System

Abstract

A system is provided.SOLUTION: A system comprising: means for capturing a message; means for transmitting the captured message to a central server; means for analyzing the message received by the central server with a natural language processing engine; means for generating feedback based on the analyzed data with a generative AI; and means for transmitting the generated feedback to a user terminal.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] Many companies implement educational programs to instill the idea of ​​diversity, equity, and inclusion (DE&I), but it is difficult to incorporate a DE&I perspective into everyday work. Furthermore, it is unrealistic to assign employees from diverse minority groups to every department and create a diverse workplace, making it difficult for them to learn about DE&I through their work and to think about it as something that concerns them personally. Therefore, there is a need to develop a system that provides opportunities to consider DE&I perspectives throughout daily work. [Means for solving the problem]

[0005] To solve this problem, we provide a system that includes a means for capturing messages, a means for sending the captured messages to a central server, a means for analyzing the messages received by the central server using a natural language processing engine, a means for a generation AI to generate feedback based on the analyzed data, and a means for sending the generated feedback to a user device. This system allows users to incorporate a DE&I perspective into their everyday communications. Specifically, messages sent by users are captured from their communication tools and sent to a central server. The server analyzes the messages using a natural language processing engine, and the generation AI generates appropriate feedback based on the analysis results. This feedback is sent to the user device, where the user can review the content and modify the message as necessary. Furthermore, this system includes a means for the generation AI to consider minority perspectives when generating feedback, allowing it to provide feedback that reflects the perspectives of each minority group.

[0006] A "message" is text information that a user sends using a communication tool.

[0007] "Capture" is the act of detecting and capturing a message entered by a user.

[0008] A "central server" is a computer system that receives captured messages and performs analysis and feedback generation.

[0009] "Transmitting" is the act of transferring captured messages or generated feedback as data to another device or system.

[0010] A "natural language processing engine" is software that analyzes messages written in natural language and understands their meaning and grammatical structure.

[0011] "Parsing" is the process of breaking down the content of a message and understanding its meaning and grammatical structure.

[0012] "Generative AI" is artificial intelligence software that automatically creates appropriate feedback based on analyzed data.

[0013] "Feedback" is information indicating evaluations and suggestions for a message, including improvements and instructions that are useful to the user.

[0014] A "minority perspective" is a view that takes into account the experiences and feelings of individuals or groups who belong to minority groups. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention promotes diversity, equity, and inclusion (DE&I) perspectives in everyday work through a system that captures messages, analyzes them, and generates feedback. Specifically, we provide a system that achieves this goal by utilizing user devices, servers, generative AI, and natural language processing engines.

[0037] First, a user uses their device to type and send a message using a communication tool such as Slack or email. At this time, the device captures the message in real time and sends it to a central server. The central server analyzes the received message using a natural language processing engine, and a generation AI generates feedback for the message based on the analysis results. This feedback is created taking into account the perspectives of each minority group and suggests how the user's message should be improved. The generated feedback is then sent back to the user's device, where the user can review it and revise the message if necessary.

[0038] To give a specific example, suppose a user sends a message such as "Ask the new employee if they like ramen." This message is captured by the device and sent to a central server. The central server passes the message to a natural language processing engine for analysis. Based on the analysis results, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can confirm it. This allows the user to revise the message to "Ask the new employee what their lunch preferences are" and send it.

[0039] This system can also be configured to handle comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, which can then be processed in the same way as other messages, providing real-time feedback. This allows it to provide improvement suggestions from a DE&I perspective for comments made during meetings.

[0040] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[0041] The above is a specific embodiment for carrying out the present invention.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] Device: A user types and sends a message using a communication tool such as Slack or email, and the device captures the message in real time.

[0045] Step 2:

[0046] Terminal: Sends captured messages to a central server using an API request.

[0047] Step 3:

[0048] Server: A central server receives messages and passes them to a natural language processing (NLP) engine, which analyzes the message for meaning and grammatical structure.

[0049] Step 4:

[0050] Server: Based on the analyzed message data, the AI ​​generates appropriate feedback that takes into account the perspectives of each minority group.

[0051] Step 5:

[0052] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[0053] Step 6:

[0054] Device: Check the feedback received by the user. Notify the user of the feedback displayed on the device.

[0055] Step 7:

[0056] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[0057] Step 8:

[0058] Terminal: Resend the corrected message. The process begins again at step 1.

[0059] The above is a specific processing flow for implementing this invention. This series of processes allows users to incorporate a DE&I perspective into their everyday communications.

[0060] Example 1

[0061] 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."

[0062] Diversity, equity, and inclusion (DE&I) are important values ​​in today's business environment, but it can be difficult to properly incorporate these perspectives into everyday work communications. Furthermore, messages and comments made during meetings can contain unconscious bias, which can negatively impact relationships and company culture. Traditional methods make it difficult to provide real-time feedback, and manual reviews and training have limitations. Therefore, there is a need for a system that automatically provides feedback that takes diversity, equity, and inclusion into consideration.

[0063] 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.

[0064] In this invention, the server includes a means for capturing messages, a means for transmitting the captured messages to a central server, a means for analyzing the messages received by the central server using a natural language processing engine, a means for a generation AI to generate feedback based on the analysis results, a means for transmitting the generated feedback to a user terminal, a means for the user to check the feedback and modify the message as necessary, and a means for converting statements made during meetings into text data using a transcription AI, analyzing the text data, and generating feedback, thereby enabling users to naturally incorporate diversity, equity, and inclusion into their daily work communications.

[0065] The "means for capturing messages" is a function for collecting messages that users input and send using a communication tool in real time.

[0066] The "means for transmitting captured messages to a central server" is a function for transferring collected message data to a central server via a network.

[0067] "Means for analyzing messages received by the central server using a natural language processing engine" refers to a function that uses natural language processing technology to analyze message data received by the central server and understand the context and meaning.

[0068] "Means for the generative AI to generate feedback based on the analysis results" refers to a function in which the generative AI automatically creates appropriate feedback based on the analysis results obtained by the natural language processing engine.

[0069] "Means for sending generated feedback to a user terminal" refers to a function that transfers the feedback created by the generation AI to a user terminal via a network.

[0070] "Means for users to review feedback and revise messages as necessary" refers to a function that allows users to view feedback on their device and edit or revise the original message based on the feedback.

[0071] "A means of converting statements made during meetings into text data using transcription AI, analyzing that text data, and generating feedback" is a function that converts spoken statements made during meetings into text using transcription technology, analyzes that text data using a natural language processing engine, and uses generation AI to create feedback.

[0072] "Diversity" means bringing together individuals with different attributes and backgrounds and respecting and accepting their differences.

[0073] "Fairness" means a state in which all individuals are treated equally and unfair discrimination and prejudice are eliminated.

[0074] "Inclusion" means that all people have the opportunity to participate and contribute to an organization or society, and their value is recognized.

[0075] The present invention is directed to promoting diversity, equity, and inclusion (DE&I) using a system that captures messages, analyzes them, and generates feedback. Specific embodiments for implementing the present invention are described below.

[0076] Components

[0077] 1. User Device

[0078] A device such as a computer or smartphone used by a user, on which communication tools such as Slack or email are installed.

[0079] 2. Central Server

[0080] A central processing unit for receiving messages, performing analysis, and generating feedback. It includes a high-performance processor and storage.

[0081] 3. Natural Language Processing Engine

[0082] Software for analyzing the context and meaning of messages. Examples include Google® Cloud Natural Language API and IBM Watson®.

[0083] 4. Generation AI

[0084] An artificial intelligence model that generates feedback based on analyzed data. Examples include OpenAI's GPT-3.

[0085] 5. Transcription AI

[0086] Software for transcribing what is said during meetings in real time, such as the open source Kaldi or the commercial Google Speech-to-Text.

[0087] Program processing

[0088] Capture and send messages

[0089] When a user sends a message from their device via Slack or email, the message is captured in real time, stored in a dedicated message queue by a script running on the device, and then sent to a central server via an HTTP POST request.

[0090] Message Parsing

[0091] When the server receives a message, it passes it to a natural language processing engine to analyze its context and meaning. This analysis is performed using Google Cloud Natural Language API, etc. The analysis results are recorded on the server and then passed to the generative AI model.

[0092] Generate feedback

[0093] The AI ​​then generates appropriate feedback based on the analysis results. The generated feedback takes into account minority perspectives in particular. For example, the following prompt is sent to the AI:

[0094] "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0095] Send and review feedback

[0096] The generated feedback is sent to the user's device via an HTTP POST request, where the user can view the feedback and modify the message if necessary.

[0097] Responding to comments made during meetings

[0098] This system can also process comments made during meetings. When a user speaks, the transcription AI converts the comment into text data. The converted text data is analyzed in the same way as other messages, and feedback is generated by the generation AI. This makes it possible to provide appropriate feedback in real time for comments made during meetings.

[0099] Specific examples

[0100] For example, if a user sends a message saying, "Let's ask the new employee if he likes ramen," the message is immediately captured and sent to the server. The server passes the message to a natural language processing engine for analysis, and the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee. We suggest changing it to a more neutral phrase, such as 'Let's ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can review it and modify the message.

[0101] Using this system will promote communication that takes diversity, equity, and inclusion into consideration, and support the understanding and implementation of DE&I across the company.

[0102] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0103] Step 1: Enter and capture your message

[0104] A user types and sends a message using a communication tool such as Slack or email.

[0105] An example of a message to enter is, "Let's ask new employees if they like ramen."

[0106] The terminal captures this message in real time and stores it in a dedicated message queue.

[0107] Input: User input message

[0108] Output: Message data stored in the message queue

[0109] Step 2: Sending and Receiving Messages

[0110] The device sends the data stored in the message queue to the central server via an HTTP POST request.

[0111] The server receives this data at the receiving endpoint (API endpoint).

[0112] Input: Message data retrieved from the message queue

[0113] Output: Message data received by the server

[0114] Step 3: Parse the message

[0115] The server passes the received message to a natural language processing (NLP) engine for analysis.

[0116] For example, use the Google Cloud Natural Language API to analyze the context and tone of messages.

[0117] Input: Message data sent to the central server

[0118] Output: Analysis results obtained from the natural language processing engine

[0119] Step 4: Generate feedback

[0120] The server sends a prompt to the generation AI based on the analysis results.

[0121] Example: Send a prompt to the generation AI saying, "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0122] Generative AI generates feedback based on prompts.

[0123] Input: Analysis results from the natural language processing engine and prompt sentences

[0124] Output: Feedback obtained from the generative AI

[0125] Step 5: Submit your feedback

[0126] The server sends the feedback received from the generated AI to the user's device via an HTTP POST request.

[0127] Input: Feedback generated by the generative AI

[0128] Output: Feedback sent to the user's device

[0129] Step 6: View and review feedback

[0130] The device displays the received feedback on the screen.

[0131] The user reviews the feedback and modifies the original message if necessary.

[0132] Input: Feedback received

[0133] Output: Corrected or confirmed message

[0134] Step 7: Transcribe what is said during the meeting and generate feedback

[0135] A user speaks during a conference.

[0136] Transcription AI converts speech into text data.

[0137] The text data is processed in the same manner as in steps 3 to 6 above to generate analysis and feedback.

[0138] Input: Voice remarks during a meeting

[0139] Output: Generated feedback

[0140] This series of steps will create a system that helps users communicate with diversity, equity, and inclusion in their daily work.

[0141] (Application example 1)

[0142] 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."

[0143] In traditional customer service, it is difficult for customer service staff to respond in real time while taking diversity, equity, and inclusion (DE&I) into consideration. As a result, they may unconsciously include bias or lack of understanding in their communications with customers, which can lead to lower customer satisfaction and problems. To solve this problem, a system is needed that provides feedback from a DE&I perspective in real time while customers are interacting with the service.

[0144] 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.

[0145] In this invention, the server includes means for capturing voice, means for converting voice to text, means for transmitting the converted text data to a central server, means for analyzing the text data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data, and means for transmitting the generated feedback to a display device. This makes it possible to provide staff with feedback that takes diversity, equity, and inclusion (DE&I) perspectives into consideration in real time while they are serving customers, thereby improving the quality of communication.

[0146] "Audio capture means" refers to a device that collects the remarks of service staff and customers in real time. Specifically, it uses a voice input device such as a microphone.

[0147] "Speech-to-text means" refers to technologies used to convert captured speech data into text, such as speech recognition engines and cloud-based speech recognition services.

[0148] "Means for transmitting the converted text data to a central server" refers to communications devices or technologies for converting speech to text and then transmitting the text data to a server via the Internet.

[0149] "Means for analyzing text data received by the central server using a natural language processing engine" refers to a process and device that analyzes text data sent to the central server using a natural language processing algorithm.

[0150] "Means for generative AI to generate feedback based on analyzed data" refers to the process by which artificial intelligence generates appropriate feedback based on data analyzed by a natural language processing engine. A generative AI model falls into this category.

[0151] "Means for transmitting the generated feedback to a display device" refers to the communication methods and technologies for transmitting the generated feedback to a display device, such as smart glasses worn by the staff member.

[0152] "Display device" refers to a device for visually displaying the generated feedback, such as smart glasses or a head-mounted display.

[0153] The invention is a system that captures voice, converts it into text, sends the text data to a central server, analyzes it, and generates and displays feedback, enabling wait staff to take diversity, equity, and inclusion (DE&I) into consideration in real time.

[0154] First, the wait staff wears smart glasses with a built-in microphone. The glasses capture the conversation in real time. This voice data is converted into text data by the voice recognition engine in the smart glasses. The voice recognition engine can use the Google Cloud Speech-to-Text API.

[0155] The text data is then sent via an internet connection to a central server, where it is analyzed using a natural language processing engine (such as SpaCy or NLTK). Based on the data analyzed by this natural language processing engine, a generative AI generates appropriate feedback. The generative AI can be a GPT model from OpenAI, for example.

[0156] The generated feedback is displayed in real time on smart glasses, allowing staff to view the feedback and take more appropriate action from a DE&I perspective. Smart glasses such as Vuzix Blade and Google Glass (registered trademark) can be used as display devices.

[0157] As a concrete example, if a waiter says, "Let's ask the new customer if he likes Japanese food," this utterance is captured by a microphone built into the smart glasses. This voice data is converted into text data using the Google Cloud Speech-to-Text API, and the text data is sent to a central server. The central server analyzes the text data with a natural language processing engine, and based on the analysis results, a generative AI model (for example, OpenAI's GPT model) generates feedback such as, "This message may be imposing a specific food culture on the new customer, so we suggest making a change by asking the customer what their lunch preferences are." The generated feedback is immediately displayed on the smart glasses' display.

[0158] Examples of prompts that can be input to a generative AI model include:

[0159] Please share your suggestions for improving the following messaging from a diversity, equity, and inclusion (DE&I) perspective:

[0160] Message: "Ask new customers if they like Japanese food."

[0161] This system enables staff to take DE&I into consideration in real time while serving customers, thereby improving customer satisfaction.

[0162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0163] Step 1:

[0164] The user puts on the smart glasses and starts serving customers. The smart glasses' built-in microphone captures the user's conversation in real time. The input of this step is voice data, and the output is the storage of the voice data for internal processing.

[0165] Step 2:

[0166] The device (smart glasses) converts the captured voice data into text data using the Google Cloud Speech-to-Text API. The input of this step is the captured voice data, and the output is the converted text data. Specifically, the speech recognition engine analyzes the voice waveform data and converts it into a string of characters.

[0167] Step 3:

[0168] The device then sends the converted text data to a central server using HTTP or HTTPS as the communication protocol. The input to this step is the text data, and the output is a notification to the server that transmission has been completed. Specifically, the device packages the text data in JSON format and sends it to the server via a REST API.

[0169] Step 4:

[0170] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). The input of this step is text data, and the output is the analysis result data. Specifically, the server extracts semantic elements from the text data and stores them in a database.

[0171] Step 5:

[0172] The server generates feedback using a generative AI model (e.g., OpenAI's GPT model) based on the analysis results. The input of this step is the analysis result data, and the output is the generated feedback message. Specifically, the server inputs a prompt sentence into the generative AI model and generates feedback in text format.

