, such as "Anyone can demonstrate leadership."

[0514] 5. Feedback Notification

[0515] The device will notify the user in real time of suggested revisions, such as "That expression contains gender bias. We recommend changing it to 'Leadership is for everyone.'"

[0516] Gathering feedback and updating learning models

[0517] 6. Collecting User Feedback

[0518] After the user makes corrections based on the suggested corrections, they send the corrections and feedback to the server, which collects this feedback and stores it in a database to improve the accuracy of analysis in the future.

[0519] 7. Updating the learning model

[0520] The server retrains the AI ​​learning model based on the feedback data collected, improving the accuracy of detecting gender-related issues.

[0521] Report generation and notification

[0522] 8. Generate a status report

[0523] The server then compiles the data analyzed and periodically generates reports detailing the occurrence and improvement of gender issues.

[0524] 9. Report Notification

[0525] The device will notify the user of the generated report and provide a link to download or view it.

[0526] Specific operation example

[0527] Example 1: Analysis of audio data during a meeting

[0528] 1. A user starts a conference

[0529] A user initiates a conference and the terminal captures the audio data.

[0530] 2. Sending and analyzing audio data

[0531] The device sends the captured voice data to a server, which converts the voice data into text and analyzes it using an AI learning model.

[0532] 3. Identifying issues and providing fixes

[0533] The server detects gender-discriminatory expressions such as "products for women" and generates a correction suggestion. The device notifies the user with a message saying, "That expression contains gender bias. We recommend changing it to 'products for all customers.'"

[0534] 4. User Corrections and Feedback

[0535] After users modify the expressions based on the suggestions, they send feedback to the server, which then reflects the improvements in gender bias in subsequent analyses.

[0536] This system can prevent gender discrimination that companies and individuals unconsciously commit on a daily basis. Through continuous feedback and updates to the learning model, the system evolves over time, enabling more accurate analysis and recommendations.

[0537] The processing flow will be explained below.

[0538] Step 1:

[0539] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[0540] Step 2:

[0541] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[0542] Step 3:

[0543] The user starts a meeting or starts writing a document. The device captures the audio data of the meeting in real time and sends it to the server. The text data is also captured in the same way.

[0544] Step 4:

[0545] The server converts the received voice data into text, and then inputs the text and sentence data into an AI learning model to analyze gender-related issues.

[0546] Step 5:

[0547] The server uses the analysis results to identify gender-related issues, such as the phrase "men should take on leadership roles."

[0548] Step 6:

[0549] Based on the problems identified by the server, a correction proposal is generated. As a correction proposal, the server provides the expression "Anyone can demonstrate leadership."

[0550] Step 7:

[0551] The device will notify the user in real time of suggested revisions, specifically displaying a message saying, "That expression contains gender bias. We recommend that you revise it to 'Leadership is open to everyone.'"

[0552] Step 8:

[0553] The user actually makes corrections based on the suggested corrections, checks the corrections, and sends feedback to the server if necessary.

[0554] Step 9:

[0555] The server receives user feedback and stores it in a database. The collected feedback data is used as retraining data for the AI ​​learning model.

[0556] Step 10:

[0557] The server periodically retrains the AI ​​learning model based on the feedback data, thereby improving the accuracy of the analysis.

[0558] Step 11:

[0559] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring problems and their improvement status.

[0560] Step 12:

[0561] The device notifies the user of the generated report, which the user can then download or view on the web.

[0562] Example 1

[0563] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0564] Until now, there has been a lack of systems that can instantly detect gender-discriminatory expressions used unconsciously during meetings and document writing and provide appropriate correction suggestions. As a result, expressions containing gender bias are often used as is, hindering the promotion of gender equality. In addition, there has been a lack of a mechanism for continuously improving the system based on feedback data, which has limited improvements in analysis accuracy. Furthermore, there has been a lack of a mechanism for regularly reporting analysis results and correction status to users.

[0565] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0566] In this invention, the server includes: means for capturing meeting and text data generated by users in real time; means for transmitting the captured data to the server; means for analyzing the data received by the server and identifying gender-related issues using an AI learning model; means for generating correction suggestions for the identified issues; means for notifying the user of the generated correction suggestions in real time; means for collecting feedback data provided by the user and updating the learning model; and means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user periodically. This makes it possible to instantly detect expressions containing gender bias and provide appropriate correction suggestions. Continuous improvement of the system based on feedback and regular status reports are also realized.

[0567] "User" refers to a user who uses the system to hold meetings or generate text data.

[0568] "Meeting and written data" refers to voice data, text data, and related information generated by the user.

[0569] "Capturing means" refers to devices and software for acquiring and processing user meeting and text data in real time.

[0570] "Server" refers to a computer system that receives data sent by users and analyzes and processes it.

[0571] "Transmitting means" refers to a communication device or network technology for delivering the captured data to the server.

[0572] "Analyzing" refers to the act of analyzing received data to identify specific issues or characteristics.

[0573] "Gender-related issues" refers to content that contains gender bias, prejudice, or discriminatory language based on gender.

[0574] An "AI learning model" refers to an algorithm that uses artificial intelligence technology to analyze data and detect specific patterns or problems.

[0575] "Means of identification" refers to techniques and methods that use AI learning models to identify gender-related issues.

[0576] "Means for generating fixes" refers to technologies and methods for automatically creating improvements or alternative expressions for identified problems.

[0577] "Notification means" refers to a device or method for notifying the user of generated revision suggestions and analysis results in real time.

[0578] "Feedback Data" refers to information about changes made by a user in response to a suggested revision and the results of those changes.

[0579] "Means for updating the learning model" refers to technologies and methods for retraining the AI ​​learning model based on collected feedback data and improving its accuracy.

[0580] "Means for generating reports" refers to the techniques and methods for creating reports summarizing gender-related issues and progress based on the analyzed data.

[0581] "Means for notification" refers to the technology or method for periodically providing the generated report to the user.

[0582] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[0583] This system captures and processes data in real time when users use their devices to hold meetings and generate documents. Specifically, the following hardware and software are used:

[0584] Device: A device used by a user, such as a computer, tablet, or smartphone, that includes a microphone, keyboard, and screen for capturing voice and text data.

[0585] Server: A computer system that receives, analyzes, and processes data, and analyzes the data using AI learning models. Examples of use include cloud services and virtual servers.

[0586] Software: This includes real-time voice recording applications and text editors used for data capture, AI learning models (e.g., GPT-3.5, BERT) used for data analysis, and report generation tools.

[0587] Using this hardware and software, the system operates as follows.

[0588] When a user accesses the system's website and creates a new account, registration information such as name, email address, and password is sent to the server, which then generates an initial setting profile based on the received information.

[0589] When a user starts a conference, the device captures voice data in real time and sends it to the server. When the user writes a sentence, data is also captured and sent to the server.

[0590] The server converts the received voice data into text and analyzes it using an AI learning model (e.g., OpenAI's GPT-3.5 or Google's BERT). This analysis identifies gender-related bias and discriminatory language. The server then generates appropriate correction suggestions for the identified issues. The generated correction suggestions are notified to the user in real time via their device.

[0591] For example, if a phrase such as "Men should demonstrate leadership" is detected, the server will generate a suggested correction such as "Anyone can demonstrate leadership." The device will notify the user and display a message saying, "That phrase contains gender bias. We recommend that you correct it to 'Anyone can demonstrate leadership.'"

[0592] The user corrects the expression based on the suggested corrections and sends the corrections and feedback to the server. The server stores this feedback in a database and uses it to retrain the AI ​​learning model, thereby improving the accuracy of detecting gender-related issues.

[0593] Based on the analyzed data, the server periodically generates reports summarizing the occurrence and improvement of gender issues, and notifies the user via their device. The user can then download and view the generated reports.

[0594] Prompt Sentence Examples

[0595] Here is an example of a prompt to input to a generative AI model:

[0596] Detect whether the following conversation contains gender bias and provide suggestions for correction.

[0597] (Conversation):

[0598] A: "In fact, there are many situations where men demonstrate leadership."

[0599] B: "Market it as a product for women."

[0600] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0601] Step 1: Initial User Setup

[0602] Input: A user visits the system's website and enters their name, email address, and password to create a new account.

[0603] Specific operation: The device captures the information entered by the user and sends it to the server.

[0604] Output: The server generates an initial profile based on the received information, which stores the user's basic information.

[0605] Step 2: Real-time data capture

[0606] Input: A user starts a conference and generates voice data.

[0607] Specific operation: The device uses the microphone to capture audio data in real time and sends the data to the server.

[0608] Output: The voice data sent to the server is saved. Similarly, when the user writes a sentence, the device captures the text data and sends it to the server.

[0609] Step 3: Convert and analyze audio data

[0610] Input: The server receives the voice data sent from the device.

[0611] Specific operation: The server converts the voice data into text (e.g., using the Google Speech-to-Text API).

[0612] Output: The server generates the converted text data and prepares it to be passed to the AI ​​learning model.

[0613] Step 4: Analyzing the text data

[0614] Input: The server receives the text data sent from the terminal.

[0615] Specific operation: The server uses an AI learning model (e.g., GPT-3.5 or BERT) to analyze text data.

[0616] Output: The server identifies gender-related issues and stores the information.

[0617] Step 5: Generate correction suggestions

[0618] Input: The server begins processing based on the parsed text data and identified issues.

[0619] Specific Actions: The server generates appropriate fixes for the identified issues.

[0620] Output: The server prepares the generated revision suggestions and creates information to notify the user.

[0621] Step 6: Notification of proposed amendments

[0622] Input: The server holds the generated revision suggestions.

[0623] Specific operation: The server sends the proposed revision to the device, and the device notifies the user. For example, a message such as "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" is displayed.

[0624] Output: The user receives notification of the proposed revision and confirms the contents.

[0625] Step 7: Gather user feedback

[0626] Input: The user corrects the text based on the suggested corrections.

[0627] Specific operation: The user inputs the corrected data and feedback into the terminal, which then transmits this data to the server.

[0628] Output: The server stores the received feedback data in a database.

[0629] Step 8: Update the learning model

[0630] Input: The server retrieves the accumulated feedback data.

[0631] Specific operation: The server retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model based on new data.

[0632] Output: Updated AI learning model.

[0633] Step 9: Generate reports and notifications

[0634] Input: The server receives the parsed data and feedback.

[0635] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues.

[0636] Output: Notifies the user of the generated report and provides a link to download or view it.

[0637] By clarifying the detailed processing and inputs and outputs at each step, it is possible to concretely demonstrate how the system prevents and resolves gender-related issues.

[0638] (Application example 1)

[0639] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0640] During meetings and work instructions within factories, unconsciously gender-biased remarks are often made, resulting in unequal working environments and a worsening atmosphere within the workplace. It is also difficult to immediately correct and improve these remarks, which can have a negative impact on employee morale and the company's reputation in the long term. Therefore, there is a growing need for a system that can identify gender-biased remarks within factories in real time and propose appropriate corrections.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0642] In this invention, the server includes means for capturing meeting and text data generated by users, means for transmitting the captured data to the server, means for the server to analyze the data received and identify gender-related issues, means for generating correction proposals for the identified issues, means for notifying the user of the generated correction proposals, and means for capturing voice data in real time during factory meetings, detecting gender issues, and generating appropriate correction proposals. This makes it possible to immediately detect gender-biased remarks in the factory and present appropriate correction proposals.

[0643] "Meeting and text data" refers to text and voice data such as conversations, instructions, and reports that users generate in the factory.

[0644] The "capturing means" refers to a device and software for collecting voice data and text data from a user in real time and transmitting the data to a server.

[0645] "Server" means a central system for analyzing data and generating suggested fixes for identified problems; it is a computer system that communicates with users over a network.

[0646] "Means for analyzing" refers to the method and function by which the server analyzes the data received using an AI learning model to identify gender-related issues.

[0647] "Gender-related issues" are gender-based prejudices or discriminatory expressions contained in users' statements or writings.

[0648] The "means for generating suggested modifications" refers to the algorithms and processes for generating suggested modifications to appropriate expressions for the issues identified by the server.

[0649] The "means for notifying the generated revision proposal" is a device or software that displays or sounds the revision proposal generated by the server to the user in real time.

[0650] "Means of capturing and detecting gender issues in real time" refers to a function that collects audio data on the spot during meetings within the factory and instantly analyzes it to identify gender issues.

[0651] The system of the present invention is designed to improve fairness in the work environment by detecting gender bias in factory meetings and work instructions and suggesting appropriate corrections. The system has the function of capturing voice data and text data generated by users in real time and transmitting them to a server. Specific embodiments of the present invention will be described below.

[0652] Main features of the program

[0653] 1. User registration and initial setup:

[0654] Users create a new account through the system's website or through the smart glasses or robot, where they enter information such as name, email address, and password, which is then sent to the server, which generates an initial setup profile.

[0655] 2. Real-time voice / text data capture:

[0656] During meetings or work instructions in factories, smart glasses or robots capture users' voice data in real time, and use the SpeechRecognition library to convert the captured voice data into text data.

[0657] 3. Data analysis and gender issue detection:

[0658] The server analyzes the received voice and text data using AI learning models to detect specific keywords and expressions to identify gender-related issues.

[0659] 4. Proposed amendment generation and notification:

[0660] The server generates appropriate corrections for identified gender-related issues. For example, it generates a correction for the statement "men should demonstrate leadership" such as "anyone can demonstrate leadership." The server notifies the user of the corrections in real time.

[0661] Hardware and software used

[0662] Smart glasses or robots:

[0663] A device that captures voice data in real time within the factory and notifies the user of suggested corrections.

[0664] server:

[0665] A central computer system that analyzes data and generates corrections, with AI learning models installed to perform the analysis.

[0666] SpeechRecognition library:

[0667] A software library for converting audio data into text data.

[0668] Specific examples

[0669] Example of operation

[0670] During a factory meeting:

[0671] 1. A user starts a meeting and the smart glasses capture the audio data.

[0672] 2. The captured audio data is sent to the server in real time.

[0673] 3. The server analyzes statements containing gender bias, such as "I think men are better at this task than women," and detects problems.

[0674] 4. The server generates appropriate correction suggestions, such as "Anyone can be good at this task," and notifies the smart glasses.

[0675] 5. The user corrects the statement based on the suggested corrections and sends feedback to the robot.

[0676] Prompt Sentence Examples

[0677] Analyzes statements made during meetings in real time to detect gender bias. If a statement such as "men should take on leadership roles" is made, the system will suggest appropriate corrections.

