System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring lecture contents of another training lecturer as video recording data, a means for converting the video recording data into transcription data by using a voice recognition tool, a means for converting the transcription data into summary data by using a summarization tool, a means for storing and managing the summary data, and a means for making the stored summary data browsable.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The quality of training is reduced by the inconsistency in the skills of training instructors and the differences in the content taught by each instructor. However, since attending lectures by other instructors takes up a lot of work time, it is currently difficult to effectively improve the content of lectures. A new approach is needed to solve these issues and maximize the overall effectiveness of training. [Means for solving the problem]

[0005] This invention relates to a system that includes a means for acquiring lecture content from other instructors as video recording data, a means for converting the video recording data into transcription data using a speech recognition tool, a means for converting the transcription data into summary data using a summarization tool, a means for saving and managing the summary data, and a means for making the saved summary data available for viewing. The system also includes a means for providing a user interface for viewing the summary data and for supporting the instructor in improving the content of the lecture. The system may further include a means for assigning student ratings to the summary data and displaying highly rated summary data as recommended data. This configuration allows instructors to effectively refer to the excellent lecture content of other instructors and improve their own lectures. This can also be expected to result in an overall improvement in the quality of lectures.

[0006] "Recorded data" refers to data in which the contents of a lecture given by a training instructor are recorded in audio and video format.

[0007] A "voice recognition tool" is software that analyzes voice data and transcribes it into language data.

[0008] "Transcription data" is text data generated from audio data analyzed by a speech recognition tool.

[0009] A "summary tool" is software that analyzes long text data, extracts important points and themes, and summarizes them concisely.

[0010] "Summary data" is text data generated by a summarization tool that summarizes important points and themes.

[0011] "Means for enabling browsing" refers to means for providing a user interface or function that allows a user to access the stored data and display its contents.

[0012] "Means of storage and management" refers to the means of storing the generated data in a database or file system and keeping it accessible as needed.

[0013] A "user interface" is a means for providing a screen and input functions that allow a user to interact with a system and perform necessary operations.

[0014] "Student evaluation" refers to data in which students provide feedback on the content of the lecture and the instructor, and evaluate their satisfaction and effectiveness.

[0015] "Recommended data" refers to data that has received a superior evaluation compared to other data, and is data that the system particularly recommends for reference. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[0038] Acquiring Recording Data

[0039] Device:

[0040] Lecturers record their lectures and upload the recordings to a server. The recordings contain audio and video, detailing the entire lecture. The recordings are then sent to the server via a dedicated application or web portal.

[0041] Transcription processing

[0042] server:

[0043] The server receives the uploaded recording data and transcribes it using a speech recognition tool. The speech recognition tool has the function of converting the audio portion of the recording data into text data. For example, if a recording data called "lecture123.mp4" is uploaded, the server will use the speech recognition tool to convert the entire content of the lecture into text data.

[0044] Summary Generation

[0045] server:

[0046] The generated transcript data is then converted into summary data using a summarization tool. The summarization tool extracts important points and themes from long text data and generates a concise summary. This summary data compactly summarizes the main content of the lecture.

[0047] Summary data storage and management

[0048] server:

[0049] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed.

[0050] Viewing summary data

[0051] User (instructor):

[0052] Lecturers can view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to the summary data of other lecturers to identify areas for improvement in their own lectures.

[0053] Reflection of participant evaluations

[0054] server:

[0055] Furthermore, the system has the function of adding student evaluation data to the summary data and displaying highly rated summaries as especially recommended data. Student evaluations are based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summaries to the instructor.

[0056] Specific examples

[0057] 1. Uploading the recording data

[0058] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[0059] 2. Transcription and summary generation

[0060] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[0061] 3. Storage and management of summary data

[0062] The server stores the generated summary data and the lecture ID together in a database.

[0063] 4. Viewing summaries by other instructors

[0064] The user (lecturer) searches for the summary data of "lecture123" through the dedicated portal and checks the content on the display screen.

[0065] 5. Displaying highly rated summary data

[0066] The server analyzes the student evaluations and displays the summary data with the highest evaluations as particularly recommended data on the portal of each instructor.

[0067] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. It is also expected to increase student satisfaction.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0071] Step 2:

[0072] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[0073] Step 3:

[0074] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[0075] Step 4:

[0076] Server: The server then calls the summarization tool, which converts the transcription data into summary data. The summarization tool analyzes the transcription data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0077] Step 5:

[0078] Server: The server saves the summary data in a database. When saving, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[0079] Step 6:

[0080] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The detected summary data is displayed on the screen, and the instructor can view its contents.