[0173] Step 6:

[0174] The server sends the generated feedback message to the device (smart glasses). The input of this step is the feedback message, and the output is a notification ready to be displayed on the smart glasses. Specifically, the server packages the feedback message in JSON format and sends it to the device via a REST API.

[0175] Step 7:

[0176] The terminal displays the received feedback message on the display of the smart glasses. The user can continue serving customers while checking the feedback in real time. The input of this step is the feedback message, and the output is the feedback displayed on the display. As a specific operation, the display control software of the smart glasses displays the feedback message on the screen.

[0177] 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.

[0178] This invention combines a message capture, analysis, and feedback generation system with an emotion engine that recognizes user emotions to more effectively promote diversity, equity, and inclusion (DE&I) perspectives in everyday work. Specifically, we provide a system that achieves this by utilizing the user's device, server, generative AI, natural language processing engine, and emotion engine.

[0179] First, the user uses the device to input and send a message via a communication tool such as Slack or email. At this time, the device captures the message in real time, and the user's emotional data is also recognized by the emotion engine. The recognized emotional data and message are then sent to a central server.

[0180] The central server passes the received message and emotional data to a natural language processing engine for analysis. Based on the analysis results, the AI ​​generates feedback for the message. This feedback not only takes into account the perspectives of each minority group, but also reflects the user's current emotional state. The generated feedback is delivered in a tone that is adjusted according to the user's emotional state.

[0181] To give a specific example, suppose a user sends a message such as "Let's ask the new employee if he likes ramen." This message is captured by the device, and the emotion engine recognizes the user's emotion as "excitement" or "enthusiasm." This message and emotion data are sent to the central server, which then passes this data to a natural language processing engine for analysis. Based on the analysis results and emotion data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Let's ask the new employee what his lunch preferences are.'" This feedback is provided in a more positive and accepting tone, tailored to the user's emotional state. This feedback is sent to the user's device, where the user can review it and modify the message to "Let's ask the new employee what his lunch preferences are."

[0182] The system can also be configured to respond to comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, and processes this text data and emotional data in the same way as other messages, allowing it to provide real-time feedback. As the meeting progresses, it can understand in real time how users feel about each comment and adjust feedback accordingly.

[0183] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[0184] The above is a specific embodiment for carrying out the present invention.

[0185] The processing flow will be explained below.

[0186] Step 1:

[0187] Device: The user types and sends a message using a communication tool such as Slack or email. The device captures the message in real time, and an emotion engine is activated to recognize the user's emotions from their facial expressions and voice.

[0188] Step 2:

[0189] Device: Sends captured messages and recognized emotion data to the central server using API requests.

[0190] Step 3:

[0191] Server: The central server passes the received message and sentiment data to a natural language processing (NLP) engine, which analyzes the meaning and grammatical structure of the message.

[0192] Step 4:

[0193] Server: The generative AI combines the analyzed message data with the emotional data to generate appropriate feedback that reflects the user's current emotional state.

[0194] Step 5:

[0195] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[0196] Step 6:

[0197] Terminal: The user checks the feedback they receive. The feedback is provided in a tone that is tailored to their emotional state.

[0198] Step 7:

[0199] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[0200] Step 8:

[0201] Terminal: Resend the corrected message. The process begins again at step 1.

[0202] For example, when a user sends a message such as "Let's ask the new employee if he likes ramen," the message is captured by the device. At the same time, the emotion engine recognizes the user's emotion (e.g., "excited"). This data is sent to a central server, which then analyzes the message using a natural language processing engine.

[0203] Next, based on the analysis results and emotional data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as, 'Let's ask the new employee about their lunch preferences.'" This feedback is expressed in an appropriate tone, taking into account the user's emotional state.

[0204] Finally, the generated feedback is sent to the user's device, where the user can review it and revise the message if necessary. The revised message is then resent, allowing the user to incorporate a DE&I perspective into their daily work.

[0205] Example 2

[0206] 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."

[0207] Considering diversity, equity, and inclusion (DE&I) is an important issue in modern communication. However, it is difficult to properly incorporate these perspectives into daily work, and many users unconsciously send messages containing bias or inappropriate language. This invention aims to promote DE&I in daily work by analyzing the content of messages sent by users in real time and generating appropriate feedback that takes emotions into account.

[0208] 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.

[0209] In this invention, the server includes means for capturing messages, means for recognizing user emotion data from the captured message using an emotion engine on the terminal, means for transmitting the recognized emotion data and the captured message to a central server, means for analyzing the message and emotion data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data and emotion data, and means for transmitting the generated feedback to the terminal, thereby enabling users to modify the content and expression of their messages in real time to take DE&I into consideration.

[0210] A "message" is text data that a user sends through a communication tool.

[0211] "Capture" refers to the terminal acquiring a message entered by a user in real time and temporarily saving it.

[0212] A "terminal" is a hardware device (e.g., a PC or smartphone) that a user uses to input or view messages.

[0213] The "emotion engine" is a software module that analyzes the user's emotional state from the input message and generates emotional data.

[0214] "Emotion data" is data that represents the user's emotional state, obtained as a result of analysis by the emotion engine.

[0215] The "central server" is a server that receives captured messages and emotion data, analyzes them, and generates feedback.

[0216] A "natural language processing engine" is a software module that analyzes messages and emotional data received by the central server and understands their content and emotions.

[0217] "Generative AI" is an artificial intelligence module that generates appropriate feedback based on the analysis results of a natural language processing engine and emotional data.

[0218] "Feedback" is a suggested message created by the generative AI to improve the content and expression of the user's message.

[0219] Diversity, Equity, and Inclusion (DE&I) are principles that ensure individuals with diverse backgrounds are treated fairly and inclusively in organizations and society.

[0220] This invention is a system that effectively promotes diversity, equity, and inclusion (DE&I) in daily work by capturing messages, analyzing them, and generating sentiment-based feedback. The system includes the following key components:

[0221] First, a user uses a device to type and send a message using a communication tool such as Slack or email. At this stage, the device captures the message in real time. Capturing means obtaining the entered message data and temporarily saving it. Next, the captured message is passed to the emotion engine, which analyzes the user's emotion and generates emotion data. For example, if a user types the message "I'll ask the leader of the new project about the next meeting," the emotion engine will recognize the user's emotion as "interest" from this message.

[0222] The device then sends the generated emotion data and the captured message to a central server, which receives and stores this data. In the above example, the message "Ask the new project leader about the next meeting" and the emotion data of "interest" are sent to the central server. This data is then analyzed by a natural language processing engine, which understands the content and emotional tone of the message and performs analysis based on that.

[0223] Based on the analysis results, the generative AI generates appropriate feedback. For example, it might generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to, 'Could you please let me know a convenient time for our next meeting?'" The generative AI adjusts the tone of the feedback based on the emotional data "interest" to generate this feedback.

[0224] The generated feedback is sent from the central server to the device and provided to the user. The user can review this feedback and modify the message as necessary. For example, the original message can be modified based on the feedback, such as "Can you please tell me a convenient time for our next meeting?" The system is also designed to handle comments made during meetings, converting them into text data using transcription AI, and processing this text data and emotional data in the same way to provide real-time feedback.

[0225] This allows users to naturally incorporate diversity, equity, and inclusion-conscious communication into their daily work. This system promotes the understanding and practice of DE&I across the company, and is extremely useful in an increasingly diverse workplace.

[0226] Examples of prompt sentences include the following:

[0227] "Why not ask your new employees what their favorite food is for lunch? (Excited)"

[0228] "Please let me know a convenient time for our next meeting (interest)"

[0229] In this way, by using this system, users can check and correct the content and tone of their messages in real time, ensuring that their communications are conscious of DE&I perspectives.

[0230] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0231] Step 1:

[0232] A user uses a device to input and send a message using a communication tool such as Slack or email. The input data is the message entered by the user, such as "Let's ask the leader of the new project about the next meeting." The device captures this message. Specifically, the device's capture function acquires the message data and temporarily saves it.

[0233] Step 2:

[0234] The device passes the captured message to the emotion engine. Here, the input data is the captured message, and the emotion engine analyzes the user's emotion from this message and generates emotion data. For example, the emotion engine recognizes the user's emotion as "interest" from the message "Let's ask the leader of the new project about the next meeting" and generates emotion data. Specifically, the emotion engine runs a text analysis algorithm and assigns a data label for the emotional state.

[0235] Step 3:

[0236] The terminal transmits the generated emotion data and the captured message to the central server. Here, the input data is the emotion data generated by the emotion engine and the captured message, and is transmitted to the central server as output data. For example, the emotion data "interest" and the captured message are transmitted to the central server. In specific operations, the terminal transmits data to the server using a network protocol.

[0237] Step 4:

[0238] The central server passes the received message and emotional data to the natural language processing engine for analysis. Here, the input data is the received message and emotional data, which the natural language processing engine analyzes and generates an analysis result. For example, the natural language processing engine analyzes the message and emotional data to understand the content of the message and analyze the emotional tone at the same time. Specifically, the natural language processing engine performs syntactic and semantic analysis to generate a data model.

[0239] Step 5:

[0240] The generative AI generates feedback based on the analysis results of the natural language processing engine. Here, the input data are the analysis results and emotional data generated by the natural language processing engine, and the generative AI generates feedback based on this, resulting in appropriate feedback as output data. For example, the generative AI may generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to the format, 'Could you please let me know a convenient time for our next meeting?'" Specifically, the generative AI uses the generative model to construct a message and adjust the emotional tone.

[0241] Step 6:

[0242] The generated feedback is sent from the central server to the terminal and provided to the user. Here, the input data is the generated feedback, and the output data is displayed on the user's terminal. For example, the feedback is provided to the user in the form of "Can you tell me a convenient time for the next meeting?" In concrete terms, the central server sends the feedback data to the terminal, and the terminal displays it.

[0243] In this way, users can see the content and tone of messages in real time and ensure their communications take DE&I perspectives into account.

[0244] (Application example 2)

[0245] 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."

[0246] To improve the quality of communication between staff and customers in brick-and-mortar stores, a system that provides real-time feedback that takes diversity, equity, and inclusion into consideration is needed. Conventional communication support systems have the challenge of fully considering minority perspectives and adjusting feedback according to the user's emotional state.

[0247] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing messages, means for transmitting the captured messages and emotion data to a central server, means for analyzing the messages and emotion data received by the central server using a natural language processing engine and an emotion engine, means for a generation AI to generate feedback based on the analyzed data, means for transmitting the generated feedback to a user terminal, and means for adjusting the feedback in a tone that takes into account minority perspectives and corresponds to the user's emotional state. This enables store staff to receive appropriate feedback in real time that takes diversity, fairness, and inclusion into consideration.

[0248] The "message capture means" is a device or function that uses a voice input device or other input means to capture user utterances and inputs in real time and acquire the data.

[0249] "Emotion data" is data that analyzes a user's statements and messages and expresses the emotions that the person is feeling (e.g., joy, excitement, anger, etc.) as numbers or categories.

[0250] The "Central Server" is a computer system that receives captured messages and emotion data, sends them to each engine (natural language processing engine, emotion engine, etc.) for analysis, and ultimately generates feedback.

[0251] A "natural language processing engine" is a computer program or device that analyzes input text data and understands its meaning, intent, and context.

[0252] An "emotion engine" is a computer program or device that analyzes and recognizes a user's emotions from input data and identifies their emotional state.

[0253] "Generative AI" is an artificial intelligence model or system that generates optimal feedback based on analyzed data.

[0254] The "feedback generation means" is a function in which the generative AI generates appropriate feedback based on data analyzed by the natural language processing engine and emotion engine.

[0255] A "user terminal" is a device for providing generated feedback to a user, such as a mobile device such as a smartphone or tablet.

[0256] "Minority perspective" is a concept that means taking into consideration the views and opinions of minorities such as those of race, gender, and disability.

[0257] The "tone adjustment means" is a function for reflecting the user's emotional state and providing feedback in an appropriate tone.

[0258] This invention is a system for improving the quality of communication between staff and customers, or between staff members, in physical stores, with the aim of achieving diversity, equity, and inclusion (DE&I). The system consists of the following components:

[0259] 1. System Components

[0260] User device: A mobile device such as a smartphone or tablet.

[0261] Message capture method: Uses a voice input device (e.g., Google Speech-to-Text API) to convert user speech into text data in real time.

[0262] Central Server: A computer system that receives and analyzes the captured message and emotion data and generates feedback.

[0263] Natural Language Processing Engine: Uses the Google Natural Language API to parse messages and understand their meaning and intent.

[0264] Emotion Engine: Uses IBM Watson to recognize user emotions from messages.

[0265] Generative AI: Use a generative AI model such as OpenAI GPT-4® to generate feedback.

[0266] Tone adjustment means: Adjust the tone of the generated feedback depending on the user's emotional state.

[0267] 2. System Operation Overview

[0268] 1. Message Capture:

[0269] The user terminal captures speech through a voice input device and converts it into text data. For example, a staff member uses a smartphone to say, "Let's ask the new employee if he likes ramen."

[0270] 2. Emotion analysis:

[0271] The text data is sent to an emotion engine to recognize the user's emotions (e.g., excitement, enthusiasm). The captured message and emotion data are sent to a central server.

[0272] 3. Natural Language Processing and Analysis:

[0273] The central server uses the Google Natural Language API to parse the messages to understand their subject and intent.

[0274] 4. Feedback Generation:

[0275] Based on the analysis results and emotional data, generative AI generates appropriate feedback, such as "Ask the new employee about their lunch preferences."

[0276] 5. Feedback Tone Adjustment:

[0277] The tone of the generated feedback is adjusted depending on the user's emotional state: if the user is excited, the feedback is provided in a more accepting tone.

[0278] 6. Providing feedback:

[0279] Finally, the adjusted feedback is sent to the user's device, where staff can review it in real time and take appropriate action or modify the message.

[0280] 3. Specific Examples

[0281] Example 1: Customer Service

[0282] Prompt: A customer asks, "How well does your store cater to families?" and a staff member responds, "We provide the best service."

[0283] Feedback: "To be more specific, our restaurant has seating reserved for families," the AI ​​generates feedback and displays it on the user's device.

[0284] Example 2: Staff communication

[0285] Prompt: When Staff A asks Staff B to help clean up, Staff B replies, "I'm busy right now, so I can't."

[0286] Feedback: "I understand, but I'll help you if you're not too busy," the AI ​​generates feedback and displays it on the user's device.

[0287] This allows store staff to more effectively engage with customers and communicate internally, effectively promoting diversity, equity, and inclusion.

[0288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0289] Step 1:

[0290] The user terminal uses a voice input device to capture what the user says and converts the voice data into text data. The input is voice data and the output is text data. Specifically, the voice is converted into text using the Google Speech-to-Text API. For example, if a staff member says on their smartphone, "Let's ask the new employee about their lunch preferences," the voice data is captured and converted into text.

[0291] Step 2:

[0292] The captured text data is sent from the user device to a central server. At the same time, an emotion engine (e.g., IBM Watson) analyzes the user's emotions and generates emotion data. The input is text data and voice data, and the output is text data and emotion data. Specifically, the data captured by the user device is sent to the central server in real time.

[0293] Step 3:

[0294] The central server stores the received text data and emotion data and passes them to a natural language processing engine (e.g., Google Natural Language API) and emotion engine. The input is text data and emotion data, and the output is the analysis results and emotional state. Specifically, the central server passes this data to the engine, which then analyzes it. As a result of the analysis, the subject matter, intent, and context of the text are understood.

[0295] Step 4:

[0296] Based on the analysis results of the natural language processing engine and emotion engine, generative AI (e.g., OpenAI GPT-4) generates feedback. The input is the analysis results and emotional state, and the output is the generated feedback. Specifically, the generative AI creates optimal feedback, such as "Let's ask about lunch preferences so as not to force a particular dietary culture on new employees."

[0297] Step 5:

[0298] The generated feedback is adjusted in tone based on emotional data. The input is the generated feedback and the user's emotional state, and the output is the adjusted feedback. Specifically, if the user's emotional state is "excited," the tone is changed to a more positive and accepting one.

[0299] Step 6:

[0300] The adjusted feedback is sent from the central server to the user terminal. The input is the adjusted feedback, and the output is the feedback displayed on the terminal. Specifically, the user terminal receives the feedback in real time, and staff can check it to improve the quality of communication.

