system

Abstract

We provide the system. [Solution] Voice input means and, A means of converting speech to text, A means of sending text data to a server, A means of saving text data on a server, A means of obtaining text data from a server, A means of displaying the acquired text data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, memorization in tests and work is inevitable and is an important skill especially for students and working people. However, methods for improving the efficiency of memorization are limited, and there is a particular shortage of a question-and-answer learning system that utilizes voice input. For this reason, there is a need for a means to easily create a dedicated memorization system for oneself and proceed with learning efficiently. The present invention aims to solve such problems and provide a system that supports individual learning processes using voice input.

Means for Solving the Problems

[0005] The present invention provides a system including a voice input means, a means for converting speech to text, a means for transmitting text data to a server, a means for storing text data on the server, a means for retrieving text data from the server, and a means for displaying the retrieved text data. First, the user inputs questions and answers by voice using the voice input means. Next, a speech recognition engine converts these speeches into text. The converted text data is transmitted to the server and stored on the server. When the user selects a learning mode, the text data is retrieved from the server and displayed to the user. In this way, the user can efficiently proceed with question-and-answer format learning through voice input.

[0006] "Voice input means" refers to a device or function that can acquire voice as a digital signal.

[0007] "Methods for converting speech to text" refer to the process of converting acquired speech data into text information using speech recognition algorithms.

[0008] "Means for sending text data to a server" refers to a communication function for sending converted character information to a server via the Internet or other network.

[0009] "Means of saving text data on a server" refers to a system for permanently storing received text information in a database, file system, or similar location.

[0010] "Means of retrieving text data from a server" refers to the process of retrieving stored character information from a server as needed and providing it to the user.

[0011] "Means for displaying acquired text data" refers to a function that displays character information acquired from a server on a screen or other display device in a way that the user can see. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system for students and working professionals to efficiently memorize knowledge necessary for exams and work, and supports learning by creating personalized question-and-answer format data using voice input.

[0034] User voice input and terminal processing

[0035] First, the user launches the application. The application screen displays a "Question Input" button and an "Answer Input" button. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by a speech recognition engine. Then, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice answer is also converted into text by the device.

[0036] Sending text data and storing it on the server

[0037] The terminal sends the converted question and answer text data to the server. Specifically, it uses an HTTP POST request to send the question and answer text data to the server in JSON format. The server receives this data and stores the question and answer pairs in its database. In this storage process, the server registers the question and answer as new records in the database.

[0038] Data retrieval from the server and display on the terminal.

[0039] When a user selects learning mode within the application, the device requests stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format. The device displays the received data on the screen. The user can then repeatedly study the retrieved question-and-answer data on the screen.

[0040] Specific example

[0041] For example, if a user wants to memorize element symbols for a chemistry exam, they would use the system as follows: The user launches the app and voice-inputs the question, "What is the element symbol for carbon?" and then voice-inputs the answer, "C". This voice data is converted to text on the device, sent to the server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will appear on the screen, with "C" displayed as the answer. The user can repeat this process multiple times to learn.

[0042] This system allows users to efficiently create question-and-answer formatted data through the natural operation of voice input, enabling them to effectively memorize information.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user launches the application. The user presses the "Enter Question" button within the application and enters a question by voice. For example, they might say, "What is the tallest mountain in the world?"

[0046] Step 2:

[0047] The device acquires audio data through its microphone. This audio data is converted into text in real time by the device's speech recognition engine (for example, Google® Speech Recognition API). The audio data is converted into the text "What is the tallest mountain in the world?".

[0048] Step 3:

[0049] The user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." The device then acquires this voice data through the microphone.

[0050] Step 4:

[0051] The device then uses its speech recognition engine again to convert the audio response into text. This audio data is then converted into the text "Everest".

[0052] Step 5:

[0053] The terminal packages the converted question and answer text data into JSON format and generates an HTTP POST request to send it to the server. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}

[0054] Step 6:

[0055] The server receives an HTTP POST request and parses the sent data. The server extracts the question and answer text data from the JSON.

[0056] Step 7:

[0057] The server connects to the database and inserts the extracted question and answer as new records. Example: INSERT INTO qa_table (question, answer) VALUES ('What is the tallest mountain in the world?', 'Mount Everest')

[0058] Step 8:

[0059] The user selects the application's learning mode. The user presses the "Start Learning Mode" button.

[0060] Step 9:

[0061] The device sends an HTTP GET request to the server to retrieve training data. Example: / get_all_qa

[0062] Step 10:

[0063] The server receives an HTTP GET request and retrieves all question-answer pairs from the database. The server then converts this data into JSON format. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}, ...]

[0064] Step 11:

[0065] The server returns the generated JSON data to the terminal as an HTTP response. The terminal parses the received JSON data and extracts question-and-answer pairs.

[0066] Step 12:

[0067] The device displays extracted question-and-answer pairs on the screen. Users can learn by repeatedly reviewing the displayed questions and answers. Example: "What is the tallest mountain in the world?" -> "Mount Everest"

[0068] (Example 1)

[0069] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0070] Currently, many systems exist to help students and working professionals efficiently memorize knowledge needed for exams and work, but they are often complex to operate or depend on specific methods, making it difficult to learn efficiently in a question-and-answer format. Furthermore, the manual input of text can be time-consuming, hindering continuous learning. Therefore, there is a need for a system that utilizes voice input to easily create user-specific question-and-answer data, enabling efficient learning.

[0071] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0072] In this invention, the server includes a voice input means, a means for converting voice to text, a means for transmitting the converted text data to the server, a means for storing the text data on the server, a means for retrieving the stored text data from the server, a means for displaying the retrieved text data, and a means for saving and displaying questions and answers entered by the user via voice in a question-and-answer format. This enables the user to efficiently create question-and-answer format data using voice in a natural manner and to repeatedly learn from that data.

[0073] "Voice input means" refers to a device or function for a user to input voice. Specifically, it includes a microphone and the software that controls it.

[0074] "Means for converting speech to text" refers to a device or function that converts captured speech data into text data using natural language processing techniques. Specifically, it refers to a speech recognition engine.

[0075] "Means for sending converted text data to a server" refers to a device or function for sending text data to a server over a network. Specifically, it refers to a communication method that uses HTTP requests.

[0076] "Means of saving text data on a server" refers to a device or function for saving received text data to a storage device within the server. Specifically, it refers to a database system.

[0077] "Means for retrieving text data stored on a server" refers to a device or function for retrieving text data stored on a server in response to a request. Specifically, it refers to a database query system.

[0078] "Means for displaying acquired text data" refers to a device or function for visually displaying acquired text data to the user. Specifically, it refers to a display and the software that controls it.

[0079] "Means for saving and displaying user-inputted questions and answers in a question-and-answer format" refers to a device or function that saves user-inputted questions and answers as pairs and displays them to the user. Specifically, it refers to a database and a user interface.

[0080] This invention is a question-and-answer format learning system that uses voice input to enable students and working professionals to efficiently memorize knowledge necessary for exams and work. Users input questions and answers using their own voice, and by saving and displaying this as text data, efficient learning becomes possible.

[0081] The user launches the application on their device (such as a smartphone or tablet). The application displays a "Question Input" button and an "Answer Input" button on the initial screen. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text data using speech recognition technology such as the Google Cloud Speech-to-Text API. Next, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice response is also converted into text data using the same method.

[0082] The converted question and answer text data is sent from the terminal to the server. Specifically, the data is sent to the server in JSON format using an HTTP POST request. The server (such as a Node.js server deployed on AWS® EC2) receives this data and stores it in a database (such as Amazon RDS). The server registers the new question and answer pair as a record in the database.

[0083] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server. The server retrieves all question-and-answer pairs stored in the database and returns them to the device in JSON format. The device displays the retrieved data on the screen. The user can then repeatedly learn from this question-and-answer data.

[0084] For example, if a user wants to memorize element symbols for a chemistry exam, they might voice-input the question, "What is the element symbol for carbon?" and answer "C" aloud. This voice data is converted to text, sent to a server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will be displayed, with "C" as the answer. The user can then repeat this process to continue learning.

[0085] This system allows for the efficient creation of question-and-answer formatted data through natural operation, thereby supporting effective learning.

[0086] Example of a prompt

[0087] The following are examples of prompts to input into the generating AI model for this system.

[0088] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[0089] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0090] Step 1:

[0091] The user launches the application on their smartphone or tablet. The application displays "Enter Question" and "Enter Answer" buttons on the initial screen, prompting the user to take action.

[0092] Input: User tap operation

[0093] Output: Initial screen display

[0094] Specific operation: When the user taps to open the app, two buttons will appear: "Enter Question" and "Enter Answer".

[0095] Step 2:

[0096] The user presses the "Enter Question" button and speaks their question into the microphone. The device captures this audio and converts the audio data into text using speech recognition technology such as the Google Cloud Speech-to-Text API.

[0097] Input: Audio data (for example, "What is the tallest mountain in the world?")

[0098] Output: Text data ("What is the tallest mountain in the world?")

[0099] Specific operation: When the user presses the "Enter Question" button and speaks "What is the tallest mountain in the world?", the device converts the speech into text and generates the text "What is the tallest mountain in the world?".

[0100] Step 3:

[0101] The user presses the "Enter Answer" button and speaks their answer into the microphone. The device captures this audio and uses the same speech recognition technology to convert the audio data into text data.

[0102] Input: Audio data (e.g., "Everest")

[0103] Output: Text data ("Everest")

[0104] Specific operation: When the user presses the "Enter Answer" button and speaks "Everest," the device converts the speech into text and generates the text "Everest."

[0105] Step 4:

[0106] The terminal formats the converted question and answer text data into JSON format and sends it to the server using an HTTP POST request.

[0107] Input: Text data of a question and answer ("What is the tallest mountain in the world?", "Mount Everest")

[0108] Output: JSON data sent to the server

[0109] Specific operation: The terminal creates data in JSON format and sends it to the server using an HTTP POST request.

[0110] Step 5:

[0111] The server receives an HTTP POST request and saves the received data to the database. The server parses the JSON data and registers the question-and-answer pairs as new records in the database.

[0112] Input: JSON data sent to the server

[0113] Output: Question and answer pairs stored in the database

[0114] Specific operation: The server receives an HTTP POST request, parses the data, and saves it to the database.

[0115] Step 6:

[0116] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server.

[0117] Input: Select learning mode

[0118] Output: Data request to the server

[0119] Specific operation: When the user selects learning mode, the device requests data from the server.

[0120] Step 7:

[0121] The server retrieves all question-and-answer pairs stored in the database and returns them to the terminal in JSON format.

[0122] Input: Question and answer data request

[0123] Output: JSON data returned to the terminal

[0124] Specific operation: The server retrieves data from the database and sends it to the terminal in JSON format.

[0125] Step 8:

[0126] The device displays the received data on its screen. Users can repeatedly learn from this question-and-answer data.

[0127] Input: JSON data returned from the server

[0128] Output: Pairs of questions and answers displayed on the screen

[0129] Specific operation: The device displays question and answer pairs it has acquired on the screen, and the user learns by looking at them.

[0130] Example of a prompt

[0131] The following are examples of prompts to input into the generating AI model for this system.

[0132] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[0133] (Application Example 1)

[0134] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0135] Traditional factory training and feedback systems have made it difficult to efficiently learn work procedures. Furthermore, the lack of real-time evaluation and feedback creates an environment prone to human error. Therefore, there is a need for a system that improves worker learning efficiency and work accuracy.

[0136] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0137] In this invention, the server includes a feedback means for efficiently learning factory work procedures, a means for performing real-time evaluations using a generative AI model, and a means for displaying acquired text data. This enables workers to learn procedures through voice input and receive appropriate feedback in real time.

[0138] "Voice input means" refers to a device or system that has the function of capturing voice data and converting it into an appropriate format.

[0139] "Methods for converting speech to text" refer to technologies that automatically analyze input speech data and convert it into a corresponding text format.

[0140] "Means of sending text data to a server" refers to the technology of transferring converted text data to a server via a network.

[0141] "Methods for saving text data on a server" refers to technologies that store received text data in a database or storage device, making it accessible for retrieval as needed.

[0142] "Methods for retrieving text data from a server" refers to technologies that retrieve stored text data from a server in response to requests.

[0143] "Means for displaying acquired text data" refers to a system that visually displays the extracted text data through a user interface.

[0144] A "feedback system for efficiently learning factory work procedures" is a system that provides real-time evaluation and appropriate advice and instructions to help workers learn the correct procedures.

[0145] "A method for performing real-time evaluation using a generative AI model" refers to a technology that uses an artificial intelligence model to evaluate the accuracy and progress of work in real time and provide immediate feedback.

[0146] The present invention is a system for efficiently learning factory work procedures and providing real-time feedback. This system includes a voice input means, a means for converting voice to text, a means for sending text data to a server, a means for storing text data on the server, a means for retrieving text data from the server, a means for displaying the retrieved text data, a feedback means for efficiently learning factory work procedures, and a means for performing real-time evaluation using a generative AI model.

[0147] Voice input method

[0148] Users input questions and answers by voice using the microphone on their smartphone or tablet while working in the factory. This eliminates the need for traditional handwriting or keyboard input, thus improving work efficiency.

[0149] Means of converting speech to text

[0150] The audio data captured by the voice input method is converted to text using the Python SpeechRecognition library. This method uses a reliable speech recognition engine, such as Google's speech recognition service.

[0151] Means of sending text data to a server

[0152] The data, converted to text, is sent to the server via an HTTP POST request. The request packages the data in JSON format and transfers it to the server over the internet.

[0153] Means for saving text data on a server

[0154] The server stores the received text data in a database. The database contains question-and-answer pairs, allowing for quick retrieval as needed. SQL-based databases are commonly used.

[0155] Means for retrieving text data from a server

[0156] When the user selects learning mode, a request for question-and-answer data stored on the server is sent to the device. The server returns all question-and-answer pairs in JSON format and sends them to the device.

[0157] Means for displaying acquired text data

[0158] The terminal displays the received text data on the user interface. This allows users to learn factory work procedures while visually confirming them.

[0159] A feedback mechanism for efficiently learning factory work procedures.

[0160] Data from factory operations is acquired in real time and evaluated based on accuracy and procedure using a generated AI model. This allows users to receive feedback on the spot and correct their work immediately.

[0161] A method for performing real-time evaluation using generative AI models.

[0162] The generative AI model evaluates work data under various conditions and notifies the user of the results in real time. This model utilizes pre-trained artificial intelligence algorithms and, as a specific example, evaluates whether "assembly is being performed correctly according to the work procedure."

[0163] Specific example

[0164] For example, when a user is learning the steps for a new assembly task, they might voice-input a question like, "In what order should I assemble the following parts?" and receive the response, "Part A, first." This data is converted to text in real time, sent to a server, and stored. Then, when the user selects learning mode, this data is displayed on the device.

[0165] Example of a prompt

[0166] 1. "How can we develop a system that uses voice input for learning work procedures?"

[0167] 2. "How can we use speech recognition to collect questions and answers and provide real-time feedback?"

[0168] As a result, this invention enables factory workers to efficiently learn procedures and receive appropriate feedback in real time.

[0169] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0170] Step 1:

[0171] The user launches an application on their smartphone or tablet and uses voice input. Specifically, they voice-input a question such as, "In what order should I assemble the following parts?" and an answer such as, "Part A, first." This voice data is captured through the microphone on the smartphone or tablet.

[0172] Input: Audio data

[0173] Output: Audio data

[0174] Step 2:

[0175] The device converts the captured audio data into text data using the Python SpeechRecognition library. This audio data is then processed through Google's speech recognition service.

[0176] Input: Audio data

[0177] Output: Text data (Example: "In what order should the following parts be assembled?", "Part A, first")

[0178] Step 3:

[0179] The terminal packages the converted text data into JSON format and sends it to the server using an HTTP POST request.

[0180] Input: Text data

[0181] Output: Text data in JSON format

[0182] Step 4:

[0183] The server saves the received JSON-formatted text data to a database. Each question and answer is recorded in the database as a pair, making it easy to retrieve later.

[0184] Input: Text data in JSON format

[0185] Output: Text data stored in the database

[0186] Step 5:

[0187] When the user selects learning mode, the device requests the stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format.

[0188] Input: Request for learning mode

[0189] Output: Question and answer data in JSON format

[0190] Step 6:

[0191] The terminal displays the received question-and-answer data through the user interface. The user visually reviews this data and learns the work procedures.