[0081] Step 7:

[0082] Server: The server collects and analyzes student evaluations of the summary data. Students evaluate the lecture after it is over, and the evaluation data is sent to the server and stored in a database.

[0083] Step 8:

[0084] Server: The server selects the highly rated summary data as recommended data based on the evaluation data. This recommended data is displayed specially when the user (instructor) views the summary data, and is used as a reference by other instructors.

[0085] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures, thereby improving the quality of the overall training.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] In the past, training instructors had few ways to efficiently refer to the content of other instructors' lectures and improve their own. As a result, it was difficult to improve the quality of the lecture content and share information between instructors, which often hindered efficient training management. There was also a lack of feedback based on trainee evaluations and recommended lecture information.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes means for acquiring lecture records, means for converting the lecture records into text data using a speech recognition device, means for converting the text data into concise content using a summary generation device, means for storing and managing the concise content in a storage device, and means for making the stored concise content accessible using a display device. This allows training instructors to efficiently refer to the content of other instructors' lectures, improve their own content, and provide feedback based on the students' evaluations.

[0091] "Lecture recording" refers to video or audio data of the content of a lecture given by a training instructor.

[0092] A "voice recognition device" refers to software or hardware for converting voice data into text data.

[0093] "Text data" refers to data containing character information converted by a voice recognition device.

[0094] A "summary generator" refers to software or hardware that extracts important points from long text data and converts them into concise content.

[0095] "Concise content" refers to the summary data created by the summary generator.

[0096] "Storage" refers to data storage for saving generated concise content and making it accessible when needed.

[0097] "Display device" refers to a device or software that includes an interface that allows a user to view stored concise content.

[0098] "User interface" refers to the screens and input devices through which a user interacts with a system and manipulates and views information.

[0099] "Participant evaluation" refers to the evaluation made by participants of the lecture on the lecture content and the lecturer's performance.

[0100] "Recommended information" refers to information for displaying to other users concise content that has received particularly high ratings based on participant ratings.

[0101] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[0102] Acquiring Recording Data

[0103] Device: Lecturers record their lectures using a dedicated recording application. The recording data includes both audio and video, and records the entire lecture in detail. After recording is complete, the lecturer uploads the recording data to the server via a dedicated application or web portal. For example, a lecturer records "Lecture 123" and sends the recording file "lecture123.mp4" to the server using an application.

[0104] Receiving recording data

[0105] Server: The server receives the uploaded recording data. The received data is temporarily stored in the server's storage. This allows the server to confirm the existence of the recording data. For example, the server receives a file called "lecture123.mp4" and temporarily stores it in a specified directory.

[0106] Transcription processing

[0107] Server: The server uses a speech recognition tool (e.g., Google Cloud Speech-to-Text) to convert the audio portion of the recorded data into text data. The server first extracts the audio portion and sends it to the speech recognition tool. The converted text data is temporarily stored. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[0108] Summary Generation

[0109] Server: The server inputs the transcribed text data into a summarization tool (e.g., OpenAI GPT-3) to generate summary data. The server generates a specific prompt and sends it to the summarization tool. The generated summary data is saved. For example, the server requests a summary using the following prompt:

[0110] prompt:

[0111] Summarize the following text:

[0112] "Hello, today's lecture will cover database basics. First..."

[0113] OpenAI GPT-3 provides the summary, and the server stores the summary data: "About the basics of databases..."

[0114] Summary data storage and management

[0115] Server: The server stores the generated summary data in a database (e.g., MySQL). The summary data is also stored here along with metadata such as the lecture ID and lecturer name. For example, the server stores the summary data "On the Fundamentals of Databases..." in the database along with the lecture ID "lecture123."

[0116] Viewing summary data

[0117] User (instructor): Instructors access the database through a dedicated application or web portal to search and view abstracts. The user interface is intuitive and designed to make it easy to find the information they need. The instructor types "lecture123" into the search box and the related abstract, "Database Fundamentals...," is displayed.

[0118] Reflection of participant evaluations

[0119] Server: The server collects evaluation data from students and associates it with the summary data. It analyzes the evaluation data and manages the highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When the instructor accesses the portal, the recommended data is prominently displayed.