[0301] This allows store staff to improve customer interactions and staff-to-staff communication through feedback delivered in the right tone, effectively promoting diversity, equity, and inclusion.

[0302] 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.

[0303] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0304] 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.

[0305] [Second embodiment]

[0306] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0307] 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.

[0308] 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).

[0309] 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.

[0310] 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.

[0311] 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).

[0312] 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.

[0313] 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.

[0314] 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.

[0315] 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.

[0316] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0317] 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."

[0318] This invention promotes diversity, equity, and inclusion (DE&I) perspectives in everyday work through a system that captures messages, analyzes them, and generates feedback. Specifically, we provide a system that achieves this goal by utilizing user devices, servers, generative AI, and natural language processing engines.

[0319] First, a user uses their device to type and send a message using a communication tool such as Slack or email. At this time, the device captures the message in real time and sends it to a central server. The central server analyzes the received message using a natural language processing engine, and a generation AI generates feedback for the message based on the analysis results. This feedback is created taking into account the perspectives of each minority group and suggests how the user's message should be improved. The generated feedback is then sent back to the user's device, where the user can review it and revise the message if necessary.

[0320] To give a specific example, suppose a user sends a message such as "Ask the new employee if they like ramen." This message is captured by the device and sent to a central server. The central server passes the message to a natural language processing engine for analysis. Based on the analysis results, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can confirm it. This allows the user to revise the message to "Ask the new employee what their lunch preferences are" and send it.

[0321] This system can also be configured to handle comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, which can then be processed in the same way as other messages, providing real-time feedback. This allows it to provide improvement suggestions from a DE&I perspective for comments made during meetings.

[0322] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[0323] The above is a specific embodiment for carrying out the present invention.

[0324] The processing flow will be explained below.

[0325] Step 1:

[0326] Device: A user types and sends a message using a communication tool such as Slack or email, and the device captures the message in real time.

[0327] Step 2:

[0328] Terminal: Sends captured messages to a central server using an API request.

[0329] Step 3:

[0330] Server: A central server receives messages and passes them to a natural language processing (NLP) engine, which analyzes the message for meaning and grammatical structure.

[0331] Step 4:

[0332] Server: Based on the analyzed message data, the AI ​​generates appropriate feedback that takes into account the perspectives of each minority group.

[0333] Step 5:

[0334] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[0335] Step 6:

[0336] Device: Check the feedback received by the user. Notify the user of the feedback displayed on the device.

[0337] Step 7:

[0338] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[0339] Step 8:

[0340] Terminal: Resend the corrected message. The process begins again at step 1.

[0341] The above is a specific processing flow for implementing this invention. This series of processes allows users to incorporate a DE&I perspective into their everyday communications.

[0342] Example 1

[0343] 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."

[0344] Diversity, equity, and inclusion (DE&I) are important values ​​in today's business environment, but it can be difficult to properly incorporate these perspectives into everyday work communications. Furthermore, messages and comments made during meetings can contain unconscious bias, which can negatively impact relationships and company culture. Traditional methods make it difficult to provide real-time feedback, and manual reviews and training have limitations. Therefore, there is a need for a system that automatically provides feedback that takes diversity, equity, and inclusion into consideration.

[0345] 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.

[0346] In this invention, the server includes a means for capturing messages, a means for transmitting the captured messages to a central server, a means for analyzing the messages received by the central server using a natural language processing engine, a means for a generation AI to generate feedback based on the analysis results, a means for transmitting the generated feedback to a user terminal, a means for the user to check the feedback and modify the message as necessary, and a means for converting statements made during meetings into text data using a transcription AI, analyzing the text data, and generating feedback, thereby enabling users to naturally incorporate diversity, equity, and inclusion into their daily work communications.

[0347] The "means for capturing messages" is a function for collecting messages that users input and send using a communication tool in real time.

[0348] The "means for transmitting captured messages to a central server" is a function for transferring collected message data to a central server via a network.

[0349] "Means for analyzing messages received by the central server using a natural language processing engine" refers to a function that uses natural language processing technology to analyze message data received by the central server and understand the context and meaning.

[0350] "Means for the generative AI to generate feedback based on the analysis results" refers to a function in which the generative AI automatically creates appropriate feedback based on the analysis results obtained by the natural language processing engine.

[0351] "Means for sending generated feedback to a user terminal" refers to a function that transfers the feedback created by the generation AI to a user terminal via a network.

[0352] "Means for users to review feedback and revise messages as necessary" refers to a function that allows users to view feedback on their device and edit or revise the original message based on the feedback.

[0353] "A means of converting statements made during meetings into text data using transcription AI, analyzing that text data, and generating feedback" is a function that converts spoken statements made during meetings into text using transcription technology, analyzes that text data using a natural language processing engine, and uses generation AI to create feedback.

[0354] "Diversity" means bringing together individuals with different attributes and backgrounds and respecting and accepting their differences.

[0355] "Fairness" means a state in which all individuals are treated equally and unfair discrimination and prejudice are eliminated.

[0356] "Inclusion" means that all people have the opportunity to participate and contribute to an organization or society, and their value is recognized.

[0357] The present invention is directed to promoting diversity, equity, and inclusion (DE&I) using a system that captures messages, analyzes them, and generates feedback. Specific embodiments for implementing the present invention are described below.

[0358] Components

[0359] 1. User Device

[0360] A device such as a computer or smartphone used by a user, on which communication tools such as Slack or email are installed.

[0361] 2. Central Server

[0362] A central processing unit for receiving messages, performing analysis, and generating feedback. It includes a high-performance processor and storage.

[0363] 3. Natural Language Processing Engine

[0364] Software for analyzing the context and meaning of messages. Examples include Google Cloud Natural Language API and IBM Watson.

[0365] 4. Generation AI

[0366] An artificial intelligence model that generates feedback based on analyzed data. Examples include OpenAI's GPT-3.

[0367] 5. Transcription AI

[0368] Software for transcribing what is said during meetings in real time, such as the open source Kaldi or the commercial Google Speech-to-Text.

[0369] Program processing

[0370] Capture and send messages

[0371] When a user sends a message from their device via Slack or email, the message is captured in real time, stored in a dedicated message queue by a script running on the device, and then sent to a central server via an HTTP POST request.

[0372] Message Parsing

[0373] When the server receives a message, it passes it to a natural language processing engine to analyze its context and meaning. This analysis is performed using Google Cloud Natural Language API, etc. The analysis results are recorded on the server and then passed to the generative AI model.

[0374] Generate feedback

[0375] The AI ​​then generates appropriate feedback based on the analysis results. The generated feedback takes into account minority perspectives in particular. For example, the following prompt is sent to the AI:

[0376] "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0377] Send and review feedback

[0378] The generated feedback is sent to the user's device via an HTTP POST request, where the user can view the feedback and modify the message if necessary.

[0379] Responding to comments made during meetings

[0380] This system can also process comments made during meetings. When a user speaks, the transcription AI converts the comment into text data. The converted text data is analyzed in the same way as other messages, and feedback is generated by the generation AI. This makes it possible to provide appropriate feedback in real time for comments made during meetings.

[0381] Specific examples

[0382] For example, if a user sends a message saying, "Let's ask the new employee if he likes ramen," the message is immediately captured and sent to the server. The server passes the message to a natural language processing engine for analysis, and the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee. We suggest changing it to a more neutral phrase, such as 'Let's ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can review it and modify the message.

[0383] Using this system will promote communication that takes diversity, equity, and inclusion into consideration, and support the understanding and implementation of DE&I across the company.

[0384] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0385] Step 1: Enter and capture your message

[0386] A user types and sends a message using a communication tool such as Slack or email.

[0387] An example of a message to enter is, "Let's ask new employees if they like ramen."

[0388] The terminal captures this message in real time and stores it in a dedicated message queue.

[0389] Input: User input message

[0390] Output: Message data stored in the message queue

[0391] Step 2: Sending and Receiving Messages

[0392] The device sends the data stored in the message queue to the central server via an HTTP POST request.

[0393] The server receives this data at the receiving endpoint (API endpoint).

[0394] Input: Message data retrieved from the message queue

[0395] Output: Message data received by the server

[0396] Step 3: Parse the message

[0397] The server passes the received message to a natural language processing (NLP) engine for analysis.

[0398] For example, use the Google Cloud Natural Language API to analyze the context and tone of messages.

[0399] Input: Message data sent to the central server

[0400] Output: Analysis results obtained from the natural language processing engine

[0401] Step 4: Generate feedback

[0402] The server sends a prompt to the generation AI based on the analysis results.

[0403] Example: Send a prompt to the generation AI saying, "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0404] Generative AI generates feedback based on prompts.

[0405] Input: Analysis results from the natural language processing engine and prompt sentences

[0406] Output: Feedback obtained from the generative AI

[0407] Step 5: Submit your feedback

[0408] The server sends the feedback received from the generated AI to the user's device via an HTTP POST request.

[0409] Input: Feedback generated by the generative AI

[0410] Output: Feedback sent to the user's device

[0411] Step 6: View and review feedback

[0412] The device displays the received feedback on the screen.

[0413] The user reviews the feedback and modifies the original message if necessary.

[0414] Input: Feedback received

[0415] Output: Corrected or confirmed message

[0416] Step 7: Transcribe what is said during the meeting and generate feedback

[0417] A user speaks during a conference.

[0418] Transcription AI converts speech into text data.

[0419] The text data is processed in the same manner as in steps 3 to 6 above to generate analysis and feedback.

[0420] Input: Voice remarks during a meeting

[0421] Output: Generated feedback

[0422] This series of steps will create a system that helps users communicate with diversity, equity, and inclusion in their daily work.

[0423] (Application example 1)

[0424] 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."

[0425] In traditional customer service, it is difficult for customer service staff to respond in real time while taking diversity, equity, and inclusion (DE&I) into consideration. As a result, they may unconsciously include bias or lack of understanding in their communications with customers, which can lead to lower customer satisfaction and problems. To solve this problem, a system is needed that provides feedback from a DE&I perspective in real time while customers are interacting with the service.

[0426] 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.

[0427] In this invention, the server includes means for capturing voice, means for converting voice to text, means for transmitting the converted text data to a central server, means for analyzing the text data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data, and means for transmitting the generated feedback to a display device. This makes it possible to provide staff with feedback that takes diversity, equity, and inclusion (DE&I) perspectives into consideration in real time while they are serving customers, thereby improving the quality of communication.

[0428] "Audio capture means" refers to a device that collects the remarks of service staff and customers in real time. Specifically, it uses a voice input device such as a microphone.

[0429] "Speech-to-text means" refers to technologies used to convert captured speech data into text, such as speech recognition engines and cloud-based speech recognition services.

[0430] "Means for transmitting the converted text data to a central server" refers to communications devices or technologies for converting speech to text and then transmitting the text data to a server via the Internet.

[0431] "Means for analyzing text data received by the central server using a natural language processing engine" refers to a process and device that analyzes text data sent to the central server using a natural language processing algorithm.

[0432] "Means for generative AI to generate feedback based on analyzed data" refers to the process by which artificial intelligence generates appropriate feedback based on data analyzed by a natural language processing engine. A generative AI model falls into this category.

[0433] "Means for transmitting the generated feedback to a display device" refers to the communication methods and technologies for transmitting the generated feedback to a display device, such as smart glasses worn by the staff member.

[0434] "Display device" refers to a device for visually displaying the generated feedback, such as smart glasses or a head-mounted display.

[0435] The invention is a system that captures voice, converts it into text, sends the text data to a central server, analyzes it, and generates and displays feedback, enabling wait staff to take diversity, equity, and inclusion (DE&I) into consideration in real time.

[0436] First, the wait staff wears smart glasses with a built-in microphone. The glasses capture the conversation in real time. This voice data is converted into text data by the voice recognition engine in the smart glasses. The voice recognition engine can use the Google Cloud Speech-to-Text API.

[0437] The text data is then sent via an internet connection to a central server, where it is analyzed using a natural language processing engine (such as SpaCy or NLTK). Based on the data analyzed by this natural language processing engine, a generative AI generates appropriate feedback. The generative AI can be a GPT model from OpenAI, for example.

[0438] The generated feedback is displayed in real time on smart glasses, allowing staff to view the feedback and take more appropriate action from a DE&I perspective. Smart glasses such as Vuzix Blade and Google Glass can be used as display devices.

[0439] As a concrete example, if a waiter says, "Let's ask the new customer if he likes Japanese food," this utterance is captured by a microphone built into the smart glasses. This voice data is converted into text data using the Google Cloud Speech-to-Text API, and the text data is sent to a central server. The central server analyzes the text data with a natural language processing engine, and based on the analysis results, a generative AI model (for example, OpenAI's GPT model) generates feedback such as, "This message may be imposing a specific food culture on the new customer, so we suggest making a change by asking the customer what their lunch preferences are." The generated feedback is immediately displayed on the smart glasses' display.

[0440] Examples of prompts that can be input to a generative AI model include:

[0441] Please share your suggestions for improving the following messaging from a diversity, equity, and inclusion (DE&I) perspective:

[0442] Message: "Ask new customers if they like Japanese food."

[0443] This system enables staff to take DE&I into consideration in real time while serving customers, thereby improving customer satisfaction.

[0444] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0445] Step 1:

[0446] The user puts on the smart glasses and starts serving customers. The smart glasses' built-in microphone captures the user's conversation in real time. The input of this step is voice data, and the output is the storage of the voice data for internal processing.

[0447] Step 2:

[0448] The device (smart glasses) converts the captured voice data into text data using the Google Cloud Speech-to-Text API. The input of this step is the captured voice data, and the output is the converted text data. Specifically, the speech recognition engine analyzes the voice waveform data and converts it into a string of characters.

[0449] Step 3:

[0450] The device then sends the converted text data to a central server using HTTP or HTTPS as the communication protocol. The input to this step is the text data, and the output is a notification to the server that transmission has been completed. Specifically, the device packages the text data in JSON format and sends it to the server via a REST API.

[0451] Step 4:

[0452] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). The input of this step is text data, and the output is the analysis result data. Specifically, the server extracts semantic elements from the text data and stores them in a database.

[0453] Step 5:

[0454] The server generates feedback using a generative AI model (e.g., OpenAI's GPT model) based on the analysis results. The input of this step is the analysis result data, and the output is the generated feedback message. Specifically, the server inputs a prompt sentence into the generative AI model and generates feedback in text format.

[0455] Step 6:

[0456] The server sends the generated feedback message to the device (smart glasses). The input of this step is the feedback message, and the output is a notification ready to be displayed on the smart glasses. Specifically, the server packages the feedback message in JSON format and sends it to the device via a REST API.

[0457] Step 7:

[0458] The terminal displays the received feedback message on the display of the smart glasses. The user can continue serving customers while checking the feedback in real time. The input of this step is the feedback message, and the output is the feedback displayed on the display. As a specific operation, the display control software of the smart glasses displays the feedback message on the screen.

[0459] 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.

[0460] This invention combines a message capture, analysis, and feedback generation system with an emotion engine that recognizes user emotions to more effectively promote diversity, equity, and inclusion (DE&I) perspectives in everyday work. Specifically, we provide a system that achieves this by utilizing the user's device, server, generative AI, natural language processing engine, and emotion engine.

[0461] First, the user uses the device to input and send a message via a communication tool such as Slack or email. At this time, the device captures the message in real time, and the user's emotional data is also recognized by the emotion engine. The recognized emotional data and message are then sent to a central server.

[0462] The central server passes the received message and emotional data to a natural language processing engine for analysis. Based on the analysis results, the AI ​​generates feedback for the message. This feedback not only takes into account the perspectives of each minority group, but also reflects the user's current emotional state. The generated feedback is delivered in a tone that is adjusted according to the user's emotional state.

[0463] To give a specific example, suppose a user sends a message such as "Let's ask the new employee if he likes ramen." This message is captured by the device, and the emotion engine recognizes the user's emotion as "excitement" or "enthusiasm." This message and emotion data are sent to the central server, which then passes this data to a natural language processing engine for analysis. Based on the analysis results and emotion data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Let's ask the new employee what his lunch preferences are.'" This feedback is provided in a more positive and accepting tone, tailored to the user's emotional state. This feedback is sent to the user's device, where the user can review it and modify the message to "Let's ask the new employee what his lunch preferences are."