[0678] effect

[0679] This makes it possible to immediately detect gender-biased remarks in factories and propose appropriate corrections, creating a fairer work environment and ensuring that all employees are evaluated equally, thereby improving the company's reputation and work efficiency.

[0680] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0681] Step 1:

[0682] A user creates a new account via a website, smart glasses, or a robot, entering information such as name, email address, and password, which is then sent to a server.

[0683] Input: User enters name, email address, and password.

[0684] Data processing / calculation: The input data is processed on the server to generate an initial setting profile.

[0685] Output: The default profile generated on the server.

[0686] Specific action: The user enters the required information to create an account and clicks the submit button.

[0687] Step 2:

[0688] Smart glasses or robots capture audio data of meetings and work instructions within the factory in real time and transmit the audio data to a server.

[0689] Input: User's speaking voice.

[0690] Data processing / calculation: Capture audio data and convert it to text data using the SpeechRecognition library. Send the converted text data to the server.

[0691] Output: The text data sent to the server.

[0692] How it works: Smart glasses or a robot senses and captures sound in real time.

[0693] Step 3:

[0694] The server analyzes the received text data and uses an AI learning model to identify gender-related issues.

[0695] Input: Text data.

[0696] Data processing / calculation: The received text data is input into an AI learning model, and calculations are performed to identify expressions with gender bias.

[0697] Output: Outcome data identifying gender-related issues.

[0698] Specific operation: The server receives the text data, analyzes it, and identifies expressions.

[0699] Step 4:

[0700] For identified gender-related issues, the server generates appropriate correction suggestions.

[0701] Input: Identified issue.

[0702] Data processing / calculation: Based on the problem, we run an algorithm to generate appropriate fixes.

[0703] Output: Revision proposal data.

[0704] What it does: The server analyzes the problem and algorithmically generates suggested fixes.

[0705] Step 5:

[0706] The generated revision suggestions are notified to the user using smart glasses or a robot.

[0707] Input: Revision proposal data.

[0708] Data processing / calculation: The proposed revision data is formatted for notification to the user and sent to the smart glasses or robot.

[0709] Output: Suggested revision notification displayed on smart glasses or robot.

[0710] Specific behavior: Smart glasses or robot receives the notification and displays it to the user.

[0711] Step 6:

[0712] The user corrects the comment based on the suggested corrections and transmits the feedback to the server.

[0713] Input: Corrected sentences and feedback data.

[0714] Data processing / calculation: The corrected sentences and feedback data are processed on the server and used to retrain the AI ​​model.

[0715] Output: Feedback data sent to the server.

[0716] Specific behavior: The user corrects their statement based on the suggested corrections, enters their feedback, and presses the submit button.

[0717] Step 7:

[0718] The server collects user feedback data and updates the AI ​​learning model.

[0719] Input: Feedback data.

[0720] Data processing / calculation: Retraining the AI ​​learning model based on feedback data.

[0721] Output: An updated AI learning model.

[0722] What happens: The server processes the feedback data and retrains the learning model.

[0723] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0724] The system of the present invention captures user-generated meeting and text data in real time, and combines this with an emotion engine that recognizes user emotions in real time to more effectively identify gender-related issues and provide appropriate correction suggestions.

[0725] What the program does

[0726] Initial setup and data reception

[0727] 1. User Initial Settings

[0728] A user accesses the system's website and creates a new account. They enter their name, email address, and password, then click the registration button. The device sends the entered information to the server, which receives the information and creates and saves the user profile.

[0729] Data capture and transmission

[0730] 2. Real-time data capture

[0731] A user starts a conference. The device captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server. Text data is also captured in the same way.

[0732] Data analysis and problem detection

[0733] 3. Data analysis and problem detection

[0734] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis. For example, if the expression "men should demonstrate leadership" is detected and the user simultaneously expresses negative feelings toward that statement, the issue will be set as a high priority.

[0735] Proposed fix generation and notification

[0736] 4. Generate correction suggestions

[0737] The server generates suggested corrections based on the identified problems and the user's emotional response to them. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentle explanation that reflects the user's emotions.

[0738] 5. Feedback Notification

[0739] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[0740] Gathering feedback and updating learning models

[0741] 6. Collecting User Feedback

[0742] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[0743] 7. Updating the learning model

[0744] The AI ​​learning model is retrained based on the feedback data collected by the server. The feedback also includes user emotional data, which further improves the accuracy of analysis.

[0745] Report generation and notification

[0746] 8. Generate a status report

[0747] The server then periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues, their improvement status, and insights based on user sentiment data.

[0748] 9. Report Notification

[0749] The device notifies the user of the generated report, which the user can then download or view on the web.

[0750] Specific operation example

[0751] Example 1: Analysis of speech and emotion data during a meeting

[0752] 1. A user starts a conference

[0753] A user initiates a conference and the terminal captures voice data and emotion data.

[0754] 2. Transmission and analysis of voice and emotion data

[0755] The device sends the captured voice and emotion data to a server. The server converts the voice data into text and analyzes it using an emotion engine. For example, if a user says "products for women" and expresses negative emotion, this will be identified as a high-priority issue.

[0756] 3. Identifying issues and providing fixes

[0757] The server determines that the expression "products for women" is gender discriminatory and generates a correction suggestion of "products for all customers." Using emotional data, the server confirms that the user has little resistance to this correction suggestion and notifies the user of the suggestion in a gentler way.

[0758] 4. User Corrections and Feedback

[0759] The user then modifies the expression based on the suggestions and provides feedback to the server. This feedback is collected along with the user's emotional data and is reflected in subsequent analyses.

[0760] This system not only identifies gender-discriminatory expressions, but also provides appropriate correction suggestions that take the user's feelings into consideration, allowing for more effective gender bias reduction. This allows users to make corrections without any resistance, and continuous feedback and updates to the learning model improve the accuracy and effectiveness of the entire system.

[0761] The processing flow will be explained below.

[0762] Step 1:

[0763] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[0764] Step 2:

[0765] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[0766] Step 3:

[0767] The user starts a meeting or starts writing a document. The device captures the meeting's audio data in real time, and simultaneously captures the user's emotional data using the emotion engine. The captured data is sent to the server.

[0768] Step 4:

[0769] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis.

[0770] Step 5:

[0771] The server uses the analysis results to identify gender-related issues, such as the expression "men should play a leadership role," and detects the user's negative emotional state in response to it.

[0772] Step 6:

[0773] The server generates correction suggestions for identified problems that take into account the user's emotional data. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentler suggestion that takes into account the user's emotional state.

[0774] Step 7:

[0775] The device notifies the user in real time of suggested revisions, specifically, "That expression is gender biased. We recommend that you revise it to 'Leadership is something everyone can demonstrate,'" and displays a gentler message tailored to the user's emotional state.

[0776] Step 8:

[0777] The user corrects the expression based on the suggested corrections, and the results of the corrections and the emotions at that time are fed back to the server.

[0778] Step 9:

[0779] The server receives user feedback and stores it in a database. The feedback data collected by the server is used to retrain the AI ​​learning model.

[0780] Step 10:

[0781] The server periodically retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model.

[0782] Step 11:

[0783] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring issues and their improvement status, as well as insights based on user sentiment data.

[0784] Step 12:

[0785] The device notifies the user of the generated report, which the user can then download or view on the web.

[0786] Example 2

[0787] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0788] Conventional meeting and text data analysis systems do not take users' feelings into account when identifying gender-related issues, which can lead to reluctance to accept suggested revisions. Furthermore, the learning model is not updated properly based on feedback, which reduces the system's analytical accuracy and effectiveness. Furthermore, it is difficult to continuously monitor the occurrence and improvement status of gender issues.

[0789] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0790] In this invention, the server includes means for capturing meeting and text data generated by a user, means for transmitting the captured data and emotional data to the server, means for converting voice data into text, means for analyzing the converted text data and emotional data to identify gender-related issues, means for generating suggested revisions using a generative AI model, and means for notifying the user of the generated suggested revisions while taking the user's emotional state into consideration. This makes it possible to identify and correct gender-related issues while taking the user's emotions into consideration, and to continuously improve the analysis accuracy and effectiveness of the entire system through feedback.

[0791] A "user" is an entity that uses the system to generate meeting and text data and receives analysis results and suggested revisions.

[0792] "Conference data" refers to voice data and text data generated by users during a conference.

[0793] "Text data" refers to text data such as documents and reports generated by users.

[0794] "Means of capture" refers to the hardware and software capabilities for collecting meeting and text data in real time.

[0795] "Emotional data" refers to data for identifying and recording a user's emotional state.

[0796] "Server" refers to a computer system that performs central data processing, analyzes received data, and outputs results.

[0797] "Means for converting to text" refers to technology or devices that convert voice data into text information.

[0798] "Means of analysis" refers to the algorithms and AI models used to process data and identify gender-related issues.

[0799] "Gender-related issues" refer to elements in meetings or written data that indicate gender bias or discrimination.

[0800] A "generative AI model" refers to a machine learning model that generates corrections and predictions from given data.

[0801] "Means for generating correction proposals" refers to technologies and functions for creating improvement proposals for identified problems.

[0802] "Notification means that take into account the emotional state" refers to a method or technology that takes the user's emotions into account and conveys information in an appropriate format.

[0803] "Feedback data" refers to information such as improvement suggestions provided by users and their impressions after use.

[0804] "Means for updating learning models" refers to techniques and methods for retraining AI models using collected feedback data to improve their accuracy.

[0805] The means for generating "reports" refers to the function for creating reports summarizing the results of analysis and the occurrence and improvement status of gender issues.

[0806] "Means of periodic notification" refers to techniques or methods that provide reports or information to users at regular intervals.

[0807] The system of the present invention captures user-generated meeting and text data, identifies gender-related issues in real time, and provides suggested corrections. A specific embodiment of the system is described below.

[0808] Hardware and software used

[0809] Hardware

[0810] Device: The device that a user uses to conduct a meeting. For example, a PC, tablet, or smartphone.

[0811] Server: A central computer system that analyzes and stores data.

[0812] software

[0813] Conferencing applications: Tools for capturing audio data. Examples: Zoom, Microsoft Teams.

[0814] Emotion engine: Software for capturing user emotional data. Example: Affectiva SDK.

[0815] Speech Recognition API: A service for converting voice data into text data. Example: Google Speech-to-Text API.

[0816] Generative AI models: Models that generate fixes for gender-related issues. Example: GPT-3.

[0817] System Operation

[0818] 1. User Initial Settings

[0819] A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button. The device sends the entered information to the server, which receives the information and creates and stores the user profile.

[0820] 2. Real-time data capture

[0821] A user starts a conference. The terminal captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server in real time.

[0822] 3. Data analysis and problem detection

[0823] The server converts the received voice data into text using a speech recognition API. The server then inputs the converted text and sentence data into a generative AI model to analyze gender-related issues. Emotion data recognized by the emotion engine is also incorporated into the analysis.

[0824] 4. Generate correction suggestions

[0825] Based on the problems identified by the server and the user's emotional response, the generative AI model generates suggested corrections. For example, it might recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions.

[0826] 5. Feedback Notification

[0827] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[0828] 6. Collecting User Feedback

[0829] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[0830] 7. Updating the learning model

[0831] The AI ​​learning model is retrained based on the feedback data collected by the server, which further improves the accuracy of analysis.

[0832] 8. Report Generation and Notification

[0833] The server periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues and their improvement status, as well as insights based on the user's emotional data. The device notifies the user of the generated report. The user can download the report or view it online.

[0834] Prompt Sentence Examples

[0835] For example, if the following audio data is captured:

[0836] "This product is for women."

[0837] For this audio data, the system generates the following correction suggestions:

[0838] This product is for all customers.

[0839] Based on this suggested fix, the system will notify the user with the following message:

[0840] "The wording has gender bias. We recommend amending it to say, 'This product is for all customers.'"

[0841] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0842] Step 1:

[0843] A user accesses the system's website and creates a new account. As input, the user enters their name, email address, and password, and presses the register button. The terminal sends this input data to the server. The server processes the received information, generates a new user profile, and stores it in the database. As output, a user profile is generated, and the user receives a notification that the account creation has been completed.

[0844] Step 2:

[0845] A user starts a conference. The user launches a conference application and communicates with conference participants via voice. As input, the user's voice data and emotion data are captured on the device. The device transmits this data to the server in real time. As output, the voice data and emotion data of the conference are stored on the server.

[0846] Step 3:

[0847] The server converts the received voice data into text data using a voice recognition API. The voice data is passed to the voice recognition API as input, and data processing is performed. The converted text data is generated as output.

[0848] Step 4:

[0849] The server analyzes the converted text data and emotion data. As input, the text data and emotion data are passed to the analysis algorithm. The server uses these data to identify gender-related issues. As output, gender-related issues are detected.

[0850] Step 5:

[0851] The server generates suggested corrections for the identified issues. As input, gender-related issues and emotional data are entered into the generative AI model. Based on this, the server generates appropriate suggested corrections. For example, it recommends the expression "Anyone can demonstrate leadership." As output, an appropriate suggested correction is generated.

[0852] Step 6:

[0853] The device notifies the user of the proposed revision in real time. As input, the generated revision proposal is sent from the server to the device. The device displays a notification message in a gentle manner that takes into account the user's emotional state. As output, the user receives a notification based on the proposed revision.

[0854] Step 7:

[0855] The user modifies the expression based on the suggested modifications and feeds the results back to the server. As input, the modified content and emotional state are sent from the device to the server. The server stores them in a database. As output, the user's feedback data is collected.

[0856] Step 8:

[0857] The server retrains the learning model based on the collected feedback data. As input, the feedback data and emotion data are passed to the AI ​​model retraining process. This allows the server to improve the analysis accuracy. As output, an updated AI model is generated.

[0858] Step 9:

[0859] The server periodically generates reports on the occurrence and improvement status of gender issues based on the analyzed data. The analyzed data is processed within the server as input. The server compiles a report on frequently occurring issues, their improvement status, and insights based on user sentiment data. A report is generated as output.

[0860] Step 10:

[0861] The terminal notifies the user of the generated report. As input, the generated report is sent from the server to the terminal. The user receives a notification and can download the report or view it on the web. As output, the report is provided to the user.