[0192] Input: Question and answer data in JSON format

[0193] Output: Displayed question-and-answer data

[0194] Step 7:

[0195] During factory work, user actions are evaluated in real time using a generative AI model. The generative AI model assesses the accuracy of the work and sends the results to the terminal.

[0196] Input: User operation data

[0197] Output: Real-time feedback results

[0198] Step 8:

[0199] The device provides feedback to the user based on the evaluation results received from the generated AI model. This allows the user to immediately verify whether their work is correct and make corrections as needed.

[0200] Input: Real-time feedback results

[0201] Output: User feedback

[0202] In this way, the system efficiently learns factory work procedures, performs real-time evaluations, and provides appropriate feedback.

[0203] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0204] This invention is a system designed to help students and working professionals efficiently memorize information needed for exams and work. It utilizes voice input to create personalized question-and-answer format data, and further incorporates an emotion engine to support learning while recognizing the user's emotional state.

[0205] User voice input and terminal processing

[0206] The user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by the speech recognition engine. Simultaneously, the emotion engine analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[0207] Next, the user presses the "Enter Answer" button and enters their answer by voice. This voice data is also acquired by the device and converted into text by the speech recognition engine. In addition, the emotion engine re-analyzes the user's emotions at the time of the answer.

[0208] Sending and storing text data and sentiment data.

[0209] The terminal packages the converted question and answer text data, along with the analyzed sentiment data, into JSON format and sends it to the server. Specifically, it sends data like the following using an HTTP POST request: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "emotions": {"question": "relaxed", "answer": "confident"}}

[0210] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident')

[0211] Data acquisition and display in learning mode

[0212] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format.

[0213] The device displays the received data on its screen. Users can then review the displayed questions and answers, and further assess their own emotional state. This allows users to adjust their learning methods according to their emotional state.

[0214] Specific example

[0215] Consider a scenario where a user wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" They then voice-input "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that they appear "calm" when asking the question and "confident" when answering.

[0216] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[0217] This system allows users to efficiently create question-and-answer formatted data using voice input, and also enables them to learn while understanding their own emotional state with the help of an emotion engine.

[0218] The following describes the processing flow.

[0219] Step 1:

[0220] The user launches the application. The user presses the "Enter Question" button in the application and enters the question by voice. For example, they might say, "What is the tallest mountain in the world?"

[0221] Step 2:

[0222] The device acquires voice data through its microphone. The acquired voice data is converted into text by the device's speech recognition engine. The text is recognized as "What is the tallest mountain in the world?".

[0223] Step 3:

[0224] The user presses the "Enter Answer" button and speaks the answer "Everest" aloud.

[0225] Step 4:

[0226] The device acquires the voice data of the response and converts it into text, "Everest," using a speech recognition engine. Simultaneously, an emotion engine analyzes the user's voice to analyze emotional data, for example, recognizing "confident."

[0227] Step 5:

[0228] The device packages the question and answer, along with the analyzed sentiment data, into JSON format. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}

[0229] Step 6:

[0230] The device sends JSON data to the server as an HTTP POST request. This request includes a question, an answer, and corresponding sentiment data.

[0231] Step 7:

[0232] The server receives an HTTP POST request and parses the JSON data. From the parsed data, it extracts question, answer, and sentiment data.

[0233] Step 8:

[0234] The server connects to the database and saves the extracted question, answer, and sentiment data as new records. Example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Mount Everest', 'calm', 'confident')

[0235] Step 9:

[0236] The user selects learning mode. The user presses the "Start Anti-Mode" button.

[0237] Step 10:

[0238] The device sends an HTTP GET request to the server to request the data necessary for learning. Example: / get_all_qa

[0239] Step 11:

[0240] The server receives an HTTP GET request and retrieves all question-and-answer pairs, along with their corresponding sentiment data, from the database. The retrieved data is then converted to JSON format.

[0241] Step 12:

[0242] The server returns JSON data to the terminal as an HTTP response. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}, ...]

[0243] Step 13:

[0244] The terminal receives a response from the server and parses the JSON data. It extracts the question and answer, as well as sentiment data, and displays it on the screen.

[0245] Step 14:

[0246] Users learn through repetition by viewing the displayed questions and answers, as well as sentiment data. For example, in addition to the question "What is the tallest mountain in the world?" and the answer "Mount Everest," sentiment data such as "When asked: calm" and "When answering: confident" is displayed. Based on this information, users can understand and optimize their learning progress.

[0247] (Example 2)

[0248] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0249] Conventional memorization systems not only struggled with voice input, but also lacked the means to understand the user's emotional state and enhance learning effectiveness. This made it difficult to adjust the learning process appropriately, resulting in challenges in efficient memorization.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0251] In this invention, the server includes means for converting speech to text, means for analyzing emotional data from the speech, and means for transmitting the converted text data and the analyzed emotional data to the server. This allows the user to efficiently perform voice input and to progress with learning while understanding their own emotional state.

[0252] "Voice input means" refers to a method for users to input questions and answers by voice, and involves using input devices such as microphones.

[0253] "Means for converting speech to text" refers to methods for converting acquired speech data into text data, and utilizes speech recognition technology.

[0254] "Methods for analyzing emotional data from voice" refer to methods for analyzing a user's emotional state from voice data, and utilize technologies that analyze acoustic characteristics such as tone, pitch, and speed.

[0255] "Means for sending converted text data and analyzed sentiment data to a server" refers to means for packaging and sending data to a server after audio data has been converted to text data and sentiment data has been analyzed.

[0256] "Means of storing text data and sentiment data on a server" refers to means of storing received text data and sentiment data in a database or similar system for proper preservation.

[0257] "Means for retrieving text data and sentiment data from a server" refers to the means of retrieving stored text data and sentiment data from a server and sending them back to the terminal.

[0258] "Means for displaying acquired text data and sentiment data" refers to means for displaying text data and sentiment data acquired by the user on their device so that they can visually confirm them.

[0259] This invention is a system that efficiently creates question-and-answer format data using voice input and further supports learning while recognizing the user's emotional state. This system includes voice input means, a voice recognition engine, emotion analysis means, data transmission means, data storage means, data acquisition means, and data display means.

[0260] First, the user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted to text by a speech recognition engine such as the Google Speech-to-Text API. Simultaneously, using an emotion engine such as the Affectiva SDK, the device analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[0261] Next, the user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." This voice data is also captured by the device's microphone and converted into text by the speech recognition engine. The emotion engine also analyzes the user's emotional state at the time of the answer. The results of this analysis are obtained in the same way as when the question was asked.

[0262] These converted text data (questions and answers) and analyzed sentiment data are packaged in JSON format by the terminal and sent to the server using an HTTP POST request. For example, the following data is sent:

[0263] json

[0264] {

[0265] "Question": "What is the tallest mountain in the world?"

[0266] "answer": "Everest",

[0267] "emotions": {

[0268] "question": "relaxed",

[0269] "answer": "confident"

[0270] }

[0271] }

[0272] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example, it executes the following SQL query:

[0273] SQL

[0274] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[0275] When a user selects a learning mode, the device sends an HTTP GET request to the server, requesting stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format. The device displays the received data on the screen. The user can check their own sentiment state while viewing the displayed questions and answers. This allows the user to adjust the learning method according to their sentiment state.

[0276] As a concrete example, consider a user who wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" Then, voice-inputs the answer, "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that the user is "calm" when asking the question and "confident" when answering.

[0277] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[0278] It is also possible to analyze the user's voice data by utilizing a generative AI model. For example, by inputting the following prompt sentences, the generative AI model can be made to input the data creation procedure in a natural conversation format, thereby supporting the effective operation of the system:

[0279] Please ask the question "What is the capital of France?" in voice. Then, please answer "Paris" in voice. At this time, ask the question in a relaxed manner and answer with confidence.

[0280] With this system, the user can not only efficiently create question-and-answer format data using voice input, but also learn while understanding their own emotional state with the help of the emotion engine.

[0281] The flow of the specific process in Example 2 will be described using FIG. 13.

[0282] Step 1:

[0283] The user launches the application and presses the "Question Input" button to input a question in voice.

[0284] Input: User's voice question (e.g., "What is the highest mountain in the world?")

[0285] Action: The terminal uses the microphone to acquire voice data.

[0286] Step 2:

[0287] The terminal uses a voice recognition engine (e.g., Google Speech-to-Text API) to convert the voice data into text data.

[0288] Input: Voice data

[0289] Operation: The speech recognition engine analyzes the audio data and converts it into corresponding text data (e.g., "What is the tallest mountain in the world?").

[0290] Output: Text data (Example: "What is the tallest mountain in the world?")

[0291] Step 3:

[0292] The device uses an emotion engine (e.g., Affectiva SDK) to analyze emotion data from the user's voice.

[0293] Input: Audio data

[0294] Operation: The emotion engine analyzes acoustic features such as tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "calm").

[0295] Output: Emotional data (e.g., "calmness")

[0296] Step 4:

[0297] The user presses the "Enter Answer" button and enters their answer by voice.

[0298] Input: User's voice response (e.g., "Everest")

[0299] Operation: The device uses the microphone to acquire audio data.

[0300] Step 5:

[0301] The device then uses the speech recognition engine again to convert the speech data into text data.

[0302] Input: Audio data

[0303] Operation: The speech recognition engine analyzes the audio data and converts it into the corresponding text data (e.g., "Everest").

[0304] Output: Text data (e.g., "Mount Everest")

[0305] Step 6:

[0306] The terminal uses the emotion engine again to analyze the emotion data from the user's voice.

[0307] Input: Voice data

[0308] Operation: The emotion engine analyzes acoustic features such as the tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "confidence").

[0309] Output: Emotion data (e.g., "confidence")

[0310] Step 7:

[0311] The terminal packages the converted question and answer text data and the analyzed emotion data in JSON format.

[0312] Input: Question and answer text data, emotion data

[0313] Operation: Convert the data into JSON format and create a package as follows.

[0314] json

[0315] {

[0316] "question": "What is the highest mountain in the world?",

[0317] "answer": "Mount Everest",

[0318] "emotions": {

[0319] "question": "relaxed",

[0320] "answer": "confident"

[0321] }

[0322] }

[0323] Output: JSON package

[0324] Step 8:

[0325] The terminal uses an HTTP POST request to send the JSON package to the server.

[0326] Input: JSON package

[0327] Operation: Creates an HTTP POST request and sends data to the server.

[0328] Output: Data received on the server side.

[0329] Step 9:

[0330] The server parses the received JSON package and extracts question, answer, and sentiment data.

[0331] Input: JSON package

[0332] Operation: Parses JSON data and extracts the necessary data fields.

[0333] Output: Question, answer, sentiment data

[0334] Step 10:

[0335] The server connects to the database and stores the question, answer, and sentiment data as new records.

[0336] Input: Question, answer, sentiment data

[0337] Operation: Establish a database connection and execute an SQL query like the following.

[0338] SQL

[0339] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[0340] Output: A new record is stored in the database.

[0341] Step 11:

[0342] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the saved question-and-answer data and sentiment data.

[0343] Input: Learning mode selection operation

[0344] Action: Creates an HTTP GET request and sends it to the server.

[0345] Output: The server receives the request.

[0346] Step 12:

[0347] The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the terminal in JSON format.

[0348] Input: Database Request

[0349] Operation: Executes a database query and converts the retrieved data into JSON format.

[0350] Output: Data in JSON format

[0351] Step 13:

[0352] The device parses the received JSON data and displays the question, answer, and sentiment data on the screen.

[0353] Input: Data in JSON format

[0354] Function: Parses JSON data and converts it into a format for visual display.

[0355] Output: Questions, answers, and sentiment data displayed on the screen.

[0356] (Application Example 2)

[0357] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0358] There is a need for support methods to help factory workers efficiently and reliably memorize the operation and maintenance procedures of new machinery. While current systems allow for the creation of question-and-answer formatted data via voice input, they fail to consider the emotional state of the workers. This makes it difficult to provide optimal learning methods tailored to each worker's learning progress and emotions, potentially leading to decreased learning efficiency.

[0359] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing text data and emotion data, means for acquiring text data and emotion data, and means for displaying the acquired text data and emotion data. This makes it possible not only to create data in a question-and-answer format using voice input, but also to analyze the emotional state of engineers and provide an optimal learning method according to their emotions.

[0360] "Voice input means" refers to an apparatus that includes a device for acquiring the user's voice and software for processing that voice data.

[0361] A "speech recognition engine" is software that analyzes acquired audio data and converts it into text data.

[0362] An "emotion engine" is software that analyzes a user's emotions from voice data and acquires them as emotion data.

[0363] "Text data" refers to character information generated from speech by a speech recognition engine.

[0364] "Emotional data" refers to information about a user's emotional state, analyzed by an emotion engine.

[0365] A "server" is a central computer that stores text data and sentiment data, and transmits this data to user terminals as needed.

[0366] An "HTTP request" is a communication protocol used to send and receive data between a client and a server.

[0367] "Acquisition means" refers to the methods and devices used to obtain necessary data from a server.

[0368] "Display means" refers to a device or software for visually displaying text data and sentiment data on a user's terminal.

[0369] "Question and answer format" refers to a data format where a question and an answer are presented as a pair.

[0370] Modes for carrying out the invention

[0371] This invention provides a support system for engineers to memorize the operation and maintenance procedures of new machinery. This system is implemented using voice input means, a speech recognition engine, an emotion engine, a server, and HTTP requests.

[0372] Voice input and processing

[0373] The user inputs questions and answers using voice input. At this time, the speech recognition engine converts the voice data into text data, and the emotion engine analyzes the user's emotional state to obtain emotion data.

[0374] Sending and storing data

[0375] The device sends the acquired text data and sentiment data to the server via an HTTP request. The server stores the received data in a database. Specifically, it packages the text data and sentiment data into JSON format and sends it to the server via a POST request.

[0376] Data acquisition and display

[0377] The server retrieves stored text and sentiment data in response to HTTP GET requests from the user. This data is sent to the device, which displays the retrieved data on its screen. Based on the displayed data, the user learns and adjusts their learning method based on the information about their sentiment state.

[0378] Examples of specific cases and prompt statements

[0379] For example, a technician learning how to operate a new machine might voice-input a question like, "Where is the start button on this machine?" and then voice-input the answer, "Bottom left of the right panel." This voice data is converted into text data, and emotional data such as "anxiety" during the question and "confirmation" during the answer is analyzed. This data is stored on a server and can later be reviewed by the user in learning mode.

[0380] The following are examples of prompt messages.

[0381] "I'm designing a question-and-answer style learning application for engineers to memorize how to operate new machinery. Users input questions and answers via voice, and sentiment data analyzed by an emotion engine is also saved. When the user enters learning mode, the questions, answers, and sentiment data are displayed. Please generate the program for this application."

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] The user inputs their question by voice using a voice input device. The terminal acquires this voice data and converts it into text data using a speech recognition engine. At the same time, an emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[0385] Step 2:

[0386] The user then uses a voice input device to enter their response by voice. The terminal acquires this voice data and uses a speech recognition engine to convert it into text data. Similarly, the emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[0387] Step 3:

[0388] The terminal packages the converted text data and analyzed sentiment data into JSON format and sends this data to the server using an HTTP POST request. The input is text data and sentiment data, and the output is an HTTP request to the server.

[0389] Step 4:

[0390] The server receives an HTTP POST request, parses the JSON data, and extracts the question, answer, and their respective sentiment data. This data is then stored in a database. The input is JSON data, and the output is the data stored in the database.

[0391] Step 5:

[0392] When the user selects learning mode, the device sends an HTTP GET request to the server to retrieve stored question-and-answer formatted text data and sentiment data. The input is the HTTP GET request, and the output is the data retrieval request to the server.

[0393] Step 6:

[0394] The server retrieves text and sentiment data stored in the database and sends them back to the terminal in JSON format. The input is a request to read data from the database, and the output is the return of the retrieved data in JSON format.

[0395] Step 7:

[0396] The device parses the received JSON data and displays question-and-answer pairs and corresponding sentiment data on the screen. The user learns from this and adjusts the learning method based on their own sentiment state. The input is JSON data, and the output is the text data and sentiment data displayed on the screen.

[0397] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0398] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0400] [Second Embodiment]

[0401] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0402] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0403] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0404] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0405] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0406] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0407] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0408] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0409] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0410] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0411] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0412] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0413] This invention is a system for students and working professionals to efficiently memorize knowledge necessary for exams and work, and supports learning by creating personalized question-and-answer format data using voice input.