[0464] The system can also be configured to respond to comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, and processes this text data and emotional data in the same way as other messages, allowing it to provide real-time feedback. As the meeting progresses, it can understand in real time how users feel about each comment and adjust feedback accordingly.

[0465] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[0466] The above is a specific embodiment for carrying out the present invention.

[0467] The processing flow will be explained below.

[0468] Step 1:

[0469] Device: The user types and sends a message using a communication tool such as Slack or email. The device captures the message in real time, and an emotion engine is activated to recognize the user's emotions from their facial expressions and voice.

[0470] Step 2:

[0471] Device: Sends captured messages and recognized emotion data to the central server using API requests.

[0472] Step 3:

[0473] Server: The central server passes the received message and sentiment data to a natural language processing (NLP) engine, which analyzes the meaning and grammatical structure of the message.

[0474] Step 4:

[0475] Server: The generative AI combines the analyzed message data with the emotional data to generate appropriate feedback that reflects the user's current emotional state.

[0476] Step 5:

[0477] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[0478] Step 6:

[0479] Terminal: The user checks the feedback they receive. The feedback is provided in a tone that is tailored to their emotional state.

[0480] Step 7:

[0481] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[0482] Step 8:

[0483] Terminal: Resend the corrected message. The process begins again at step 1.

[0484] For example, when a user sends a message such as "Let's ask the new employee if he likes ramen," the message is captured by the device. At the same time, the emotion engine recognizes the user's emotion (e.g., "excited"). This data is sent to a central server, which then analyzes the message using a natural language processing engine.

[0485] Next, based on the analysis results and emotional data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as, 'Let's ask the new employee about their lunch preferences.'" This feedback is expressed in an appropriate tone, taking into account the user's emotional state.

[0486] Finally, the generated feedback is sent to the user's device, where the user can review it and revise the message if necessary. The revised message is then resent, allowing the user to incorporate a DE&I perspective into their daily work.

[0487] Example 2

[0488] 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."

[0489] Considering diversity, equity, and inclusion (DE&I) is an important issue in modern communication. However, it is difficult to properly incorporate these perspectives into daily work, and many users unconsciously send messages containing bias or inappropriate language. This invention aims to promote DE&I in daily work by analyzing the content of messages sent by users in real time and generating appropriate feedback that takes emotions into account.

[0490] 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.

[0491] In this invention, the server includes means for capturing messages, means for recognizing user emotion data from the captured message using an emotion engine on the terminal, means for transmitting the recognized emotion data and the captured message to a central server, means for analyzing the message and emotion data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data and emotion data, and means for transmitting the generated feedback to the terminal, thereby enabling users to modify the content and expression of their messages in real time to take DE&I into consideration.

[0492] A "message" is text data that a user sends through a communication tool.

[0493] "Capture" refers to the terminal acquiring a message entered by a user in real time and temporarily saving it.

[0494] A "terminal" is a hardware device (e.g., a PC or smartphone) that a user uses to input or view messages.

[0495] The "emotion engine" is a software module that analyzes the user's emotional state from the input message and generates emotional data.

[0496] "Emotion data" is data that represents the user's emotional state, obtained as a result of analysis by the emotion engine.

[0497] The "central server" is a server that receives captured messages and emotion data, analyzes them, and generates feedback.

[0498] A "natural language processing engine" is a software module that analyzes messages and emotional data received by the central server and understands their content and emotions.

[0499] "Generative AI" is an artificial intelligence module that generates appropriate feedback based on the analysis results of a natural language processing engine and emotional data.

[0500] "Feedback" is a suggested message created by the generative AI to improve the content and expression of the user's message.

[0501] Diversity, Equity, and Inclusion (DE&I) are principles that ensure individuals with diverse backgrounds are treated fairly and inclusively in organizations and society.

[0502] This invention is a system that effectively promotes diversity, equity, and inclusion (DE&I) in daily work by capturing messages, analyzing them, and generating sentiment-based feedback. The system includes the following key components:

[0503] First, a user uses a device to type and send a message using a communication tool such as Slack or email. At this stage, the device captures the message in real time. Capturing means obtaining the entered message data and temporarily saving it. Next, the captured message is passed to the emotion engine, which analyzes the user's emotion and generates emotion data. For example, if a user types the message "I'll ask the leader of the new project about the next meeting," the emotion engine will recognize the user's emotion as "interest" from this message.

[0504] The device then sends the generated emotion data and the captured message to a central server, which receives and stores this data. In the above example, the message "Ask the new project leader about the next meeting" and the emotion data of "interest" are sent to the central server. This data is then analyzed by a natural language processing engine, which understands the content and emotional tone of the message and performs analysis based on that.

[0505] Based on the analysis results, the generative AI generates appropriate feedback. For example, it might generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to, 'Could you please let me know a convenient time for our next meeting?'" The generative AI adjusts the tone of the feedback based on the emotional data "interest" to generate this feedback.

[0506] The generated feedback is sent from the central server to the device and provided to the user. The user can review this feedback and modify the message as necessary. For example, the original message can be modified based on the feedback, such as "Can you please tell me a convenient time for our next meeting?" The system is also designed to handle comments made during meetings, converting them into text data using transcription AI, and processing this text data and emotional data in the same way to provide real-time feedback.

[0507] This allows users to naturally incorporate diversity, equity, and inclusion-conscious communication into their daily work. This system promotes the understanding and practice of DE&I across the company, and is extremely useful in an increasingly diverse workplace.

[0508] Examples of prompt sentences include the following:

[0509] "Why not ask your new employees what their favorite food is for lunch? (Excited)"

[0510] "Please let me know a convenient time for our next meeting (interest)"

[0511] In this way, by using this system, users can check and correct the content and tone of their messages in real time, ensuring that their communications are conscious of DE&I perspectives.

[0512] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0513] Step 1:

[0514] A user uses a device to input and send a message using a communication tool such as Slack or email. The input data is the message entered by the user, such as "Let's ask the leader of the new project about the next meeting." The device captures this message. Specifically, the device's capture function acquires the message data and temporarily saves it.

[0515] Step 2:

[0516] The device passes the captured message to the emotion engine. Here, the input data is the captured message, and the emotion engine analyzes the user's emotion from this message and generates emotion data. For example, the emotion engine recognizes the user's emotion as "interest" from the message "Let's ask the leader of the new project about the next meeting" and generates emotion data. Specifically, the emotion engine runs a text analysis algorithm and assigns a data label for the emotional state.

[0517] Step 3:

[0518] The terminal transmits the generated emotion data and the captured message to the central server. Here, the input data is the emotion data generated by the emotion engine and the captured message, and is transmitted to the central server as output data. For example, the emotion data "interest" and the captured message are transmitted to the central server. In specific operations, the terminal transmits data to the server using a network protocol.

[0519] Step 4:

[0520] The central server passes the received message and emotional data to the natural language processing engine for analysis. Here, the input data is the received message and emotional data, which the natural language processing engine analyzes and generates an analysis result. For example, the natural language processing engine analyzes the message and emotional data to understand the content of the message and analyze the emotional tone at the same time. Specifically, the natural language processing engine performs syntactic and semantic analysis to generate a data model.

[0521] Step 5:

[0522] The generative AI generates feedback based on the analysis results of the natural language processing engine. Here, the input data are the analysis results and emotional data generated by the natural language processing engine, and the generative AI generates feedback based on this, resulting in appropriate feedback as output data. For example, the generative AI may generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to the format, 'Could you please let me know a convenient time for our next meeting?'" Specifically, the generative AI uses the generative model to construct a message and adjust the emotional tone.

[0523] Step 6:

[0524] The generated feedback is sent from the central server to the terminal and provided to the user. Here, the input data is the generated feedback, and the output data is displayed on the user's terminal. For example, the feedback is provided to the user in the form of "Can you tell me a convenient time for the next meeting?" In concrete terms, the central server sends the feedback data to the terminal, and the terminal displays it.

[0525] In this way, users can see the content and tone of messages in real time and ensure their communications take DE&I perspectives into account.

[0526] (Application example 2)

[0527] 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."

[0528] To improve the quality of communication between staff and customers in brick-and-mortar stores, a system that provides real-time feedback that takes diversity, equity, and inclusion into consideration is needed. Conventional communication support systems have the challenge of fully considering minority perspectives and adjusting feedback according to the user's emotional state.

[0529] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing messages, means for transmitting the captured messages and emotion data to a central server, means for analyzing the messages and emotion data received by the central server using a natural language processing engine and an emotion engine, means for a generation AI to generate feedback based on the analyzed data, means for transmitting the generated feedback to a user terminal, and means for adjusting the feedback in a tone that takes into account minority perspectives and corresponds to the user's emotional state. This enables store staff to receive appropriate feedback in real time that takes diversity, fairness, and inclusion into consideration.

[0530] The "message capture means" is a device or function that uses a voice input device or other input means to capture user utterances and inputs in real time and acquire the data.

[0531] "Emotion data" is data that analyzes a user's statements and messages and expresses the emotions that the person is feeling (e.g., joy, excitement, anger, etc.) as numbers or categories.

[0532] The "Central Server" is a computer system that receives captured messages and emotion data, sends them to each engine (natural language processing engine, emotion engine, etc.) for analysis, and ultimately generates feedback.

[0533] A "natural language processing engine" is a computer program or device that analyzes input text data and understands its meaning, intent, and context.

[0534] An "emotion engine" is a computer program or device that analyzes and recognizes a user's emotions from input data and identifies their emotional state.

[0535] "Generative AI" is an artificial intelligence model or system that generates optimal feedback based on analyzed data.

[0536] The "feedback generation means" is a function in which the generative AI generates appropriate feedback based on data analyzed by the natural language processing engine and emotion engine.

[0537] A "user terminal" is a device for providing generated feedback to a user, such as a mobile device such as a smartphone or tablet.

[0538] "Minority perspective" is a concept that means taking into consideration the views and opinions of minorities such as those of race, gender, and disability.

[0539] The "tone adjustment means" is a function for reflecting the user's emotional state and providing feedback in an appropriate tone.

[0540] This invention is a system for improving the quality of communication between staff and customers, or between staff members, in physical stores, with the aim of achieving diversity, equity, and inclusion (DE&I). The system consists of the following components:

[0541] 1. System Components

[0542] User device: A mobile device such as a smartphone or tablet.

[0543] Message capture method: Uses a voice input device (e.g., Google Speech-to-Text API) to convert user speech into text data in real time.

[0544] Central Server: A computer system that receives and analyzes the captured message and emotion data and generates feedback.

[0545] Natural Language Processing Engine: Uses the Google Natural Language API to parse messages and understand their meaning and intent.

[0546] Emotion Engine: Uses IBM Watson to recognize user emotions from messages.

[0547] Generative AI: Use a generative AI model, such as OpenAI GPT-4, to generate feedback.

[0548] Tone adjustment means: Adjust the tone of the generated feedback depending on the user's emotional state.

[0549] 2. System Operation Overview

[0550] 1. Message Capture:

[0551] The user terminal captures speech through a voice input device and converts it into text data. For example, a staff member uses a smartphone to say, "Let's ask the new employee if he likes ramen."

[0552] 2. Emotion analysis:

[0553] The text data is sent to an emotion engine to recognize the user's emotions (e.g., excitement, enthusiasm). The captured message and emotion data are sent to a central server.

[0554] 3. Natural Language Processing and Analysis:

[0555] The central server uses the Google Natural Language API to parse the messages to understand their subject and intent.

[0556] 4. Feedback Generation:

[0557] Based on the analysis results and emotional data, generative AI generates appropriate feedback, such as "Ask the new employee about their lunch preferences."

[0558] 5. Feedback Tone Adjustment:

[0559] The tone of the generated feedback is adjusted depending on the user's emotional state: if the user is excited, the feedback is provided in a more accepting tone.

[0560] 6. Providing feedback:

[0561] Finally, the adjusted feedback is sent to the user's device, where staff can review it in real time and take appropriate action or modify the message.

[0562] 3. Specific Examples

[0563] Example 1: Customer Service

[0564] Prompt: A customer asks, "How well does your store cater to families?" and a staff member responds, "We provide the best service."

[0565] Feedback: "To be more specific, our restaurant has seating reserved for families," the AI ​​generates feedback and displays it on the user's device.

[0566] Example 2: Staff communication

[0567] Prompt: When Staff A asks Staff B to help clean up, Staff B replies, "I'm busy right now, so I can't."

[0568] Feedback: "I understand, but I'll help you if you're not too busy," the AI ​​generates feedback and displays it on the user's device.

[0569] This allows store staff to more effectively engage with customers and communicate internally, effectively promoting diversity, equity, and inclusion.

[0570] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0571] Step 1:

[0572] The user terminal uses a voice input device to capture what the user says and converts the voice data into text data. The input is voice data and the output is text data. Specifically, the voice is converted into text using the Google Speech-to-Text API. For example, if a staff member says on their smartphone, "Let's ask the new employee about their lunch preferences," the voice data is captured and converted into text.

[0573] Step 2:

[0574] The captured text data is sent from the user device to a central server. At the same time, an emotion engine (e.g., IBM Watson) analyzes the user's emotions and generates emotion data. The input is text data and voice data, and the output is text data and emotion data. Specifically, the data captured by the user device is sent to the central server in real time.

[0575] Step 3:

[0576] The central server stores the received text data and emotion data and passes them to a natural language processing engine (e.g., Google Natural Language API) and emotion engine. The input is text data and emotion data, and the output is the analysis results and emotional state. Specifically, the central server passes this data to the engine, which then analyzes it. As a result of the analysis, the subject matter, intent, and context of the text are understood.

[0577] Step 4:

[0578] Based on the analysis results of the natural language processing engine and emotion engine, generative AI (e.g., OpenAI GPT-4) generates feedback. The input is the analysis results and emotional state, and the output is the generated feedback. Specifically, the generative AI creates optimal feedback, such as "Let's ask about lunch preferences so as not to force a particular dietary culture on new employees."

[0579] Step 5:

[0580] The generated feedback is adjusted in tone based on emotional data. The input is the generated feedback and the user's emotional state, and the output is the adjusted feedback. Specifically, if the user's emotional state is "excited," the tone is changed to a more positive and accepting one.

[0581] Step 6:

[0582] The adjusted feedback is sent from the central server to the user terminal. The input is the adjusted feedback, and the output is the feedback displayed on the terminal. Specifically, the user terminal receives the feedback in real time, and staff can check it to improve the quality of communication.

[0583] This allows store staff to improve customer interactions and staff-to-staff communication through feedback delivered in the right tone, effectively promoting diversity, equity, and inclusion.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] [Third embodiment]

[0588] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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."

[0600] This invention promotes diversity, equity, and inclusion (DE&I) perspectives in everyday work through a system that captures messages, analyzes them, and generates feedback. Specifically, we provide a system that achieves this goal by utilizing user devices, servers, generative AI, and natural language processing engines.

[0601] First, a user uses their device to type and send a message using a communication tool such as Slack or email. At this time, the device captures the message in real time and sends it to a central server. The central server analyzes the received message using a natural language processing engine, and a generation AI generates feedback for the message based on the analysis results. This feedback is created taking into account the perspectives of each minority group and suggests how the user's message should be improved. The generated feedback is then sent back to the user's device, where the user can review it and revise the message if necessary.

[0602] To give a specific example, suppose a user sends a message such as "Ask the new employee if they like ramen." This message is captured by the device and sent to a central server. The central server passes the message to a natural language processing engine for analysis. Based on the analysis results, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can confirm it. This allows the user to revise the message to "Ask the new employee what their lunch preferences are" and send it.

[0603] This system can also be configured to handle comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, which can then be processed in the same way as other messages, providing real-time feedback. This allows it to provide improvement suggestions from a DE&I perspective for comments made during meetings.

[0604] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[0605] The above is a specific embodiment for carrying out the present invention.

[0606] The processing flow will be explained below.

[0607] Step 1:

[0608] Device: A user types and sends a message using a communication tool such as Slack or email, and the device captures the message in real time.