[0862] (Application example 2)

[0863] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0864] Gender bias and harassment remain serious issues in modern workplaces and online communities. In particular, unconsciously discriminatory gender remarks in meetings and written texts can have a negative impact on the work environment and interpersonal relationships. Furthermore, some users find it difficult to make corrections without feeling uncomfortable, making it difficult to take appropriate measures. Therefore, a system that can effectively detect gender bias and harassment and provide appropriate correction suggestions is needed.

[0865] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0866] In this invention, the server includes a means incorporating an emotion engine that recognizes a user's emotion data in real time, a means for providing suggested revisions in a gentle tone based on the emotion data, and a means for notifying the user of the generated suggested revisions. This allows the user to make corrections without feeling any resistance. Furthermore, by effectively identifying gender bias issues and quickly providing suggested improvements, the system can contribute to improving the workplace and community environment.

[0867] A "user" is a subject who uses this system and is a person who holds meetings and generates text data.

[0868] "Meeting and written data" refers to the content of communication generated by users, and includes voice data and text data.

[0869] "Capture" refers to the act of collecting and storing user-generated meeting and text data in real time.

[0870] "Server" refers to the computer and system that receives and analyzes the captured data.

[0871] "Gender-related issues" refer to elements of gender bias and harassment contained in meetings and written data.

[0872] "Amendment" refers to alternative language or courses of action proposed to remedy a gender-related shortcoming.

[0873] "Notification" is the act of informing the user of the generated revision proposal.

[0874] "Emotion data" refers to data that indicates the emotional state detected from the user's statements and actions.

[0875] "Emotion Engine" refers to algorithms and systems that recognize and analyze a user's emotional state in real time.

[0876] "Feedback" is the act of a user returning their reaction or opinion to the server regarding a proposed revision.

[0877] "Learning model" refers to a machine learning algorithm that is retrained based on collected data to improve analysis accuracy.

[0878] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[0879] 1. Initial Setup

[0880] A user accesses the system's website and creates a new account. By entering information such as name, email address, and password and pressing the registration button, a user profile is created. This information is sent from the client terminal to the server, and then received by the server.

[0881] 2. Data Capture

[0882] When a user starts a conference, the client device (smartphone, computer, tablet, etc.) captures the conference audio data in real time. The emotion engine also recognizes the user's emotion data in real time. This data is then sent to the server in real time.

[0883] 3. Data Analysis

[0884] The server uses speech recognition software to convert the received voice data into text. The converted text and sentence data are then input into an AI learning model to analyze gender-related issues. Emotional data recognized by an emotion engine is also incorporated into the analysis, and issues are prioritized based on the user's emotions. For example, if the expression "men should take on leadership roles" is detected and the user is expressing negative emotions, this issue is set as a high priority.

[0885] 4. Proposed amendment generation and notification

[0886] The server generates suggested revisions based on the identified issues and the user's emotional data. For example, it may recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions. The generated revisions are notified to the user in real time. Specifically, the message displayed is gentle and takes into account the user's emotional state: "That expression contains gender bias. We recommend revising it to 'Anyone can demonstrate leadership.'"

[0887] 5. Gather feedback and update the learning model

[0888] The user makes corrections based on the suggested corrections and then provides feedback on the content and emotional state of the corrections to the server. This feedback data is stored in a database and later used to retrain the AI ​​learning model. This improves the system's analysis accuracy and allows it to provide more effective corrections.

[0889] 6. Report Generation and Notifications

[0890] The server generates a report on the occurrence and improvement status of gender issues based on the analyzed data. The report details frequently occurring problems and their improvement status, as well as insights based on the user's emotional data. The generated report is periodically notified to the user, who can download the report or view it online.

[0891] Specific examples

[0892] For example, if a user says "a product for women" during a meeting, the system will detect this statement as gender bias and suggest the expression "a product for all customers." At the same time, the system will analyze the user's negative sentiment toward the statement and notify them of appropriate revisions in a gentler tone.

[0893] Example prompts for generative AI models

[0894] Analyze the following text to determine whether it contains gender bias:

[0895] "Products for women"

[0896] Also, determine whether this text evokes negative emotions.

[0897] In this way, the present invention provides a system that effectively detects gender bias and harassment and provides appropriate correction suggestions.

[0898] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0899] Step 1: Initial User Setup

[0900] Specific operation: A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button.

[0901] Input: Name, email address, and password entered by the user

[0902] Data processing: The terminal formats the input information and sends it to the server.

[0903] Output: The server generates and stores a user profile based on the information received.

[0904] Step 2: Real-time data capture

[0905] Specific operation: A user starts a conference, and the terminal captures the voice data and emotion data of the conference.

[0906] Input: Voice data and user emotion data obtained from the meeting

[0907] Data processing: Voice data is captured in real time, and emotion data is collected simultaneously.

[0908] Output: Captured data is sent to the server

[0909] Step 3: Data analysis and problem detection

[0910] What it does: The server uses speech recognition software to convert the received voice data into text. It also inputs the text and sentence data into an AI learning model to analyze gender-related issues. The emotion engine also incorporates emotional data into the analysis.

[0911] Input: Voice data and emotion data received by the server

[0912] Data processing: Converting voice data into text and inputting it into an AI learning model for analysis. Emotional data is also incorporated into the analysis.

[0913] Output: Gender-related issues are identified and prioritized.

[0914] Step 4: Generate correction suggestions

[0915] Specific operation: The server generates a correction suggestion based on the identified problem and the user's sentiment data. For example, it recommends the expression "Anyone can demonstrate leadership."

[0916] Input: Identified issues and sentiment data

[0917] Data processing: Generate correction suggestions based on problem and sentiment data

[0918] Output: Generated revision suggestions are generated

[0919] Step 5: Notification of proposed amendments

[0920] Specific behavior: The generated revision suggestions are notified to the user in real time, with a message saying, "That expression contains gender bias. We recommend changing it to 'Leadership is open to everyone.'"

[0921] Input: Generated correction suggestions

[0922] Data processing: Converting data into the appropriate notification format

[0923] Output: The user is notified of the proposed fix

[0924] Step 6: Gather feedback

[0925] Specific operation: The user makes corrections based on the suggested corrections and feeds back the results and emotional state to the server.

[0926] Input: Feedback data and revised content provided by the user

[0927] Data processing: Format the feedback data and store it in a database

[0928] Output: Feedback data is saved in a database

[0929] Step 7: Update the learning model

[0930] Specific operation: The AI ​​learning model is retrained using the feedback data collected by the server.

[0931] Input: Feedback data stored in the database

[0932] Data processing: Retraining the AI ​​learning model with feedback data

[0933] Output: Updated training model is completed.

[0934] Step 8: Generate a status report

[0935] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues based on the analyzed data.

[0936] Input: Parsed data

[0937] Data processing: Collect and analyze the occurrence and improvement status and generate reports

[0938] Output: A report is generated

[0939] Step 9: Report Notification

[0940] Specific Behavior: Notifies the user of the generated report. The user can download the report or view it on the web.

[0941] Input: Generated report

[0942] Data processing: Converting data into the appropriate notification format

[0943] Output: The user is notified of the report

[0944] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0945] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0946] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0947] [Third embodiment]

[0948] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0949] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0950] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0951] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0952] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0953] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0954] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0955] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0956] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0957] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0958] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0959] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0960] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[0961] What the program does

[0962] Initial setup and data reception

[0963] 1. User Initial Settings

[0964] A user accesses the system's website and creates a new account. Registration information such as name, email address, and password are entered. After each piece of information is entered, the device sends it to the server. The server receives this information and generates an initial setting profile.

[0965] Data capture and transmission

[0966] 2. Real-time data capture

[0967] A user starts a conference. The terminal captures the user's voice data in real time and sends it to the server. Similarly, text data is captured as the user composes the text.

[0968] Data analysis and problem detection

[0969] 3. Data analysis and problem detection

[0970] The server analyzes the received audio and text materials and uses AI learning models to identify gender-related bias and discriminatory language. For example, the server will detect if the content includes the phrase "men should play a leadership role."

[0971] Proposed fix generation and notification

[0972] 4. Generate correction suggestions

[0973] The server generates suggested corrections for the identified problems. For example, it generates a suggested correction for the detected expression, such as "Anyone can demonstrate leadership."

[0974] 5. Feedback Notification

[0975] The device will notify the user in real time of suggested revisions, such as "That expression contains gender bias. We recommend changing it to 'Leadership is open to everyone.'"

[0976] Gathering feedback and updating learning models

[0977] 6. Collecting User Feedback

[0978] After the user makes corrections based on the suggested corrections, they send the corrections and feedback to the server, which collects this feedback and stores it in a database to improve the accuracy of analysis in the future.

[0979] 7. Updating the learning model

[0980] The server retrains the AI ​​learning model based on the feedback data collected, improving the accuracy of detecting gender-related issues.

[0981] Report generation and notification

[0982] 8. Generate a status report

[0983] The server then compiles the data analyzed and periodically generates reports detailing the occurrence and improvement of gender issues.

[0984] 9. Report Notification

[0985] The device will notify the user of the generated report and provide a link to download or view it.

[0986] Specific operation example

[0987] Example 1: Analysis of audio data during a meeting

[0988] 1. A user starts a conference

[0989] A user initiates a conference and the terminal captures the audio data.

[0990] 2. Sending and analyzing audio data

[0991] The device sends the captured voice data to a server, which converts the voice data into text and analyzes it using an AI learning model.

[0992] 3. Identifying issues and providing fixes

[0993] The server detects gender-discriminatory expressions such as "products for women" and generates a correction suggestion. The device notifies the user with a message saying, "That expression contains gender bias. We recommend changing it to 'products for all customers.'"

[0994] 4. User Corrections and Feedback

[0995] After users modify the expressions based on the suggestions, they send feedback to the server, which then reflects the improvements in gender bias in subsequent analyses.

[0996] This system can prevent gender discrimination that companies and individuals unconsciously commit on a daily basis. Through continuous feedback and updates to the learning model, the system evolves over time, enabling more accurate analysis and recommendations.

[0997] The processing flow will be explained below.

[0998] Step 1:

[0999] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[1000] Step 2:

[1001] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[1002] Step 3:

[1003] The user starts a meeting or starts writing a document. The device captures the audio data of the meeting in real time and sends it to the server. The text data is also captured in the same way.

[1004] Step 4:

[1005] The server converts the received voice data into text, and then inputs the text and sentence data into an AI learning model to analyze gender-related issues.

[1006] Step 5:

[1007] The server uses the analysis results to identify gender-related issues, such as the phrase "men should take on leadership roles."

[1008] Step 6:

[1009] Based on the problems identified by the server, a correction proposal is generated. As a correction proposal, the server provides the expression "Anyone can demonstrate leadership."

[1010] Step 7:

[1011] The device will notify the user in real time of suggested revisions, specifically displaying a message saying, "That expression contains gender bias. We recommend that you revise it to 'Leadership is open to everyone.'"

[1012] Step 8:

[1013] The user actually makes corrections based on the suggested corrections, checks the corrections, and sends feedback to the server if necessary.

[1014] Step 9:

[1015] The server receives user feedback and stores it in a database. The collected feedback data is used as retraining data for the AI ​​learning model.

[1016] Step 10:

[1017] The server periodically retrains the AI ​​learning model based on the feedback data, thereby improving the accuracy of the analysis.

[1018] Step 11:

[1019] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring problems and their improvement status.

[1020] Step 12:

[1021] The device notifies the user of the generated report, which the user can then download or view on the web.

[1022] Example 1

[1023] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1024] Until now, there has been a lack of systems that can instantly detect gender-discriminatory expressions used unconsciously during meetings and document writing and provide appropriate correction suggestions. As a result, expressions containing gender bias are often used as is, hindering the promotion of gender equality. In addition, there has been a lack of a mechanism for continuously improving the system based on feedback data, which has limited improvements in analysis accuracy. Furthermore, there has been a lack of a mechanism for regularly reporting analysis results and correction status to users.

[1025] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1026] In this invention, the server includes: means for capturing meeting and text data generated by users in real time; means for transmitting the captured data to the server; means for analyzing the data received by the server and identifying gender-related issues using an AI learning model; means for generating correction suggestions for the identified issues; means for notifying the user of the generated correction suggestions in real time; means for collecting feedback data provided by the user and updating the learning model; and means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user periodically. This makes it possible to instantly detect expressions containing gender bias and provide appropriate correction suggestions. Continuous improvement of the system based on feedback and regular status reports are also realized.

[1027] "User" refers to a user who uses the system to hold meetings or generate text data.

[1028] "Meeting and written data" refers to voice data, text data, and related information generated by the user.

[1029] "Capturing means" refers to devices and software for acquiring and processing user meeting and text data in real time.

[1030] "Server" refers to a computer system that receives data sent by users and analyzes and processes it.

[1031] "Transmitting means" refers to a communication device or network technology for delivering the captured data to the server.

[1032] "Analyzing" refers to the act of analyzing received data to identify specific issues or characteristics.

[1033] "Gender-related issues" refers to content that contains gender bias, prejudice, or discriminatory language based on gender.

[1034] An "AI learning model" refers to an algorithm that uses artificial intelligence technology to analyze data and detect specific patterns or problems.

[1035] "Means of identification" refers to techniques and methods that use AI learning models to identify gender-related issues.

[1036] "Means for generating fixes" refers to technologies and methods for automatically creating improvements or alternative expressions for identified problems.

[1037] "Notification means" refers to a device or method for notifying the user of generated revision suggestions and analysis results in real time.

[1038] "Feedback Data" refers to information about changes made by a user in response to a suggested revision and the results of those changes.

[1039] "Means for updating the learning model" refers to technologies and methods for retraining the AI ​​learning model based on collected feedback data and improving its accuracy.

[1040] "Means for generating reports" refers to the techniques and methods for creating reports summarizing gender-related issues and progress based on the analyzed data.

[1041] "Means for notification" refers to the technology or method for periodically providing the generated report to the user.

[1042] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[1043] This system captures and processes data in real time when users use their devices to hold meetings and generate documents. Specifically, the following hardware and software are used:

[1044] Device: A device used by a user, such as a computer, tablet, or smartphone, that includes a microphone, keyboard, and screen for capturing voice and text data.

[1045] Server: A computer system that receives, analyzes, and processes data, and analyzes the data using AI learning models. Examples of use include cloud services and virtual servers.

[1046] Software: This includes real-time voice recording applications and text editors used for data capture, AI learning models (e.g., GPT-3.5, BERT) used for data analysis, and report generation tools.

[1047] Using this hardware and software, the system operates as follows.