[0414] User voice input and terminal processing

[0415] First, the user launches the application. The application screen displays a "Question Input" button and an "Answer Input" button. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by a speech recognition engine. Then, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice answer is also converted into text by the device.

[0416] Sending text data and storing it on the server

[0417] The terminal sends the converted question and answer text data to the server. Specifically, it uses an HTTP POST request to send the question and answer text data to the server in JSON format. The server receives this data and stores the question and answer pairs in its database. In this storage process, the server registers the question and answer as new records in the database.

[0418] Data retrieval from the server and display on the terminal.

[0419] When a user selects learning mode within the application, the device requests stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format. The device displays the received data on the screen. The user can then repeatedly study the retrieved question-and-answer data on the screen.

[0420] Specific example

[0421] For example, if a user wants to memorize element symbols for a chemistry exam, they would use the system as follows: The user launches the app and voice-inputs the question, "What is the element symbol for carbon?" and then voice-inputs the answer, "C". This voice data is converted to text on the device, sent to the server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will appear on the screen, with "C" displayed as the answer. The user can repeat this process multiple times to learn.

[0422] This system allows users to efficiently create question-and-answer formatted data through the natural operation of voice input, enabling them to effectively memorize information.

[0423] The following describes the processing flow.

[0424] Step 1:

[0425] The user launches the application. The user presses the "Enter Question" button within the application and enters a question by voice. For example, they might say, "What is the tallest mountain in the world?"

[0426] Step 2:

[0427] The device acquires audio data through its microphone. This audio data is converted to text in real time by the device's speech recognition engine (for example, Google Speech Recognition API). The audio data is converted to the text "What is the tallest mountain in the world?".

[0428] Step 3:

[0429] The user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." The device then acquires this voice data through the microphone.

[0430] Step 4:

[0431] The device then uses its speech recognition engine again to convert the audio response into text. This audio data is then converted into the text "Everest".

[0432] Step 5:

[0433] The terminal packages the converted question and answer text data into JSON format and generates an HTTP POST request to send it to the server. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}

[0434] Step 6:

[0435] The server receives an HTTP POST request and parses the sent data. The server extracts the question and answer text data from the JSON.

[0436] Step 7:

[0437] The server connects to the database and inserts the extracted question and answer as new records. Example: INSERT INTO qa_table (question, answer) VALUES ('What is the tallest mountain in the world?', 'Mount Everest')

[0438] Step 8:

[0439] The user selects the application's learning mode. The user presses the "Start Learning Mode" button.

[0440] Step 9:

[0441] The device sends an HTTP GET request to the server to retrieve training data. Example: / get_all_qa

[0442] Step 10:

[0443] The server receives an HTTP GET request and retrieves all question-answer pairs from the database. The server then converts this data into JSON format. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}, ...]

[0444] Step 11:

[0445] The server returns the generated JSON data to the terminal as an HTTP response. The terminal parses the received JSON data and extracts question-and-answer pairs.

[0446] Step 12:

[0447] The device displays extracted question-and-answer pairs on the screen. Users can learn by repeatedly reviewing the displayed questions and answers. Example: "What is the tallest mountain in the world?" -> "Mount Everest"

[0448] (Example 1)

[0449] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0450] Currently, many systems exist to help students and working professionals efficiently memorize knowledge needed for exams and work, but they are often complex to operate or depend on specific methods, making it difficult to learn efficiently in a question-and-answer format. Furthermore, the manual input of text can be time-consuming, hindering continuous learning. Therefore, there is a need for a system that utilizes voice input to easily create user-specific question-and-answer data, enabling efficient learning.

[0451] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0452] In this invention, the server includes a voice input means, a means for converting voice to text, a means for transmitting the converted text data to the server, a means for storing the text data on the server, a means for retrieving the stored text data from the server, a means for displaying the retrieved text data, and a means for saving and displaying questions and answers entered by the user via voice in a question-and-answer format. This enables the user to efficiently create question-and-answer format data using voice in a natural manner and to repeatedly learn from that data.

[0453] "Voice input means" refers to a device or function for a user to input voice. Specifically, it includes a microphone and the software that controls it.

[0454] "Means for converting speech to text" refers to a device or function that converts captured speech data into text data using natural language processing techniques. Specifically, it refers to a speech recognition engine.

[0455] "Means for sending converted text data to a server" refers to a device or function for sending text data to a server over a network. Specifically, it refers to a communication method that uses HTTP requests.

[0456] "Means of saving text data on a server" refers to a device or function for saving received text data to a storage device within the server. Specifically, it refers to a database system.

[0457] "Means for retrieving text data stored on a server" refers to a device or function for retrieving text data stored on a server in response to a request. Specifically, it refers to a database query system.

[0458] "Means for displaying acquired text data" refers to a device or function for visually displaying acquired text data to the user. Specifically, it refers to a display and the software that controls it.

[0459] "Means for saving and displaying user-inputted questions and answers in a question-and-answer format" refers to a device or function that saves user-inputted questions and answers as pairs and displays them to the user. Specifically, it refers to a database and a user interface.

[0460] This invention is a question-and-answer format learning system that uses voice input to enable students and working professionals to efficiently memorize knowledge necessary for exams and work. Users input questions and answers using their own voice, and by saving and displaying this as text data, efficient learning becomes possible.

[0461] The user launches the application on their device (such as a smartphone or tablet). The application displays a "Question Input" button and an "Answer Input" button on the initial screen. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text data using speech recognition technology such as the Google Cloud Speech-to-Text API. Next, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice response is also converted into text data using the same method.

[0462] The converted question and answer text data is sent from the terminal to the server. Specifically, the data is sent to the server in JSON format using an HTTP POST request. The server (such as a Node.js server deployed on AWS EC2) receives this data and stores it in a database (such as Amazon RDS). The server registers the new question and answer pair as a record in the database.

[0463] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server. The server retrieves all question-and-answer pairs stored in the database and returns them to the device in JSON format. The device displays the retrieved data on the screen. The user can then repeatedly learn from this question-and-answer data.

[0464] For example, if a user wants to memorize element symbols for a chemistry exam, they might voice-input the question, "What is the element symbol for carbon?" and answer "C" aloud. This voice data is converted to text, sent to a server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will be displayed, with "C" as the answer. The user can then repeat this process to continue learning.

[0465] This system allows for the efficient creation of question-and-answer formatted data through natural operation, thereby supporting effective learning.

[0466] Example of a prompt

[0467] The following are examples of prompts to input into the generating AI model for this system.

[0468] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1:

[0471] The user launches the application on their smartphone or tablet. The application displays "Enter Question" and "Enter Answer" buttons on the initial screen, prompting the user to take action.

[0472] Input: User tap operation

[0473] Output: Initial screen display

[0474] Specific operation: When the user taps to open the app, two buttons will appear: "Enter Question" and "Enter Answer".

[0475] Step 2:

[0476] The user presses the "Enter Question" button and speaks their question into the microphone. The device captures this audio and converts the audio data into text using speech recognition technology such as the Google Cloud Speech-to-Text API.

[0477] Input: Audio data (for example, "What is the tallest mountain in the world?")

[0478] Output: Text data ("What is the tallest mountain in the world?")

[0479] Specific operation: When the user presses the "Enter Question" button and speaks "What is the tallest mountain in the world?", the device converts the speech into text and generates the text "What is the tallest mountain in the world?".

[0480] Step 3:

[0481] The user presses the "Enter Answer" button and speaks their answer into the microphone. The device captures this audio and uses the same speech recognition technology to convert the audio data into text data.

[0482] Input: Audio data (e.g., "Everest")

[0483] Output: Text data ("Everest")

[0484] Specific operation: When the user presses the "Enter Answer" button and speaks "Everest," the device converts the speech into text and generates the text "Everest."

[0485] Step 4:

[0486] The terminal formats the converted question and answer text data into JSON format and sends it to the server using an HTTP POST request.

[0487] Input: Text data of a question and answer ("What is the tallest mountain in the world?", "Mount Everest")

[0488] Output: JSON data sent to the server

[0489] Specific operation: The terminal creates data in JSON format and sends it to the server using an HTTP POST request.

[0490] Step 5:

[0491] The server receives an HTTP POST request and saves the received data to the database. The server parses the JSON data and registers the question-and-answer pairs as new records in the database.

[0492] Input: JSON data sent to the server

[0493] Output: Question and answer pairs stored in the database

[0494] Specific operation: The server receives an HTTP POST request, parses the data, and saves it to the database.

[0495] Step 6:

[0496] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server.

[0497] Input: Select learning mode

[0498] Output: Data request to the server

[0499] Specific operation: When the user selects learning mode, the device requests data from the server.

[0500] Step 7:

[0501] The server retrieves all question-and-answer pairs stored in the database and returns them to the terminal in JSON format.

[0502] Input: Question and answer data request

[0503] Output: JSON data returned to the terminal

[0504] Specific operation: The server retrieves data from the database and sends it to the terminal in JSON format.

[0505] Step 8:

[0506] The device displays the received data on its screen. Users can repeatedly learn from this question-and-answer data.

[0507] Input: JSON data returned from the server

[0508] Output: Pairs of questions and answers displayed on the screen

[0509] Specific operation: The device displays question and answer pairs it has acquired on the screen, and the user learns by looking at them.

[0510] Example of a prompt

[0511] The following are examples of prompts to input into the generating AI model for this system.

[0512] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[0513] (Application Example 1)

[0514] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0515] Traditional factory training and feedback systems have made it difficult to efficiently learn work procedures. Furthermore, the lack of real-time evaluation and feedback creates an environment prone to human error. Therefore, there is a need for a system that improves worker learning efficiency and work accuracy.

[0516] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0517] In this invention, the server includes a feedback means for efficiently learning factory work procedures, a means for performing real-time evaluations using a generative AI model, and a means for displaying acquired text data. This enables workers to learn procedures through voice input and receive appropriate feedback in real time.

[0518] "Voice input means" refers to a device or system that has the function of capturing voice data and converting it into an appropriate format.

[0519] "Methods for converting speech to text" refer to technologies that automatically analyze input speech data and convert it into a corresponding text format.

[0520] "Means of sending text data to a server" refers to the technology of transferring converted text data to a server via a network.

[0521] "Methods for saving text data on a server" refers to technologies that store received text data in a database or storage device, making it accessible for retrieval as needed.

[0522] "Methods for retrieving text data from a server" refers to technologies that retrieve stored text data from a server in response to requests.

[0523] "Means for displaying acquired text data" refers to a system that visually displays the extracted text data through a user interface.

[0524] A "feedback system for efficiently learning factory work procedures" is a system that provides real-time evaluation and appropriate advice and instructions to help workers learn the correct procedures.

[0525] "A method for performing real-time evaluation using a generative AI model" refers to a technology that uses an artificial intelligence model to evaluate the accuracy and progress of work in real time and provide immediate feedback.

[0526] The present invention is a system for efficiently learning factory work procedures and providing real-time feedback. This system includes a voice input means, a means for converting voice to text, a means for sending text data to a server, a means for storing text data on the server, a means for retrieving text data from the server, a means for displaying the retrieved text data, a feedback means for efficiently learning factory work procedures, and a means for performing real-time evaluation using a generative AI model.

[0527] Voice input method

[0528] Users input questions and answers by voice using the microphone on their smartphone or tablet while working in the factory. This eliminates the need for traditional handwriting or keyboard input, thus improving work efficiency.

[0529] Means of converting speech to text

[0530] The audio data captured by the voice input method is converted to text using the Python SpeechRecognition library. This method uses a reliable speech recognition engine, such as Google's speech recognition service.

[0531] Means of sending text data to a server

[0532] The data, converted to text, is sent to the server via an HTTP POST request. The request packages the data in JSON format and transfers it to the server over the internet.

[0533] Means for saving text data on a server

[0534] The server stores the received text data in a database. The database contains question-and-answer pairs, allowing for quick retrieval as needed. SQL-based databases are commonly used.

[0535] Means for retrieving text data from a server

[0536] When the user selects learning mode, a request for question-and-answer data stored on the server is sent to the device. The server returns all question-and-answer pairs in JSON format and sends them to the device.

[0537] Means for displaying acquired text data

[0538] The terminal displays the received text data on the user interface. This allows users to learn factory work procedures while visually confirming them.

[0539] A feedback mechanism for efficiently learning factory work procedures.

[0540] Data from factory operations is acquired in real time and evaluated based on accuracy and procedure using a generated AI model. This allows users to receive feedback on the spot and correct their work immediately.

[0541] A method for performing real-time evaluation using generative AI models.

[0542] The generative AI model evaluates work data under various conditions and notifies the user of the results in real time. This model utilizes pre-trained artificial intelligence algorithms and, as a specific example, evaluates whether "assembly is being performed correctly according to the work procedure."

[0543] Specific example

[0544] For example, when a user is learning the steps for a new assembly task, they might voice-input a question like, "In what order should I assemble the following parts?" and receive the response, "Part A, first." This data is converted to text in real time, sent to a server, and stored. Then, when the user selects learning mode, this data is displayed on the device.

[0545] Example of a prompt

[0546] 1. "How can we develop a system that uses voice input for learning work procedures?"

[0547] 2. "How can we use speech recognition to collect questions and answers and provide real-time feedback?"

[0548] As a result, this invention enables factory workers to efficiently learn procedures and receive appropriate feedback in real time.

[0549] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0550] Step 1:

[0551] The user launches an application on their smartphone or tablet and uses voice input. Specifically, they voice-input a question such as, "In what order should I assemble the following parts?" and an answer such as, "Part A, first." This voice data is captured through the microphone on the smartphone or tablet.

[0552] Input: Audio data

[0553] Output: Audio data

[0554] Step 2:

[0555] The device converts the captured audio data into text data using the Python SpeechRecognition library. This audio data is then processed through Google's speech recognition service.

[0556] Input: Audio data

[0557] Output: Text data (Example: "In what order should the following parts be assembled?", "Part A, first")

[0558] Step 3:

[0559] The terminal packages the converted text data into JSON format and sends it to the server using an HTTP POST request.

[0560] Input: Text data

[0561] Output: Text data in JSON format

[0562] Step 4:

[0563] The server saves the received JSON-formatted text data to a database. Each question and answer is recorded in the database as a pair, making it easy to retrieve later.

[0564] Input: Text data in JSON format

[0565] Output: Text data stored in the database

[0566] Step 5:

[0567] When the user selects learning mode, the device requests the stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format.

[0568] Input: Request for learning mode

[0569] Output: Question and answer data in JSON format

[0570] Step 6:

[0571] The terminal displays the received question-and-answer data through the user interface. The user visually reviews this data and learns the work procedures.

[0572] Input: Question and answer data in JSON format

[0573] Output: Displayed question-and-answer data

[0574] Step 7:

[0575] During factory work, user actions are evaluated in real time using a generative AI model. The generative AI model assesses the accuracy of the work and sends the results to the terminal.

[0576] Input: User operation data

[0577] Output: Real-time feedback results

[0578] Step 8:

[0579] The device provides feedback to the user based on the evaluation results received from the generated AI model. This allows the user to immediately verify whether their work is correct and make corrections as needed.

[0580] Input: Real-time feedback results

[0581] Output: User feedback

[0582] In this way, the system efficiently learns factory work procedures, performs real-time evaluations, and provides appropriate feedback.

[0583] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0584] This invention is a system designed to help students and working professionals efficiently memorize information needed for exams and work. It utilizes voice input to create personalized question-and-answer format data, and further incorporates an emotion engine to support learning while recognizing the user's emotional state.

[0585] User voice input and terminal processing

[0586] The user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by the speech recognition engine. Simultaneously, the emotion engine analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[0587] Next, the user presses the "Enter Answer" button and enters their answer by voice. This voice data is also acquired by the device and converted into text by the speech recognition engine. In addition, the emotion engine re-analyzes the user's emotions at the time of the answer.

[0588] Sending and storing text data and sentiment data.

[0589] The terminal packages the converted question and answer text data, along with the analyzed sentiment data, into JSON format and sends it to the server. Specifically, it sends data like the following using an HTTP POST request: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "emotions": {"question": "relaxed", "answer": "confident"}}

[0590] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident')

[0591] Data acquisition and display in learning mode

[0592] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format.

[0593] The device displays the received data on its screen. Users can then review the displayed questions and answers, and further assess their own emotional state. This allows users to adjust their learning methods according to their emotional state.

[0594] Specific example

[0595] Consider a scenario where a user wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" They then voice-input "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that they appear "calm" when asking the question and "confident" when answering.