[0609] Step 2:

[0610] Terminal: Sends captured messages to a central server using an API request.

[0611] Step 3:

[0612] Server: A central server receives messages and passes them to a natural language processing (NLP) engine, which analyzes the message for meaning and grammatical structure.

[0613] Step 4:

[0614] Server: Based on the analyzed message data, the AI ​​generates appropriate feedback that takes into account the perspectives of each minority group.

[0615] Step 5:

[0616] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[0617] Step 6:

[0618] Device: Check the feedback received by the user. Notify the user of the feedback displayed on the device.

[0619] Step 7:

[0620] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[0621] Step 8:

[0622] Terminal: Resend the corrected message. The process begins again at step 1.

[0623] The above is a specific processing flow for implementing this invention. This series of processes allows users to incorporate a DE&I perspective into their everyday communications.

[0624] Example 1

[0625] 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."

[0626] Diversity, equity, and inclusion (DE&I) are important values ​​in today's business environment, but it can be difficult to properly incorporate these perspectives into everyday work communications. Furthermore, messages and comments made during meetings can contain unconscious bias, which can negatively impact relationships and company culture. Traditional methods make it difficult to provide real-time feedback, and manual reviews and training have limitations. Therefore, there is a need for a system that automatically provides feedback that takes diversity, equity, and inclusion into consideration.

[0627] 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.

[0628] In this invention, the server includes a means for capturing messages, a means for transmitting the captured messages to a central server, a means for analyzing the messages received by the central server using a natural language processing engine, a means for a generation AI to generate feedback based on the analysis results, a means for transmitting the generated feedback to a user terminal, a means for the user to check the feedback and modify the message as necessary, and a means for converting statements made during meetings into text data using a transcription AI, analyzing the text data, and generating feedback, thereby enabling users to naturally incorporate diversity, equity, and inclusion into their daily work communications.

[0629] The "means for capturing messages" is a function for collecting messages that users input and send using a communication tool in real time.

[0630] The "means for transmitting captured messages to a central server" is a function for transferring collected message data to a central server via a network.

[0631] "Means for analyzing messages received by the central server using a natural language processing engine" refers to a function that uses natural language processing technology to analyze message data received by the central server and understand the context and meaning.

[0632] "Means for the generative AI to generate feedback based on the analysis results" refers to a function in which the generative AI automatically creates appropriate feedback based on the analysis results obtained by the natural language processing engine.

[0633] "Means for sending generated feedback to a user terminal" refers to a function that transfers the feedback created by the generation AI to a user terminal via a network.

[0634] "Means for users to review feedback and revise messages as necessary" refers to a function that allows users to view feedback on their device and edit or revise the original message based on the feedback.

[0635] "A means of converting statements made during meetings into text data using transcription AI, analyzing that text data, and generating feedback" is a function that converts spoken statements made during meetings into text using transcription technology, analyzes that text data using a natural language processing engine, and uses generation AI to create feedback.

[0636] "Diversity" means bringing together individuals with different attributes and backgrounds and respecting and accepting their differences.

[0637] "Fairness" means a state in which all individuals are treated equally and unfair discrimination and prejudice are eliminated.

[0638] "Inclusion" means that all people have the opportunity to participate and contribute to an organization or society, and their value is recognized.

[0639] The present invention is directed to promoting diversity, equity, and inclusion (DE&I) using a system that captures messages, analyzes them, and generates feedback. Specific embodiments for implementing the present invention are described below.

[0640] Components

[0641] 1. User Device

[0642] A device such as a computer or smartphone used by a user, on which communication tools such as Slack or email are installed.

[0643] 2. Central Server

[0644] A central processing unit for receiving messages, performing analysis, and generating feedback. It includes a high-performance processor and storage.

[0645] 3. Natural Language Processing Engine

[0646] Software for analyzing the context and meaning of messages. Examples include Google Cloud Natural Language API and IBM Watson.

[0647] 4. Generation AI

[0648] An artificial intelligence model that generates feedback based on analyzed data. Examples include OpenAI's GPT-3.

[0649] 5. Transcription AI

[0650] Software for transcribing what is said during meetings in real time, such as the open source Kaldi or the commercial Google Speech-to-Text.

[0651] Program processing

[0652] Capture and send messages

[0653] When a user sends a message from their device via Slack or email, the message is captured in real time, stored in a dedicated message queue by a script running on the device, and then sent to a central server via an HTTP POST request.

[0654] Message Parsing

[0655] When the server receives a message, it passes it to a natural language processing engine to analyze its context and meaning. This analysis is performed using Google Cloud Natural Language API, etc. The analysis results are recorded on the server and then passed to the generative AI model.

[0656] Generate feedback

[0657] The AI ​​then generates appropriate feedback based on the analysis results. The generated feedback takes into account minority perspectives in particular. For example, the following prompt is sent to the AI:

[0658] "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0659] Send and review feedback

[0660] The generated feedback is sent to the user's device via an HTTP POST request, where the user can view the feedback and modify the message if necessary.

[0661] Responding to comments made during meetings

[0662] This system can also process comments made during meetings. When a user speaks, the transcription AI converts the comment into text data. The converted text data is analyzed in the same way as other messages, and feedback is generated by the generation AI. This makes it possible to provide appropriate feedback in real time for comments made during meetings.

[0663] Specific examples

[0664] For example, if a user sends a message saying, "Let's ask the new employee if he likes ramen," the message is immediately captured and sent to the server. The server passes the message to a natural language processing engine for analysis, and the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee. We suggest changing it to a more neutral phrase, such as 'Let's ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can review it and modify the message.

[0665] Using this system will promote communication that takes diversity, equity, and inclusion into consideration, and support the understanding and implementation of DE&I across the company.

[0666] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0667] Step 1: Enter and capture your message

[0668] A user types and sends a message using a communication tool such as Slack or email.

[0669] An example of a message to enter is, "Let's ask new employees if they like ramen."

[0670] The terminal captures this message in real time and stores it in a dedicated message queue.

[0671] Input: User input message

[0672] Output: Message data stored in the message queue

[0673] Step 2: Sending and Receiving Messages

[0674] The device sends the data stored in the message queue to the central server via an HTTP POST request.

[0675] The server receives this data at the receiving endpoint (API endpoint).

[0676] Input: Message data retrieved from the message queue

[0677] Output: Message data received by the server

[0678] Step 3: Parse the message

[0679] The server passes the received message to a natural language processing (NLP) engine for analysis.

[0680] For example, use the Google Cloud Natural Language API to analyze the context and tone of messages.

[0681] Input: Message data sent to the central server

[0682] Output: Analysis results obtained from the natural language processing engine

[0683] Step 4: Generate feedback

[0684] The server sends a prompt to the generation AI based on the analysis results.

[0685] Example: Send a prompt to the generation AI saying, "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0686] Generative AI generates feedback based on prompts.

[0687] Input: Analysis results from the natural language processing engine and prompt sentences

[0688] Output: Feedback obtained from the generative AI

[0689] Step 5: Submit your feedback

[0690] The server sends the feedback received from the generated AI to the user's device via an HTTP POST request.

[0691] Input: Feedback generated by the generative AI

[0692] Output: Feedback sent to the user's device

[0693] Step 6: View and review feedback

[0694] The device displays the received feedback on the screen.

[0695] The user reviews the feedback and modifies the original message if necessary.

[0696] Input: Feedback received

[0697] Output: Corrected or confirmed message

[0698] Step 7: Transcribe what is said during the meeting and generate feedback

[0699] A user speaks during a conference.

[0700] Transcription AI converts speech into text data.

[0701] The text data is processed in the same manner as in steps 3 to 6 above to generate analysis and feedback.

[0702] Input: Voice remarks during a meeting

[0703] Output: Generated feedback

[0704] This series of steps will create a system that helps users communicate with diversity, equity, and inclusion in their daily work.

[0705] (Application example 1)

[0706] 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."

[0707] In traditional customer service, it is difficult for customer service staff to respond in real time while taking diversity, equity, and inclusion (DE&I) into consideration. As a result, they may unconsciously include bias or lack of understanding in their communications with customers, which can lead to lower customer satisfaction and problems. To solve this problem, a system is needed that provides feedback from a DE&I perspective in real time while customers are interacting with the service.

[0708] 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.

[0709] In this invention, the server includes means for capturing voice, means for converting voice to text, means for transmitting the converted text data to a central server, means for analyzing the text data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data, and means for transmitting the generated feedback to a display device. This makes it possible to provide staff with feedback that takes diversity, equity, and inclusion (DE&I) perspectives into consideration in real time while they are serving customers, thereby improving the quality of communication.

[0710] "Audio capture means" refers to a device that collects the remarks of service staff and customers in real time. Specifically, it uses a voice input device such as a microphone.

[0711] "Speech-to-text means" refers to technologies used to convert captured speech data into text, such as speech recognition engines and cloud-based speech recognition services.

[0712] "Means for transmitting the converted text data to a central server" refers to communications devices or technologies for converting speech to text and then transmitting the text data to a server via the Internet.

[0713] "Means for analyzing text data received by the central server using a natural language processing engine" refers to a process and device that analyzes text data sent to the central server using a natural language processing algorithm.

[0714] "Means for generative AI to generate feedback based on analyzed data" refers to the process by which artificial intelligence generates appropriate feedback based on data analyzed by a natural language processing engine. A generative AI model falls into this category.

[0715] "Means for transmitting the generated feedback to a display device" refers to the communication methods and technologies for transmitting the generated feedback to a display device, such as smart glasses worn by the staff member.

[0716] "Display device" refers to a device for visually displaying the generated feedback, such as smart glasses or a head-mounted display.

[0717] The invention is a system that captures voice, converts it into text, sends the text data to a central server, analyzes it, and generates and displays feedback, enabling wait staff to take diversity, equity, and inclusion (DE&I) into consideration in real time.

[0718] First, the wait staff wears smart glasses with a built-in microphone. The glasses capture the conversation in real time. This voice data is converted into text data by the voice recognition engine in the smart glasses. The voice recognition engine can use the Google Cloud Speech-to-Text API.

[0719] The text data is then sent via an internet connection to a central server, where it is analyzed using a natural language processing engine (such as SpaCy or NLTK). Based on the data analyzed by this natural language processing engine, a generative AI generates appropriate feedback. The generative AI can be a GPT model from OpenAI, for example.

[0720] The generated feedback is displayed in real time on smart glasses, allowing staff to view the feedback and take more appropriate action from a DE&I perspective. Smart glasses such as Vuzix Blade and Google Glass can be used as display devices.

[0721] As a concrete example, if a waiter says, "Let's ask the new customer if he likes Japanese food," this utterance is captured by a microphone built into the smart glasses. This voice data is converted into text data using the Google Cloud Speech-to-Text API, and the text data is sent to a central server. The central server analyzes the text data with a natural language processing engine, and based on the analysis results, a generative AI model (for example, OpenAI's GPT model) generates feedback such as, "This message may be imposing a specific food culture on the new customer, so we suggest making a change by asking the customer what their lunch preferences are." The generated feedback is immediately displayed on the smart glasses' display.

[0722] Examples of prompts that can be input to a generative AI model include:

[0723] Please share your suggestions for improving the following messaging from a diversity, equity, and inclusion (DE&I) perspective:

[0724] Message: "Ask new customers if they like Japanese food."

[0725] This system enables staff to take DE&I into consideration in real time while serving customers, thereby improving customer satisfaction.

[0726] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0727] Step 1:

[0728] The user puts on the smart glasses and starts serving customers. The smart glasses' built-in microphone captures the user's conversation in real time. The input of this step is voice data, and the output is the storage of the voice data for internal processing.

[0729] Step 2:

[0730] The device (smart glasses) converts the captured voice data into text data using the Google Cloud Speech-to-Text API. The input of this step is the captured voice data, and the output is the converted text data. Specifically, the speech recognition engine analyzes the voice waveform data and converts it into a string of characters.

[0731] Step 3:

[0732] The device then sends the converted text data to a central server using HTTP or HTTPS as the communication protocol. The input to this step is the text data, and the output is a notification to the server that transmission has been completed. Specifically, the device packages the text data in JSON format and sends it to the server via a REST API.

[0733] Step 4:

[0734] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). The input of this step is text data, and the output is the analysis result data. Specifically, the server extracts semantic elements from the text data and stores them in a database.

[0735] Step 5:

[0736] The server generates feedback using a generative AI model (e.g., OpenAI's GPT model) based on the analysis results. The input of this step is the analysis result data, and the output is the generated feedback message. Specifically, the server inputs a prompt sentence into the generative AI model and generates feedback in text format.

[0737] Step 6:

[0738] The server sends the generated feedback message to the device (smart glasses). The input of this step is the feedback message, and the output is a notification ready to be displayed on the smart glasses. Specifically, the server packages the feedback message in JSON format and sends it to the device via a REST API.

[0739] Step 7:

[0740] The terminal displays the received feedback message on the display of the smart glasses. The user can continue serving customers while checking the feedback in real time. The input of this step is the feedback message, and the output is the feedback displayed on the display. As a specific operation, the display control software of the smart glasses displays the feedback message on the screen.

[0741] 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.

[0742] This invention combines a message capture, analysis, and feedback generation system with an emotion engine that recognizes user emotions to more effectively promote diversity, equity, and inclusion (DE&I) perspectives in everyday work. Specifically, we provide a system that achieves this by utilizing the user's device, server, generative AI, natural language processing engine, and emotion engine.

[0743] First, the user uses the device to input and send a message via a communication tool such as Slack or email. At this time, the device captures the message in real time, and the user's emotional data is also recognized by the emotion engine. The recognized emotional data and message are then sent to a central server.

[0744] The central server passes the received message and emotional data to a natural language processing engine for analysis. Based on the analysis results, the AI ​​generates feedback for the message. This feedback not only takes into account the perspectives of each minority group, but also reflects the user's current emotional state. The generated feedback is delivered in a tone that is adjusted according to the user's emotional state.

[0745] To give a specific example, suppose a user sends a message such as "Let's ask the new employee if he likes ramen." This message is captured by the device, and the emotion engine recognizes the user's emotion as "excitement" or "enthusiasm." This message and emotion data are sent to the central server, which then passes this data to a natural language processing engine for analysis. Based on the analysis results and emotion data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Let's ask the new employee what his lunch preferences are.'" This feedback is provided in a more positive and accepting tone, tailored to the user's emotional state. This feedback is sent to the user's device, where the user can review it and modify the message to "Let's ask the new employee what his lunch preferences are."

[0746] The system can also be configured to respond to comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, and processes this text data and emotional data in the same way as other messages, allowing it to provide real-time feedback. As the meeting progresses, it can understand in real time how users feel about each comment and adjust feedback accordingly.

[0747] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[0748] The above is a specific embodiment for carrying out the present invention.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] Device: The user types and sends a message using a communication tool such as Slack or email. The device captures the message in real time, and an emotion engine is activated to recognize the user's emotions from their facial expressions and voice.

[0752] Step 2:

[0753] Device: Sends captured messages and recognized emotion data to the central server using API requests.

[0754] Step 3:

[0755] Server: The central server passes the received message and sentiment data to a natural language processing (NLP) engine, which analyzes the meaning and grammatical structure of the message.

[0756] Step 4:

[0757] Server: The generative AI combines the analyzed message data with the emotional data to generate appropriate feedback that reflects the user's current emotional state.

[0758] Step 5:

[0759] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[0760] Step 6:

[0761] Terminal: The user checks the feedback they receive. The feedback is provided in a tone that is tailored to their emotional state.

[0762] Step 7:

[0763] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[0764] Step 8:

[0765] Terminal: Resend the corrected message. The process begins again at step 1.

[0766] For example, when a user sends a message such as "Let's ask the new employee if he likes ramen," the message is captured by the device. At the same time, the emotion engine recognizes the user's emotion (e.g., "excited"). This data is sent to a central server, which then analyzes the message using a natural language processing engine.

[0767] Next, based on the analysis results and emotional data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as, 'Let's ask the new employee about their lunch preferences.'" This feedback is expressed in an appropriate tone, taking into account the user's emotional state.

[0768] Finally, the generated feedback is sent to the user's device, where the user can review it and revise the message if necessary. The revised message is then resent, allowing the user to incorporate a DE&I perspective into their daily work.