[1048] When a user accesses the system's website and creates a new account, registration information such as name, email address, and password is sent to the server, which then generates an initial setting profile based on the received information.

[1049] When a user starts a conference, the device captures voice data in real time and sends it to the server. When the user writes a sentence, data is also captured and sent to the server.

[1050] The server converts the received voice data into text and analyzes it using an AI learning model (e.g., OpenAI's GPT-3.5 or Google's BERT). This analysis identifies gender-related bias and discriminatory language. The server then generates appropriate correction suggestions for the identified issues. The generated correction suggestions are notified to the user in real time via their device.

[1051] For example, if a phrase such as "Men should demonstrate leadership" is detected, the server will generate a suggested correction such as "Anyone can demonstrate leadership." The device will notify the user and display a message saying, "That phrase contains gender bias. We recommend that you correct it to 'Anyone can demonstrate leadership.'"

[1052] The user corrects the expression based on the suggested corrections and sends the corrections and feedback to the server. The server stores this feedback in a database and uses it to retrain the AI ​​learning model, thereby improving the accuracy of detecting gender-related issues.

[1053] Based on the analyzed data, the server periodically generates reports summarizing the occurrence and improvement of gender issues, and notifies the user via their device. The user can then download and view the generated reports.

[1054] Prompt Sentence Examples

[1055] Here is an example of a prompt to input to a generative AI model:

[1056] Detect whether the following conversation contains gender bias and provide suggestions for correction.

[1057] (Conversation):

[1058] A: "In fact, there are many situations where men demonstrate leadership."

[1059] B: "Market it as a product for women."

[1060] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1061] Step 1: Initial User Setup

[1062] Input: A user visits the system's website and enters their name, email address, and password to create a new account.

[1063] Specific operation: The device captures the information entered by the user and sends it to the server.

[1064] Output: The server generates an initial profile based on the received information, which stores the user's basic information.

[1065] Step 2: Real-time data capture

[1066] Input: A user starts a conference and generates voice data.

[1067] Specific operation: The device uses the microphone to capture audio data in real time and sends the data to the server.

[1068] Output: The voice data sent to the server is saved. Similarly, when the user writes a sentence, the device captures the text data and sends it to the server.

[1069] Step 3: Convert and analyze audio data

[1070] Input: The server receives the voice data sent from the device.

[1071] Specific operation: The server converts the voice data into text (e.g., using the Google Speech-to-Text API).

[1072] Output: The server generates the converted text data and prepares it to be passed to the AI ​​learning model.

[1073] Step 4: Analyzing the text data

[1074] Input: The server receives the text data sent from the terminal.

[1075] Specific operation: The server uses an AI learning model (e.g., GPT-3.5 or BERT) to analyze text data.

[1076] Output: The server identifies gender-related issues and stores the information.

[1077] Step 5: Generate correction suggestions

[1078] Input: The server begins processing based on the parsed text data and identified issues.

[1079] Specific Actions: The server generates appropriate fixes for the identified issues.

[1080] Output: The server prepares the generated revision suggestions and creates information to notify the user.

[1081] Step 6: Notification of proposed amendments

[1082] Input: The server holds the generated revision suggestions.

[1083] Specific operation: The server sends the proposed revision to the device, and the device notifies the user. For example, a message such as "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" is displayed.

[1084] Output: The user receives notification of the proposed revision and confirms the contents.

[1085] Step 7: Gather user feedback

[1086] Input: The user corrects the text based on the suggested corrections.

[1087] Specific operation: The user inputs the corrected data and feedback into the terminal, which then transmits this data to the server.

[1088] Output: The server stores the received feedback data in a database.

[1089] Step 8: Update the learning model

[1090] Input: The server retrieves the accumulated feedback data.

[1091] Specific operation: The server retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model based on new data.

[1092] Output: Updated AI learning model.

[1093] Step 9: Generate reports and notifications

[1094] Input: The server receives the parsed data and feedback.

[1095] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues.

[1096] Output: Notifies the user of the generated report and provides a link to download or view it.

[1097] By clarifying the detailed processing and inputs and outputs at each step, it is possible to concretely demonstrate how the system prevents and resolves gender-related issues.

[1098] (Application example 1)

[1099] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1100] During meetings and work instructions within factories, unconsciously gender-biased remarks are often made, resulting in unequal working environments and a worsening atmosphere within the workplace. It is also difficult to immediately correct and improve these remarks, which can have a negative impact on employee morale and the company's reputation in the long term. Therefore, there is a growing need for a system that can identify gender-biased remarks within factories in real time and propose appropriate corrections.

[1101] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1102] In this invention, the server includes means for capturing meeting and text data generated by users, means for transmitting the captured data to the server, means for the server to analyze the data received and identify gender-related issues, means for generating correction proposals for the identified issues, means for notifying the user of the generated correction proposals, and means for capturing voice data in real time during factory meetings, detecting gender issues, and generating appropriate correction proposals. This makes it possible to immediately detect gender-biased remarks in the factory and present appropriate correction proposals.

[1103] "Meeting and text data" refers to text and voice data such as conversations, instructions, and reports that users generate in the factory.

[1104] The "capturing means" refers to a device and software for collecting voice data and text data from a user in real time and transmitting the data to a server.

[1105] "Server" means a central system for analyzing data and generating suggested fixes for identified problems; it is a computer system that communicates with users over a network.

[1106] "Means for analyzing" refers to the method and function by which the server analyzes the data received using an AI learning model to identify gender-related issues.

[1107] "Gender-related issues" are gender-based prejudices or discriminatory expressions contained in users' statements or writings.

[1108] The "means for generating suggested modifications" refers to the algorithms and processes for generating suggested modifications to appropriate expressions for the issues identified by the server.

[1109] The "means for notifying the generated revision proposal" is a device or software that displays or sounds the revision proposal generated by the server to the user in real time.

[1110] "Means of capturing and detecting gender issues in real time" refers to a function that collects audio data on the spot during meetings within the factory and instantly analyzes it to identify gender issues.

[1111] The system of the present invention is designed to improve fairness in the work environment by detecting gender bias in factory meetings and work instructions and suggesting appropriate corrections. The system has the function of capturing voice data and text data generated by users in real time and transmitting them to a server. Specific embodiments of the present invention will be described below.

[1112] Main features of the program

[1113] 1. User registration and initial setup:

[1114] Users create a new account through the system's website or through the smart glasses or robot, where they enter information such as name, email address, and password, which is then sent to the server, which generates an initial setup profile.

[1115] 2. Real-time voice / text data capture:

[1116] During meetings or work instructions in factories, smart glasses or robots capture users' voice data in real time, and use the SpeechRecognition library to convert the captured voice data into text data.

[1117] 3. Data analysis and gender issue detection:

[1118] The server analyzes the received voice and text data using AI learning models to detect specific keywords and expressions to identify gender-related issues.

[1119] 4. Proposed amendment generation and notification:

[1120] The server generates appropriate corrections for identified gender-related issues. For example, it generates a correction for the statement "men should demonstrate leadership" such as "anyone can demonstrate leadership." The server notifies the user of the corrections in real time.

[1121] Hardware and software used

[1122] Smart glasses or robots:

[1123] A device that captures voice data in real time within the factory and notifies the user of suggested corrections.

[1124] server:

[1125] A central computer system that analyzes data and generates corrections, with AI learning models installed to perform the analysis.

[1126] SpeechRecognition library:

[1127] A software library for converting audio data into text data.

[1128] Specific examples

[1129] Example of operation

[1130] During a factory meeting:

[1131] 1. A user starts a meeting and the smart glasses capture the audio data.

[1132] 2. The captured audio data is sent to the server in real time.

[1133] 3. The server analyzes statements containing gender bias, such as "I think men are better at this task than women," and detects problems.

[1134] 4. The server generates appropriate correction suggestions, such as "Anyone can be good at this task," and notifies the smart glasses.

[1135] 5. The user corrects the statement based on the suggested corrections and sends feedback to the robot.

[1136] Prompt Sentence Examples

[1137] Analyzes statements made during meetings in real time to detect gender bias. If a statement such as "men should take on leadership roles" is made, the system will suggest appropriate corrections.

[1138] effect

[1139] This makes it possible to immediately detect gender-biased remarks in factories and propose appropriate corrections, creating a fairer work environment and ensuring that all employees are evaluated equally, thereby improving the company's reputation and work efficiency.

[1140] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1141] Step 1:

[1142] A user creates a new account via a website, smart glasses, or a robot, entering information such as name, email address, and password, which is then sent to a server.

[1143] Input: User enters name, email address, and password.

[1144] Data processing / calculation: The input data is processed on the server to generate an initial setting profile.

[1145] Output: The default profile generated on the server.

[1146] Specific action: The user enters the required information to create an account and clicks the submit button.

[1147] Step 2:

[1148] Smart glasses or robots capture audio data of meetings and work instructions within the factory in real time and transmit the audio data to a server.

[1149] Input: User's speaking voice.

[1150] Data processing / calculation: Capture audio data and convert it to text data using the SpeechRecognition library. Send the converted text data to the server.

[1151] Output: The text data sent to the server.

[1152] How it works: Smart glasses or a robot senses and captures sound in real time.

[1153] Step 3:

[1154] The server analyzes the received text data and uses an AI learning model to identify gender-related issues.

[1155] Input: Text data.

[1156] Data processing / calculation: The received text data is input into an AI learning model, and calculations are performed to identify expressions with gender bias.

[1157] Output: Outcome data identifying gender-related issues.

[1158] Specific operation: The server receives the text data, analyzes it, and identifies expressions.

[1159] Step 4:

[1160] For identified gender-related issues, the server generates appropriate correction suggestions.

[1161] Input: Identified issue.

[1162] Data processing / calculation: Based on the problem, we run an algorithm to generate appropriate fixes.

[1163] Output: Revision proposal data.

[1164] What it does: The server analyzes the problem and algorithmically generates suggested fixes.

[1165] Step 5:

[1166] The generated revision suggestions are notified to the user using smart glasses or a robot.

[1167] Input: Revision proposal data.

[1168] Data processing / calculation: The proposed revision data is formatted for notification to the user and sent to the smart glasses or robot.

[1169] Output: Suggested revision notification displayed on smart glasses or robot.

[1170] Specific behavior: Smart glasses or robot receives the notification and displays it to the user.

[1171] Step 6:

[1172] The user corrects the comment based on the suggested corrections and transmits the feedback to the server.

[1173] Input: Corrected sentences and feedback data.

[1174] Data processing / calculation: The corrected sentences and feedback data are processed on the server and used to retrain the AI ​​model.

[1175] Output: Feedback data sent to the server.

[1176] Specific behavior: The user corrects their statement based on the suggested corrections, enters their feedback, and presses the submit button.

[1177] Step 7:

[1178] The server collects user feedback data and updates the AI ​​learning model.

[1179] Input: Feedback data.

[1180] Data processing / calculation: Retraining the AI ​​learning model based on feedback data.

[1181] Output: An updated AI learning model.

[1182] What happens: The server processes the feedback data and retrains the learning model.

[1183] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1184] The system of the present invention captures user-generated meeting and text data in real time, and combines this with an emotion engine that recognizes user emotions in real time to more effectively identify gender-related issues and provide appropriate correction suggestions.

[1185] What the program does

[1186] Initial setup and data reception

[1187] 1. User Initial Settings

[1188] A user accesses the system's website and creates a new account. They enter their name, email address, and password, then click the registration button. The device sends the entered information to the server, which receives the information and creates and saves the user profile.

[1189] Data capture and transmission

[1190] 2. Real-time data capture

[1191] A user starts a conference. The device captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server. Text data is also captured in the same way.

[1192] Data analysis and problem detection

[1193] 3. Data analysis and problem detection

[1194] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis. For example, if the expression "men should demonstrate leadership" is detected and the user simultaneously expresses negative feelings toward that statement, the issue will be set as a high priority.

[1195] Proposed fix generation and notification

[1196] 4. Generate correction suggestions

[1197] The server generates suggested corrections based on the identified problems and the user's emotional response to them. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentle explanation that reflects the user's emotions.

[1198] 5. Feedback Notification

[1199] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[1200] Gathering feedback and updating learning models

[1201] 6. Collecting User Feedback

[1202] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[1203] 7. Updating the learning model

[1204] The AI ​​learning model is retrained based on the feedback data collected by the server. The feedback also includes user emotional data, which further improves the accuracy of analysis.

[1205] Report generation and notification

[1206] 8. Generate a status report

[1207] The server then periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues, their improvement status, and insights based on user sentiment data.

[1208] 9. Report Notification

[1209] The device notifies the user of the generated report, which the user can then download or view on the web.

[1210] Specific operation example

[1211] Example 1: Analysis of speech and emotion data during a meeting

[1212] 1. A user starts a conference

[1213] A user initiates a conference and the terminal captures voice data and emotion data.

[1214] 2. Transmission and analysis of voice and emotion data

[1215] The device sends the captured voice and emotion data to a server. The server converts the voice data into text and analyzes it using an emotion engine. For example, if a user says "products for women" and expresses negative emotion, this will be identified as a high-priority issue.

[1216] 3. Identifying issues and providing fixes

[1217] The server determines that the expression "products for women" is gender discriminatory and generates a correction suggestion of "products for all customers." Using emotional data, the server confirms that the user has little resistance to this correction suggestion and notifies the user of the suggestion in a gentler way.

[1218] 4. User Corrections and Feedback

[1219] The user then modifies the expression based on the suggestions and provides feedback to the server. This feedback is collected along with the user's emotional data and is reflected in subsequent analyses.

[1220] This system not only identifies gender-discriminatory expressions, but also provides appropriate correction suggestions that take the user's feelings into consideration, allowing for more effective gender bias reduction. This allows users to make corrections without any resistance, and continuous feedback and updates to the learning model improve the accuracy and effectiveness of the entire system.

[1221] The processing flow will be explained below.

[1222] Step 1:

[1223] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[1224] Step 2:

[1225] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[1226] Step 3:

[1227] The user starts a meeting or starts writing a document. The device captures the meeting's audio data in real time, and simultaneously captures the user's emotional data using the emotion engine. The captured data is sent to the server.

[1228] Step 4:

[1229] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis.

[1230] Step 5:

[1231] The server uses the analysis results to identify gender-related issues, such as the expression "men should play a leadership role," and detects the user's negative emotional state in response to it.

[1232] Step 6:

[1233] The server generates correction suggestions for identified problems that take into account the user's emotional data. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentler suggestion that takes into account the user's emotional state.