[0596] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[0597] This system allows users to efficiently create question-and-answer formatted data using voice input, and also enables them to learn while understanding their own emotional state with the help of an emotion engine.

[0598] The following describes the processing flow.

[0599] Step 1:

[0600] The user launches the application. The user presses the "Enter Question" button in the application and enters the question by voice. For example, they might say, "What is the tallest mountain in the world?"

[0601] Step 2:

[0602] The device acquires voice data through its microphone. The acquired voice data is converted into text by the device's speech recognition engine. The text is recognized as "What is the tallest mountain in the world?".

[0603] Step 3:

[0604] The user presses the "Enter Answer" button and speaks the answer "Everest" aloud.

[0605] Step 4:

[0606] The device acquires the voice data of the response and converts it into text, "Everest," using a speech recognition engine. Simultaneously, an emotion engine analyzes the user's voice to analyze emotional data, for example, recognizing "confident."

[0607] Step 5:

[0608] The device packages the question and answer, along with the analyzed sentiment data, into JSON format. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}

[0609] Step 6:

[0610] The device sends JSON data to the server as an HTTP POST request. This request includes a question, an answer, and corresponding sentiment data.

[0611] Step 7:

[0612] The server receives an HTTP POST request and parses the JSON data. From the parsed data, it extracts question, answer, and sentiment data.

[0613] Step 8:

[0614] The server connects to the database and saves the extracted question, answer, and sentiment data as new records. Example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Mount Everest', 'calm', 'confident')

[0615] Step 9:

[0616] The user selects learning mode. The user presses the "Start Anti-Mode" button.

[0617] Step 10:

[0618] The device sends an HTTP GET request to the server to request the data necessary for learning. Example: / get_all_qa

[0619] Step 11:

[0620] The server receives an HTTP GET request and retrieves all question-and-answer pairs, along with their corresponding sentiment data, from the database. The retrieved data is then converted to JSON format.

[0621] Step 12:

[0622] The server returns JSON data to the terminal as an HTTP response. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}, ...]

[0623] Step 13:

[0624] The terminal receives a response from the server and parses the JSON data. It extracts the question and answer, as well as sentiment data, and displays it on the screen.

[0625] Step 14:

[0626] Users learn through repetition by viewing the displayed questions and answers, as well as sentiment data. For example, in addition to the question "What is the tallest mountain in the world?" and the answer "Mount Everest," sentiment data such as "When asked: calm" and "When answering: confident" is displayed. Based on this information, users can understand and optimize their learning progress.

[0627] (Example 2)

[0628] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0629] Conventional memorization systems not only struggled with voice input, but also lacked the means to understand the user's emotional state and enhance learning effectiveness. This made it difficult to adjust the learning process appropriately, resulting in challenges in efficient memorization.

[0630] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0631] In this invention, the server includes means for converting speech to text, means for analyzing emotional data from the speech, and means for transmitting the converted text data and the analyzed emotional data to the server. This allows the user to efficiently perform voice input and to progress with learning while understanding their own emotional state.

[0632] "Voice input means" refers to a method for users to input questions and answers by voice, and involves using input devices such as microphones.

[0633] "Means for converting speech to text" refers to methods for converting acquired speech data into text data, and utilizes speech recognition technology.

[0634] "Methods for analyzing emotional data from voice" refer to methods for analyzing a user's emotional state from voice data, and utilize technologies that analyze acoustic characteristics such as tone, pitch, and speed.

[0635] "Means for sending converted text data and analyzed sentiment data to a server" refers to means for packaging and sending data to a server after audio data has been converted to text data and sentiment data has been analyzed.

[0636] "Means of storing text data and sentiment data on a server" refers to means of storing received text data and sentiment data in a database or similar system for proper preservation.

[0637] "Means for retrieving text data and sentiment data from a server" refers to the means of retrieving stored text data and sentiment data from a server and sending them back to the terminal.

[0638] "Means for displaying acquired text data and sentiment data" refers to means for displaying text data and sentiment data acquired by the user on their device so that they can visually confirm them.

[0639] This invention is a system that efficiently creates question-and-answer format data using voice input and further supports learning while recognizing the user's emotional state. This system includes voice input means, a voice recognition engine, emotion analysis means, data transmission means, data storage means, data acquisition means, and data display means.

[0640] First, the user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted to text by a speech recognition engine such as the Google Speech-to-Text API. Simultaneously, using an emotion engine such as the Affectiva SDK, the device analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[0641] Next, the user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." This voice data is also captured by the device's microphone and converted into text by the speech recognition engine. The emotion engine also analyzes the user's emotional state at the time of the answer. The results of this analysis are obtained in the same way as when the question was asked.

[0642] These converted text data (questions and answers) and analyzed sentiment data are packaged in JSON format by the terminal and sent to the server using an HTTP POST request. For example, the following data is sent:

[0643] json

[0644] {

[0645] "Question": "What is the tallest mountain in the world?"

[0646] "answer": "Everest",

[0647] "emotions": {

[0648] "question": "relaxed",

[0649] "answer": "confident"

[0650] }

[0651] }

[0652] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example, it executes the following SQL query:

[0653] SQL

[0654] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[0655] When a user selects a learning mode, the device sends an HTTP GET request to the server, requesting stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format. The device displays the received data on the screen. The user can check their own sentiment state while viewing the displayed questions and answers. This allows the user to adjust the learning method according to their sentiment state.

[0656] As a concrete example, consider a user who wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" Then, voice-inputs the answer, "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that the user is "calm" when asking the question and "confident" when answering.

[0657] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[0658] Furthermore, it is possible to analyze user voice data using generative AI models. For example, by inputting prompts like the following, the generative AI model can be guided through the data creation process in a natural conversational format, supporting the effective operation of the system:

[0659] Please ask the question aloud, "What is the capital of France?" Then, answer aloud, "Paris." When doing so, ask the question in a relaxed tone and answer with confidence.

[0660] This system allows users to efficiently create question-and-answer formatted data using voice input, and also enables them to learn while understanding their own emotional state with the help of an emotion engine.

[0661] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0662] Step 1:

[0663] The user launches the application, presses the "Enter Question" button, and enters the question by voice.

[0664] Input: User's voice question (e.g., "What is the tallest mountain in the world?")

[0665] Operation: The device uses the microphone to acquire audio data.

[0666] Step 2:

[0667] The device uses a speech recognition engine (for example, Google Speech-to-Text API) to convert speech data into text data.

[0668] Input: Audio data

[0669] Operation: The speech recognition engine analyzes the audio data and converts it into corresponding text data (e.g., "What is the tallest mountain in the world?").

[0670] Output: Text data (Example: "What is the tallest mountain in the world?")

[0671] Step 3:

[0672] The device uses an emotion engine (e.g., Affectiva SDK) to analyze emotion data from the user's voice.

[0673] Input: Audio data

[0674] Operation: The emotion engine analyzes acoustic features such as tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "calm").

[0675] Output: Emotional data (e.g., "calmness")

[0676] Step 4:

[0677] The user presses the "Enter Answer" button and enters their answer by voice.

[0678] Input: User's voice response (e.g., "Everest")

[0679] Operation: The device uses the microphone to acquire audio data.

[0680] Step 5:

[0681] The device then uses the speech recognition engine again to convert the speech data into text data.

[0682] Input: Audio data

[0683] Operation: The speech recognition engine analyzes the audio data and converts it into the corresponding text data (e.g., "Everest").

[0684] Output: Text data (e.g., "Everest")

[0685] Step 6:

[0686] The device then uses the emotion engine again to analyze emotional data from the user's voice.

[0687] Input: Audio data

[0688] Operation: The emotion engine analyzes acoustic features such as tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "confidence").

[0689] Output: Sentiment data (e.g., "confidence")

[0690] Step 7:

[0691] The terminal packages the converted question and answer text data, as well as the analyzed sentiment data, into JSON format.

[0692] Input: Text data of questions and answers, sentiment data

[0693] Operation: Converts data to JSON format and creates a package like the one below.

[0694] json

[0695] {

[0696] "Question": "What is the tallest mountain in the world?"

[0697] "answer": "Everest",

[0698] "emotions": {

[0699] "question": "relaxed",

[0700] "answer": "confident"

[0701] }

[0702] }

[0703] Output: JSON package

[0704] Step 8:

[0705] The terminal uses an HTTP POST request to send the JSON package to the server.

[0706] Input: JSON package

[0707] Operation: Creates an HTTP POST request and sends data to the server.

[0708] Output: Data received on the server side.

[0709] Step 9:

[0710] The server parses the received JSON package and extracts question, answer, and sentiment data.

[0711] Input: JSON package

[0712] Operation: Parses JSON data and extracts the necessary data fields.

[0713] Output: Question, answer, sentiment data

[0714] Step 10:

[0715] The server connects to the database and stores the question, answer, and sentiment data as new records.

[0716] Input: Question, answer, sentiment data

[0717] Operation: Establish a database connection and execute an SQL query like the following.

[0718] SQL

[0719] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[0720] Output: A new record is stored in the database.

[0721] Step 11:

[0722] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the saved question-and-answer data and sentiment data.

[0723] Input: Learning mode selection operation

[0724] Action: Creates an HTTP GET request and sends it to the server.

[0725] Output: The server receives the request.

[0726] Step 12:

[0727] The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the terminal in JSON format.

[0728] Input: Database Request

[0729] Operation: Executes a database query and converts the retrieved data into JSON format.

[0730] Output: Data in JSON format

[0731] Step 13:

[0732] The device parses the received JSON data and displays the question, answer, and sentiment data on the screen.

[0733] Input: Data in JSON format

[0734] Function: Parses JSON data and converts it into a format for visual display.

[0735] Output: Questions, answers, and sentiment data displayed on the screen.

[0736] (Application Example 2)

[0737] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0738] There is a need for support methods to help factory workers efficiently and reliably memorize the operation and maintenance procedures of new machinery. While current systems allow for the creation of question-and-answer formatted data via voice input, they fail to consider the emotional state of the workers. This makes it difficult to provide optimal learning methods tailored to each worker's learning progress and emotions, potentially leading to decreased learning efficiency.

[0739] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing text data and emotion data, means for acquiring text data and emotion data, and means for displaying the acquired text data and emotion data. This makes it possible not only to create data in a question-and-answer format using voice input, but also to analyze the emotional state of engineers and provide an optimal learning method according to their emotions.

[0740] "Voice input means" refers to an apparatus that includes a device for acquiring the user's voice and software for processing that voice data.

[0741] A "speech recognition engine" is software that analyzes acquired audio data and converts it into text data.

[0742] An "emotion engine" is software that analyzes a user's emotions from voice data and acquires them as emotion data.

[0743] "Text data" refers to character information generated from speech by a speech recognition engine.

[0744] "Emotional data" refers to information about a user's emotional state, analyzed by an emotion engine.

[0745] A "server" is a central computer that stores text data and sentiment data, and transmits this data to user terminals as needed.

[0746] An "HTTP request" is a communication protocol used to send and receive data between a client and a server.

[0747] "Acquisition means" refers to the methods and devices used to obtain necessary data from a server.

[0748] "Display means" refers to a device or software for visually displaying text data and sentiment data on a user's terminal.

[0749] "Question and answer format" refers to a data format where a question and an answer are presented as a pair.

[0750] Modes for carrying out the invention

[0751] This invention provides a support system for engineers to memorize the operation and maintenance procedures of new machinery. This system is implemented using voice input means, a speech recognition engine, an emotion engine, a server, and HTTP requests.

[0752] Voice input and processing

[0753] The user inputs questions and answers using voice input. At this time, the speech recognition engine converts the voice data into text data, and the emotion engine analyzes the user's emotional state to obtain emotion data.

[0754] Sending and storing data

[0755] The device sends the acquired text data and sentiment data to the server via an HTTP request. The server stores the received data in a database. Specifically, it packages the text data and sentiment data into JSON format and sends it to the server via a POST request.

[0756] Data acquisition and display

[0757] The server retrieves stored text and sentiment data in response to HTTP GET requests from the user. This data is sent to the device, which displays the retrieved data on its screen. Based on the displayed data, the user learns and adjusts their learning method based on the information about their sentiment state.

[0758] Examples of specific cases and prompt statements

[0759] For example, a technician learning how to operate a new machine might voice-input a question like, "Where is the start button on this machine?" and then voice-input the answer, "Bottom left of the right panel." This voice data is converted into text data, and emotional data such as "anxiety" during the question and "confirmation" during the answer is analyzed. This data is stored on a server and can later be reviewed by the user in learning mode.

[0760] The following are examples of prompt messages.

[0761] "I'm designing a question-and-answer style learning application for engineers to memorize how to operate new machinery. Users input questions and answers via voice, and sentiment data analyzed by an emotion engine is also saved. When the user enters learning mode, the questions, answers, and sentiment data are displayed. Please generate the program for this application."

[0762] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0763] Step 1:

[0764] The user inputs their question by voice using a voice input device. The terminal acquires this voice data and converts it into text data using a speech recognition engine. At the same time, an emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[0765] Step 2:

[0766] The user then uses a voice input device to enter their response by voice. The terminal acquires this voice data and uses a speech recognition engine to convert it into text data. Similarly, the emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[0767] Step 3:

[0768] The terminal packages the converted text data and analyzed sentiment data into JSON format and sends this data to the server using an HTTP POST request. The input is text data and sentiment data, and the output is an HTTP request to the server.

[0769] Step 4:

[0770] The server receives an HTTP POST request, parses the JSON data, and extracts the question, answer, and their respective sentiment data. This data is then stored in a database. The input is JSON data, and the output is the data stored in the database.

[0771] Step 5:

[0772] When the user selects learning mode, the device sends an HTTP GET request to the server to retrieve stored question-and-answer formatted text data and sentiment data. The input is the HTTP GET request, and the output is the data retrieval request to the server.

[0773] Step 6:

[0774] The server retrieves text and sentiment data stored in the database and sends them back to the terminal in JSON format. The input is a request to read data from the database, and the output is the return of the retrieved data in JSON format.

[0775] Step 7:

[0776] The device parses the received JSON data and displays question-and-answer pairs and corresponding sentiment data on the screen. The user learns from this and adjusts the learning method based on their own sentiment state. The input is JSON data, and the output is the text data and sentiment data displayed on the screen.

[0777] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0778] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0779] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0780] [Third Embodiment]

[0781] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0782] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0783] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0784] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0785] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0786] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0787] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0788] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0789] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0790] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0791] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0792] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0793] This invention is a system for students and working professionals to efficiently memorize knowledge necessary for exams and work, and supports learning by creating personalized question-and-answer format data using voice input.

[0794] User voice input and terminal processing

[0795] First, the user launches the application. The application screen displays a "Question Input" button and an "Answer Input" button. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by a speech recognition engine. Then, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice answer is also converted into text by the device.

[0796] Sending text data and storing it on the server

[0797] The terminal sends the converted question and answer text data to the server. Specifically, it uses an HTTP POST request to send the question and answer text data to the server in JSON format. The server receives this data and stores the question and answer pairs in its database. In this storage process, the server registers the question and answer as new records in the database.

[0798] Data retrieval from the server and display on the terminal.

[0799] When a user selects learning mode within the application, the device requests stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format. The device displays the received data on the screen. The user can then repeatedly study the retrieved question-and-answer data on the screen.

[0800] Specific example

[0801] For example, if a user wants to memorize element symbols for a chemistry exam, they would use the system as follows: The user launches the app and voice-inputs the question, "What is the element symbol for carbon?" and then voice-inputs the answer, "C". This voice data is converted to text on the device, sent to the server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will appear on the screen, with "C" displayed as the answer. The user can repeat this process multiple times to learn.

[0802] This system allows users to efficiently create question-and-answer formatted data through the natural operation of voice input, enabling them to effectively memorize information.

[0803] The following describes the processing flow.

[0804] Step 1:

[0805] The user launches the application. The user presses the "Enter Question" button within the application and enters a question by voice. For example, they might say, "What is the tallest mountain in the world?"

[0806] Step 2:

[0807] The device acquires audio data through its microphone. This audio data is converted to text in real time by the device's speech recognition engine (for example, Google Speech Recognition API). The audio data is converted to the text "What is the tallest mountain in the world?".

[0808] Step 3:

[0809] The user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." The device then acquires this voice data through the microphone.

[0810] Step 4:

[0811] The device then uses its speech recognition engine again to convert the audio response into text. This audio data is then converted into the text "Everest".

[0812] Step 5:

[0813] The terminal packages the converted question and answer text data into JSON format and generates an HTTP POST request to send it to the server. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}

[0814] Step 6:

[0815] The server receives an HTTP POST request and parses the sent data. The server extracts the question and answer text data from the JSON.