[0769] Example 2

[0770] 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."

[0771] Considering diversity, equity, and inclusion (DE&I) is an important issue in modern communication. However, it is difficult to properly incorporate these perspectives into daily work, and many users unconsciously send messages containing bias or inappropriate language. This invention aims to promote DE&I in daily work by analyzing the content of messages sent by users in real time and generating appropriate feedback that takes emotions into account.

[0772] 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.

[0773] In this invention, the server includes means for capturing messages, means for recognizing user emotion data from the captured message using an emotion engine on the terminal, means for transmitting the recognized emotion data and the captured message to a central server, means for analyzing the message and emotion data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data and emotion data, and means for transmitting the generated feedback to the terminal, thereby enabling users to modify the content and expression of their messages in real time to take DE&I into consideration.

[0774] A "message" is text data that a user sends through a communication tool.

[0775] "Capture" refers to the terminal acquiring a message entered by a user in real time and temporarily saving it.

[0776] A "terminal" is a hardware device (e.g., a PC or smartphone) that a user uses to input or view messages.

[0777] The "emotion engine" is a software module that analyzes the user's emotional state from the input message and generates emotional data.

[0778] "Emotion data" is data that represents the user's emotional state, obtained as a result of analysis by the emotion engine.

[0779] The "central server" is a server that receives captured messages and emotion data, analyzes them, and generates feedback.

[0780] A "natural language processing engine" is a software module that analyzes messages and emotional data received by the central server and understands their content and emotions.

[0781] "Generative AI" is an artificial intelligence module that generates appropriate feedback based on the analysis results of a natural language processing engine and emotional data.

[0782] "Feedback" is a suggested message created by the generative AI to improve the content and expression of the user's message.

[0783] Diversity, Equity, and Inclusion (DE&I) are principles that ensure individuals with diverse backgrounds are treated fairly and inclusively in organizations and society.

[0784] This invention is a system that effectively promotes diversity, equity, and inclusion (DE&I) in daily work by capturing messages, analyzing them, and generating sentiment-based feedback. The system includes the following key components:

[0785] First, a user uses a device to type and send a message using a communication tool such as Slack or email. At this stage, the device captures the message in real time. Capturing means obtaining the entered message data and temporarily saving it. Next, the captured message is passed to the emotion engine, which analyzes the user's emotion and generates emotion data. For example, if a user types the message "I'll ask the leader of the new project about the next meeting," the emotion engine will recognize the user's emotion as "interest" from this message.

[0786] The device then sends the generated emotion data and the captured message to a central server, which receives and stores this data. In the above example, the message "Ask the new project leader about the next meeting" and the emotion data of "interest" are sent to the central server. This data is then analyzed by a natural language processing engine, which understands the content and emotional tone of the message and performs analysis based on that.

[0787] Based on the analysis results, the generative AI generates appropriate feedback. For example, it might generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to, 'Could you please let me know a convenient time for our next meeting?'" The generative AI adjusts the tone of the feedback based on the emotional data "interest" to generate this feedback.

[0788] The generated feedback is sent from the central server to the device and provided to the user. The user can review this feedback and modify the message as necessary. For example, the original message can be modified based on the feedback, such as "Can you please tell me a convenient time for our next meeting?" The system is also designed to handle comments made during meetings, converting them into text data using transcription AI, and processing this text data and emotional data in the same way to provide real-time feedback.

[0789] This allows users to naturally incorporate diversity, equity, and inclusion-conscious communication into their daily work. This system promotes the understanding and practice of DE&I across the company, and is extremely useful in an increasingly diverse workplace.

[0790] Examples of prompt sentences include the following:

[0791] "Why not ask your new employees what their favorite food is for lunch? (Excited)"

[0792] "Please let me know a convenient time for our next meeting (interest)"

[0793] In this way, by using this system, users can check and correct the content and tone of their messages in real time, ensuring that their communications are conscious of DE&I perspectives.

[0794] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0795] Step 1:

[0796] A user uses a device to input and send a message using a communication tool such as Slack or email. The input data is the message entered by the user, such as "Let's ask the leader of the new project about the next meeting." The device captures this message. Specifically, the device's capture function acquires the message data and temporarily saves it.

[0797] Step 2:

[0798] The device passes the captured message to the emotion engine. Here, the input data is the captured message, and the emotion engine analyzes the user's emotion from this message and generates emotion data. For example, the emotion engine recognizes the user's emotion as "interest" from the message "Let's ask the leader of the new project about the next meeting" and generates emotion data. Specifically, the emotion engine runs a text analysis algorithm and assigns a data label for the emotional state.

[0799] Step 3:

[0800] The terminal transmits the generated emotion data and the captured message to the central server. Here, the input data is the emotion data generated by the emotion engine and the captured message, and is transmitted to the central server as output data. For example, the emotion data "interest" and the captured message are transmitted to the central server. In specific operations, the terminal transmits data to the server using a network protocol.

[0801] Step 4:

[0802] The central server passes the received message and emotional data to the natural language processing engine for analysis. Here, the input data is the received message and emotional data, which the natural language processing engine analyzes and generates an analysis result. For example, the natural language processing engine analyzes the message and emotional data to understand the content of the message and analyze the emotional tone at the same time. Specifically, the natural language processing engine performs syntactic and semantic analysis to generate a data model.

[0803] Step 5:

[0804] The generative AI generates feedback based on the analysis results of the natural language processing engine. Here, the input data are the analysis results and emotional data generated by the natural language processing engine, and the generative AI generates feedback based on this, resulting in appropriate feedback as output data. For example, the generative AI may generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to the format, 'Could you please let me know a convenient time for our next meeting?'" Specifically, the generative AI uses the generative model to construct a message and adjust the emotional tone.

[0805] Step 6:

[0806] The generated feedback is sent from the central server to the terminal and provided to the user. Here, the input data is the generated feedback, and the output data is displayed on the user's terminal. For example, the feedback is provided to the user in the form of "Can you tell me a convenient time for the next meeting?" In concrete terms, the central server sends the feedback data to the terminal, and the terminal displays it.

[0807] In this way, users can see the content and tone of messages in real time and ensure their communications take DE&I perspectives into account.

[0808] (Application example 2)

[0809] 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."

[0810] To improve the quality of communication between staff and customers in brick-and-mortar stores, a system that provides real-time feedback that takes diversity, equity, and inclusion into consideration is needed. Conventional communication support systems have the challenge of fully considering minority perspectives and adjusting feedback according to the user's emotional state.

[0811] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing messages, means for transmitting the captured messages and emotion data to a central server, means for analyzing the messages and emotion data received by the central server using a natural language processing engine and an emotion engine, means for a generation AI to generate feedback based on the analyzed data, means for transmitting the generated feedback to a user terminal, and means for adjusting the feedback in a tone that takes into account minority perspectives and corresponds to the user's emotional state. This enables store staff to receive appropriate feedback in real time that takes diversity, fairness, and inclusion into consideration.

[0812] The "message capture means" is a device or function that uses a voice input device or other input means to capture user utterances and inputs in real time and acquire the data.

[0813] "Emotion data" is data that analyzes a user's statements and messages and expresses the emotions that the person is feeling (e.g., joy, excitement, anger, etc.) as numbers or categories.

[0814] The "Central Server" is a computer system that receives captured messages and emotion data, sends them to each engine (natural language processing engine, emotion engine, etc.) for analysis, and ultimately generates feedback.

[0815] A "natural language processing engine" is a computer program or device that analyzes input text data and understands its meaning, intent, and context.

[0816] An "emotion engine" is a computer program or device that analyzes and recognizes a user's emotions from input data and identifies their emotional state.

[0817] "Generative AI" is an artificial intelligence model or system that generates optimal feedback based on analyzed data.

[0818] The "feedback generation means" is a function in which the generative AI generates appropriate feedback based on data analyzed by the natural language processing engine and emotion engine.

[0819] A "user terminal" is a device for providing generated feedback to a user, such as a mobile device such as a smartphone or tablet.

[0820] "Minority perspective" is a concept that means taking into consideration the views and opinions of minorities such as those of race, gender, and disability.

[0821] The "tone adjustment means" is a function for reflecting the user's emotional state and providing feedback in an appropriate tone.

[0822] This invention is a system for improving the quality of communication between staff and customers, or between staff members, in physical stores, with the aim of achieving diversity, equity, and inclusion (DE&I). The system consists of the following components:

[0823] 1. System Components

[0824] User device: A mobile device such as a smartphone or tablet.

[0825] Message capture method: Uses a voice input device (e.g., Google Speech-to-Text API) to convert user speech into text data in real time.

[0826] Central Server: A computer system that receives and analyzes the captured message and emotion data and generates feedback.

[0827] Natural Language Processing Engine: Uses the Google Natural Language API to parse messages and understand their meaning and intent.

[0828] Emotion Engine: Uses IBM Watson to recognize user emotions from messages.

[0829] Generative AI: Use a generative AI model, such as OpenAI GPT-4, to generate feedback.

[0830] Tone adjustment means: Adjust the tone of the generated feedback depending on the user's emotional state.

[0831] 2. System Operation Overview

[0832] 1. Message Capture:

[0833] The user terminal captures speech through a voice input device and converts it into text data. For example, a staff member uses a smartphone to say, "Let's ask the new employee if he likes ramen."

[0834] 2. Emotion analysis:

[0835] The text data is sent to an emotion engine to recognize the user's emotions (e.g., excitement, enthusiasm). The captured message and emotion data are sent to a central server.

[0836] 3. Natural Language Processing and Analysis:

[0837] The central server uses the Google Natural Language API to parse the messages to understand their subject and intent.

[0838] 4. Feedback Generation:

[0839] Based on the analysis results and emotional data, generative AI generates appropriate feedback, such as "Ask the new employee about their lunch preferences."

[0840] 5. Feedback Tone Adjustment:

[0841] The tone of the generated feedback is adjusted depending on the user's emotional state: if the user is excited, the feedback is provided in a more accepting tone.

[0842] 6. Providing feedback:

[0843] Finally, the adjusted feedback is sent to the user's device, where staff can review it in real time and take appropriate action or modify the message.

[0844] 3. Specific Examples

[0845] Example 1: Customer Service

[0846] Prompt: A customer asks, "How well does your store cater to families?" and a staff member responds, "We provide the best service."

[0847] Feedback: "To be more specific, our restaurant has seating reserved for families," the AI ​​generates feedback and displays it on the user's device.

[0848] Example 2: Staff communication

[0849] Prompt: When Staff A asks Staff B to help clean up, Staff B replies, "I'm busy right now, so I can't."

[0850] Feedback: "I understand, but I'll help you if you're not too busy," the AI ​​generates feedback and displays it on the user's device.

[0851] This allows store staff to more effectively engage with customers and communicate internally, effectively promoting diversity, equity, and inclusion.

[0852] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0853] Step 1:

[0854] The user terminal uses a voice input device to capture what the user says and converts the voice data into text data. The input is voice data and the output is text data. Specifically, the voice is converted into text using the Google Speech-to-Text API. For example, if a staff member says on their smartphone, "Let's ask the new employee about their lunch preferences," the voice data is captured and converted into text.

[0855] Step 2:

[0856] The captured text data is sent from the user device to a central server. At the same time, an emotion engine (e.g., IBM Watson) analyzes the user's emotions and generates emotion data. The input is text data and voice data, and the output is text data and emotion data. Specifically, the data captured by the user device is sent to the central server in real time.

[0857] Step 3:

[0858] The central server stores the received text data and emotion data and passes them to a natural language processing engine (e.g., Google Natural Language API) and emotion engine. The input is text data and emotion data, and the output is the analysis results and emotional state. Specifically, the central server passes this data to the engine, which then analyzes it. As a result of the analysis, the subject matter, intent, and context of the text are understood.

[0859] Step 4:

[0860] Based on the analysis results of the natural language processing engine and emotion engine, generative AI (e.g., OpenAI GPT-4) generates feedback. The input is the analysis results and emotional state, and the output is the generated feedback. Specifically, the generative AI creates optimal feedback, such as "Let's ask about lunch preferences so as not to force a particular dietary culture on new employees."

[0861] Step 5:

[0862] The generated feedback is adjusted in tone based on emotional data. The input is the generated feedback and the user's emotional state, and the output is the adjusted feedback. Specifically, if the user's emotional state is "excited," the tone is changed to a more positive and accepting one.

[0863] Step 6:

[0864] The adjusted feedback is sent from the central server to the user terminal. The input is the adjusted feedback, and the output is the feedback displayed on the terminal. Specifically, the user terminal receives the feedback in real time, and staff can check it to improve the quality of communication.

[0865] This allows store staff to improve customer interactions and staff-to-staff communication through feedback delivered in the right tone, effectively promoting diversity, equity, and inclusion.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] [Fourth embodiment]

[0870] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0871] 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.

[0872] 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).

[0873] 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.

[0874] 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.

[0875] 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).

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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."

[0883] This invention promotes diversity, equity, and inclusion (DE&I) perspectives in everyday work through a system that captures messages, analyzes them, and generates feedback. Specifically, we provide a system that achieves this goal by utilizing user devices, servers, generative AI, and natural language processing engines.

[0884] First, a user uses their device to type and send a message using a communication tool such as Slack or email. At this time, the device captures the message in real time and sends it to a central server. The central server analyzes the received message using a natural language processing engine, and a generation AI generates feedback for the message based on the analysis results. This feedback is created taking into account the perspectives of each minority group and suggests how the user's message should be improved. The generated feedback is then sent back to the user's device, where the user can review it and revise the message if necessary.

[0885] To give a specific example, suppose a user sends a message such as "Ask the new employee if they like ramen." This message is captured by the device and sent to a central server. The central server passes the message to a natural language processing engine for analysis. Based on the analysis results, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can confirm it. This allows the user to revise the message to "Ask the new employee what their lunch preferences are" and send it.

[0886] This system can also be configured to handle comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, which can then be processed in the same way as other messages, providing real-time feedback. This allows it to provide improvement suggestions from a DE&I perspective for comments made during meetings.

[0887] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[0888] The above is a specific embodiment for carrying out the present invention.

[0889] The processing flow will be explained below.

[0890] Step 1:

[0891] Device: A user types and sends a message using a communication tool such as Slack or email, and the device captures the message in real time.

[0892] Step 2:

[0893] Terminal: Sends captured messages to a central server using an API request.

[0894] Step 3:

[0895] Server: A central server receives messages and passes them to a natural language processing (NLP) engine, which analyzes the message for meaning and grammatical structure.

[0896] Step 4:

[0897] Server: Based on the analyzed message data, the AI ​​generates appropriate feedback that takes into account the perspectives of each minority group.

[0898] Step 5:

[0899] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[0900] Step 6:

[0901] Device: Check the feedback received by the user. Notify the user of the feedback displayed on the device.

[0902] Step 7:

[0903] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[0904] Step 8:

[0905] Terminal: Resend the corrected message. The process begins again at step 1.

[0906] The above is a specific processing flow for implementing this invention. This series of processes allows users to incorporate a DE&I perspective into their everyday communications.

[0907] Example 1

[0908] 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."

[0909] Diversity, equity, and inclusion (DE&I) are important values ​​in today's business environment, but it can be difficult to properly incorporate these perspectives into everyday work communications. Furthermore, messages and comments made during meetings can contain unconscious bias, which can negatively impact relationships and company culture. Traditional methods make it difficult to provide real-time feedback, and manual reviews and training have limitations. Therefore, there is a need for a system that automatically provides feedback that takes diversity, equity, and inclusion into consideration.

[0910] 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.

[0911] In this invention, the server includes a means for capturing messages, a means for transmitting the captured messages to a central server, a means for analyzing the messages received by the central server using a natural language processing engine, a means for a generation AI to generate feedback based on the analysis results, a means for transmitting the generated feedback to a user terminal, a means for the user to check the feedback and modify the message as necessary, and a means for converting statements made during meetings into text data using a transcription AI, analyzing the text data, and generating feedback, thereby enabling users to naturally incorporate diversity, equity, and inclusion into their daily work communications.

[0912] The "means for capturing messages" is a function for collecting messages that users input and send using a communication tool in real time.