[1234] Step 7:

[1235] The device notifies the user in real time of suggested revisions, specifically, "That expression is gender biased. We recommend that you revise it to 'Leadership is something everyone can demonstrate,'" and displays a gentler message tailored to the user's emotional state.

[1236] Step 8:

[1237] The user corrects the expression based on the suggested corrections, and the results of the corrections and the emotions at that time are fed back to the server.

[1238] Step 9:

[1239] The server receives user feedback and stores it in a database. The feedback data collected by the server is used to retrain the AI ​​learning model.

[1240] Step 10:

[1241] The server periodically retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model.

[1242] Step 11:

[1243] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring issues and their improvement status, as well as insights based on user sentiment data.

[1244] Step 12:

[1245] The device notifies the user of the generated report, which the user can then download or view on the web.

[1246] Example 2

[1247] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1248] Conventional meeting and text data analysis systems do not take users' feelings into account when identifying gender-related issues, which can lead to reluctance to accept suggested revisions. Furthermore, the learning model is not updated properly based on feedback, which reduces the system's analytical accuracy and effectiveness. Furthermore, it is difficult to continuously monitor the occurrence and improvement status of gender issues.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1250] In this invention, the server includes means for capturing meeting and text data generated by a user, means for transmitting the captured data and emotional data to the server, means for converting voice data into text, means for analyzing the converted text data and emotional data to identify gender-related issues, means for generating suggested revisions using a generative AI model, and means for notifying the user of the generated suggested revisions while taking the user's emotional state into consideration. This makes it possible to identify and correct gender-related issues while taking the user's emotions into consideration, and to continuously improve the analysis accuracy and effectiveness of the entire system through feedback.

[1251] A "user" is an entity that uses the system to generate meeting and text data and receives analysis results and suggested revisions.

[1252] "Conference data" refers to voice data and text data generated by users during a conference.

[1253] "Text data" refers to text data such as documents and reports generated by users.

[1254] "Means of capture" refers to the hardware and software capabilities for collecting meeting and text data in real time.

[1255] "Emotional data" refers to data for identifying and recording a user's emotional state.

[1256] "Server" refers to a computer system that performs central data processing, analyzes received data, and outputs results.

[1257] "Means for converting to text" refers to technology or devices that convert voice data into text information.

[1258] "Means of analysis" refers to the algorithms and AI models used to process data and identify gender-related issues.

[1259] "Gender-related issues" refer to elements in meetings or written data that indicate gender bias or discrimination.

[1260] A "generative AI model" refers to a machine learning model that generates corrections and predictions from given data.

[1261] "Means for generating correction proposals" refers to technologies and functions for creating improvement proposals for identified problems.

[1262] "Notification means that take into account the emotional state" refers to a method or technology that takes the user's emotions into account and conveys information in an appropriate format.

[1263] "Feedback data" refers to information such as improvement suggestions provided by users and their impressions after use.

[1264] "Means for updating learning models" refers to techniques and methods for retraining AI models using collected feedback data to improve their accuracy.

[1265] The means for generating "reports" refers to the function for creating reports summarizing the results of analysis and the occurrence and improvement status of gender issues.

[1266] "Means of periodic notification" refers to techniques or methods that provide reports or information to users at regular intervals.

[1267] The system of the present invention captures user-generated meeting and text data, identifies gender-related issues in real time, and provides suggested corrections. A specific embodiment of the system is described below.

[1268] Hardware and software used

[1269] Hardware

[1270] Device: The device that a user uses to conduct a meeting. For example, a PC, tablet, or smartphone.

[1271] Server: A central computer system that analyzes and stores data.

[1272] software

[1273] Conferencing applications: Tools for capturing audio data. Examples: Zoom, Microsoft Teams.

[1274] Emotion engine: Software for capturing user emotional data. Example: Affectiva SDK.

[1275] Speech Recognition API: A service for converting voice data into text data. Example: Google Speech-to-Text API.

[1276] Generative AI models: Models that generate fixes for gender-related issues. Example: GPT-3.

[1277] System Operation

[1278] 1. User Initial Settings

[1279] A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button. The device sends the entered information to the server, which receives the information and creates and stores the user profile.

[1280] 2. Real-time data capture

[1281] A user starts a conference. The terminal captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server in real time.

[1282] 3. Data analysis and problem detection

[1283] The server converts the received voice data into text using a speech recognition API. The server then inputs the converted text and sentence data into a generative AI model to analyze gender-related issues. Emotion data recognized by the emotion engine is also incorporated into the analysis.

[1284] 4. Generate correction suggestions

[1285] Based on the problems identified by the server and the user's emotional response, the generative AI model generates suggested corrections. For example, it might recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions.

[1286] 5. Feedback Notification

[1287] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[1288] 6. Collecting User Feedback

[1289] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[1290] 7. Updating the learning model

[1291] The AI ​​learning model is retrained based on the feedback data collected by the server, which further improves the accuracy of analysis.

[1292] 8. Report Generation and Notification

[1293] The server periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues and their improvement status, as well as insights based on the user's emotional data. The device notifies the user of the generated report. The user can download the report or view it online.

[1294] Prompt Sentence Examples

[1295] For example, if the following audio data is captured:

[1296] "This product is for women."

[1297] For this audio data, the system generates the following correction suggestions:

[1298] This product is for all customers.

[1299] Based on this suggested fix, the system will notify the user with the following message:

[1300] "The wording has gender bias. We recommend amending it to say, 'This product is for all customers.'"

[1301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1302] Step 1:

[1303] A user accesses the system's website and creates a new account. As input, the user enters their name, email address, and password, and presses the register button. The terminal sends this input data to the server. The server processes the received information, generates a new user profile, and stores it in the database. As output, a user profile is generated, and the user receives a notification that the account creation has been completed.

[1304] Step 2:

[1305] A user starts a conference. The user launches a conference application and communicates with conference participants via voice. As input, the user's voice data and emotion data are captured on the device. The device transmits this data to the server in real time. As output, the voice data and emotion data of the conference are stored on the server.

[1306] Step 3:

[1307] The server converts the received voice data into text data using a voice recognition API. The voice data is passed to the voice recognition API as input, and data processing is performed. The converted text data is generated as output.

[1308] Step 4:

[1309] The server analyzes the converted text data and emotion data. As input, the text data and emotion data are passed to the analysis algorithm. The server uses these data to identify gender-related issues. As output, gender-related issues are detected.

[1310] Step 5:

[1311] The server generates suggested corrections for the identified issues. As input, gender-related issues and emotional data are entered into the generative AI model. Based on this, the server generates appropriate suggested corrections. For example, it recommends the expression "Anyone can demonstrate leadership." As output, an appropriate suggested correction is generated.

[1312] Step 6:

[1313] The device notifies the user of the proposed revision in real time. As input, the generated revision proposal is sent from the server to the device. The device displays a notification message in a gentle manner that takes into account the user's emotional state. As output, the user receives a notification based on the proposed revision.

[1314] Step 7:

[1315] The user modifies the expression based on the suggested modifications and feeds the results back to the server. As input, the modified content and emotional state are sent from the device to the server. The server stores them in a database. As output, the user's feedback data is collected.

[1316] Step 8:

[1317] The server retrains the learning model based on the collected feedback data. As input, the feedback data and emotion data are passed to the AI ​​model retraining process. This allows the server to improve the analysis accuracy. As output, an updated AI model is generated.

[1318] Step 9:

[1319] The server periodically generates reports on the occurrence and improvement status of gender issues based on the analyzed data. The analyzed data is processed within the server as input. The server compiles a report on frequently occurring issues, their improvement status, and insights based on user sentiment data. A report is generated as output.

[1320] Step 10:

[1321] The terminal notifies the user of the generated report. As input, the generated report is sent from the server to the terminal. The user receives a notification and can download the report or view it on the web. As output, the report is provided to the user.

[1322] (Application example 2)

[1323] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1324] Gender bias and harassment remain serious issues in modern workplaces and online communities. In particular, unconsciously discriminatory gender remarks in meetings and written texts can have a negative impact on the work environment and interpersonal relationships. Furthermore, some users find it difficult to make corrections without feeling uncomfortable, making it difficult to take appropriate measures. Therefore, a system that can effectively detect gender bias and harassment and provide appropriate correction suggestions is needed.

[1325] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1326] In this invention, the server includes a means incorporating an emotion engine that recognizes a user's emotion data in real time, a means for providing suggested revisions in a gentle tone based on the emotion data, and a means for notifying the user of the generated suggested revisions. This allows the user to make corrections without feeling any resistance. Furthermore, by effectively identifying gender bias issues and quickly providing suggested improvements, the system can contribute to improving the workplace and community environment.

[1327] A "user" is a subject who uses this system and is a person who holds meetings and generates text data.

[1328] "Meeting and written data" refers to the content of communication generated by users, and includes voice data and text data.

[1329] "Capture" refers to the act of collecting and storing user-generated meeting and text data in real time.

[1330] "Server" refers to the computer and system that receives and analyzes the captured data.

[1331] "Gender-related issues" refer to elements of gender bias and harassment contained in meetings and written data.

[1332] "Amendment" refers to alternative language or courses of action proposed to remedy a gender-related shortcoming.

[1333] "Notification" is the act of informing the user of the generated revision proposal.

[1334] "Emotion data" refers to data that indicates the emotional state detected from the user's statements and actions.

[1335] "Emotion Engine" refers to algorithms and systems that recognize and analyze a user's emotional state in real time.

[1336] "Feedback" is the act of a user returning their reaction or opinion to the server regarding a proposed revision.

[1337] "Learning model" refers to a machine learning algorithm that is retrained based on collected data to improve analysis accuracy.

[1338] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[1339] 1. Initial Setup

[1340] A user accesses the system's website and creates a new account. By entering information such as name, email address, and password and pressing the registration button, a user profile is created. This information is sent from the client terminal to the server, and then received by the server.

[1341] 2. Data Capture

[1342] When a user starts a conference, the client device (smartphone, computer, tablet, etc.) captures the conference audio data in real time. The emotion engine also recognizes the user's emotion data in real time. This data is then sent to the server in real time.

[1343] 3. Data Analysis

[1344] The server uses speech recognition software to convert the received voice data into text. The converted text and sentence data are then input into an AI learning model to analyze gender-related issues. Emotional data recognized by an emotion engine is also incorporated into the analysis, and issues are prioritized based on the user's emotions. For example, if the expression "men should take on leadership roles" is detected and the user is expressing negative emotions, this issue is set as a high priority.

[1345] 4. Proposed amendment generation and notification

[1346] The server generates suggested revisions based on the identified issues and the user's emotional data. For example, it may recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions. The generated revisions are notified to the user in real time. Specifically, the message displayed is gentle and takes into account the user's emotional state: "That expression contains gender bias. We recommend revising it to 'Anyone can demonstrate leadership.'"

[1347] 5. Gather feedback and update the learning model

[1348] The user makes corrections based on the suggested corrections and then provides feedback on the content and emotional state of the corrections to the server. This feedback data is stored in a database and later used to retrain the AI ​​learning model. This improves the system's analysis accuracy and allows it to provide more effective corrections.

[1349] 6. Report Generation and Notifications

[1350] The server generates a report on the occurrence and improvement status of gender issues based on the analyzed data. The report details frequently occurring problems and their improvement status, as well as insights based on the user's emotional data. The generated report is periodically notified to the user, who can download the report or view it online.

[1351] Specific examples

[1352] For example, if a user says "a product for women" during a meeting, the system will detect this statement as gender bias and suggest the expression "a product for all customers." At the same time, the system will analyze the user's negative sentiment toward the statement and notify them of appropriate revisions in a gentler tone.

[1353] Example prompts for generative AI models

[1354] Analyze the following text to determine whether it contains gender bias:

[1355] "Products for women"

[1356] Also, determine whether this text evokes negative emotions.

[1357] In this way, the present invention provides a system that effectively detects gender bias and harassment and provides appropriate correction suggestions.

[1358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1359] Step 1: Initial User Setup

[1360] Specific operation: A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button.

[1361] Input: Name, email address, and password entered by the user

[1362] Data processing: The terminal formats the input information and sends it to the server.

[1363] Output: The server generates and stores a user profile based on the information received.

[1364] Step 2: Real-time data capture

[1365] Specific operation: A user starts a conference, and the terminal captures the voice data and emotion data of the conference.

[1366] Input: Voice data and user emotion data obtained from the meeting

[1367] Data processing: Voice data is captured in real time, and emotion data is collected simultaneously.

[1368] Output: Captured data is sent to the server

[1369] Step 3: Data analysis and problem detection

[1370] What it does: The server uses speech recognition software to convert the received voice data into text. It also inputs the text and sentence data into an AI learning model to analyze gender-related issues. The emotion engine also incorporates emotional data into the analysis.

[1371] Input: Voice data and emotion data received by the server

[1372] Data processing: Converting voice data into text and inputting it into an AI learning model for analysis. Emotional data is also incorporated into the analysis.

[1373] Output: Gender-related issues are identified and prioritized.

[1374] Step 4: Generate correction suggestions

[1375] Specific operation: The server generates a correction suggestion based on the identified problem and the user's sentiment data. For example, it recommends the expression "Anyone can demonstrate leadership."

[1376] Input: Identified issues and sentiment data

[1377] Data processing: Generate correction suggestions based on problem and sentiment data

[1378] Output: Generated revision suggestions are generated

[1379] Step 5: Notification of proposed amendments

[1380] Specific behavior: The generated revision suggestions are notified to the user in real time, with a message saying, "That expression contains gender bias. We recommend changing it to 'Leadership is open to everyone.'"

[1381] Input: Generated correction suggestions

[1382] Data processing: Converting data into the appropriate notification format

[1383] Output: The user is notified of the proposed fix

[1384] Step 6: Gather feedback

[1385] Specific operation: The user makes corrections based on the suggested corrections and feeds back the results and emotional state to the server.

[1386] Input: Feedback data and revised content provided by the user

[1387] Data processing: Format the feedback data and store it in a database

[1388] Output: Feedback data is saved in a database

[1389] Step 7: Update the learning model

[1390] Specific operation: The AI ​​learning model is retrained using the feedback data collected by the server.

[1391] Input: Feedback data stored in the database

[1392] Data processing: Retraining the AI ​​learning model with feedback data

[1393] Output: Updated training model is completed.

[1394] Step 8: Generate a status report

[1395] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues based on the analyzed data.