[0816] Step 7:

[0817] The server connects to the database and inserts the extracted question and answer as new records. Example: INSERT INTO qa_table (question, answer) VALUES ('What is the tallest mountain in the world?', 'Mount Everest')

[0818] Step 8:

[0819] The user selects the application's learning mode. The user presses the "Start Learning Mode" button.

[0820] Step 9:

[0821] The device sends an HTTP GET request to the server to retrieve training data. Example: / get_all_qa

[0822] Step 10:

[0823] The server receives an HTTP GET request and retrieves all question-answer pairs from the database. The server then converts this data into JSON format. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}, ...]

[0824] Step 11:

[0825] The server returns the generated JSON data to the terminal as an HTTP response. The terminal parses the received JSON data and extracts question-and-answer pairs.

[0826] Step 12:

[0827] The device displays extracted question-and-answer pairs on the screen. Users can learn by repeatedly reviewing the displayed questions and answers. Example: "What is the tallest mountain in the world?" -> "Mount Everest"

[0828] (Example 1)

[0829] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0830] Currently, many systems exist to help students and working professionals efficiently memorize knowledge needed for exams and work, but they are often complex to operate or depend on specific methods, making it difficult to learn efficiently in a question-and-answer format. Furthermore, the manual input of text can be time-consuming, hindering continuous learning. Therefore, there is a need for a system that utilizes voice input to easily create user-specific question-and-answer data, enabling efficient learning.

[0831] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0832] In this invention, the server includes a voice input means, a means for converting voice to text, a means for transmitting the converted text data to the server, a means for storing the text data on the server, a means for retrieving the stored text data from the server, a means for displaying the retrieved text data, and a means for saving and displaying questions and answers entered by the user via voice in a question-and-answer format. This enables the user to efficiently create question-and-answer format data using voice in a natural manner and to repeatedly learn from that data.

[0833] "Voice input means" refers to a device or function for a user to input voice. Specifically, it includes a microphone and the software that controls it.

[0834] "Means for converting speech to text" refers to a device or function that converts captured speech data into text data using natural language processing techniques. Specifically, it refers to a speech recognition engine.

[0835] "Means for sending converted text data to a server" refers to a device or function for sending text data to a server over a network. Specifically, it refers to a communication method that uses HTTP requests.

[0836] "Means of saving text data on a server" refers to a device or function for saving received text data to a storage device within the server. Specifically, it refers to a database system.

[0837] "Means for retrieving text data stored on a server" refers to a device or function for retrieving text data stored on a server in response to a request. Specifically, it refers to a database query system.

[0838] "Means for displaying acquired text data" refers to a device or function for visually displaying acquired text data to the user. Specifically, it refers to a display and the software that controls it.

[0839] "Means for saving and displaying user-inputted questions and answers in a question-and-answer format" refers to a device or function that saves user-inputted questions and answers as pairs and displays them to the user. Specifically, it refers to a database and a user interface.

[0840] This invention is a question-and-answer format learning system that uses voice input to enable students and working professionals to efficiently memorize knowledge necessary for exams and work. Users input questions and answers using their own voice, and by saving and displaying this as text data, efficient learning becomes possible.

[0841] The user launches the application on their device (such as a smartphone or tablet). The application displays a "Question Input" button and an "Answer Input" button on the initial screen. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text data using speech recognition technology such as the Google Cloud Speech-to-Text API. Next, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice response is also converted into text data using the same method.

[0842] The converted question and answer text data is sent from the terminal to the server. Specifically, the data is sent to the server in JSON format using an HTTP POST request. The server (such as a Node.js server deployed on AWS EC2) receives this data and stores it in a database (such as Amazon RDS). The server registers the new question and answer pair as a record in the database.

[0843] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server. The server retrieves all question-and-answer pairs stored in the database and returns them to the device in JSON format. The device displays the retrieved data on the screen. The user can then repeatedly learn from this question-and-answer data.

[0844] For example, if a user wants to memorize element symbols for a chemistry exam, they might voice-input the question, "What is the element symbol for carbon?" and answer "C" aloud. This voice data is converted to text, sent to a server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will be displayed, with "C" as the answer. The user can then repeat this process to continue learning.

[0845] This system allows for the efficient creation of question-and-answer formatted data through natural operation, thereby supporting effective learning.

[0846] Example of a prompt

[0847] The following are examples of prompts to input into the generating AI model for this system.

[0848] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[0849] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0850] Step 1:

[0851] The user launches the application on their smartphone or tablet. The application displays a "Question Input" button and an "Answer Input" button on the initial screen, prompting the user to take action.

[0852] Input: User tap operation

[0853] Output: Initial screen display

[0854] Specific operation: When the user taps to open the app, two buttons will appear: "Enter Question" and "Enter Answer".

[0855] Step 2:

[0856] The user presses the "Enter Question" button and speaks their question into the microphone. The device captures this audio and converts the audio data into text using speech recognition technology such as the Google Cloud Speech-to-Text API.

[0857] Input: Audio data (for example, "What is the tallest mountain in the world?")

[0858] Output: Text data ("What is the tallest mountain in the world?")

[0859] Specific operation: When the user presses the "Enter Question" button and speaks "What is the tallest mountain in the world?", the device converts the speech into text and generates the text "What is the tallest mountain in the world?".

[0860] Step 3:

[0861] The user presses the "Enter Answer" button and speaks their answer into the microphone. The device captures this audio and uses the same speech recognition technology to convert the audio data into text data.

[0862] Input: Audio data (e.g., "Everest")

[0863] Output: Text data ("Everest")

[0864] Specific operation: When the user presses the "Enter Answer" button and speaks "Everest," the device converts the speech into text and generates the text "Everest."

[0865] Step 4:

[0866] The terminal formats the converted question and answer text data into JSON format and sends it to the server using an HTTP POST request.

[0867] Input: Text data of a question and answer ("What is the tallest mountain in the world?", "Mount Everest")

[0868] Output: JSON data sent to the server

[0869] Specific operation: The terminal creates data in JSON format and sends it to the server using an HTTP POST request.

[0870] Step 5:

[0871] The server receives an HTTP POST request and saves the received data to the database. The server parses the JSON data and registers the question-and-answer pairs as new records in the database.

[0872] Input: JSON data sent to the server

[0873] Output: Question and answer pairs stored in the database

[0874] Specific operation: The server receives an HTTP POST request, parses the data, and saves it to the database.

[0875] Step 6:

[0876] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server.

[0877] Input: Select learning mode

[0878] Output: Data request to the server

[0879] Specific operation: When the user selects learning mode, the device requests data from the server.

[0880] Step 7:

[0881] The server retrieves all question-and-answer pairs stored in the database and returns them to the terminal in JSON format.

[0882] Input: Question and answer data request

[0883] Output: JSON data returned to the terminal

[0884] Specific operation: The server retrieves data from the database and sends it to the terminal in JSON format.

[0885] Step 8:

[0886] The device displays the received data on its screen. Users can repeatedly learn from this question-and-answer data.

[0887] Input: JSON data returned from the server

[0888] Output: Pairs of questions and answers displayed on the screen

[0889] Specific operation: The device displays question and answer pairs it has acquired on the screen, and the user learns by looking at them.

[0890] Example of a prompt

[0891] The following are examples of prompts to input into the generating AI model for this system.

[0892] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[0893] (Application Example 1)

[0894] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0895] Traditional factory training and feedback systems have made it difficult to efficiently learn work procedures. Furthermore, the lack of real-time evaluation and feedback creates an environment prone to human error. Therefore, there is a need for a system that improves worker learning efficiency and work accuracy.

[0896] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0897] In this invention, the server includes a feedback means for efficiently learning factory work procedures, a means for performing real-time evaluations using a generative AI model, and a means for displaying acquired text data. This enables workers to learn procedures through voice input and receive appropriate feedback in real time.

[0898] "Voice input means" refers to a device or system that has the function of capturing voice data and converting it into an appropriate format.

[0899] "Methods for converting speech to text" refer to technologies that automatically analyze input speech data and convert it into a corresponding text format.

[0900] "Means of sending text data to a server" refers to the technology of transferring converted text data to a server via a network.

[0901] "Methods for saving text data on a server" refers to technologies that store received text data in a database or storage device, making it accessible for retrieval as needed.

[0902] "Methods for retrieving text data from a server" refers to technologies that retrieve stored text data from a server in response to requests.

[0903] "Means for displaying acquired text data" refers to a system that visually displays the extracted text data through a user interface.

[0904] A "feedback system for efficiently learning factory work procedures" is a system that provides real-time evaluation and appropriate advice and instructions to help workers learn the correct procedures.

[0905] "A method for performing real-time evaluation using a generative AI model" refers to a technology that uses an artificial intelligence model to evaluate the accuracy and progress of work in real time and provide immediate feedback.

[0906] The present invention is a system for efficiently learning factory work procedures and providing real-time feedback. This system includes a voice input means, a means for converting voice to text, a means for sending text data to a server, a means for storing text data on the server, a means for retrieving text data from the server, a means for displaying the retrieved text data, a feedback means for efficiently learning factory work procedures, and a means for performing real-time evaluation using a generative AI model.

[0907] Voice input method

[0908] Users input questions and answers by voice using the microphone on their smartphone or tablet while working in the factory. This eliminates the need for traditional handwriting or keyboard input, thus improving work efficiency.

[0909] Means of converting speech to text

[0910] The audio data captured by the voice input method is converted to text using the Python SpeechRecognition library. This method uses a reliable speech recognition engine, such as Google's speech recognition service.

[0911] Means of sending text data to a server

[0912] The data, converted to text, is sent to the server via an HTTP POST request. The request packages the data in JSON format and transfers it to the server over the internet.

[0913] Means for saving text data on a server

[0914] The server stores the received text data in a database. The database contains question-and-answer pairs, allowing for quick retrieval as needed. SQL-based databases are commonly used.

[0915] Means for retrieving text data from a server

[0916] When the user selects learning mode, a request for question-and-answer data stored on the server is sent to the device. The server returns all question-and-answer pairs in JSON format and sends them to the device.

[0917] Means for displaying acquired text data

[0918] The terminal displays the received text data on the user interface. This allows users to learn factory work procedures while visually confirming them.

[0919] A feedback mechanism for efficiently learning factory work procedures.

[0920] Data from factory operations is acquired in real time and evaluated based on accuracy and procedure using a generated AI model. This allows users to receive feedback on the spot and correct their work immediately.

[0921] A method for performing real-time evaluation using generative AI models.

[0922] The generative AI model evaluates work data under various conditions and notifies the user of the results in real time. This model utilizes pre-trained artificial intelligence algorithms and, as a specific example, evaluates whether "assembly is being performed correctly according to the work procedure."

[0923] Specific example

[0924] For example, when a user is learning the steps for a new assembly task, they might voice-input a question like, "In what order should I assemble the following parts?" and receive the response, "Part A, first." This data is converted to text in real time, sent to a server, and stored. Then, when the user selects learning mode, this data is displayed on the device.

[0925] Example of a prompt

[0926] 1. "How can we develop a system that uses voice input for learning work procedures?"

[0927] 2. "How can we use speech recognition to collect questions and answers and provide real-time feedback?"

[0928] As a result, this invention enables factory workers to efficiently learn procedures and receive appropriate feedback in real time.

[0929] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0930] Step 1:

[0931] The user launches an application on their smartphone or tablet and uses voice input. Specifically, they voice-input a question such as, "In what order should I assemble the following parts?" and an answer such as, "Part A, first." This voice data is captured through the microphone on the smartphone or tablet.

[0932] Input: Audio data

[0933] Output: Audio data

[0934] Step 2:

[0935] The device converts the captured audio data into text data using the Python SpeechRecognition library. This audio data is then processed through Google's speech recognition service.

[0936] Input: Audio data

[0937] Output: Text data (Example: "In what order should the following parts be assembled?", "Part A, first")

[0938] Step 3:

[0939] The terminal packages the converted text data into JSON format and sends it to the server using an HTTP POST request.

[0940] Input: Text data

[0941] Output: Text data in JSON format

[0942] Step 4:

[0943] The server saves the received JSON-formatted text data to a database. Each question and answer is recorded in the database as a pair, making it easy to retrieve later.

[0944] Input: Text data in JSON format

[0945] Output: Text data stored in the database

[0946] Step 5:

[0947] When the user selects learning mode, the device requests the stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format.

[0948] Input: Request for learning mode

[0949] Output: Question and answer data in JSON format

[0950] Step 6:

[0951] The terminal displays the received question-and-answer data through the user interface. The user visually reviews this data and learns the work procedures.

[0952] Input: Question and answer data in JSON format

[0953] Output: Displayed question-and-answer data

[0954] Step 7:

[0955] During factory work, user actions are evaluated in real time using a generative AI model. The generative AI model assesses the accuracy of the work and sends the results to the terminal.

[0956] Input: User operation data

[0957] Output: Real-time feedback results

[0958] Step 8:

[0959] The device provides feedback to the user based on the evaluation results received from the generated AI model. This allows the user to immediately verify whether their work is correct and make corrections as needed.

[0960] Input: Real-time feedback results

[0961] Output: User feedback

[0962] In this way, the system efficiently learns factory work procedures, performs real-time evaluations, and provides appropriate feedback.

[0963] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0964] This invention is a system designed to help students and working professionals efficiently memorize information needed for exams and work. It utilizes voice input to create personalized question-and-answer format data, and further incorporates an emotion engine to support learning while recognizing the user's emotional state.

[0965] User voice input and terminal processing

[0966] The user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by the speech recognition engine. Simultaneously, the emotion engine analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[0967] Next, the user presses the "Enter Answer" button and enters their answer by voice. This voice data is also acquired by the device and converted into text by the speech recognition engine. In addition, the emotion engine re-analyzes the user's emotions at the time of the answer.

[0968] Sending and storing text data and sentiment data.

[0969] The terminal packages the converted question and answer text data, along with the analyzed sentiment data, into JSON format and sends it to the server. Specifically, it sends data like the following using an HTTP POST request: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "emotions": {"question": "relaxed", "answer": "confident"}}

[0970] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident')

[0971] Data acquisition and display in learning mode

[0972] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format.

[0973] The device displays the received data on its screen. Users can then review the displayed questions and answers, and further assess their own emotional state. This allows users to adjust their learning methods according to their emotional state.

[0974] Specific example

[0975] Consider a scenario where a user wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" They then voice-input "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that they appear "calm" when asking the question and "confident" when answering.

[0976] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[0977] This system allows users to efficiently create question-and-answer formatted data using voice input, and also enables them to learn while understanding their own emotional state with the help of an emotion engine.

[0978] The following describes the processing flow.

[0979] Step 1:

[0980] The user launches the application. The user presses the "Enter Question" button in the application and enters the question by voice. For example, they might say, "What is the tallest mountain in the world?"

[0981] Step 2:

[0982] The device acquires voice data through its microphone. The acquired voice data is converted into text by the device's speech recognition engine. The text is recognized as "What is the tallest mountain in the world?".

[0983] Step 3:

[0984] The user presses the "Enter Answer" button and speaks the answer "Everest" aloud.

[0985] Step 4:

[0986] The device acquires the voice data of the response and converts it into text, "Everest," using a speech recognition engine. Simultaneously, an emotion engine analyzes the user's voice to analyze emotional data, for example, recognizing "confident."

[0987] Step 5:

[0988] The device packages the question and answer, along with the analyzed sentiment data, into JSON format. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}

[0989] Step 6:

[0990] The device sends JSON data to the server as an HTTP POST request. This request includes a question, an answer, and corresponding sentiment data.

[0991] Step 7:

[0992] The server receives an HTTP POST request and parses the JSON data. From the parsed data, it extracts question, answer, and sentiment data.

[0993] Step 8:

[0994] The server connects to the database and saves the extracted question, answer, and sentiment data as new records. Example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Mount Everest', 'calm', 'confident')

[0995] Step 9:

[0996] The user selects learning mode. The user presses the "Start Anti-Mode" button.

[0997] Step 10:

[0998] The device sends an HTTP GET request to the server to request the data necessary for learning. Example: / get_all_qa

[0999] Step 11:

[1000] The server receives an HTTP GET request and retrieves all question-and-answer pairs, along with their corresponding sentiment data, from the database. The retrieved data is then converted to JSON format.

[1001] Step 12:

[1002] The server returns JSON data to the terminal as an HTTP response. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}, ...]