[0120] By utilizing generative AI models and prompts, this system allows instructors to efficiently refer to other instructors' lecture content and improve the quality of their own lectures. It also provides feedback based on student evaluations, contributing to increased student satisfaction.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1: Obtaining Recording Data

[0123] Terminal: The lecturer records the lecture using a dedicated recording application. After the recording is complete, the recorded data (input) is uploaded to the server (output) via the dedicated application or web portal. For example, if you record "Lecture 123," the recording file "lecture123.mp4" is sent to the server using the application.

[0124] Step 2: Receive recording data

[0125] Server: The server receives the uploaded recording data (input) and temporarily stores it in the server's storage (output). For example, a file called "lecture123.mp4" is received and temporarily stored in the specified directory " / uploads / lecture123.mp4." This allows the server to confirm the existence of the recording data.

[0126] Step 3: Transcription processing

[0127] Server: The server receives recorded data (input) and converts the audio portion into text data (output) using a speech recognition tool (e.g., Google Cloud Speech-to-Text). Specifically, the server first extracts the audio portion from the recorded data and sends it to the speech recognition tool. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[0128] Step 4: Summary generation

[0129] Server: The server inputs the transcribed text data (input) into a summarization tool (e.g., OpenAI GPT-3) and generates summary data (output). Specifically, the server generates a prompt and sends it to the summarization tool. The generated summary data is saved. For example, the following prompt can be used to request a summary:

[0130] prompt:

[0131] Summarize the following text:

[0132] "Hello, today's lecture will cover database basics. First..."

[0133] Based on the prompt, OpenAI GPT-3 provides a summary, and the server retrieves the summary data: "About the basics of databases..."

[0134] Step 5: Storing and managing summary data

[0135] Server: The server saves the generated summary data (input) in a database (e.g., MySQL) (output). Here, the summary data is saved along with metadata such as the lecture ID and lecturer name. For example, the summary data "On the Fundamentals of Databases..." is stored in the database along with the lecture ID "lecture123."

[0136] Step 6: View summary data

[0137] User (instructor): The instructor accesses the database through a dedicated application or web portal to search and view abstract data (input) (output). The user interface is intuitive and designed to make it easy to find the information needed. The instructor types "lecture123" in the search box and the related abstract data, "Database Fundamentals...," is displayed.

[0138] Step 7: Reflecting student evaluations

[0139] Server: The server collects evaluation data from students (input) and associates it with summary data (output). It analyzes the evaluation data and manages highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When a lecturer accesses the portal, the recommended data is prominently displayed.

[0140] (Application example 1)

[0141] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0142] Training personnel at factories lack the means to easily refer to the training content of other trainers and quickly and effectively improve their own training methods. Furthermore, the efficiency of improving training content by reflecting trainee evaluations is also low. This results in a decline in the quality of training and hinders improvements in production efficiency and safety.

[0143] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0144] In this invention, the server includes means for acquiring the training content of other trainers as recorded data, means for converting the recorded data into transcription data using a voice recognition tool, means for converting the transcription data into summary data using a summarization tool, means for saving and managing the summary data, means for making the saved summary data available for viewing, and means for including recorded data used for training on the operation and maintenance of industrial equipment. This allows trainers to quickly refer to the training content of other trainers and efficiently improve their own training methods. Furthermore, trainee evaluations can be efficiently reflected, improving the quality of training.

[0145] A "training instructor" is a person who is responsible for teaching other employees about the operation and maintenance of equipment within a factory.

[0146] "Recorded data" refers to digital data that records the contents of lectures and training given by training instructors in audio and video format.

[0147] A "voice recognition tool" is software or hardware that converts the audio portion of recorded data into text data.

[0148] "Transcription data" refers to text data converted from audio data using a speech recognition tool.

[0149] A "summary tool" is software that extracts important points and themes from long text data and generates a concise summary.

[0150] "Summary data" is text data generated by a summarization tool that briefly summarizes the main points of lectures or training content.

[0151] "Storage and management means" means means for safely and efficiently storing and managing Abstract Data, including databases and storage systems.

[0152] "Means for making it viewable" means means for providing a function to search and display the stored summary data through a user interface.

[0153] "Industrial equipment" refers to machines and facilities used in production and maintenance in factories.

[0154] "Participant evaluation" is an evaluation made by employees who have received training about the training content and instructor, and is provided in the form of numbers and comments.

[0155] This invention is a system that allows in-plant trainers to effectively refer to training materials and improve their own training methods. This system acquires recorded lecture data and provides functions for efficiently generating, managing, and viewing summary data using voice recognition and summarization tools.