[1396] Input: Parsed data

[1397] Data processing: Collect and analyze the occurrence and improvement status and generate reports

[1398] Output: A report is generated

[1399] Step 9: Report Notification

[1400] Specific Behavior: Notifies the user of the generated report. The user can download the report or view it on the web.

[1401] Input: Generated report

[1402] Data processing: Converting data into the appropriate notification format

[1403] Output: The user is notified of the report

[1404] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1405] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1406] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1407] [Fourth embodiment]

[1408] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1409] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1410] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1411] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1412] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1414] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1415] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1416] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1417] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1418] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1419] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1420] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1421] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[1422] What the program does

[1423] Initial setup and data reception

[1424] 1. User Initial Settings

[1425] A user accesses the system's website and creates a new account. Registration information such as name, email address, and password are entered. After each piece of information is entered, the device sends it to the server. The server receives this information and generates an initial setting profile.

[1426] Data capture and transmission

[1427] 2. Real-time data capture

[1428] A user starts a conference. The terminal captures the user's voice data in real time and sends it to the server. Similarly, text data is captured as the user composes the text.

[1429] Data analysis and problem detection

[1430] 3. Data analysis and problem detection

[1431] The server analyzes the received audio and text materials and uses AI learning models to identify gender-related bias and discriminatory language. For example, the server will detect if the content includes the phrase "men should play a leadership role."

[1432] Proposed fix generation and notification

[1433] 4. Generate correction suggestions

[1434] The server generates suggested corrections for the identified problems. For example, it generates a suggested correction for the detected expression, such as "Anyone can demonstrate leadership."

[1435] 5. Feedback Notification

[1436] The device will notify the user in real time of suggested revisions, such as "That expression contains gender bias. We recommend changing it to 'Leadership is open to everyone.'"

[1437] Gathering feedback and updating learning models

[1438] 6. Collecting User Feedback

[1439] After the user makes corrections based on the suggested corrections, they send the corrections and feedback to the server, which collects this feedback and stores it in a database to improve the accuracy of analysis in the future.

[1440] 7. Updating the learning model

[1441] The server retrains the AI ​​learning model based on the feedback data collected, improving the accuracy of detecting gender-related issues.

[1442] Report generation and notification

[1443] 8. Generate a status report

[1444] The server then compiles the data analyzed and periodically generates reports detailing the occurrence and improvement of gender issues.

[1445] 9. Report Notification

[1446] The device will notify the user of the generated report and provide a link to download or view it.

[1447] Specific operation example

[1448] Example 1: Analysis of audio data during a meeting

[1449] 1. A user starts a conference

[1450] A user initiates a conference and the terminal captures the audio data.

[1451] 2. Sending and analyzing audio data

[1452] The device sends the captured voice data to a server, which converts the voice data into text and analyzes it using an AI learning model.

[1453] 3. Identifying issues and providing fixes

[1454] The server detects gender-discriminatory expressions such as "products for women" and generates a correction suggestion. The device notifies the user with a message saying, "That expression contains gender bias. We recommend changing it to 'products for all customers.'"

[1455] 4. User Corrections and Feedback

[1456] After users modify the expressions based on the suggestions, they send feedback to the server, which then reflects the improvements in gender bias in subsequent analyses.

[1457] This system can prevent gender discrimination that companies and individuals unconsciously commit on a daily basis. Through continuous feedback and updates to the learning model, the system evolves over time, enabling more accurate analysis and recommendations.

[1458] The processing flow will be explained below.

[1459] Step 1:

[1460] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[1461] Step 2:

[1462] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[1463] Step 3:

[1464] The user starts a meeting or starts writing a document. The device captures the audio data of the meeting in real time and sends it to the server. The text data is also captured in the same way.

[1465] Step 4:

[1466] The server converts the received voice data into text, and then inputs the text and sentence data into an AI learning model to analyze gender-related issues.

[1467] Step 5:

[1468] The server uses the analysis results to identify gender-related issues, such as the phrase "men should take on leadership roles."

[1469] Step 6:

[1470] Based on the problems identified by the server, a correction proposal is generated. As a correction proposal, the server provides the expression "Anyone can demonstrate leadership."

[1471] Step 7:

[1472] The device will notify the user in real time of suggested revisions, specifically displaying a message saying, "That expression contains gender bias. We recommend that you revise it to 'Leadership is open to everyone.'"

[1473] Step 8:

[1474] The user actually makes corrections based on the suggested corrections, checks the corrections, and sends feedback to the server if necessary.

[1475] Step 9:

[1476] The server receives user feedback and stores it in a database. The collected feedback data is used as retraining data for the AI ​​learning model.

[1477] Step 10:

[1478] The server periodically retrains the AI ​​learning model based on the feedback data, thereby improving the accuracy of the analysis.

[1479] Step 11:

[1480] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring problems and their improvement status.

[1481] Step 12:

[1482] The device notifies the user of the generated report, which the user can then download or view on the web.

[1483] Example 1

[1484] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1485] Until now, there has been a lack of systems that can instantly detect gender-discriminatory expressions used unconsciously during meetings and document writing and provide appropriate correction suggestions. As a result, expressions containing gender bias are often used as is, hindering the promotion of gender equality. In addition, there has been a lack of a mechanism for continuously improving the system based on feedback data, which has limited improvements in analysis accuracy. Furthermore, there has been a lack of a mechanism for regularly reporting analysis results and correction status to users.

[1486] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1487] In this invention, the server includes: means for capturing meeting and text data generated by users in real time; means for transmitting the captured data to the server; means for analyzing the data received by the server and identifying gender-related issues using an AI learning model; means for generating correction suggestions for the identified issues; means for notifying the user of the generated correction suggestions in real time; means for collecting feedback data provided by the user and updating the learning model; and means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user periodically. This makes it possible to instantly detect expressions containing gender bias and provide appropriate correction suggestions. Continuous improvement of the system based on feedback and regular status reports are also realized.

[1488] "User" refers to a user who uses the system to hold meetings or generate text data.

[1489] "Meeting and written data" refers to voice data, text data, and related information generated by the user.

[1490] "Capturing means" refers to devices and software for acquiring and processing user meeting and text data in real time.

[1491] "Server" refers to a computer system that receives data sent by users and analyzes and processes it.

[1492] "Transmitting means" refers to a communication device or network technology for delivering the captured data to the server.

[1493] "Analyzing" refers to the act of analyzing received data to identify specific issues or characteristics.

[1494] "Gender-related issues" refers to gender-based prejudice or discriminatory language, or content that contains gender bias.

[1495] An "AI learning model" refers to an algorithm that uses artificial intelligence technology to analyze data and detect specific patterns or problems.

[1496] "Means of identification" refers to techniques and methods that use AI learning models to identify gender-related issues.

[1497] "Means for generating fixes" refers to technologies or methods for automatically creating improvements or alternative expressions for identified problems.

[1498] "Notification means" refers to a device or method that notifies the user of generated revision suggestions and analysis results in real time.

[1499] "Feedback Data" refers to information about changes made by users in response to suggested revisions and the results of those changes.

[1500] "Means for updating the learning model" refers to technologies and methods for retraining the AI ​​learning model based on collected feedback data and improving its accuracy.

[1501] "Means for generating reports" refers to the techniques and methods for creating reports summarizing gender-related issues and progress based on the analyzed data.

[1502] "Means for notification" refers to the technology or method for periodically providing the generated report to the user.

[1503] The system of the present invention captures meeting and text data generated by users in real time and analyzes it on a server to identify gender-related issues and provide appropriate corrections, thereby preventing gender discrimination.

[1504] This system captures and processes data in real time when users use their devices to hold meetings and generate documents. Specifically, the following hardware and software are used:

[1505] Device: A device used by a user, such as a computer, tablet, or smartphone, that includes a microphone, keyboard, and screen for capturing voice and text data.

[1506] Server: A computer system that receives, analyzes, and processes data, and analyzes the data using AI learning models. Examples of use include cloud services and virtual servers.

[1507] Software: This includes real-time voice recording applications and text editors used for data capture, AI learning models (e.g., GPT-3.5, BERT) used for data analysis, and report generation tools.

[1508] Using this hardware and software, the system operates as follows.

[1509] When a user accesses the system's website and creates a new account, registration information such as name, email address, and password is sent to the server, which then generates an initial setting profile based on the received information.

[1510] When a user starts a conference, the device captures voice data in real time and sends it to the server. When the user writes a sentence, data is also captured and sent to the server.

[1511] The server converts the received voice data into text and analyzes it using an AI learning model (e.g., OpenAI's GPT-3.5 or Google's BERT). This analysis identifies gender-related bias and discriminatory language. The server then generates appropriate correction suggestions for the identified issues. The generated correction suggestions are notified to the user in real time via their device.

[1512] For example, if a phrase such as "Men should demonstrate leadership" is detected, the server will generate a suggested correction such as "Anyone can demonstrate leadership." The device will notify the user and display a message saying, "That phrase contains gender bias. We recommend that you correct it to 'Anyone can demonstrate leadership.'"

[1513] The user corrects the expression based on the suggested corrections and sends the corrections and feedback to the server. The server stores this feedback in a database and uses it to retrain the AI ​​learning model, thereby improving the accuracy of detecting gender-related issues.

[1514] Based on the analyzed data, the server periodically generates reports summarizing the occurrence and improvement of gender issues, and notifies the user via their device. The user can then download and view the generated reports.

[1515] Prompt Sentence Examples

[1516] Here is an example of a prompt to input to a generative AI model:

[1517] Detect whether the following conversation contains gender bias and provide suggestions for correction.

[1518] (Conversation):

[1519] A: "In fact, there are many situations where men demonstrate leadership."

[1520] B: "Market it as a product for women."

[1521] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1522] Step 1: Initial User Setup

[1523] Input: A user visits the system's website and enters their name, email address, and password to create a new account.

[1524] Specific operation: The device captures the information entered by the user and sends it to the server.

[1525] Output: The server generates an initial profile based on the received information, which stores the user's basic information.

[1526] Step 2: Real-time data capture

[1527] Input: A user starts a conference and generates voice data.

[1528] Specific operation: The device uses the microphone to capture audio data in real time and sends the data to the server.

[1529] Output: The voice data sent to the server is saved. Similarly, when the user writes a sentence, the device captures the text data and sends it to the server.

[1530] Step 3: Convert and analyze audio data

[1531] Input: The server receives the voice data sent from the device.

[1532] Specific operation: The server converts the voice data into text (e.g., using the Google Speech-to-Text API).

[1533] Output: The server generates the converted text data and prepares it to be passed to the AI ​​learning model.

[1534] Step 4: Analyzing the text data

[1535] Input: The server receives the text data sent from the terminal.

[1536] Specific operation: The server uses an AI learning model (e.g., GPT-3.5 or BERT) to analyze text data.

[1537] Output: The server identifies gender-related issues and stores the information.

[1538] Step 5: Generate correction suggestions

[1539] Input: The server begins processing based on the parsed text data and identified issues.

[1540] Specific Actions: The server generates appropriate fixes for the identified issues.

[1541] Output: The server prepares the generated revision suggestions and creates information to notify the user.

[1542] Step 6: Notification of proposed amendments

[1543] Input: The server holds the generated revision suggestions.

[1544] Specific operation: The server sends the proposed revision to the device, and the device notifies the user. For example, a message such as "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" is displayed.

[1545] Output: The user receives notification of the proposed revision and confirms the contents.

[1546] Step 7: Gather user feedback

[1547] Input: The user corrects the text based on the suggested corrections.

[1548] Specific operation: The user inputs the corrected data and feedback into the terminal, which then transmits this data to the server.

[1549] Output: The server stores the received feedback data in a database.

[1550] Step 8: Update the learning model

[1551] Input: The server retrieves the accumulated feedback data.

[1552] Specific operation: The server retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model based on new data.

[1553] Output: Updated AI learning model.

[1554] Step 9: Generate reports and notifications

[1555] Input: The server receives the parsed data and feedback.

[1556] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues.

[1557] Output: Notifies the user of the generated report and provides a link to download or view it.

[1558] By clarifying the detailed processing and inputs and outputs at each step, it is possible to concretely demonstrate how the system prevents and resolves gender-related issues.

[1559] (Application example 1)

[1560] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1561] During meetings and work instructions within factories, unconsciously gender-biased remarks are often made, resulting in unequal working environments and a worsening atmosphere within the workplace. It is also difficult to immediately correct and improve these remarks, which can have a negative impact on employee morale and the company's reputation in the long term. Therefore, there is a growing need for a system that can identify gender-biased remarks within factories in real time and propose appropriate corrections.

[1562] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1563] In this invention, the server includes means for capturing meeting and text data generated by users, means for transmitting the captured data to the server, means for the server to analyze the data received and identify gender-related issues, means for generating correction proposals for the identified issues, means for notifying the user of the generated correction proposals, and means for capturing voice data in real time during factory meetings, detecting gender issues, and generating appropriate correction proposals. This makes it possible to immediately detect gender-biased remarks in the factory and present appropriate correction proposals.

[1564] "Meeting and text data" refers to text and voice data such as conversations, instructions, and reports that users generate in the factory.

[1565] The "capturing means" refers to a device and software for collecting voice data and text data from a user in real time and transmitting the data to a server.

[1566] "Server" means a central system for analyzing data and generating suggested fixes for identified problems; it is a computer system that communicates with users over a network.

[1567] "Means for analyzing" refers to the method and function by which the server analyzes the data received using an AI learning model to identify gender-related issues.

[1568] "Gender-related issues" are gender-based prejudices or discriminatory expressions contained in users' statements or writings.

[1569] The "means for generating suggested modifications" refers to the algorithms and processes for generating suggested modifications to appropriate expressions for the issues identified by the server.

[1570] The "means for notifying the generated revision proposal" is a device or software that displays or sounds the revision proposal generated by the server to the user in real time.

[1571] "Means of capturing and detecting gender issues in real time" refers to a function that collects audio data on the spot during meetings within the factory and instantly analyzes it to identify gender issues.

[1572] The system of the present invention is designed to improve fairness in the work environment by detecting gender bias in factory meetings and work instructions and suggesting appropriate corrections. The system has the function of capturing voice data and text data generated by users in real time and transmitting them to a server. Specific embodiments of the present invention will be described below.

[1573] Main features of the program

[1574] 1. User registration and initial setup:

[1575] Users create a new account through the system's website or through the smart glasses or robot, where they enter information such as name, email address, and password, which is then sent to the server, which generates an initial setup profile.