[1003] Step 13:

[1004] The terminal receives a response from the server and parses the JSON data. It extracts the question and answer, as well as sentiment data, and displays it on the screen.

[1005] Step 14:

[1006] Users learn through repetition by viewing the displayed questions and answers, as well as sentiment data. For example, in addition to the question "What is the tallest mountain in the world?" and the answer "Mount Everest," sentiment data such as "When asked: calm" and "When answering: confident" is displayed. Based on this information, users can understand and optimize their learning progress.

[1007] (Example 2)

[1008] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1009] Conventional memorization systems not only struggled with voice input, but also lacked the means to understand the user's emotional state and enhance learning effectiveness. This made it difficult to adjust the learning process appropriately, resulting in challenges in efficient memorization.

[1010] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1011] In this invention, the server includes means for converting speech to text, means for analyzing emotional data from the speech, and means for transmitting the converted text data and the analyzed emotional data to the server. This allows the user to efficiently perform voice input and to progress with learning while understanding their own emotional state.

[1012] "Voice input means" refers to a method for users to input questions and answers by voice, and involves using input devices such as microphones.

[1013] "Means for converting speech to text" refers to methods for converting acquired speech data into text data, and utilizes speech recognition technology.

[1014] "Methods for analyzing emotional data from voice" refer to methods for analyzing a user's emotional state from voice data, and utilize technologies that analyze acoustic characteristics such as tone, pitch, and speed.

[1015] "Means for sending converted text data and analyzed sentiment data to a server" refers to means for packaging and sending data to a server after audio data has been converted to text data and sentiment data has been analyzed.

[1016] "Means of storing text data and sentiment data on a server" refers to means of storing received text data and sentiment data in a database or similar system for proper preservation.

[1017] "Means for retrieving text data and sentiment data from a server" refers to the means of retrieving stored text data and sentiment data from a server and sending them back to the terminal.

[1018] "Means for displaying acquired text data and sentiment data" refers to means for displaying text data and sentiment data acquired by the user on their device so that they can visually confirm them.

[1019] This invention is a system that efficiently creates question-and-answer format data using voice input and further supports learning while recognizing the user's emotional state. This system includes voice input means, a voice recognition engine, emotion analysis means, data transmission means, data storage means, data acquisition means, and data display means.

[1020] First, the user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted to text by a speech recognition engine such as the Google Speech-to-Text API. Simultaneously, using an emotion engine such as the Affectiva SDK, the device analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[1021] Next, the user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." This voice data is also captured by the device's microphone and converted into text by the speech recognition engine. The emotion engine also analyzes the user's emotional state at the time of the answer. The results of this analysis are obtained in the same way as when the question was asked.

[1022] These converted text data (questions and answers) and analyzed sentiment data are packaged in JSON format by the terminal and sent to the server using an HTTP POST request. For example, the following data is sent:

[1023] json

[1024] {

[1025] "Question": "What is the tallest mountain in the world?"

[1026] "answer": "Everest",

[1027] "emotions": {

[1028] "question": "relaxed",

[1029] "answer": "confident"

[1030] }

[1031] }

[1032] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example, it executes the following SQL query:

[1033] sql

[1034] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[1035] When a user selects a learning mode, the device sends an HTTP GET request to the server, requesting stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format. The device displays the received data on the screen. The user can check their own sentiment state while viewing the displayed questions and answers. This allows the user to adjust the learning method according to their sentiment state.

[1036] As a concrete example, consider a user who wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" Then, voice-inputs the answer, "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that the user is "calm" when asking the question and "confident" when answering.

[1037] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[1038] Furthermore, it is possible to analyze user voice data using generative AI models. For example, by inputting prompts like the following, the generative AI model can be guided through the data creation process in a natural conversational format, supporting the effective operation of the system:

[1039] Please ask the question aloud, "What is the capital of France?" Then, answer aloud, "Paris." When doing so, ask the question in a relaxed tone and answer with confidence.

[1040] This system allows users to efficiently create question-and-answer formatted data using voice input, and also enables them to learn while understanding their own emotional state with the help of an emotion engine.

[1041] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1042] Step 1:

[1043] The user launches the application, presses the "Enter Question" button, and enters the question by voice.

[1044] Input: User's voice question (e.g., "What is the tallest mountain in the world?")

[1045] Operation: The device uses the microphone to acquire audio data.

[1046] Step 2:

[1047] The device uses a speech recognition engine (for example, Google Speech-to-Text API) to convert speech data into text data.

[1048] Input: Audio data

[1049] Operation: The speech recognition engine analyzes the audio data and converts it into corresponding text data (e.g., "What is the tallest mountain in the world?").

[1050] Output: Text data (Example: "What is the tallest mountain in the world?")

[1051] Step 3:

[1052] The device uses an emotion engine (e.g., Affectiva SDK) to analyze emotion data from the user's voice.

[1053] Input: Audio data

[1054] Operation: The emotion engine analyzes acoustic features such as tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "calm").

[1055] Output: Emotional data (e.g., "calmness")

[1056] Step 4:

[1057] The user presses the "Enter Answer" button and enters their answer by voice.

[1058] Input: User's voice response (e.g., "Everest")

[1059] Operation: The device uses the microphone to acquire audio data.

[1060] Step 5:

[1061] The device then uses the speech recognition engine again to convert the speech data into text data.

[1062] Input: Audio data

[1063] Operation: The speech recognition engine analyzes the audio data and converts it into the corresponding text data (e.g., "Everest").

[1064] Output: Text data (e.g., "Everest")

[1065] Step 6:

[1066] The device then uses the emotion engine again to analyze emotional data from the user's voice.

[1067] Input: Audio data

[1068] Operation: The emotion engine analyzes acoustic features such as tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "confidence").

[1069] Output: Sentiment data (e.g., "confidence")

[1070] Step 7:

[1071] The terminal packages the converted question and answer text data, as well as the analyzed sentiment data, into JSON format.

[1072] Input: Text data of questions and answers, sentiment data

[1073] Operation: Converts data to JSON format and creates a package like the one below.

[1074] json

[1075] {

[1076] "Question": "What is the tallest mountain in the world?"

[1077] "answer": "Everest",

[1078] "emotions": {

[1079] "question": "relaxed",

[1080] "answer": "confident"

[1081] }

[1082] }

[1083] Output: JSON package

[1084] Step 8:

[1085] The terminal uses an HTTP POST request to send the JSON package to the server.

[1086] Input: JSON package

[1087] Operation: Creates an HTTP POST request and sends data to the server.

[1088] Output: Data received on the server side.

[1089] Step 9:

[1090] The server parses the received JSON package and extracts question, answer, and sentiment data.

[1091] Input: JSON package

[1092] Operation: Parses JSON data and extracts the necessary data fields.

[1093] Output: Question, answer, sentiment data

[1094] Step 10:

[1095] The server connects to the database and stores the question, answer, and sentiment data as new records.

[1096] Input: Question, answer, sentiment data

[1097] Operation: Establish a database connection and execute an SQL query like the following.

[1098] SQL

[1099] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[1100] Output: A new record is stored in the database.

[1101] Step 11:

[1102] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the saved question-and-answer data and sentiment data.

[1103] Input: Learning mode selection operation

[1104] Action: Creates an HTTP GET request and sends it to the server.

[1105] Output: The server receives the request.

[1106] Step 12:

[1107] The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the terminal in JSON format.

[1108] Input: Database Request

[1109] Operation: Executes a database query and converts the retrieved data into JSON format.

[1110] Output: Data in JSON format

[1111] Step 13:

[1112] The device parses the received JSON data and displays the question, answer, and sentiment data on the screen.

[1113] Input: Data in JSON format

[1114] Function: Parses JSON data and converts it into a format for visual display.

[1115] Output: Questions, answers, and sentiment data displayed on the screen.

[1116] (Application Example 2)

[1117] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1118] There is a need for support methods to help factory workers efficiently and reliably memorize the operation and maintenance procedures of new machinery. While current systems allow for the creation of question-and-answer formatted data via voice input, they fail to consider the emotional state of the workers. This makes it difficult to provide optimal learning methods tailored to each worker's learning progress and emotions, potentially leading to decreased learning efficiency.

[1119] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing text data and emotion data, means for acquiring text data and emotion data, and means for displaying the acquired text data and emotion data. This makes it possible not only to create data in a question-and-answer format using voice input, but also to analyze the emotional state of engineers and provide an optimal learning method according to their emotions.

[1120] "Voice input means" refers to an apparatus that includes a device for acquiring the user's voice and software for processing that voice data.

[1121] A "speech recognition engine" is software that analyzes acquired audio data and converts it into text data.

[1122] An "emotion engine" is software that analyzes a user's emotions from voice data and acquires them as emotion data.

[1123] "Text data" refers to character information generated from speech by a speech recognition engine.

[1124] "Emotional data" refers to information about a user's emotional state, analyzed by an emotion engine.

[1125] A "server" is a central computer that stores text data and sentiment data, and transmits this data to user terminals as needed.

[1126] An "HTTP request" is a communication protocol used to send and receive data between a client and a server.

[1127] "Acquisition means" refers to the methods and devices used to obtain necessary data from a server.

[1128] "Display means" refers to a device or software for visually displaying text data and sentiment data on a user's terminal.

[1129] "Question and answer format" refers to a data format where a question and an answer are presented as a pair.

[1130] Modes for carrying out the invention

[1131] This invention provides a support system for engineers to memorize the operation and maintenance procedures of new machinery. This system is implemented using voice input means, a speech recognition engine, an emotion engine, a server, and HTTP requests.

[1132] Voice input and processing

[1133] The user inputs questions and answers using voice input. At this time, the speech recognition engine converts the voice data into text data, and the emotion engine analyzes the user's emotional state to obtain emotion data.

[1134] Sending and storing data

[1135] The device sends the acquired text data and sentiment data to the server via an HTTP request. The server stores the received data in a database. Specifically, it packages the text data and sentiment data into JSON format and sends it to the server via a POST request.

[1136] Data acquisition and display

[1137] The server retrieves stored text and sentiment data in response to HTTP GET requests from the user. This data is sent to the device, which displays the retrieved data on its screen. Based on the displayed data, the user learns and adjusts their learning method based on the information about their sentiment state.

[1138] Examples of specific cases and prompt statements

[1139] For example, a technician learning how to operate a new machine might voice-input a question like, "Where is the start button on this machine?" and then voice-input the answer, "Bottom left of the right panel." This voice data is converted into text data, and emotional data such as "anxiety" during the question and "confirmation" during the answer is analyzed. This data is stored on a server and can later be reviewed by the user in learning mode.

[1140] The following are examples of prompt messages.

[1141] "I'm designing a question-and-answer style learning application for engineers to memorize how to operate new machinery. Users input questions and answers via voice, and sentiment data analyzed by an emotion engine is also saved. When the user enters learning mode, the questions, answers, and sentiment data are displayed. Please generate the program for this application."

[1142] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1143] Step 1:

[1144] The user inputs their question by voice using a voice input device. The terminal acquires this voice data and converts it into text data using a speech recognition engine. At the same time, an emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[1145] Step 2:

[1146] The user then uses a voice input device to enter their response by voice. The terminal acquires this voice data and uses a speech recognition engine to convert it into text data. Similarly, the emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[1147] Step 3:

[1148] The terminal packages the converted text data and analyzed sentiment data into JSON format and sends this data to the server using an HTTP POST request. The input is text data and sentiment data, and the output is an HTTP request to the server.

[1149] Step 4:

[1150] The server receives an HTTP POST request, parses the JSON data, and extracts the question, answer, and their respective sentiment data. This data is then stored in a database. The input is JSON data, and the output is the data stored in the database.

[1151] Step 5:

[1152] When the user selects learning mode, the device sends an HTTP GET request to the server to retrieve stored question-and-answer formatted text data and sentiment data. The input is the HTTP GET request, and the output is the data retrieval request to the server.

[1153] Step 6:

[1154] The server retrieves text and sentiment data stored in the database and sends them back to the terminal in JSON format. The input is a request to read data from the database, and the output is the return of the retrieved data in JSON format.

[1155] Step 7:

[1156] The device parses the received JSON data and displays question-and-answer pairs and corresponding sentiment data on the screen. The user learns from this and adjusts the learning method based on their own sentiment state. The input is JSON data, and the output is the text data and sentiment data displayed on the screen.

[1157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1158] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1159] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1160] [Fourth Embodiment]

[1161] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1165] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1170] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1171] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1172] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1173] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1174] This invention is a system for students and working professionals to efficiently memorize knowledge necessary for exams and work, and supports learning by creating personalized question-and-answer format data using voice input.

[1175] User voice input and terminal processing

[1176] First, the user launches the application. The application screen displays a "Question Input" button and an "Answer Input" button. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by a speech recognition engine. Then, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice answer is also converted into text by the device.

[1177] Sending text data and storing it on the server

[1178] The terminal sends the converted question and answer text data to the server. Specifically, it uses an HTTP POST request to send the question and answer text data to the server in JSON format. The server receives this data and stores the question and answer pairs in its database. In this storage process, the server registers the question and answer as new records in the database.

[1179] Data retrieval from the server and display on the terminal.

[1180] When a user selects learning mode within the application, the device requests stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format. The device displays the received data on the screen. The user can then repeatedly study the retrieved question-and-answer data on the screen.

[1181] Specific example

[1182] For example, if a user wants to memorize element symbols for a chemistry exam, they would use the system as follows: The user launches the app and voice-inputs the question, "What is the element symbol for carbon?" and then voice-inputs the answer, "C". This voice data is converted to text on the device, sent to the server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will appear on the screen, with "C" displayed as the answer. The user can repeat this process multiple times to learn.

[1183] This system allows users to efficiently create question-and-answer formatted data through the natural operation of voice input, enabling them to effectively memorize information.

[1184] The following describes the processing flow.

[1185] Step 1:

[1186] The user launches the application. The user presses the "Enter Question" button within the application and enters a question by voice. For example, they might say, "What is the tallest mountain in the world?"

[1187] Step 2:

[1188] The device acquires audio data through its microphone. This audio data is converted to text in real time by the device's speech recognition engine (for example, Google Speech Recognition API). The audio data is converted to the text "What is the tallest mountain in the world?".

[1189] Step 3:

[1190] The user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." The device then acquires this voice data through the microphone.

[1191] Step 4:

[1192] The device then uses its speech recognition engine again to convert the audio response into text. This audio data is then converted into the text "Everest".

[1193] Step 5:

[1194] The terminal packages the converted question and answer text data into JSON format and generates an HTTP POST request to send it to the server. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}

[1195] Step 6:

[1196] The server receives an HTTP POST request and parses the sent data. The server extracts the question and answer text data from the JSON.

[1197] Step 7:

[1198] The server connects to the database and inserts the extracted question and answer as new records. Example: INSERT INTO qa_table (question, answer) VALUES ('What is the tallest mountain in the world?', 'Mount Everest')

[1199] Step 8:

[1200] The user selects the application's learning mode. The user presses the "Start Learning Mode" button.

[1201] Step 9:

[1202] The device sends an HTTP GET request to the server to retrieve training data. Example: / get_all_qa

[1203] Step 10:

[1204] The server receives an HTTP GET request and retrieves all question-answer pairs from the database. The server then converts this data into JSON format. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest"}, ...]

[1205] Step 11:

[1206] The server returns the generated JSON data to the terminal as an HTTP response. The terminal parses the received JSON data and extracts question-and-answer pairs.

[1207] Step 12:

[1208] The device displays extracted question-and-answer pairs on the screen. Users can learn by repeatedly reviewing the displayed questions and answers. Example: "What is the tallest mountain in the world?" -> "Mount Everest"

[1209] (Example 1)

[1210] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1211] Currently, many systems exist to help students and working professionals efficiently memorize knowledge needed for exams and work, but they are often complex to operate or depend on specific methods, making it difficult to learn efficiently in a question-and-answer format. Furthermore, the manual input of text can be time-consuming, hindering continuous learning. Therefore, there is a need for a system that utilizes voice input to easily create user-specific question-and-answer data, enabling efficient learning.

[1212] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1213] In this invention, the server includes a voice input means, a means for converting voice to text, a means for transmitting the converted text data to the server, a means for storing the text data on the server, a means for retrieving the stored text data from the server, a means for displaying the retrieved text data, and a means for saving and displaying questions and answers entered by the user via voice in a question-and-answer format. This enables the user to efficiently create question-and-answer format data using voice in a natural manner and to repeatedly learn from that data.