[0156] The server performs the following main processes. First, it acquires the contents of lectures given by in-plant training instructors as recorded data. The recorded data is about the operation and maintenance of factory equipment and is usually recorded using a device equipped with a camera and microphone. After the training is completed, this recorded data is uploaded to the server via a dedicated application.

[0157] The server then converts the uploaded recordings into transcripts using a speech recognition tool (e.g., Google Cloud Speech-to-Text). The speech recognition tool analyzes the audio portion of the recordings and converts them into text. The transcripts are then stored for further processing.

[0158] The server then converts the generated transcript data into summary data using a summarization tool (e.g., OpenAI GPT-4). The summarization tool extracts key points and themes from the text data and generates a concise summary. This summary effectively captures the main content of the lecture and helps the training instructor quickly grasp the content.

[0159] The generated summary data is stored in a database. The database manages summary data for each lecture, allowing for easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed. This allows training personnel to easily search and refer to the content of lectures given by other lecturers.

[0160] Furthermore, the server has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Student evaluations are given based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summary data to training instructors. This allows instructors to efficiently improve their own training methods.

[0161] For example, if a recording called "lecture123.wav" is uploaded, the server converts the audio into text using Google Cloud Speech-to-Text. Next, OpenAI GPT-4 is used to summarize the transcript, generating a summary such as, "In this lecture, we explained basic maintenance procedures and precautions." This summary is stored in a database, and if it receives high marks from students, it will be displayed to other instructors as a recommended resource.

[0162] An example prompt might be something like, "Summarize the following text: Today we will learn about maintaining factory robots. First..."

[0163] This system allows training instructors to quickly refer to the training content of other trainers and effectively improve their own training methods. It is also possible to efficiently reflect trainee evaluations, which is expected to improve the quality of training.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] The device's built-in camera and microphone record the lectures of the training instructor. The input is the lecture content, and the output is the recorded data. Specifically, the instructor gives an explanation on the operation and maintenance of the equipment, which is then recorded in digital format.

[0167] Step 2:

[0168] The device uploads the recorded data to the server. The input is the recorded data, and the output is the recorded data saved on the server. Specifically, after recording is completed, the data is sent to the server using a dedicated application.

[0169] Step 3:

[0170] The server uses a speech recognition tool to convert the audio portion of the recorded data into transcribed data. The input is the recorded data, and the output is the transcribed data. Specifically, Google Cloud Speech-to-Text is used to analyze the audio data and generate text data.

[0171] Step 4:

[0172] The server converts the generated transcription data into summary data using a summarization tool. The input is transcription data, and the output is summary data. Specifically, OpenAI GPT-4 is used to extract key points and generate summaries.

[0173] Step 5:

[0174] The server stores and manages the generated summary data in a database. The input is summary data, and the output is summary data stored in the database. Specifically, the summary data is registered in the database along with the lecture ID and lecturer name.

[0175] Step 6:

[0176] Users access the database through a dedicated user interface and view the summary data. The input is a search query from the user interface, and the output is summary data as search results. Specifically, users enter a lecture ID or keyword to search for summary data.

[0177] Step 7:

[0178] The server analyzes the students' evaluation data and displays the highly rated summary data as especially recommended data. The input is the students' evaluation data, and the output is the summary data with ratings. Specifically, the server analyzes the evaluation points and comments provided by the students and displays the highly rated summary data on the user interface.

[0179] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0180] This invention combines an emotion engine with a system that allows training instructors to efficiently refer to the content of other instructors' lectures and refine their own lectures. The system performs a series of processes: recording lectures, transcribing them, and generating summaries. Furthermore, when viewing saved summaries, the emotion engine is used to recognize the user's emotions, and the display content can be flexibly adjusted based on those emotions.

[0181] Acquiring Recording Data

[0182] Device:

[0183] The lecturer records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0184] Transcription processing

[0185] server:

[0186] The server receives the recorded data and temporarily stores it. Once the recording data has been received, the transcription process begins. The server calls a speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data, and the generated transcription data is temporarily stored on the server.

[0187] Summary Generation

[0188] server:

[0189] The generated transcription data is then converted into summary data using a summarization tool. The summarization tool analyzes the transcription data, extracts important points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0190] Summary data storage and management

[0191] server:

[0192] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored.

[0193] Viewing summary data

[0194] User (instructor):

[0195] Lecturers view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to other lecturers' summaries to identify areas for improvement in their own lectures. At this time, an emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions. For example, it can identify parts that the lecturer found interesting or uncomfortable while viewing.