[1576] 2. Real-time voice / text data capture:

[1577] During meetings or work instructions in factories, smart glasses or robots capture users' voice data in real time, and use the SpeechRecognition library to convert the captured voice data into text data.

[1578] 3. Data analysis and gender issue detection:

[1579] The server analyzes the received voice and text data using AI learning models to detect specific keywords and expressions to identify gender-related issues.

[1580] 4. Proposed amendment generation and notification:

[1581] The server generates appropriate corrections for identified gender-related issues. For example, it generates a correction for the statement "men should demonstrate leadership" such as "anyone can demonstrate leadership." The server notifies the user of the corrections in real time.

[1582] Hardware and software used

[1583] Smart glasses or robots:

[1584] A device that captures voice data in real time within the factory and notifies the user of suggested corrections.

[1585] server:

[1586] A central computer system that analyzes data and generates corrections, with AI learning models installed to perform the analysis.

[1587] SpeechRecognition library:

[1588] A software library for converting audio data into text data.

[1589] Specific examples

[1590] Example of operation

[1591] During a factory meeting:

[1592] 1. A user starts a meeting and the smart glasses capture the audio data.

[1593] 2. The captured audio data is sent to the server in real time.

[1594] 3. The server analyzes statements containing gender bias, such as "I think men are better at this task than women," and detects problems.

[1595] 4. The server generates appropriate correction suggestions, such as "Anyone can be good at this task," and notifies the smart glasses.

[1596] 5. The user corrects the statement based on the suggested corrections and sends feedback to the robot.

[1597] Prompt Sentence Examples

[1598] Analyzes statements made during meetings in real time to detect gender bias. If a statement such as "men should take on leadership roles" is made, the system will suggest appropriate corrections.

[1599] effect

[1600] This makes it possible to immediately detect gender-biased remarks in factories and propose appropriate corrections, creating a fairer work environment and ensuring that all employees are evaluated equally, thereby improving the company's reputation and work efficiency.

[1601] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1602] Step 1:

[1603] A user creates a new account via a website, smart glasses, or a robot, entering information such as name, email address, and password, which is then sent to a server.

[1604] Input: User enters name, email address, and password.

[1605] Data processing / calculation: The input data is processed on the server to generate an initial setting profile.

[1606] Output: The default profile generated on the server.

[1607] Specific action: The user enters the required information to create an account and clicks the submit button.

[1608] Step 2:

[1609] Smart glasses or robots capture audio data of meetings and work instructions within the factory in real time and transmit the audio data to a server.

[1610] Input: User's speaking voice.

[1611] Data processing / calculation: Capture audio data and convert it to text data using the SpeechRecognition library. Send the converted text data to the server.

[1612] Output: The text data sent to the server.

[1613] How it works: Smart glasses or a robot senses and captures sound in real time.

[1614] Step 3:

[1615] The server analyzes the received text data and uses an AI learning model to identify gender-related issues.

[1616] Input: Text data.

[1617] Data processing / calculation: The received text data is input into an AI learning model, and calculations are performed to identify expressions with gender bias.

[1618] Output: Outcome data identifying gender-related issues.

[1619] Specific operation: The server receives the text data, analyzes it, and identifies expressions.

[1620] Step 4:

[1621] For identified gender-related issues, the server generates appropriate correction suggestions.

[1622] Input: Identified issue.

[1623] Data processing / calculation: Based on the problem, we run an algorithm to generate appropriate fixes.

[1624] Output: Revision proposal data.

[1625] What it does: The server analyzes the problem and algorithmically generates suggested fixes.

[1626] Step 5:

[1627] The generated revision suggestions are notified to the user using smart glasses or a robot.

[1628] Input: Revision proposal data.

[1629] Data processing / calculation: The proposed revision data is formatted for notification to the user and sent to the smart glasses or robot.

[1630] Output: Suggested revision notification displayed on smart glasses or robot.

[1631] Specific behavior: Smart glasses or robot receives the notification and displays it to the user.

[1632] Step 6:

[1633] The user corrects the comment based on the suggested corrections and transmits the feedback to the server.

[1634] Input: Corrected sentences and feedback data.

[1635] Data processing / calculation: The corrected sentences and feedback data are processed on the server and used to retrain the AI ​​model.

[1636] Output: Feedback data sent to the server.

[1637] Specific behavior: The user corrects their statement based on the suggested corrections, enters their feedback, and presses the submit button.

[1638] Step 7:

[1639] The server collects user feedback data and updates the AI ​​learning model.

[1640] Input: Feedback data.

[1641] Data processing / calculation: Retraining the AI ​​learning model based on feedback data.

[1642] Output: An updated AI learning model.

[1643] What happens: The server processes the feedback data and retrains the learning model.

[1644] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1645] The system of the present invention captures user-generated meeting and text data in real time, and combines this with an emotion engine that recognizes user emotions in real time to more effectively identify gender-related issues and provide appropriate correction suggestions.

[1646] What the program does

[1647] Initial setup and data reception

[1648] 1. User Initial Settings

[1649] A user accesses the system's website and creates a new account. They enter their name, email address, and password, then click the registration button. The device sends the entered information to the server, which receives the information and creates and saves the user profile.

[1650] Data capture and transmission

[1651] 2. Real-time data capture

[1652] A user starts a conference. The device captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server. Text data is also captured in the same way.

[1653] Data analysis and problem detection

[1654] 3. Data analysis and problem detection

[1655] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis. For example, if the expression "men should demonstrate leadership" is detected and the user simultaneously expresses negative feelings toward that statement, the issue will be set as a high priority.

[1656] Proposed fix generation and notification

[1657] 4. Generate correction suggestions

[1658] The server generates suggested corrections based on the identified problems and the user's emotional response to them. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentle explanation that reflects the user's emotions.

[1659] 5. Feedback Notification

[1660] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[1661] Gathering feedback and updating learning models

[1662] 6. Collecting User Feedback

[1663] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[1664] 7. Updating the learning model

[1665] The AI ​​learning model is retrained based on the feedback data collected by the server. The feedback also includes user emotional data, which further improves the accuracy of analysis.

[1666] Report generation and notification

[1667] 8. Generate a status report

[1668] The server then periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues, their improvement status, and insights based on user sentiment data.

[1669] 9. Report Notification

[1670] The device notifies the user of the generated report, which the user can then download or view on the web.

[1671] Specific operation example

[1672] Example 1: Analysis of speech and emotion data during a meeting

[1673] 1. A user starts a conference

[1674] A user initiates a conference and the terminal captures voice data and emotion data.

[1675] 2. Transmission and analysis of voice and emotion data

[1676] The device sends the captured voice and emotion data to a server. The server converts the voice data into text and analyzes it using an emotion engine. For example, if a user says "products for women" and expresses negative emotion, this will be identified as a high-priority issue.

[1677] 3. Identifying issues and providing fixes

[1678] The server determines that the expression "products for women" is gender discriminatory and generates a correction suggestion of "products for all customers." Using emotional data, the server confirms that the user has little resistance to this correction suggestion and notifies the user of the suggestion in a gentler way.

[1679] 4. User Corrections and Feedback

[1680] The user then modifies the expression based on the suggestions and provides feedback to the server. This feedback is collected along with the user's emotional data and is reflected in subsequent analyses.

[1681] This system not only identifies gender-discriminatory expressions, but also provides appropriate correction suggestions that take the user's feelings into consideration, allowing for more effective gender bias reduction. This allows users to make corrections without any resistance, and continuous feedback and updates to the learning model improve the accuracy and effectiveness of the entire system.

[1682] The processing flow will be explained below.

[1683] Step 1:

[1684] A user accesses the system's website and creates a new account. The user enters their name, email address, and password and presses the registration button. The device sends the entered information to the server.

[1685] Step 2:

[1686] The server receives the user's registration information and stores it in a database. The server creates a user profile and performs initial settings.

[1687] Step 3:

[1688] The user starts a meeting or starts writing a document. The device captures the meeting's audio data in real time, and simultaneously captures the user's emotional data using the emotion engine. The captured data is sent to the server.

[1689] Step 4:

[1690] The server converts the received voice data into text. The server then inputs the text and sentence data into an AI learning model to analyze gender-related issues. Emotional data recognized by the emotion engine is also incorporated into the analysis.

[1691] Step 5:

[1692] The server uses the analysis results to identify gender-related issues, such as the expression "men should play a leadership role," and detects the user's negative emotional state in response to it.

[1693] Step 6:

[1694] The server generates correction suggestions for identified problems that take into account the user's emotional data. For example, it recommends the expression "Anyone can demonstrate leadership" and adds a gentler suggestion that takes into account the user's emotional state.

[1695] Step 7:

[1696] The device notifies the user in real time of suggested revisions, specifically, "That expression is gender biased. We recommend that you revise it to 'Leadership is something everyone can demonstrate,'" and displays a gentler message tailored to the user's emotional state.

[1697] Step 8:

[1698] The user corrects the expression based on the suggested corrections, and the results of the corrections and the emotions at that time are fed back to the server.

[1699] Step 9:

[1700] The server receives user feedback and stores it in a database. The feedback data collected by the server is used to retrain the AI ​​learning model.

[1701] Step 10:

[1702] The server periodically retrains the AI ​​learning model based on the feedback data, improving the accuracy of the model.

[1703] Step 11:

[1704] Based on the analyzed data, the server generates a report summarizing the occurrence and improvement status of gender issues. The report details frequently occurring issues and their improvement status, as well as insights based on user sentiment data.

[1705] Step 12:

[1706] The device notifies the user of the generated report, which the user can then download or view on the web.

[1707] Example 2

[1708] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1709] Conventional meeting and text data analysis systems do not take users' feelings into account when identifying gender-related issues, which can lead to reluctance to accept suggested revisions. Furthermore, the learning model is not updated properly based on feedback, which reduces the system's analytical accuracy and effectiveness. Furthermore, it is difficult to continuously monitor the occurrence and improvement status of gender issues.

[1710] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1711] In this invention, the server includes means for capturing meeting and text data generated by a user, means for transmitting the captured data and emotional data to the server, means for converting voice data into text, means for analyzing the converted text data and emotional data to identify gender-related issues, means for generating suggested revisions using a generative AI model, and means for notifying the user of the generated suggested revisions while taking the user's emotional state into consideration. This makes it possible to identify and correct gender-related issues while taking the user's emotions into consideration, and to continuously improve the analysis accuracy and effectiveness of the entire system through feedback.

[1712] A "user" is an entity that uses the system to generate meeting and text data and receives analysis results and suggested revisions.

[1713] "Conference data" refers to voice data and text data generated by users during a conference.

[1714] "Text data" refers to text data such as documents and reports generated by users.

[1715] "Means of capture" refers to the hardware and software capabilities for collecting meeting and text data in real time.

[1716] "Emotional data" refers to data for identifying and recording a user's emotional state.

[1717] "Server" refers to a computer system that performs central data processing, analyzes received data, and outputs results.

[1718] "Means for converting to text" refers to technology or devices that convert voice data into text information.

[1719] "Means of analysis" refers to the algorithms and AI models used to process data and identify gender-related issues.

[1720] "Gender-related issues" refer to elements in meetings or written data that indicate gender bias or discrimination.

[1721] A "generative AI model" refers to a machine learning model that generates corrections and predictions from given data.

[1722] "Means for generating correction proposals" refers to technologies and functions for creating improvement proposals for identified problems.

[1723] "Notification means that take into account the emotional state" refers to a method or technology that takes the user's emotions into account and conveys information in an appropriate format.

[1724] "Feedback data" refers to information such as improvement suggestions provided by users and their impressions after use.

[1725] "Means for updating learning models" refers to techniques and methods for retraining AI models using collected feedback data to improve their accuracy.

[1726] The means for generating "reports" refers to the function for creating reports summarizing the results of analysis and the occurrence and improvement status of gender issues.

[1727] "Means of periodic notification" refers to techniques or methods that provide reports or information to users at regular intervals.

[1728] The system of the present invention captures user-generated meeting and text data, identifies gender-related issues in real time, and provides suggested corrections. A specific embodiment of the system is described below.

[1729] Hardware and software used

[1730] Hardware

[1731] Device: The device that a user uses to conduct a meeting. For example, a PC, tablet, or smartphone.

[1732] Server: A central computer system that analyzes and stores data.

[1733] software

[1734] Conferencing applications: Tools for capturing audio data. Examples: Zoom, Microsoft Teams.

[1735] Emotion engine: Software for capturing user emotional data. Example: Affectiva SDK.

[1736] Speech Recognition API: A service for converting voice data into text data. Example: Google Speech-to-Text API.

[1737] Generative AI models: Models that generate fixes for gender-related issues. Example: GPT-3.

[1738] System Operation

[1739] 1. User Initial Settings

[1740] A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button. The device sends the entered information to the server, which receives the information and creates and stores the user profile.

[1741] 2. Real-time data capture

[1742] A user starts a conference. The terminal captures the conference's audio data, and the emotion engine simultaneously captures the user's emotional data. These data are sent to the server in real time.

[1743] 3. Data analysis and problem detection

[1744] The server converts the received voice data into text using a speech recognition API. The server then inputs the converted text and sentence data into a generative AI model to analyze gender-related issues. Emotion data recognized by the emotion engine is also incorporated into the analysis.

[1745] 4. Generate correction suggestions

[1746] Based on the problems identified by the server and the user's emotional response, the generative AI model generates suggested corrections. For example, it might recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions.

[1747] 5. Feedback Notification

[1748] The device notifies the user in real time of suggested revisions, specifically, "That expression contains gender bias. We recommend that you revise it to 'Leadership is available to everyone.'" The message is displayed in a gentler tone that takes into account the user's emotional state.

[1749] 6. Collecting User Feedback

[1750] The user actually makes corrections based on the suggested corrections. They check the corrections and their emotional state, and send feedback to the server if necessary. The server receives this feedback and stores it in a database.

[1751] 7. Updating the learning model

[1752] The AI ​​learning model is retrained based on the feedback data collected by the server, which further improves the accuracy of analysis.

[1753] 8. Report Generation and Notification

[1754] The server periodically generates reports summarizing the occurrence and improvement status of gender issues based on the analyzed data. The reports include detailed information on frequently occurring issues and their improvement status, as well as insights based on the user's emotional data. The device notifies the user of the generated report. The user can download the report or view it online.

[1755] Prompt Sentence Examples

[1756] For example, if the following audio data is captured:

[1757] "This product is for women."