[1214] "Voice input means" refers to a device or function for a user to input voice. Specifically, it includes a microphone and the software that controls it.

[1215] "Means for converting speech to text" refers to a device or function that converts captured speech data into text data using natural language processing techniques. Specifically, it refers to a speech recognition engine.

[1216] "Means for sending converted text data to a server" refers to a device or function for sending text data to a server over a network. Specifically, it refers to a communication method that uses HTTP requests.

[1217] "Means of saving text data on a server" refers to a device or function for saving received text data to a storage device within the server. Specifically, it refers to a database system.

[1218] "Means for retrieving text data stored on a server" refers to a device or function for retrieving text data stored on a server in response to a request. Specifically, it refers to a database query system.

[1219] "Means for displaying acquired text data" refers to a device or function for visually displaying acquired text data to the user. Specifically, it refers to a display and the software that controls it.

[1220] "Means for saving and displaying user-inputted questions and answers in a question-and-answer format" refers to a device or function that saves user-inputted questions and answers as pairs and displays them to the user. Specifically, it refers to a database and a user interface.

[1221] This invention is a question-and-answer format learning system that uses voice input to enable students and working professionals to efficiently memorize knowledge necessary for exams and work. Users input questions and answers using their own voice, and by saving and displaying this as text data, efficient learning becomes possible.

[1222] The user launches the application on their device (such as a smartphone or tablet). The application displays a "Question Input" button and an "Answer Input" button on the initial screen. The user presses the "Question Input" button and inputs a question by voice. For example, they might input the question, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text data using speech recognition technology such as the Google Cloud Speech-to-Text API. Next, the user presses the "Answer Input" button and similarly inputs the answer by voice, "Mount Everest." This voice response is also converted into text data using the same method.

[1223] The converted question and answer text data is sent from the terminal to the server. Specifically, the data is sent to the server in JSON format using an HTTP POST request. The server (such as a Node.js server deployed on AWS EC2) receives this data and stores it in a database (such as Amazon RDS). The server registers the new question and answer pair as a record in the database.

[1224] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server. The server retrieves all question-and-answer pairs stored in the database and returns them to the device in JSON format. The device displays the retrieved data on the screen. The user can then repeatedly learn from this question-and-answer data.

[1225] For example, if a user wants to memorize element symbols for a chemistry exam, they might voice-input the question, "What is the element symbol for carbon?" and answer "C" aloud. This voice data is converted to text, sent to a server, and stored. Later, when the user selects learning mode, the question "What is the element symbol for carbon?" will be displayed, with "C" as the answer. The user can then repeat this process to continue learning.

[1226] This system allows for the efficient creation of question-and-answer formatted data through natural operation, thereby supporting effective learning.

[1227] Example of a prompt

[1228] The following are examples of prompts to input into the generating AI model for this system.

[1229] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[1230] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1231] Step 1:

[1232] The user launches the application on their smartphone or tablet. The application displays a "Question Input" button and an "Answer Input" button on the initial screen, prompting the user to take action.

[1233] Input: User tap operation

[1234] Output: Initial screen display

[1235] Specific operation: When the user taps to open the app, two buttons will appear: "Enter Question" and "Enter Answer".

[1236] Step 2:

[1237] The user presses the "Enter Question" button and speaks their question into the microphone. The device captures this audio and converts the audio data into text using speech recognition technology such as the Google Cloud Speech-to-Text API.

[1238] Input: Audio data (for example, "What is the tallest mountain in the world?")

[1239] Output: Text data ("What is the tallest mountain in the world?")

[1240] Specific operation: When the user presses the "Enter Question" button and speaks "What is the tallest mountain in the world?", the device converts the speech into text and generates the text "What is the tallest mountain in the world?".

[1241] Step 3:

[1242] The user presses the "Enter Answer" button and speaks their answer into the microphone. The device captures this audio and uses the same speech recognition technology to convert the audio data into text data.

[1243] Input: Audio data (e.g., "Everest")

[1244] Output: Text data ("Everest")

[1245] Specific operation: When the user presses the "Enter Answer" button and speaks "Everest," the device converts the speech into text and generates the text "Everest."

[1246] Step 4:

[1247] The terminal formats the converted question and answer text data into JSON format and sends it to the server using an HTTP POST request.

[1248] Input: Text data of a question and answer ("What is the tallest mountain in the world?", "Mount Everest")

[1249] Output: JSON data sent to the server

[1250] Specific operation: The terminal creates data in JSON format and sends it to the server using an HTTP POST request.

[1251] Step 5:

[1252] The server receives an HTTP POST request and saves the received data to the database. The server parses the JSON data and registers the question-and-answer pairs as new records in the database.

[1253] Input: JSON data sent to the server

[1254] Output: Question and answer pairs stored in the database

[1255] Specific operation: The server receives an HTTP POST request, parses the data, and saves it to the database.

[1256] Step 6:

[1257] When a user selects learning mode within the application, the device sends a request for question-and-answer data to the server.

[1258] Input: Select learning mode

[1259] Output: Data request to the server

[1260] Specific operation: When the user selects learning mode, the device requests data from the server.

[1261] Step 7:

[1262] The server retrieves all question-and-answer pairs stored in the database and returns them to the terminal in JSON format.

[1263] Input: Question and answer data request

[1264] Output: JSON data returned to the terminal

[1265] Specific operation: The server retrieves data from the database and sends it to the terminal in JSON format.

[1266] Step 8:

[1267] The device displays the received data on its screen. Users can repeatedly learn from this question-and-answer data.

[1268] Input: JSON data returned from the server

[1269] Output: Pairs of questions and answers displayed on the screen

[1270] Specific operation: The device displays question and answer pairs it has acquired on the screen, and the user learns by looking at them.

[1271] Example of a prompt

[1272] The following are examples of prompts to input into the generating AI model for this system.

[1273] Please explain this system in detail. The system uses voice input to create personalized question-and-answer format data to support learning. The user launches the app and inputs questions and answers by voice. The voice data is converted to text on the device, sent to a server, and stored. When the user selects a learning mode, the data is retrieved from the server and displayed on the device, and the user learns by repeating it.

[1274] (Application Example 1)

[1275] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1276] Traditional factory training and feedback systems have made it difficult to efficiently learn work procedures. Furthermore, the lack of real-time evaluation and feedback creates an environment prone to human error. Therefore, there is a need for a system that improves worker learning efficiency and work accuracy.

[1277] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1278] In this invention, the server includes a feedback means for efficiently learning factory work procedures, a means for performing real-time evaluations using a generative AI model, and a means for displaying acquired text data. This enables workers to learn procedures through voice input and receive appropriate feedback in real time.

[1279] "Voice input means" refers to a device or system that has the function of capturing voice data and converting it into an appropriate format.

[1280] "Methods for converting speech to text" refer to technologies that automatically analyze input speech data and convert it into a corresponding text format.

[1281] "Means of sending text data to a server" refers to the technology of transferring converted text data to a server via a network.

[1282] "Methods for saving text data on a server" refers to technologies that store received text data in a database or storage device, making it accessible for retrieval as needed.

[1283] "Methods for retrieving text data from a server" refers to technologies that retrieve stored text data from a server in response to requests.

[1284] "Means for displaying acquired text data" refers to a system that visually displays the extracted text data through a user interface.

[1285] A "feedback system for efficiently learning factory work procedures" is a system that provides real-time evaluation and appropriate advice and instructions to help workers learn the correct procedures.

[1286] "A method for performing real-time evaluation using a generative AI model" refers to a technology that uses an artificial intelligence model to evaluate the accuracy and progress of work in real time and provide immediate feedback.

[1287] The present invention is a system for efficiently learning factory work procedures and providing real-time feedback. This system includes a voice input means, a means for converting voice to text, a means for sending text data to a server, a means for storing text data on the server, a means for retrieving text data from the server, a means for displaying the retrieved text data, a feedback means for efficiently learning factory work procedures, and a means for performing real-time evaluation using a generative AI model.

[1288] Voice input method

[1289] Users input questions and answers by voice using the microphone on their smartphone or tablet while working in the factory. This eliminates the need for traditional handwriting or keyboard input, thus improving work efficiency.

[1290] Means of converting speech to text

[1291] The audio data captured by the voice input method is converted to text using the Python SpeechRecognition library. This method uses a reliable speech recognition engine, such as Google's speech recognition service.

[1292] Means of sending text data to a server

[1293] The data, converted to text, is sent to the server via an HTTP POST request. The request packages the data in JSON format and transfers it to the server over the internet.

[1294] Means for saving text data on a server

[1295] The server stores the received text data in a database. The database contains question-and-answer pairs, allowing for quick retrieval as needed. SQL-based databases are commonly used.

[1296] Means for retrieving text data from a server

[1297] When the user selects learning mode, a request for question-and-answer data stored on the server is sent to the device. The server returns all question-and-answer pairs in JSON format and sends them to the device.

[1298] Means for displaying acquired text data

[1299] The terminal displays the received text data on the user interface. This allows users to learn factory work procedures while visually confirming them.

[1300] A feedback mechanism for efficiently learning factory work procedures.

[1301] Data from factory operations is acquired in real time and evaluated based on accuracy and procedure using a generated AI model. This allows users to receive feedback on the spot and correct their work immediately.

[1302] A method for performing real-time evaluation using generative AI models.

[1303] The generative AI model evaluates work data under various conditions and notifies the user of the results in real time. This model utilizes pre-trained artificial intelligence algorithms and, as a specific example, evaluates whether "assembly is being performed correctly according to the work procedure."

[1304] Specific example

[1305] For example, when a user is learning the steps for a new assembly task, they might voice-input a question like, "In what order should I assemble the following parts?" and receive the response, "Part A, first." This data is converted to text in real time, sent to a server, and stored. Then, when the user selects learning mode, this data is displayed on the device.

[1306] Example of a prompt

[1307] 1. "How can we develop a system that uses voice input for learning work procedures?"

[1308] 2. "How can we use speech recognition to collect questions and answers and provide real-time feedback?"

[1309] As a result, this invention enables factory workers to efficiently learn procedures and receive appropriate feedback in real time.

[1310] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1311] Step 1:

[1312] The user launches an application on their smartphone or tablet and uses voice input. Specifically, they voice-input a question such as, "In what order should I assemble the following parts?" and an answer such as, "Part A, first." This voice data is captured through the microphone on the smartphone or tablet.

[1313] Input: Audio data

[1314] Output: Audio data

[1315] Step 2:

[1316] The device converts the captured audio data into text data using the Python SpeechRecognition library. This audio data is then processed through Google's speech recognition service.

[1317] Input: Audio data

[1318] Output: Text data (Example: "In what order should the following parts be assembled?", "Part A, first")

[1319] Step 3:

[1320] The terminal packages the converted text data into JSON format and sends it to the server using an HTTP POST request.

[1321] Input: Text data

[1322] Output: Text data in JSON format

[1323] Step 4:

[1324] The server saves the received JSON-formatted text data to a database. Each question and answer is recorded in the database as a pair, making it easy to retrieve later.

[1325] Input: Text data in JSON format

[1326] Output: Text data stored in the database

[1327] Step 5:

[1328] When the user selects learning mode, the device requests the stored question-and-answer data from the server. The server retrieves all question-and-answer pairs from the database and returns them to the device in JSON format.

[1329] Input: Request for learning mode

[1330] Output: Question and answer data in JSON format

[1331] Step 6:

[1332] The terminal displays the received question-and-answer data through the user interface. The user visually reviews this data and learns the work procedures.

[1333] Input: Question and answer data in JSON format

[1334] Output: Displayed question-and-answer data

[1335] Step 7:

[1336] During factory work, user actions are evaluated in real time using a generative AI model. The generative AI model assesses the accuracy of the work and sends the results to the terminal.

[1337] Input: User operation data

[1338] Output: Real-time feedback results

[1339] Step 8:

[1340] The device provides feedback to the user based on the evaluation results received from the generated AI model. This allows the user to immediately verify whether their work is correct and make corrections as needed.

[1341] Input: Real-time feedback results

[1342] Output: User feedback

[1343] In this way, the system efficiently learns factory work procedures, performs real-time evaluations, and provides appropriate feedback.

[1344] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1345] This invention is a system designed to help students and working professionals efficiently memorize information needed for exams and work. It utilizes voice input to create personalized question-and-answer format data, and further incorporates an emotion engine to support learning while recognizing the user's emotional state.

[1346] User voice input and terminal processing

[1347] The user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted into text by the speech recognition engine. Simultaneously, the emotion engine analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[1348] Next, the user presses the "Enter Answer" button and enters their answer by voice. This voice data is also acquired by the device and converted into text by the speech recognition engine. In addition, the emotion engine re-analyzes the user's emotions at the time of the answer.

[1349] Sending and storing text data and sentiment data.

[1350] The terminal packages the converted question and answer text data, along with the analyzed sentiment data, into JSON format and sends it to the server. Specifically, it sends data like the following using an HTTP POST request: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "emotions": {"question": "relaxed", "answer": "confident"}}

[1351] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident')

[1352] Data acquisition and display in learning mode

[1353] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format.

[1354] The device displays the received data on its screen. Users can then review the displayed questions and answers, and further assess their own emotional state. This allows users to adjust their learning methods according to their emotional state.

[1355] Specific example

[1356] Consider a scenario where a user wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" They then voice-input "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that they appear "calm" when asking the question and "confident" when answering.

[1357] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[1358] This system allows users to efficiently create question-and-answer formatted data using voice input, and also enables them to learn while understanding their own emotional state with the help of an emotion engine.

[1359] The following describes the processing flow.

[1360] Step 1:

[1361] The user launches the application. The user presses the "Enter Question" button in the application and enters the question by voice. For example, they might say, "What is the tallest mountain in the world?"

[1362] Step 2:

[1363] The device acquires voice data through its microphone. The acquired voice data is converted into text by the device's speech recognition engine. The text is recognized as "What is the tallest mountain in the world?".

[1364] Step 3:

[1365] The user presses the "Enter Answer" button and speaks the answer "Everest" aloud.

[1366] Step 4:

[1367] The device acquires the voice data of the response and converts it into text, "Everest," using a speech recognition engine. Simultaneously, an emotion engine analyzes the user's voice to analyze emotional data, for example, recognizing "confident."

[1368] Step 5:

[1369] The device packages the question and answer, along with the analyzed sentiment data, into JSON format. Example: {"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}

[1370] Step 6:

[1371] The device sends JSON data to the server as an HTTP POST request. This request includes a question, an answer, and corresponding sentiment data.

[1372] Step 7:

[1373] The server receives an HTTP POST request and parses the JSON data. From the parsed data, it extracts question, answer, and sentiment data.

[1374] Step 8:

[1375] The server connects to the database and saves the extracted question, answer, and sentiment data as new records. Example: INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Mount Everest', 'calm', 'confident')

[1376] Step 9:

[1377] The user selects learning mode. The user presses the "Start Anti-Mode" button.

[1378] Step 10:

[1379] The device sends an HTTP GET request to the server to request the data necessary for learning. Example: / get_all_qa

[1380] Step 11:

[1381] The server receives an HTTP GET request and retrieves all question-and-answer pairs, along with their corresponding sentiment data, from the database. The retrieved data is then converted to JSON format.

[1382] Step 12:

[1383] The server returns JSON data to the terminal as an HTTP response. Example: [{"question": "What is the tallest mountain in the world?", "answer": "Mount Everest", "question_emotion": "calm", "answer_emotion": "confident"}, ...]

[1384] Step 13:

[1385] The terminal receives a response from the server and parses the JSON data. It extracts the question and answer, as well as sentiment data, and displays it on the screen.

[1386] Step 14:

[1387] Users learn through repetition by viewing the displayed questions and answers, as well as sentiment data. For example, in addition to the question "What is the tallest mountain in the world?" and the answer "Mount Everest," sentiment data such as "When asked: calm" and "When answering: confident" is displayed. Based on this information, users can understand and optimize their learning progress.

[1388] (Example 2)

[1389] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1390] Conventional memorization systems not only struggled with voice input, but also lacked the means to understand the user's emotional state and enhance learning effectiveness. This made it difficult to adjust the learning process appropriately, resulting in challenges in efficient memorization.

[1391] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1392] In this invention, the server includes means for converting speech to text, means for analyzing emotional data from the speech, and means for transmitting the converted text data and the analyzed emotional data to the server. This allows the user to efficiently perform voice input and to progress with learning while understanding their own emotional state.

[1393] "Voice input means" refers to a method for users to input questions and answers by voice, and involves using input devices such as microphones.