[0196] Reflecting emotional data

[0197] server:

[0198] The emotion engine adjusts the content of the summary data based on the emotional data it recognizes. For example, it can highlight parts that are recognized as interesting, or suggest other related materials for parts that are recognized as unpleasant. This improves the accuracy and satisfaction of the information provided to users.

[0199] Reflection of participant evaluations

[0200] server:

[0201] The system has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Students evaluate the lecture after it is over, and the data is sent to the server and stored in a database. The server analyzes this evaluation data and can recommend highly rated summary data to the instructor. Furthermore, emotional data recognized by the emotion engine is also reflected as part of the evaluation. This further improves the fairness and accuracy of the evaluation.

[0202] Specific examples

[0203] 1. Uploading the recording data

[0204] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[0205] 2. Transcription and summary generation

[0206] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[0207] 3. Storage and management of summary data

[0208] The server stores the generated summary data and the lecture ID together in a database.

[0209] 4. Viewing summaries by other instructors

[0210] The user (lecturer) searches for the summary data of "lecture123" through a dedicated portal and checks the content on the display screen. At that time, the emotion engine analyzes the user's facial expressions and tone of voice, and the emotional data is also saved.

[0211] 5. Displaying highly rated summary data

[0212] The server analyzes the student evaluations and emotion data, and displays the highly evaluated summary data as especially recommended data on each instructor's portal.

[0213] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. In addition, the flexible provision of information based on emotional data is expected to improve the quality of learning for students.

[0214] The processing flow will be explained below.

[0215] Step 1:

[0216] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0217] Step 2:

[0218] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[0219] Step 3:

[0220] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[0221] Step 4:

[0222] Server: The server then calls the summarization tool, which converts the transcript into summary data. The summarization tool analyzes the text data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0223] Step 5:

[0224] Server: The generated summary data is saved in a database. When saved, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[0225] Step 6:

[0226] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The search results are displayed, and the summary data can be viewed.

[0227] Step 7:

[0228] User (instructor): While viewing the summary data, the emotion engine analyzes the user's facial expressions and vocal tone. The emotion engine identifies the parts that the user found interesting or unpleasant, and sends the emotion data to the server.

[0229] Step 8:

[0230] Server: The server stores the emotion data recognized by the emotion engine. The emotion data is associated with the summary data and used for future analysis and display adjustments.

[0231] Step 9:

[0232] Server: Based on the emotion data, the server adjusts the content of the summary data displayed. For example, it highlights parts that the user finds interesting, and suggests other related materials for parts that are perceived as unpleasant. This adjustment allows the server to provide information that is tailored to the user's interests.

[0233] Step 10:

[0234] Server: Collects and analyzes student evaluation data, and displays highly rated summary data as especially recommended data. Based on the analysis results of student evaluations and emotion data, highly rated summary data is recommended to the instructor.

[0235] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures. It also enables flexible information provision based on user emotions, which is expected to improve the quality of learning for students.

[0236] Example 2

[0237] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0238] Conventional training systems have the drawback of requiring time and effort to refer to other lecturers' lecture content. Furthermore, they do not provide feedback that reflects the students' feelings and evaluations, making it difficult to improve the lecture content. Furthermore, there is a lack of a way to increase student satisfaction while maintaining the quality of the summary data.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0240] In this invention, the server includes means for acquiring lecture content from other lecturers as recorded data, means for converting the recorded data into transcription data using a speech recognition device, means for converting the transcription data into summary data using a summarization device, means for making the saved summary data viewable, means for recognizing a user's emotions when viewing the summary data and adjusting the display content, and means for collecting student evaluation data on the lecture and recommending highly rated data. This allows lecturers to efficiently refer to the lecture content of other lecturers and improve their own lecture content. Furthermore, flexible feedback reflecting student emotions and evaluations is provided, thereby increasing student satisfaction.

[0241] A "lecturer" is a person who gives a lecture in an educational or training setting.

[0242] "Recorded data" refers to digital data containing video and audio recordings of lecture content.

[0243] A "voice recognition device" is a device or software that analyzes recorded speech and converts it into text data.

[0244] "Transcription data" is text data generated from speech by a speech recognition device.

[0245] A "summarization device" is a device or software that analyzes transcription data, extracts important points and themes, and generates concise summary data.

[0246] "Summary data" is text data that succinctly summarizes the important points and themes of the lecture content.