[1758] For this audio data, the system generates the following correction suggestions:

[1759] This product is for all customers.

[1760] Based on this suggested fix, the system will notify the user with the following message:

[1761] "The wording has gender bias. We recommend amending it to say, 'This product is for all customers.'"

[1762] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1763] Step 1:

[1764] A user accesses the system's website and creates a new account. As input, the user enters their name, email address, and password, and presses the register button. The terminal sends this input data to the server. The server processes the received information, generates a new user profile, and stores it in the database. As output, a user profile is generated, and the user receives a notification that the account creation has been completed.

[1765] Step 2:

[1766] A user starts a conference. The user launches a conference application and communicates with conference participants via voice. As input, the user's voice data and emotion data are captured on the device. The device transmits this data to the server in real time. As output, the voice data and emotion data of the conference are stored on the server.

[1767] Step 3:

[1768] The server converts the received voice data into text data using a voice recognition API. The voice data is passed to the voice recognition API as input, and data processing is performed. The converted text data is generated as output.

[1769] Step 4:

[1770] The server analyzes the converted text data and emotion data. As input, the text data and emotion data are passed to the analysis algorithm. The server uses these data to identify gender-related issues. As output, gender-related issues are detected.

[1771] Step 5:

[1772] The server generates suggested corrections for the identified issues. As input, gender-related issues and emotional data are entered into the generative AI model. Based on this, the server generates appropriate suggested corrections. For example, it recommends the expression "Anyone can demonstrate leadership." As output, an appropriate suggested correction is generated.

[1773] Step 6:

[1774] The device notifies the user of the proposed revision in real time. As input, the generated revision proposal is sent from the server to the device. The device displays a notification message in a gentle manner that takes into account the user's emotional state. As output, the user receives a notification based on the proposed revision.

[1775] Step 7:

[1776] The user modifies the expression based on the suggested modifications and feeds the results back to the server. As input, the modified content and emotional state are sent from the device to the server. The server stores them in a database. As output, the user's feedback data is collected.

[1777] Step 8:

[1778] The server retrains the learning model based on the collected feedback data. As input, the feedback data and emotion data are passed to the AI ​​model retraining process. This allows the server to improve the analysis accuracy. As output, an updated AI model is generated.

[1779] Step 9:

[1780] The server periodically generates reports on the occurrence and improvement status of gender issues based on the analyzed data. The analyzed data is processed within the server as input. The server compiles a report on frequently occurring issues, their improvement status, and insights based on user sentiment data. A report is generated as output.

[1781] Step 10:

[1782] The terminal notifies the user of the generated report. As input, the generated report is sent from the server to the terminal. The user receives a notification and can download the report or view it on the web. As output, the report is provided to the user.

[1783] (Application example 2)

[1784] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1785] Gender bias and harassment remain serious issues in modern workplaces and online communities. In particular, unconsciously discriminatory gender remarks in meetings and written texts can have a negative impact on the work environment and interpersonal relationships. Furthermore, some users find it difficult to make corrections without feeling uncomfortable, making it difficult to take appropriate measures. Therefore, a system that can effectively detect gender bias and harassment and provide appropriate correction suggestions is needed.

[1786] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1787] In this invention, the server includes a means incorporating an emotion engine that recognizes a user's emotion data in real time, a means for providing suggested revisions in a gentle tone based on the emotion data, and a means for notifying the user of the generated suggested revisions. This allows the user to make corrections without feeling any resistance. Furthermore, by effectively identifying gender bias issues and quickly providing suggested improvements, the system can contribute to improving the workplace and community environment.

[1788] A "user" is a subject who uses this system and is a person who holds meetings and generates text data.

[1789] "Meeting and written data" refers to the content of communication generated by users, and includes voice data and text data.

[1790] "Capture" refers to the act of collecting and storing user-generated meeting and text data in real time.

[1791] "Server" refers to the computer and system that receives and analyzes the captured data.

[1792] "Gender-related issues" refer to elements of gender bias and harassment contained in meetings and written data.

[1793] "Amendment" refers to alternative language or courses of action proposed to remedy a gender-related shortcoming.

[1794] "Notification" is the act of informing the user of the generated revision proposal.

[1795] "Emotion data" refers to data that indicates the emotional state detected from the user's statements and actions.

[1796] "Emotion Engine" refers to algorithms and systems that recognize and analyze a user's emotional state in real time.

[1797] "Feedback" is the act of a user returning their reaction or opinion to the server regarding a proposed revision.

[1798] "Learning model" refers to a machine learning algorithm that is retrained based on collected data to improve analysis accuracy.

[1799] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described in detail below with reference to the accompanying drawings.

[1800] 1. Initial Setup

[1801] A user accesses the system's website and creates a new account. By entering information such as name, email address, and password and pressing the registration button, a user profile is created. This information is sent from the client terminal to the server, and then received by the server.

[1802] 2. Data Capture

[1803] When a user starts a conference, the client device (smartphone, computer, tablet, etc.) captures the conference audio data in real time. The emotion engine also recognizes the user's emotion data in real time. This data is then sent to the server in real time.

[1804] 3. Data Analysis

[1805] The server uses speech recognition software to convert the received voice data into text. The converted text and sentence data are then input into an AI learning model to analyze gender-related issues. Emotional data recognized by an emotion engine is also incorporated into the analysis, and issues are prioritized based on the user's emotions. For example, if the expression "men should take on leadership roles" is detected and the user is expressing negative emotions, this issue is set as a high priority.

[1806] 4. Proposed amendment generation and notification

[1807] The server generates suggested revisions based on the identified issues and the user's emotional data. For example, it may recommend the expression "Anyone can demonstrate leadership," and add a gentle explanation that reflects the user's emotions. The generated revisions are notified to the user in real time. Specifically, the message displayed is gentle and takes into account the user's emotional state: "That expression contains gender bias. We recommend revising it to 'Anyone can demonstrate leadership.'"

[1808] 5. Gather feedback and update the learning model

[1809] The user makes corrections based on the suggested corrections and then provides feedback on the content and emotional state of the corrections to the server. This feedback data is stored in a database and later used to retrain the AI ​​learning model. This improves the system's analysis accuracy and allows it to provide more effective corrections.

[1810] 6. Report Generation and Notifications

[1811] The server generates a report on the occurrence and improvement status of gender issues based on the analyzed data. The report details frequently occurring problems and their improvement status, as well as insights based on the user's emotional data. The generated report is periodically notified to the user, who can download the report or view it online.

[1812] Specific examples

[1813] For example, if a user says "a product for women" during a meeting, the system will detect this statement as gender bias and suggest the expression "a product for all customers." At the same time, the system will analyze the user's negative sentiment toward the statement and notify them of appropriate revisions in a gentler tone.

[1814] Example prompts for generative AI models

[1815] Analyze the following text to determine whether it contains gender bias:

[1816] "Products for women"

[1817] Also, determine whether this text evokes negative emotions.

[1818] In this way, the present invention provides a system that effectively detects gender bias and harassment and provides appropriate correction suggestions.

[1819] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1820] Step 1: Initial User Setup

[1821] Specific operation: A user accesses the system's website and creates a new account. The user enters their name, email address, and password, and presses the register button.

[1822] Input: Name, email address, and password entered by the user

[1823] Data processing: The terminal formats the input information and sends it to the server.

[1824] Output: The server generates and stores a user profile based on the information received.

[1825] Step 2: Real-time data capture

[1826] Specific operation: A user starts a conference, and the terminal captures the voice data and emotion data of the conference.

[1827] Input: Voice data and user emotion data obtained from the meeting

[1828] Data processing: Voice data is captured in real time, and emotion data is collected simultaneously.

[1829] Output: Captured data is sent to the server

[1830] Step 3: Data analysis and problem detection

[1831] What it does: The server uses speech recognition software to convert the received voice data into text. It also inputs the text and sentence data into an AI learning model to analyze gender-related issues. The emotion engine also incorporates emotional data into the analysis.

[1832] Input: Voice data and emotion data received by the server

[1833] Data processing: Converting voice data into text and inputting it into an AI learning model for analysis. Emotional data is also incorporated into the analysis.

[1834] Output: Gender-related issues are identified and prioritized.

[1835] Step 4: Generate correction suggestions

[1836] Specific operation: The server generates a correction suggestion based on the identified problem and the user's sentiment data. For example, it recommends the expression "Anyone can demonstrate leadership."

[1837] Input: Identified issues and sentiment data

[1838] Data processing: Generate correction suggestions based on problem and sentiment data

[1839] Output: Generated revision suggestions are generated

[1840] Step 5: Notification of proposed amendments

[1841] Specific behavior: The generated revision suggestions are notified to the user in real time, with a message saying, "That expression contains gender bias. We recommend changing it to 'Leadership is open to everyone.'"

[1842] Input: Generated correction suggestions

[1843] Data processing: Converting data into the appropriate notification format

[1844] Output: The user is notified of the proposed fix

[1845] Step 6: Gather feedback

[1846] Specific operation: The user makes corrections based on the suggested corrections and feeds back the results and emotional state to the server.

[1847] Input: Feedback data and revised content provided by the user

[1848] Data processing: Format the feedback data and store it in a database

[1849] Output: Feedback data is saved in a database

[1850] Step 7: Update the learning model

[1851] Specific operation: The AI ​​learning model is retrained using the feedback data collected by the server.

[1852] Input: Feedback data stored in the database

[1853] Data processing: Retraining the AI ​​learning model with feedback data

[1854] Output: Updated training model is completed.

[1855] Step 8: Generate a status report

[1856] Specific operation: The server generates a report summarizing the occurrence and improvement status of gender issues based on the analyzed data.

[1857] Input: Parsed data

[1858] Data processing: Collect and analyze the occurrence and improvement status and generate reports

[1859] Output: A report is generated

[1860] Step 9: Report Notification

[1861] Specific Behavior: Notifies the user of the generated report. The user can download the report or view it on the web.

[1862] Input: Generated report

[1863] Data processing: Converting data into the appropriate notification format

[1864] Output: The user is notified of the report

[1865] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1866] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1867] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1868] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1869] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1870] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1871] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1872] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1873] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1874] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1875] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1876] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1877] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1878] 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.

[1879] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1880] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1881] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1882] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1883] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1884] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1885] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1886] The following is further disclosed regarding the above embodiment.

[1887] (Claim 1)

[1888] means for capturing user-generated meeting and text data;

[1889] means for transmitting the captured data to a server;

[1890] a means for the server to analyze the data received and identify gender-related issues; and

[1891] a means for generating suggested fixes for identified problems;

[1892] means for notifying the user of the generated revision suggestions;

[1893] A system including:

[1894] (Claim 2)

[1895] 10. The system of claim 1, further comprising means for collecting user-provided feedback data and updating the learning model based on the server-identified gender-related issues and suggested corrections.

[1896] (Claim 3)

[1897] The system according to claim 1, further comprising means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user of the report on a regular basis.

[1898] "Example 1"

[1899] (Claim 1)

[1900] a means for capturing user-generated meeting and text data in real time;

[1901] means for transmitting the captured data to a server;

[1902] The server analyzes the received data and identifies gender-related issues using an AI learning model; and

[1903] a means for generating suggested fixes for identified problems;

[1904] means for notifying the user of the generated revision suggestions in real time;

[1905] A system including:

[1906] (Claim 2)

[1907] 10. The system of claim 1, further comprising means for collecting user-provided feedback data and updating the learning model based on the server-identified gender-related issues and suggested corrections.

[1908] (Claim 3)

[1909] The system according to claim 1, further comprising means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user of the report on a regular basis.

[1910] "Application Example 1"

[1911] (Claim 1)

[1912] means for capturing user-generated meeting and text data;

[1913] means for transmitting the captured data to a server;

[1914] a means for the server to analyze the data received and identify gender-related issues; and

[1915] a means for generating suggested fixes for identified problems;

[1916] means for notifying the user of the generated revision suggestions;

[1917] A means to capture real-time audio data during factory meetings to detect gender issues and generate appropriate corrections;

[1918] A system including:

[1919] (Claim 2)

[1920] 10. The system of claim 1, further comprising means for collecting user-provided feedback data and updating the learning model based on the server-identified gender-related issues and suggested corrections.

[1921] (Claim 3)

[1922] The system according to claim 1, further comprising means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user of the report on a regular basis.

[1923] "Example 2: Combining Emotion Engines"

[1924] (Claim 1)

[1925] means for capturing user-generated meeting and text data;

[1926] means for transmitting the captured data and emotion data to a server;

[1927] A means for converting the received voice data into text by the server;

[1928] a means for analyzing the converted text data and sentiment data to identify gender-related issues;

[1929] A means for generating suggested fixes for identified issues using a generative AI model; and

[1930] a means for notifying the user of the generated revision proposal while taking into account the user's emotional state;

[1931] A system including:

[1932] (Claim 2)

[1933] 10. The system of claim 1, further comprising means for collecting user-provided feedback data and updating the learning model based on the server-identified gender-related issues and suggested corrections.

[1934] (Claim 3)

[1935] The system according to claim 1, further comprising means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user of the report on a regular basis.

[1936] "Application example 2 when combining emotion engines"

[1937] (Claim 1)

[1938] means for capturing user-generated meeting and text data;

[1939] means for transmitting the captured data to a server;

[1940] a means for the server to analyze the data received and identify gender-related issues; and

[1941] a means for generating suggested fixes for identified problems;

[1942] means for notifying the user of the generated revision suggestions;

[1943] A means incorporating an emotion engine that recognizes user emotion data in real time;

[1944] A means of providing gentle revision suggestions based on the sentiment data;

[1945] A system including:

[1946] (Claim 2)

[1947] 10. The system of claim 1, further comprising means for collecting user-provided feedback data and updating the learning model based on the server-identified gender-related issues and suggested corrections.

[1948] (Claim 3)

[1949] The system according to claim 1, further comprising means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data and notifying the user of the report on a regular basis. [Explanation of symbols]

[1950] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing user-generated meeting and text data; means for transmitting the captured data to a server; a means for the server to analyze the data received and identify gender-related issues; and a means for generating suggested fixes for identified problems; means for notifying the user of the generated revision suggestions; A system including:

2. The system of claim 1 , further comprising means for collecting user-provided feedback data and updating the learning model based on the server-identified gender-related issues and suggested corrections.

3. The system according to claim 1, further comprising means for generating a report summarizing the occurrence and improvement status of gender issues based on the analyzed data, and notifying the user of the report periodically.

Images