[1394] "Means for converting speech to text" refers to methods for converting acquired speech data into text data, and utilizes speech recognition technology.

[1395] "Methods for analyzing emotional data from voice" refer to methods for analyzing a user's emotional state from voice data, and utilize technologies that analyze acoustic characteristics such as tone, pitch, and speed.

[1396] "Means for sending converted text data and analyzed sentiment data to a server" refers to means for packaging and sending data to a server after audio data has been converted to text data and sentiment data has been analyzed.

[1397] "Means of storing text data and sentiment data on a server" refers to means of storing received text data and sentiment data in a database or similar system for proper preservation.

[1398] "Means for retrieving text data and sentiment data from a server" refers to the means of retrieving stored text data and sentiment data from a server and sending them back to the terminal.

[1399] "Means for displaying acquired text data and sentiment data" refers to means for displaying text data and sentiment data acquired by the user on their device so that they can visually confirm them.

[1400] This invention is a system that efficiently creates question-and-answer format data using voice input and further supports learning while recognizing the user's emotional state. This system includes voice input means, a voice recognition engine, emotion analysis means, data transmission means, data storage means, data acquisition means, and data display means.

[1401] First, the user launches the application and presses the "Enter Question" button to input a question by voice. For example, they might say, "What is the tallest mountain in the world?" This voice data is captured by the device's microphone and converted to text by a speech recognition engine such as the Google Speech-to-Text API. Simultaneously, using an emotion engine such as the Affectiva SDK, the device analyzes emotional data (e.g., tension, joy, calmness, etc.) from the user's voice.

[1402] Next, the user presses the "Enter Answer" button and enters their answer by voice. For example, they might say "Everest." This voice data is also captured by the device's microphone and converted into text by the speech recognition engine. The emotion engine also analyzes the user's emotional state at the time of the answer. The results of this analysis are obtained in the same way as when the question was asked.

[1403] These converted text data (questions and answers) and analyzed sentiment data are packaged in JSON format by the terminal and sent to the server using an HTTP POST request. For example, the following data is sent:

[1404] json

[1405] {

[1406] "Question": "What is the tallest mountain in the world?"

[1407] "answer": "Everest",

[1408] "emotions": {

[1409] "question": "relaxed",

[1410] "answer": "confident"

[1411] }

[1412] }

[1413] The server receives this data and extracts the question, answer, and sentiment data from the JSON. The server connects to the database and saves this data as new records. For example, it executes the following SQL query:

[1414] sql

[1415] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[1416] When a user selects a learning mode, the device sends an HTTP GET request to the server, requesting stored question-and-answer data and sentiment data. The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the device in JSON format. The device displays the received data on the screen. The user can check their own sentiment state while viewing the displayed questions and answers. This allows the user to adjust the learning method according to their sentiment state.

[1417] As a concrete example, consider a user who wants to memorize element symbols for a chemistry exam. The user launches the app, presses the "Input Question" button, and voice-inputs the question, "What is the element symbol for carbon?" Then, voice-inputs the answer, "C". At this point, the emotion engine analyzes the user's voice to determine their emotions. For example, it might analyze that the user is "calm" when asking the question and "confident" when answering.

[1418] This data is stored on the server, and later, when the user starts learning mode, it will display "What is the chemical symbol for carbon? -> C," along with information such as "Emotion at the time of the question: Calm" and "Emotion at the time of the answer: Confidence." Based on this, the user can optimize their learning process.

[1419] Furthermore, it is possible to analyze user voice data using generative AI models. For example, by inputting prompts like the following, the generative AI model can be guided through the data creation process in a natural conversational format, supporting the effective operation of the system:

[1420] Please ask the question aloud, "What is the capital of France?" Then, answer aloud, "Paris." When doing so, ask the question in a relaxed tone and answer with confidence.

[1421] This system allows users to efficiently create question-and-answer formatted data using voice input, and also enables them to learn while understanding their own emotional state with the help of an emotion engine.

[1422] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1423] Step 1:

[1424] The user launches the application, presses the "Enter Question" button, and enters the question by voice.

[1425] Input: User's voice question (e.g., "What is the tallest mountain in the world?")

[1426] Operation: The device uses the microphone to acquire audio data.

[1427] Step 2:

[1428] The device uses a speech recognition engine (for example, Google Speech-to-Text API) to convert speech data into text data.

[1429] Input: Audio data

[1430] Operation: The speech recognition engine analyzes the audio data and converts it into corresponding text data (e.g., "What is the tallest mountain in the world?").

[1431] Output: Text data (Example: "What is the tallest mountain in the world?")

[1432] Step 3:

[1433] The device uses an emotion engine (e.g., Affectiva SDK) to analyze emotion data from the user's voice.

[1434] Input: Audio data

[1435] Operation: The emotion engine analyzes acoustic features such as tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "calm").

[1436] Output: Emotional data (e.g., "calmness")

[1437] Step 4:

[1438] The user presses the "Enter Answer" button and enters their answer by voice.

[1439] Input: User's voice response (e.g., "Everest")

[1440] Operation: The device uses the microphone to acquire audio data.

[1441] Step 5:

[1442] The device then uses the speech recognition engine again to convert the speech data into text data.

[1443] Input: Audio data

[1444] Operation: The speech recognition engine analyzes the audio data and converts it into the corresponding text data (e.g., "Everest").

[1445] Output: Text data (e.g., "Everest")

[1446] Step 6:

[1447] The device then uses the emotion engine again to analyze emotional data from the user's voice.

[1448] Input: Audio data

[1449] Operation: The emotion engine analyzes acoustic features such as tone, pitch, and speed of the voice to identify the user's emotional state (e.g., "confidence").

[1450] Output: Sentiment data (e.g., "confidence")

[1451] Step 7:

[1452] The terminal packages the converted question and answer text data, as well as the analyzed sentiment data, into JSON format.

[1453] Input: Text data of questions and answers, sentiment data

[1454] Operation: Converts data to JSON format and creates a package like the one below.

[1455] json

[1456] {

[1457] "Question": "What is the tallest mountain in the world?"

[1458] "answer": "Everest",

[1459] "emotions": {

[1460] "question": "relaxed",

[1461] "answer": "confident"

[1462] }

[1463] }

[1464] Output: JSON package

[1465] Step 8:

[1466] The terminal uses an HTTP POST request to send the JSON package to the server.

[1467] Input: JSON package

[1468] Operation: Creates an HTTP POST request and sends data to the server.

[1469] Output: Data received on the server side.

[1470] Step 9:

[1471] The server parses the received JSON package and extracts question, answer, and sentiment data.

[1472] Input: JSON package

[1473] Operation: Parses JSON data and extracts the necessary data fields.

[1474] Output: Question, answer, sentiment data

[1475] Step 10:

[1476] The server connects to the database and stores the question, answer, and sentiment data as new records.

[1477] Input: Question, answer, sentiment data

[1478] Operation: Establish a database connection and execute an SQL query like the following.

[1479] sql

[1480] INSERT INTO qa_table (question, answer, question_emotion, answer_emotion) VALUES ('What is the tallest mountain in the world?', 'Everest', 'relaxed', 'confident');

[1481] Output: A new record is stored in the database.

[1482] Step 11:

[1483] When the user selects learning mode, the device sends an HTTP GET request to the server, requesting the saved question-and-answer data and sentiment data.

[1484] Input: Learning mode selection operation

[1485] Action: Creates an HTTP GET request and sends it to the server.

[1486] Output: The server receives the request.

[1487] Step 12:

[1488] The server retrieves all question-and-answer pairs and sentiment data from the database and sends them back to the terminal in JSON format.

[1489] Input: Database Request

[1490] Operation: Executes a database query and converts the retrieved data into JSON format.

[1491] Output: Data in JSON format

[1492] Step 13:

[1493] The device parses the received JSON data and displays the question, answer, and sentiment data on the screen.

[1494] Input: Data in JSON format

[1495] Function: Parses JSON data and converts it into a format for visual display.

[1496] Output: Questions, answers, and sentiment data displayed on the screen.

[1497] (Application Example 2)

[1498] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1499] There is a need for support methods to help factory workers efficiently and reliably memorize the operation and maintenance procedures of new machinery. While current systems allow for the creation of question-and-answer formatted data via voice input, they fail to consider the emotional state of the workers. This makes it difficult to provide optimal learning methods tailored to each worker's learning progress and emotions, potentially leading to decreased learning efficiency.

[1500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for storing text data and emotion data, means for acquiring text data and emotion data, and means for displaying the acquired text data and emotion data. This makes it possible not only to create data in a question-and-answer format using voice input, but also to analyze the emotional state of engineers and provide an optimal learning method according to their emotions.

[1501] "Voice input means" refers to an apparatus that includes a device for acquiring the user's voice and software for processing that voice data.

[1502] A "speech recognition engine" is software that analyzes acquired audio data and converts it into text data.

[1503] An "emotion engine" is software that analyzes a user's emotions from voice data and acquires them as emotion data.

[1504] "Text data" refers to character information generated from speech by a speech recognition engine.

[1505] "Emotional data" refers to information about a user's emotional state, analyzed by an emotion engine.

[1506] A "server" is a central computer that stores text data and sentiment data, and transmits this data to user terminals as needed.

[1507] An "HTTP request" is a communication protocol used to send and receive data between a client and a server.

[1508] "Acquisition means" refers to the methods and devices used to obtain necessary data from a server.

[1509] "Display means" refers to a device or software for visually displaying text data and sentiment data on a user's terminal.

[1510] "Question and answer format" refers to a data format where a question and an answer are presented as a pair.

[1511] Modes for carrying out the invention

[1512] This invention provides a support system for engineers to memorize the operation and maintenance procedures of new machinery. This system is implemented using voice input means, a speech recognition engine, an emotion engine, a server, and HTTP requests.

[1513] Voice input and processing

[1514] The user inputs questions and answers using voice input. At this time, the speech recognition engine converts the voice data into text data, and the emotion engine analyzes the user's emotional state to obtain emotion data.

[1515] Sending and storing data

[1516] The device sends the acquired text data and sentiment data to the server via an HTTP request. The server stores the received data in a database. Specifically, it packages the text data and sentiment data into JSON format and sends it to the server via a POST request.

[1517] Data acquisition and display

[1518] The server retrieves stored text and sentiment data in response to HTTP GET requests from the user. This data is sent to the device, which displays the retrieved data on its screen. Based on the displayed data, the user learns and adjusts their learning method based on the information about their sentiment state.

[1519] Examples of specific cases and prompt statements

[1520] For example, a technician learning how to operate a new machine might voice-input a question like, "Where is the start button on this machine?" and then voice-input the answer, "Bottom left of the right panel." This voice data is converted into text data, and emotional data such as "anxiety" during the question and "confirmation" during the answer is analyzed. This data is stored on a server and can later be reviewed by the user in learning mode.

[1521] The following are examples of prompt messages.

[1522] "I'm designing a question-and-answer style learning application for engineers to memorize how to operate new machinery. Users input questions and answers via voice, and sentiment data analyzed by an emotion engine is also saved. When the user enters learning mode, the questions, answers, and sentiment data are displayed. Please generate the program for this application."

[1523] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1524] Step 1:

[1525] The user inputs their question by voice using a voice input device. The terminal acquires this voice data and converts it into text data using a speech recognition engine. At the same time, an emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[1526] Step 2:

[1527] The user then uses a voice input device to enter their response by voice. The terminal acquires this voice data and uses a speech recognition engine to convert it into text data. Similarly, the emotion engine analyzes the voice data and acquires the user's emotion data. The input is voice data, and the output is text data and emotion data.

[1528] Step 3:

[1529] The terminal packages the converted text data and analyzed sentiment data into JSON format and sends this data to the server using an HTTP POST request. The input is text data and sentiment data, and the output is an HTTP request to the server.

[1530] Step 4:

[1531] The server receives an HTTP POST request, parses the JSON data, and extracts the question, answer, and their respective sentiment data. This data is then stored in a database. The input is JSON data, and the output is the data stored in the database.

[1532] Step 5:

[1533] When the user selects learning mode, the device sends an HTTP GET request to the server to retrieve stored question-and-answer formatted text data and sentiment data. The input is the HTTP GET request, and the output is the data retrieval request to the server.

[1534] Step 6:

[1535] The server retrieves text and sentiment data stored in the database and sends them back to the terminal in JSON format. The input is a request to read data from the database, and the output is the return of the retrieved data in JSON format.

[1536] Step 7:

[1537] The device parses the received JSON data and displays question-and-answer pairs and corresponding sentiment data on the screen. The user learns from this and adjusts the learning method based on their own sentiment state. The input is JSON data, and the output is the text data and sentiment data displayed on the screen.

[1538] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1539] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1540] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1541] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1542] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1543] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1544] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1545] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1546] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1547] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1548] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1549] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1550] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1551] 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.

[1552] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1553] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1554] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1555] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1556] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1557] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1558] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1559] The following is further disclosed regarding the embodiments described above.

[1560] (Claim 1)

[1561] Voice input method,

[1562] A means of converting speech to text,

[1563] A means of sending text data to a server,

[1564] A means of saving text data on a server,

[1565] A means of obtaining text data from a server,

[1566] A means of displaying the acquired text data,

[1567] A system that includes this.

[1568] (Claim 2)

[1569] The system according to claim 1, wherein the voice input means converts speech to text using a speech recognition engine.

[1570] (Claim 3)

[1571] The system according to claim 1, which sends text data to a server via an HTTP request.

[1572] "Example 1"

[1573] (Claim 1)

[1574] Voice input method,

[1575] A means of converting speech to text,

[1576] A means of sending the converted text data to the server,

[1577] A means of saving text data on a server,

[1578] A means of retrieving text data stored from the server,

[1579] A means of displaying the acquired text data,

[1580] A means of saving and displaying questions and answers entered by the user via voice in a question-and-answer format,

[1581] A system that includes this.

[1582] (Claim 2)

[1583] The system according to claim 1, wherein the voice input means converts speech to text using speech recognition technology.

[1584] (Claim 3)

[1585] The system according to claim 1, which sends text data to a server via an HTTP request.

[1586] "Application Example 1"

[1587] (Claim 1)

[1588] Voice input method,

[1589] A means of converting speech to text,

[1590] A means of sending text data to a server,

[1591] A means of saving text data on a server,

[1592] A means of obtaining text data from a server,

[1593] A means of displaying the acquired text data,

[1594] A feedback mechanism for efficiently learning factory work procedures,

[1595] A method for performing real-time evaluation using a generative AI model,

[1596] A system that includes this.

[1597] (Claim 2)

[1598] The system according to claim 1, wherein the voice input means converts speech to text using a speech recognition engine.

[1599] (Claim 3)

[1600] The system according to claim 1, which sends text data to a server via an HTTP request.

[1601] "Example 2 of combining an emotion engine"

[1602] (Claim 1)

[1603] Voice input method,

[1604] A means of converting speech to text,

[1605] Methods for analyzing emotional data from voice,

[1606] A means for sending the converted text data and analyzed sentiment data to a server,

[1607] A means of storing text data and sentiment data on a server,

[1608] A means of obtaining text data and sentiment data from a server,

[1609] A means of displaying acquired text data and sentiment data,

[1610] A system that includes this.

[1611] (Claim 2)

[1612] The system according to claim 1, wherein the voice input means converts speech to text using a speech recognition engine.

[1613] (Claim 3)

[1614] The system according to claim 1, which sends text data and sentiment data to a server via an HTTP request.

[1615] "Application example 2 when combining with an emotional engine"

[1616] (Claim 1)

[1617] Voice input method,

[1618] A means of converting speech to text,

[1619] Means for sending text data and sentiment data to a server,

[1620] A means of storing text data and sentiment data on a server,

[1621] A means of obtaining text data and sentiment data from a server,

[1622] A means for displaying acquired text data and sentiment data,

[1623] A system that includes this.

[1624] (Claim 2)

[1625] The system according to claim 1, wherein the voice input means converts voice into text and emotion data using a voice recognition engine and an emotion engine.

[1626] (Claim 3)

[1627] The system according to claim 1, which sends text data and sentiment data to a server via an HTTP request. [Explanation of Symbols]

[1628] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Voice input method, A means of converting speech to text, A means of sending text data to a server, A means of saving text data on a server, A means of obtaining text data from a server, A means of displaying the acquired text data, A system that includes this.

2. The system according to claim 1, wherein the voice input means converts speech to text using a speech recognition engine.

3. The system according to claim 1, which sends text data to a server via an HTTP request.

Images