[0247] A "database" is a system that stores and manages multiple data in an organized manner, making it easy to search and access.

[0248] "Emotion recognition" refers to analyzing a user's facial expressions and tone of voice to identify their emotional state at that moment.

[0249] "Adjusting the display content" means improving the accuracy of information provision by changing or highlighting the content of the summary data in accordance with the user's emotions.

[0250] "Evaluation data" refers to data on evaluations and feedback on the content of a lecture provided by students after the lecture.

[0251] "Recommended data" is data that has been judged to have a particularly high rating from a large amount of evaluation data and is to be recommended to other users.

[0252] This invention combines an emotion engine with a system that allows users to efficiently refer to the lecture content of other lecturers and refine their own lecture content. The system acquires recorded lecture data, transcribes it, and then performs a series of processes to generate a summary. Furthermore, when viewing saved summary data, the emotion engine is used to recognize the user's emotions and provides a function to flexibly adjust the displayed content based on those emotions.

[0253] Acquiring and uploading recording data

[0254] The user (lecturer) records the lecture content and saves the recorded data on their device. Next, they access a dedicated application or web portal and use the upload function for the recorded data. By selecting the recorded data and pressing the upload button, the recorded data is sent to the server. For example, the user uploads "lecture123.mp4" to the server through the dedicated portal.

[0255] Transcription processing

[0256] The server analyzes the received recording data using a speech recognition device (e.g., Google Cloud Speech-to-Text API). The server converts the audio data into text data and temporarily stores the generated transcription data. For example, the server calls a speech recognition tool, analyzes the audio portion of "lecture123.mp4," and transcribes it.

[0257] Summary Generation

[0258] The server analyzes the generated transcript data using a summarization device (e.g., OpenAI GPT-3), extracts important points and themes, and generates summary data. The generated summary data is temporarily stored on the server. For example, the server analyzes "lecture123_transcript.txt" using a summarization tool and generates "lecture123_summary.txt," which summarizes the important points.

[0259] Summary data storage and management

[0260] The server stores the generated summary data in a database. The database manages the summary data for each lecture and also stores metadata such as the lecture ID and lecturer name. For example, the summary data "lecture123_summary.txt" along with the lecture ID and lecturer name is stored in the database.

[0261] Viewing summary data

[0262] Users (lecturers) search for and view summary data through a dedicated application or web portal. The user interface is intuitive and includes a function for viewing the summary data for each lecture. The emotion engine analyzes the user's facial expressions and tone of voice to identify parts that interest or annoy the user. For example, a user can search for "lecture123_summary" through the dedicated portal and view the summary data on the display screen.

[0263] Reflecting emotional data

[0264] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. For example, parts that the user finds interesting are displayed in bold, and parts that the user finds unpleasant are displayed as links to supplementary materials.

[0265] Reflection of participant evaluations

[0266] The server assigns the students' evaluation data to the summary data and displays the highly rated summary data as recommended data. Students evaluate the data after the lecture, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. For example, evaluation data collected from students after the lecture is analyzed, and the highly rated summary data is displayed as recommended data for other lecturers.

[0267] Prompt Sentence Examples

[0268] Use a speech recognition tool to transcribe the recording data "lecture123.mp4" and a summarization tool to generate a summary. This summary data and related metadata will be stored in a database and made available for other lecturers to view. An emotion engine will be used to analyze facial expressions and tone of voice during viewing and adjust the displayed content. Also, based on the student's evaluation, particularly recommended summary data will be displayed.

[0269] This system allows lecturers to efficiently refer to the content of other lecturers' lectures and improve their own lecture content. It also provides flexible feedback that reflects the students' feelings and evaluations, thereby improving student satisfaction.

[0270] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0271] Step 1: Obtain and upload recording data

[0272] A user (lecturer) records their own lecture and saves the recorded data (e.g., "lecture123.mp4") on their device. Next, the user accesses a dedicated application or web portal and uses the upload function for the recorded data. The user selects the recorded data and presses the upload button to send the recorded data to the server. The input is the recorded data, and the output is the recorded data uploaded to the server.

[0273] Specific operation: The user selects the recorded data on the device and clicks the "Upload" button.

[0274] Step 2: Transcription processing

[0275] The server temporarily stores the received recording data. Next, the server calls a speech recognizer (e.g., Google Cloud Speech-to-Text API) to analyze the audio portion of the recording data. The speech recognizer converts the audio data into text data, and the generated transcription data (e.g., "lecture123_transcript.txt") is temporarily stored on the server. The input is the recording data, and the output is the transcription data.