[0913] The "means for transmitting captured messages to a central server" is a function for transferring collected message data to a central server via a network.

[0914] "Means for analyzing messages received by the central server using a natural language processing engine" refers to a function that uses natural language processing technology to analyze message data received by the central server and understand the context and meaning.

[0915] "Means for the generative AI to generate feedback based on the analysis results" refers to a function in which the generative AI automatically creates appropriate feedback based on the analysis results obtained by the natural language processing engine.

[0916] "Means for sending generated feedback to a user terminal" refers to a function that transfers the feedback created by the generation AI to a user terminal via a network.

[0917] "Means for users to review feedback and revise messages as necessary" refers to a function that allows users to view feedback on their device and edit or revise the original message based on the feedback.

[0918] "A means of converting statements made during meetings into text data using transcription AI, analyzing that text data, and generating feedback" is a function that converts spoken statements made during meetings into text using transcription technology, analyzes that text data using a natural language processing engine, and uses generation AI to create feedback.

[0919] "Diversity" means bringing together individuals with different attributes and backgrounds and respecting and accepting their differences.

[0920] "Fairness" means a state in which all individuals are treated equally and unfair discrimination and prejudice are eliminated.

[0921] "Inclusion" means that all people have the opportunity to participate and contribute to an organization or society, and their value is recognized.

[0922] The present invention is directed to promoting diversity, equity, and inclusion (DE&I) using a system that captures messages, analyzes them, and generates feedback. Specific embodiments for implementing the present invention are described below.

[0923] Components

[0924] 1. User Device

[0925] A device such as a computer or smartphone used by a user, on which communication tools such as Slack or email are installed.

[0926] 2. Central Server

[0927] A central processing unit for receiving messages, performing analysis, and generating feedback. It includes a high-performance processor and storage.

[0928] 3. Natural Language Processing Engine

[0929] Software for analyzing the context and meaning of messages. Examples include Google Cloud Natural Language API and IBM Watson.

[0930] 4. Generation AI

[0931] An artificial intelligence model that generates feedback based on analyzed data. Examples include OpenAI's GPT-3.

[0932] 5. Transcription AI

[0933] Software for transcribing what is said during meetings in real time, such as the open source Kaldi or the commercial Google Speech-to-Text.

[0934] Program processing

[0935] Capture and send messages

[0936] When a user sends a message from their device via Slack or email, the message is captured in real time, stored in a dedicated message queue by a script running on the device, and then sent to a central server via an HTTP POST request.

[0937] Message Parsing

[0938] When the server receives a message, it passes it to a natural language processing engine to analyze its context and meaning. This analysis is performed using Google Cloud Natural Language API, etc. The analysis results are recorded on the server and then passed to the generative AI model.

[0939] Generate feedback

[0940] The AI ​​then generates appropriate feedback based on the analysis results. The generated feedback takes into account minority perspectives in particular. For example, the following prompt is sent to the AI:

[0941] "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0942] Send and review feedback

[0943] The generated feedback is sent to the user's device via an HTTP POST request, where the user can view the feedback and modify the message if necessary.

[0944] Responding to comments made during meetings

[0945] This system can also process comments made during meetings. When a user speaks, the transcription AI converts the comment into text data. The converted text data is analyzed in the same way as other messages, and feedback is generated by the generation AI. This makes it possible to provide appropriate feedback in real time for comments made during meetings.

[0946] Specific examples

[0947] For example, if a user sends a message saying, "Let's ask the new employee if he likes ramen," the message is immediately captured and sent to the server. The server passes the message to a natural language processing engine for analysis, and the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee. We suggest changing it to a more neutral phrase, such as 'Let's ask the new employee what their lunch preferences are.'" This feedback is sent to the user's device, where the user can review it and modify the message.

[0948] Using this system will promote communication that takes diversity, equity, and inclusion into consideration, and support the understanding and implementation of DE&I across the company.

[0949] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0950] Step 1: Enter and capture your message

[0951] A user types and sends a message using a communication tool such as Slack or email.

[0952] An example of a message to enter is, "Let's ask new employees if they like ramen."

[0953] The terminal captures this message in real time and stores it in a dedicated message queue.

[0954] Input: User input message

[0955] Output: Message data stored in the message queue

[0956] Step 2: Sending and Receiving Messages

[0957] The device sends the data stored in the message queue to the central server via an HTTP POST request.

[0958] The server receives this data at the receiving endpoint (API endpoint).

[0959] Input: Message data retrieved from the message queue

[0960] Output: Message data received by the server

[0961] Step 3: Parse the message

[0962] The server passes the received message to a natural language processing (NLP) engine for analysis.

[0963] For example, use the Google Cloud Natural Language API to analyze the context and tone of messages.

[0964] Input: Message data sent to the central server

[0965] Output: Analysis results obtained from the natural language processing engine

[0966] Step 4: Generate feedback

[0967] The server sends a prompt to the generation AI based on the analysis results.

[0968] Example: Send a prompt to the generation AI saying, "This message may be pushing a specific food culture. Please suggest a more neutral wording."

[0969] Generative AI generates feedback based on prompts.

[0970] Input: Analysis results from the natural language processing engine and prompt sentences

[0971] Output: Feedback obtained from the generative AI

[0972] Step 5: Submit your feedback

[0973] The server sends the feedback received from the generated AI to the user's device via an HTTP POST request.

[0974] Input: Feedback generated by the generative AI

[0975] Output: Feedback sent to the user's device

[0976] Step 6: View and review feedback

[0977] The device displays the received feedback on the screen.

[0978] The user reviews the feedback and modifies the original message if necessary.

[0979] Input: Feedback received

[0980] Output: Corrected or confirmed message

[0981] Step 7: Transcribe what is said during the meeting and generate feedback

[0982] A user speaks during a conference.

[0983] Transcription AI converts speech into text data.

[0984] The text data is processed in the same manner as in steps 3 to 6 above to generate analysis and feedback.

[0985] Input: Voice remarks during a meeting

[0986] Output: Generated feedback

[0987] This series of steps will create a system that helps users communicate with diversity, equity, and inclusion in their daily work.

[0988] (Application example 1)

[0989] 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."

[0990] In traditional customer service, it is difficult for customer service staff to respond in real time while taking diversity, equity, and inclusion (DE&I) into consideration. As a result, they may unconsciously include bias or lack of understanding in their communications with customers, which can lead to lower customer satisfaction and problems. To solve this problem, a system is needed that provides feedback from a DE&I perspective in real time while customers are interacting with the service.

[0991] 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.

[0992] In this invention, the server includes means for capturing voice, means for converting voice to text, means for transmitting the converted text data to a central server, means for analyzing the text data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data, and means for transmitting the generated feedback to a display device. This makes it possible to provide staff with feedback that takes diversity, equity, and inclusion (DE&I) perspectives into consideration in real time while they are serving customers, thereby improving the quality of communication.

[0993] "Audio capture means" refers to a device that collects the remarks of service staff and customers in real time. Specifically, it uses a voice input device such as a microphone.

[0994] "Speech-to-text means" refers to technologies used to convert captured speech data into text, such as speech recognition engines and cloud-based speech recognition services.

[0995] "Means for transmitting the converted text data to a central server" refers to communications devices or technologies for converting speech to text and then transmitting the text data to a server via the Internet.

[0996] "Means for analyzing text data received by the central server using a natural language processing engine" refers to a process and device that analyzes text data sent to the central server using a natural language processing algorithm.

[0997] "Means for generative AI to generate feedback based on analyzed data" refers to the process by which artificial intelligence generates appropriate feedback based on data analyzed by a natural language processing engine. A generative AI model falls into this category.

[0998] "Means for transmitting the generated feedback to a display device" refers to the communication methods and technologies for transmitting the generated feedback to a display device, such as smart glasses worn by the staff member.

[0999] "Display device" refers to a device for visually displaying the generated feedback, such as smart glasses or a head-mounted display.

[1000] The invention is a system that captures voice, converts it into text, sends the text data to a central server, analyzes it, and generates and displays feedback, enabling wait staff to take diversity, equity, and inclusion (DE&I) into consideration in real time.

[1001] First, the wait staff wears smart glasses with a built-in microphone. The glasses capture the conversation in real time. This voice data is converted into text data by the voice recognition engine in the smart glasses. The voice recognition engine can use the Google Cloud Speech-to-Text API.

[1002] The text data is then sent via an internet connection to a central server, where it is analyzed using a natural language processing engine (such as SpaCy or NLTK). Based on the data analyzed by this natural language processing engine, a generative AI generates appropriate feedback. The generative AI can be a GPT model from OpenAI, for example.

[1003] The generated feedback is displayed in real time on smart glasses, allowing staff to view the feedback and take more appropriate action from a DE&I perspective. Smart glasses such as Vuzix Blade and Google Glass can be used as display devices.

[1004] As a concrete example, if a waiter says, "Let's ask the new customer if he likes Japanese food," this utterance is captured by a microphone built into the smart glasses. This voice data is converted into text data using the Google Cloud Speech-to-Text API, and the text data is sent to a central server. The central server analyzes the text data with a natural language processing engine, and based on the analysis results, a generative AI model (for example, OpenAI's GPT model) generates feedback such as, "This message may be imposing a specific food culture on the new customer, so we suggest making a change by asking the customer what their lunch preferences are." The generated feedback is immediately displayed on the smart glasses' display.

[1005] Examples of prompts that can be input to a generative AI model include:

[1006] Please share your suggestions for improving the following messaging from a diversity, equity, and inclusion (DE&I) perspective:

[1007] Message: "Ask new customers if they like Japanese food."

[1008] This system enables staff to take DE&I into consideration in real time while serving customers, thereby improving customer satisfaction.

[1009] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1010] Step 1:

[1011] The user puts on the smart glasses and starts serving customers. The smart glasses' built-in microphone captures the user's conversation in real time. The input of this step is voice data, and the output is the storage of the voice data for internal processing.

[1012] Step 2:

[1013] The device (smart glasses) converts the captured voice data into text data using the Google Cloud Speech-to-Text API. The input of this step is the captured voice data, and the output is the converted text data. Specifically, the speech recognition engine analyzes the voice waveform data and converts it into a string of characters.

[1014] Step 3:

[1015] The device then sends the converted text data to a central server using HTTP or HTTPS as the communication protocol. The input to this step is the text data, and the output is a notification to the server that transmission has been completed. Specifically, the device packages the text data in JSON format and sends it to the server via a REST API.

[1016] Step 4:

[1017] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). The input of this step is text data, and the output is the analysis result data. Specifically, the server extracts semantic elements from the text data and stores them in a database.

[1018] Step 5:

[1019] The server generates feedback using a generative AI model (e.g., OpenAI's GPT model) based on the analysis results. The input of this step is the analysis result data, and the output is the generated feedback message. Specifically, the server inputs a prompt sentence into the generative AI model and generates feedback in text format.

[1020] Step 6:

[1021] The server sends the generated feedback message to the device (smart glasses). The input of this step is the feedback message, and the output is a notification ready to be displayed on the smart glasses. Specifically, the server packages the feedback message in JSON format and sends it to the device via a REST API.

[1022] Step 7:

[1023] The terminal displays the received feedback message on the display of the smart glasses. The user can continue serving customers while checking the feedback in real time. The input of this step is the feedback message, and the output is the feedback displayed on the display. As a specific operation, the display control software of the smart glasses displays the feedback message on the screen.

[1024] 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.

[1025] This invention combines a message capture, analysis, and feedback generation system with an emotion engine that recognizes user emotions to more effectively promote diversity, equity, and inclusion (DE&I) perspectives in everyday work. Specifically, we provide a system that achieves this by utilizing the user's device, server, generative AI, natural language processing engine, and emotion engine.

[1026] First, the user uses the device to input and send a message via a communication tool such as Slack or email. At this time, the device captures the message in real time, and the user's emotional data is also recognized by the emotion engine. The recognized emotional data and message are then sent to a central server.

[1027] The central server passes the received message and emotional data to a natural language processing engine for analysis. Based on the analysis results, the AI ​​generates feedback for the message. This feedback not only takes into account the perspectives of each minority group, but also reflects the user's current emotional state. The generated feedback is delivered in a tone that is adjusted according to the user's emotional state.

[1028] To give a specific example, suppose a user sends a message such as "Let's ask the new employee if he likes ramen." This message is captured by the device, and the emotion engine recognizes the user's emotion as "excitement" or "enthusiasm." This message and emotion data are sent to the central server, which then passes this data to a natural language processing engine for analysis. Based on the analysis results and emotion data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as 'Let's ask the new employee what his lunch preferences are.'" This feedback is provided in a more positive and accepting tone, tailored to the user's emotional state. This feedback is sent to the user's device, where the user can review it and modify the message to "Let's ask the new employee what his lunch preferences are."

[1029] The system can also be configured to respond to comments made during meetings. It uses transcription AI to convert comments made during meetings into text data, and processes this text data and emotional data in the same way as other messages, allowing it to provide real-time feedback. As the meeting progresses, it can understand in real time how users feel about each comment and adjust feedback accordingly.

[1030] The system serves as a powerful tool for embedding the important perspectives of diversity, equity, and inclusion into everyday work. Users can naturally incorporate these perspectives through their communications, promoting the understanding and practice of DE&I across the company.

[1031] The above is a specific embodiment for carrying out the present invention.

[1032] The processing flow will be explained below.

[1033] Step 1:

[1034] Device: The user types and sends a message using a communication tool such as Slack or email. The device captures the message in real time, and an emotion engine is activated to recognize the user's emotions from their facial expressions and voice.

[1035] Step 2:

[1036] Device: Sends captured messages and recognized emotion data to the central server using API requests.

[1037] Step 3:

[1038] Server: The central server passes the received message and sentiment data to a natural language processing (NLP) engine, which analyzes the meaning and grammatical structure of the message.

[1039] Step 4:

[1040] Server: The generative AI combines the analyzed message data with the emotional data to generate appropriate feedback that reflects the user's current emotional state.

[1041] Step 5:

[1042] Server: Sends the generated feedback to the user's device. The feedback information is included in the API response.

[1043] Step 6:

[1044] Terminal: The user checks the feedback they receive. The feedback is provided in a tone that is tailored to their emotional state.

[1045] Step 7:

[1046] User: Based on feedback, the message is revised as needed. For example, the message "Ask new employees if they like ramen" is changed to "Ask new employees what their lunch preferences are."

[1047] Step 8:

[1048] Terminal: Resend the corrected message. The process begins again at step 1.

[1049] For example, when a user sends a message such as "Let's ask the new employee if he likes ramen," the message is captured by the device. At the same time, the emotion engine recognizes the user's emotion (e.g., "excited"). This data is sent to a central server, which then analyzes the message using a natural language processing engine.

[1050] Next, based on the analysis results and emotional data, the generative AI generates feedback such as, "This message may be imposing a specific food culture on the new employee, so we suggest changing it to a more neutral phrase such as, 'Let's ask the new employee about their lunch preferences.'" This feedback is expressed in an appropriate tone, taking into account the user's emotional state.

[1051] Finally, the generated feedback is sent to the user's device, where the user can review it and revise the message if necessary. The revised message is then resent, allowing the user to incorporate a DE&I perspective into their daily work.

[1052] Example 2

[1053] 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."

[1054] Considering diversity, equity, and inclusion (DE&I) is an important issue in modern communication. However, it is difficult to properly incorporate these perspectives into daily work, and many users unconsciously send messages containing bias or inappropriate language. This invention aims to promote DE&I in daily work by analyzing the content of messages sent by users in real time and generating appropriate feedback that takes emotions into account.

[1055] 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.

[1056] In this invention, the server includes means for capturing messages, means for recognizing user emotion data from the captured message using an emotion engine on the terminal, means for transmitting the recognized emotion data and the captured message to a central server, means for analyzing the message and emotion data received by the central server using a natural language processing engine, means for a generation AI to generate feedback based on the analyzed data and emotion data, and means for transmitting the generated feedback to the terminal, thereby enabling users to modify the content and expression of their messages in real time to take DE&I into consideration.

[1057] A "message" is text data that a user sends through a communication tool.

[1058] "Capture" refers to the terminal acquiring a message entered by a user in real time and temporarily saving it.