[0276] Specific operation: The server calls the speech recognition API, analyzes the voice data, and saves the generated text data.

[0277] Step 3: Summary generation

[0278] The server analyzes the generated transcription data using a summarization device (e.g., OpenAI GPT-3). The server extracts important points and themes and generates a concise summary (e.g., "lecture123_summary.txt"). The generated summary data is temporarily stored on the server. The input is the transcription data, and the output is the summary data.

[0279] Specific operation: The server calls the summarization device, summarizes the transcription data, and saves the summary data.

[0280] Step 4: Storing and managing summary data

[0281] The server saves the generated summary data in a database. The database manages summary data for each lecture, along with metadata such as lecture ID and lecturer name. The input is the summary data, lecture ID, and lecturer name, and the output is the data saved in the database.

[0282] Specific operation: The server stores and manages the summary data and related metadata in a database.

[0283] Step 5: View summary data

[0284] Users (lecturers) search and view the summary data through a dedicated application or web portal. The user interface is intuitive and has a function to display summary data for each lecture. In addition, an emotion engine analyzes the user's facial expressions and tone of voice to identify parts that showed interest or discomfort. The input is the viewing request and user behavior data, and the output is an adjusted summary display.

[0285] Specific operation: The user searches for summary data through the dedicated portal and checks the summary content on the display screen.

[0286] Step 6: Reflecting emotional data

[0287] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. The input is emotional data and summary data, and the output is a display of the adjusted summary data.

[0288] Specific operation: The server uses an emotion engine to analyze the user's emotions and adjust the displayed content.

[0289] Step 7: Reflecting student evaluations

[0290] The server adds student evaluation data to the summary data and displays the highly rated summary data as recommended data. Student evaluations are conducted after the lecture ends, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. The input is evaluation data and emotional data, and the output is summary data that is displayed as recommended data.

[0291] Specific operation: The server analyzes the evaluation data of the students and displays the summary data of the highly evaluated data as especially recommended data.

[0292] (Application example 2)

[0293] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0294] In today's brick-and-mortar stores, improving customer service quality is crucial to increasing customer satisfaction. However, there is no adequate system in place for store instructors to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, there is no function to automatically adjust the displayed content based on the user's emotions, which can lead to insufficient understanding of the training content. This issue limits each store's efforts to improve customer service quality.

[0295] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0296] In this invention, the server includes: means for acquiring the content of other instructors' lectures as recorded data; means for converting the recorded data into transcription data using a voice recognition tool; means for converting the transcription data into summary data using a summarization tool; means for saving and managing the summary data; means for making the saved summary data viewable; and means including an emotion engine that recognizes the user's emotions when viewing the summary data and adjusts the display content. This allows instructors at each store to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, because the display content is adjusted based on the user's emotions, it is expected that the user's understanding of the training content will deepen and the quality of their customer service will improve.

[0297] "Lecture content of other instructors" refers to all or part of educational materials or presentations used during training or education.

[0298] "Recorded data" refers to digital data that records audio and video.

[0299] "Speech recognition tools" refers to technology or software that converts speech into text.

[0300] "Transcription data" refers to data converted from audio into text format.

[0301] A "summary tool" refers to technology or software that extracts important points from long pieces of text and converts them into short summaries.

[0302] "Summary data" refers to concise text data generated using a summarization tool.

[0303] "Means of storage and management" refers to a system that uses a database or other means to consistently store data and keep it in a state that allows it to be searched or retrieved as needed.

[0304] "Means for making data available for viewing" refers to an interface or mechanism that allows users to easily access and display stored data.

[0305] An "emotion engine" refers to technology or software that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[0306] "User emotion" refers to the emotional state, such as interest, pleasure, or discomfort, shown by the user while browsing.

[0307] "Adjusting the display content" refers to dynamically changing the format or emphasis of displayed information based on the user's emotional state.

[0308] To implement the invention, the following details regarding the server, terminals, and users are provided.

[0309] The server has a means for acquiring lecture content from other instructors as recorded data. The recorded data is digital data containing audio and video and is stored on the server. The server also has a means for converting the recorded data into transcribed data using a speech recognition tool. This conversion uses speech recognition technology and software such as speech_recognition.

[0310] The transcription data is converted into summary data using a summarization tool. This summarization tool uses the transformers library to condense long sentences into short ones. For example, a model called t5-small is used to generate summaries. This extracts key points from the transcription data and generates concise summaries.