[1059] A "terminal" is a hardware device (e.g., a PC or smartphone) that a user uses to input or view messages.

[1060] The "emotion engine" is a software module that analyzes the user's emotional state from the input message and generates emotional data.

[1061] "Emotion data" is data that represents the user's emotional state, obtained as a result of analysis by the emotion engine.

[1062] The "central server" is a server that receives captured messages and emotion data, analyzes them, and generates feedback.

[1063] A "natural language processing engine" is a software module that analyzes messages and emotional data received by the central server and understands their content and emotions.

[1064] "Generative AI" is an artificial intelligence module that generates appropriate feedback based on the analysis results of a natural language processing engine and emotional data.

[1065] "Feedback" is a suggested message created by the generative AI to improve the content and expression of the user's message.

[1066] Diversity, Equity, and Inclusion (DE&I) are principles that ensure individuals with diverse backgrounds are treated fairly and inclusively in organizations and society.

[1067] This invention is a system that effectively promotes diversity, equity, and inclusion (DE&I) in daily work by capturing messages, analyzing them, and generating sentiment-based feedback. The system includes the following key components:

[1068] First, a user uses a device to type and send a message using a communication tool such as Slack or email. At this stage, the device captures the message in real time. Capturing means obtaining the entered message data and temporarily saving it. Next, the captured message is passed to the emotion engine, which analyzes the user's emotion and generates emotion data. For example, if a user types the message "I'll ask the leader of the new project about the next meeting," the emotion engine will recognize the user's emotion as "interest" from this message.

[1069] The device then sends the generated emotion data and the captured message to a central server, which receives and stores this data. In the above example, the message "Ask the new project leader about the next meeting" and the emotion data of "interest" are sent to the central server. This data is then analyzed by a natural language processing engine, which understands the content and emotional tone of the message and performs analysis based on that.

[1070] Based on the analysis results, the generative AI generates appropriate feedback. For example, it might generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to, 'Could you please let me know a convenient time for our next meeting?'" The generative AI adjusts the tone of the feedback based on the emotional data "interest" to generate this feedback.

[1071] The generated feedback is sent from the central server to the device and provided to the user. The user can review this feedback and modify the message as necessary. For example, the original message can be modified based on the feedback, such as "Can you please tell me a convenient time for our next meeting?" The system is also designed to handle comments made during meetings, converting them into text data using transcription AI, and processing this text data and emotional data in the same way to provide real-time feedback.

[1072] This allows users to naturally incorporate diversity, equity, and inclusion-conscious communication into their daily work. This system promotes the understanding and practice of DE&I across the company, and is extremely useful in an increasingly diverse workplace.

[1073] Examples of prompt sentences include the following:

[1074] "Why not ask your new employees what their favorite food is for lunch? (Excited)"

[1075] "Please let me know a convenient time for our next meeting (interest)"

[1076] In this way, by using this system, users can check and correct the content and tone of their messages in real time, ensuring that their communications are conscious of DE&I perspectives.

[1077] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1078] Step 1:

[1079] A user uses a device to input and send a message using a communication tool such as Slack or email. The input data is the message entered by the user, such as "Let's ask the leader of the new project about the next meeting." The device captures this message. Specifically, the device's capture function acquires the message data and temporarily saves it.

[1080] Step 2:

[1081] The device passes the captured message to the emotion engine. Here, the input data is the captured message, and the emotion engine analyzes the user's emotion from this message and generates emotion data. For example, the emotion engine recognizes the user's emotion as "interest" from the message "Let's ask the leader of the new project about the next meeting" and generates emotion data. Specifically, the emotion engine runs a text analysis algorithm and assigns a data label for the emotional state.

[1082] Step 3:

[1083] The terminal transmits the generated emotion data and the captured message to the central server. Here, the input data is the emotion data generated by the emotion engine and the captured message, and is transmitted to the central server as output data. For example, the emotion data "interest" and the captured message are transmitted to the central server. In specific operations, the terminal transmits data to the server using a network protocol.

[1084] Step 4:

[1085] The central server passes the received message and emotional data to the natural language processing engine for analysis. Here, the input data is the received message and emotional data, which the natural language processing engine analyzes and generates an analysis result. For example, the natural language processing engine analyzes the message and emotional data to understand the content of the message and analyze the emotional tone at the same time. Specifically, the natural language processing engine performs syntactic and semantic analysis to generate a data model.

[1086] Step 5:

[1087] The generative AI generates feedback based on the analysis results of the natural language processing engine. Here, the input data are the analysis results and emotional data generated by the natural language processing engine, and the generative AI generates feedback based on this, resulting in appropriate feedback as output data. For example, the generative AI may generate feedback such as, "This message is polite, but it may be burdensome for the leader, so I suggest changing it to the format, 'Could you please let me know a convenient time for our next meeting?'" Specifically, the generative AI uses the generative model to construct a message and adjust the emotional tone.

[1088] Step 6:

[1089] The generated feedback is sent from the central server to the terminal and provided to the user. Here, the input data is the generated feedback, and the output data is displayed on the user's terminal. For example, the feedback is provided to the user in the form of "Can you tell me a convenient time for the next meeting?" In concrete terms, the central server sends the feedback data to the terminal, and the terminal displays it.

[1090] In this way, users can see the content and tone of messages in real time and ensure their communications take DE&I perspectives into account.

[1091] (Application example 2)

[1092] 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."

[1093] To improve the quality of communication between staff and customers in brick-and-mortar stores, a system that provides real-time feedback that takes diversity, equity, and inclusion into consideration is needed. Conventional communication support systems have the challenge of fully considering minority perspectives and adjusting feedback according to the user's emotional state.

[1094] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing messages, means for transmitting the captured messages and emotion data to a central server, means for analyzing the messages and emotion data received by the central server using a natural language processing engine and an emotion engine, means for a generation AI to generate feedback based on the analyzed data, means for transmitting the generated feedback to a user terminal, and means for adjusting the feedback in a tone that takes into account minority perspectives and corresponds to the user's emotional state. This enables store staff to receive appropriate feedback in real time that takes diversity, fairness, and inclusion into consideration.

[1095] The "message capture means" is a device or function that uses a voice input device or other input means to capture user utterances and inputs in real time and acquire the data.

[1096] "Emotion data" is data that analyzes a user's statements and messages and expresses the emotions that the person is feeling (e.g., joy, excitement, anger, etc.) as numbers or categories.

[1097] The "Central Server" is a computer system that receives captured messages and emotion data, sends them to each engine (natural language processing engine, emotion engine, etc.) for analysis, and ultimately generates feedback.

[1098] A "natural language processing engine" is a computer program or device that analyzes input text data and understands its meaning, intent, and context.

[1099] An "emotion engine" is a computer program or device that analyzes and recognizes a user's emotions from input data and identifies their emotional state.

[1100] "Generative AI" is an artificial intelligence model or system that generates optimal feedback based on analyzed data.

[1101] The "feedback generation means" is a function in which the generative AI generates appropriate feedback based on data analyzed by the natural language processing engine and emotion engine.

[1102] A "user terminal" is a device for providing generated feedback to a user, such as a mobile device such as a smartphone or tablet.

[1103] "Minority perspective" is a concept that means taking into consideration the views and opinions of minorities such as those of race, gender, and disability.

[1104] The "tone adjustment means" is a function for reflecting the user's emotional state and providing feedback in an appropriate tone.

[1105] This invention is a system for improving the quality of communication between staff and customers, or between staff members, in physical stores, with the aim of achieving diversity, equity, and inclusion (DE&I). The system consists of the following components:

[1106] 1. System Components

[1107] User device: A mobile device such as a smartphone or tablet.

[1108] Message capture method: Uses a voice input device (e.g., Google Speech-to-Text API) to convert user speech into text data in real time.

[1109] Central Server: A computer system that receives and analyzes the captured message and emotion data and generates feedback.

[1110] Natural Language Processing Engine: Uses the Google Natural Language API to parse messages and understand their meaning and intent.

[1111] Emotion Engine: Uses IBM Watson to recognize user emotions from messages.

[1112] Generative AI: Use a generative AI model, such as OpenAI GPT-4, to generate feedback.

[1113] Tone adjustment means: Adjust the tone of the generated feedback depending on the user's emotional state.

[1114] 2. System Operation Overview

[1115] 1. Message Capture:

[1116] The user terminal captures speech through a voice input device and converts it into text data. For example, a staff member uses a smartphone to say, "Let's ask the new employee if he likes ramen."

[1117] 2. Emotion analysis:

[1118] The text data is sent to an emotion engine to recognize the user's emotions (e.g., excitement, enthusiasm). The captured message and emotion data are sent to a central server.

[1119] 3. Natural Language Processing and Analysis:

[1120] The central server uses the Google Natural Language API to parse the messages to understand their subject and intent.

[1121] 4. Feedback Generation:

[1122] Based on the analysis results and emotional data, generative AI generates appropriate feedback, such as "Ask the new employee about their lunch preferences."

[1123] 5. Feedback Tone Adjustment:

[1124] The tone of the generated feedback is adjusted depending on the user's emotional state: if the user is excited, the feedback is provided in a more accepting tone.

[1125] 6. Providing feedback:

[1126] Finally, the adjusted feedback is sent to the user's device, where staff can review it in real time and take appropriate action or modify the message.

[1127] 3. Specific Examples

[1128] Example 1: Customer Service

[1129] Prompt: A customer asks, "How well does your store cater to families?" and a staff member responds, "We provide the best service."

[1130] Feedback: "To be more specific, our restaurant has seating reserved for families," the AI ​​generates feedback and displays it on the user's device.

[1131] Example 2: Staff communication

[1132] Prompt: When Staff A asks Staff B to help clean up, Staff B replies, "I'm busy right now, so I can't."

[1133] Feedback: "I understand, but I'll help you if you're not too busy," the AI ​​generates feedback and displays it on the user's device.

[1134] This allows store staff to more effectively engage with customers and communicate internally, effectively promoting diversity, equity, and inclusion.

[1135] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1136] Step 1:

[1137] The user terminal uses a voice input device to capture what the user says and converts the voice data into text data. The input is voice data and the output is text data. Specifically, the voice is converted into text using the Google Speech-to-Text API. For example, if a staff member says on their smartphone, "Let's ask the new employee about their lunch preferences," the voice data is captured and converted into text.

[1138] Step 2:

[1139] The captured text data is sent from the user device to a central server. At the same time, an emotion engine (e.g., IBM Watson) analyzes the user's emotions and generates emotion data. The input is text data and voice data, and the output is text data and emotion data. Specifically, the data captured by the user device is sent to the central server in real time.

[1140] Step 3:

[1141] The central server stores the received text data and emotion data and passes them to a natural language processing engine (e.g., Google Natural Language API) and emotion engine. The input is text data and emotion data, and the output is the analysis results and emotional state. Specifically, the central server passes this data to the engine, which then analyzes it. As a result of the analysis, the subject matter, intent, and context of the text are understood.

[1142] Step 4:

[1143] Based on the analysis results of the natural language processing engine and emotion engine, generative AI (e.g., OpenAI GPT-4) generates feedback. The input is the analysis results and emotional state, and the output is the generated feedback. Specifically, the generative AI creates optimal feedback, such as "Let's ask about lunch preferences so as not to force a particular dietary culture on new employees."

[1144] Step 5:

[1145] The generated feedback is adjusted in tone based on emotional data. The input is the generated feedback and the user's emotional state, and the output is the adjusted feedback. Specifically, if the user's emotional state is "excited," the tone is changed to a more positive and accepting one.

[1146] Step 6:

[1147] The adjusted feedback is sent from the central server to the user terminal. The input is the adjusted feedback, and the output is the feedback displayed on the terminal. Specifically, the user terminal receives the feedback in real time, and staff can check it to improve the quality of communication.

[1148] This allows store staff to improve customer interactions and staff-to-staff communication through feedback delivered in the right tone, effectively promoting diversity, equity, and inclusion.

[1149] 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.

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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.

[1154] 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.

[1155] 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).

[1156] 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.

[1157] 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."

[1158] 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.

[1159] 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).

[1160] 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.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] 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.

[1165] 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.

[1166] 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.

[1167] 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.

[1168] 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.

[1169] 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.

[1170] The following is further disclosed regarding the above embodiment.

[1171] (Claim 1)

[1172] a means for capturing messages;

[1173] means for transmitting the captured messages to a central server;

[1174] means for analyzing messages received by the central server using a natural language processing engine;

[1175] A means for the AI ​​to generate feedback based on the analyzed data, and

[1176] The system includes means for transmitting the generated feedback to a user terminal.

[1177] (Claim 2)

[1178] 10. The system of claim 1, wherein the message capture means captures messages from the communication tool.

[1179] (Claim 3)

[1180] 10. The system of claim 1, further comprising means for the generating AI to consider minority perspectives when generating feedback.

[1181] "Example 1"

[1182] (Claim 1)

[1183] a means for capturing messages;

[1184] means for transmitting the captured messages to a central server;

[1185] means for analyzing messages received by the central server using a natural language processing engine;

[1186] A means for the AI ​​to generate feedback based on the analysis results,

[1187] means for transmitting the generated feedback to a user terminal;

[1188] a means for users to review the feedback and revise the message if necessary; and

[1189] A method to transcribe what is said during a meeting and convert it into text data using AI, then analyze the text data and generate feedback.

[1190] A system including:

[1191] (Claim 2)

[1192] 10. The system of claim 1, wherein the message capture means captures messages from the communication tool.

[1193] (Claim 3)

[1194] 10. The system of claim 1, further comprising means for the generating AI to consider minority perspectives when generating feedback.

[1195] "Application Example 1"

[1196] (Claim 1)

[1197] a means for capturing audio;

[1198] a means for converting the captured audio into text;

[1199] means for transmitting the converted text data to a central server;

[1200] A means for analyzing the text data received by the central server using a natural language processing engine;

[1201] A means for the AI ​​to generate feedback based on the analyzed data, and

[1202] The system includes means for transmitting the generated feedback to a display device.

[1203] (Claim 2)

[1204] 10. The system of claim 1, wherein the voice capturing means captures the voice from a voice recognition device.

[1205] (Claim 3)

[1206] 10. The system of claim 1, further comprising means for the generative AI to consider diversity, equity, and inclusion considerations when generating feedback.

[1207] "Example 2: Combining Emotion Engines"

[1208] (Claim 1)

[1209] a means for capturing messages;

[1210] means for recognizing user emotion data from the captured message using an emotion engine in the terminal;

[1211] means for transmitting the recognized emotion data and the captured message to a central server;

[1212] A means for analyzing the message and emotion data received by the central server using a natural language processing engine;

[1213] A means for the AI ​​to generate feedback based on the analyzed data and emotional data,

[1214] The system includes means for transmitting the generated feedback to the terminal.

[1215] (Claim 2)

[1216] 10. The system of claim 1, wherein the message capture means captures messages from the communication tool.

[1217] (Claim 3)

[1218] 10. The system of claim 1, further comprising means for the generating AI to consider minority perspectives and the user's emotional state when generating feedback.

[1219] "Application example 2 when combining emotion engines"

[1220] (Claim 1)

[1221] a means for capturing messages;

[1222] means for transmitting the captured message and emotion data to a central server;

[1223] means for analyzing the message and emotion data received by the central server using a natural language processing engine and an emotion engine;

[1224] A means for the AI ​​to generate feedback based on the analyzed data, and

[1225] The system includes means for transmitting the generated feedback to a user terminal.

[1226] (Claim 2)

[1227] 10. The system of claim 1, wherein the message capturing means captures the message from a voice input device.

[1228] (Claim 3)

[1229] The system of claim 1, further comprising means for the generating AI to take into account minority viewpoints when generating feedback and to adjust the feedback in a tone that corresponds to the user's emotional state. [Explanation of symbols]

[1230] 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. a means for capturing messages; means for transmitting the captured messages to a central server; means for analyzing messages received by the central server using a natural language processing engine; A means for the AI ​​to generate feedback based on the analyzed data, and The system includes means for transmitting the generated feedback to a user terminal.

2. 2. The system according to claim 1, wherein the message capturing means captures messages from a communication tool.

3. The system of claim 1 , further comprising means for the generating AI to take minority perspectives into account when generating feedback.

Images