[0311] The server has a means for storing and managing the generated summary data, and this is managed using a database. The database stores each summary data and its corresponding metadata, and important information is kept in a state where it can be easily retrieved.

[0312] An interface is also provided that allows users to view the summary data. This interface is accessible through a dedicated application or web portal and is intuitive to use. Users can refer to other instructors' summary data and obtain information to improve their own customer service skills and teaching methods. In addition, an emotion engine analyzes the user's emotional state and dynamically adjusts the displayed content based on that. The emotion engine uses OpenCV to perform facial expression analysis and identify interesting areas and areas for improvement.

[0313] For example, store A uploads a recording of a training session, and the server transcribes it using a speech recognition tool, then uses a summarization tool to generate a concise summary. Users can view this summary through smart glasses, and the emotion engine automatically highlights points of interest.

[0314] As an example of a prompt sentence, the following sentence can be input to the generative AI model:

[0315] "Today's customer service training emphasized the importance of direct communication with customers. In particular, we are required to quickly grasp customer reactions and make suggestions that meet their needs."

[0316] This allows the server to provide optimal information to users through speech recognition, summary generation, emotion analysis, and display content adjustment. This system will help improve customer service skills in brick-and-mortar stores and contribute to increased customer satisfaction.

[0317] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0318] Step 1:

[0319] The device acquires the recording data.

[0320] Specifically, the system identifies videos of training sessions at stores that are recorded on devices and saves the data in a specific file format (e.g., .mp4). Users upload the recorded data saved on their devices to a server using a dedicated application or web portal. The input is the training recording data, and the output is the recording data sent to the server.

[0321] Step 2:

[0322] The server converts the recorded data into transcribed data using a voice recognition tool.

[0323] Specifically, the server analyzes the uploaded recording data and converts the audio portion into text data using the speech_recognition library. The input is the recording data, and the output is a text file that is saved as the transcription data.

[0324] Step 3:

[0325] The server converts the transcribed data into summary data using a summarization tool.

[0326] Specifically, the server summarizes the transcription data using a summarization tool (e.g., t5-small) from the transformers library. The input is the transcription data, and the output is a summary that extracts the important points.

[0327] Step 4:

[0328] A server stores and manages the abstract data.

[0329] Specifically, the generated summary data is stored in a database, along with metadata corresponding to each summary data (e.g., training ID, instructor name, etc.). The input is the summary data and metadata, and the output is the stored summary data.

[0330] Step 5:

[0331] The user views the summary data.

[0332] Specifically, users can access the stored summary data through a dedicated application or web portal and view the contents using an intuitive interface. The input is the search criteria for the summary data, and the output is the summary data displayed as a search result.

[0333] Step 6:

[0334] The emotion engine recognizes the user's emotions and adjusts the displayed content.

[0335] Specifically, while the user is viewing the summary data, the system uses the OpenCV library to analyze the user's facial expressions and tone of voice, highlighting the parts it finds interesting, and suggesting other related materials for areas that need improvement. The input is the user's facial expressions and voice data, and the output is the adjusted display content.

[0336] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0337] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0338] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0339] [Second embodiment]

[0340] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0341] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0342] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0343] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0344] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0345] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0346] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0347] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0348] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0349] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0350] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0351] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0352] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[0353] Acquiring Recording Data

[0354] Device:

[0355] Lecturers record their lectures and upload the recordings to a server. The recordings contain audio and video, detailing the entire lecture. The recordings are then sent to the server via a dedicated application or web portal.

[0356] Transcription processing

[0357] server:

[0358] The server receives the uploaded recording data and transcribes it using a speech recognition tool. The speech recognition tool has the function of converting the audio portion of the recording data into text data. For example, if a recording data called "lecture123.mp4" is uploaded, the server will use the speech recognition tool to convert the entire content of the lecture into text data.

[0359] Summary Generation

[0360] server:

[0361] The generated transcript data is then converted into summary data using a summarization tool. The summarization tool extracts important points and themes from long text data and generates a concise summary. This summary data compactly summarizes the main content of the lecture.

[0362] Summary data storage and management

[0363] server:

[0364] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed.

[0365] Viewing summary data

[0366] User (instructor):

[0367] Lecturers can view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to the summary data of other lecturers to identify areas for improvement in their own lectures.

[0368] Reflection of participant evaluations

[0369] server:

[0370] Furthermore, the system has the function of adding student evaluation data to the summary data and displaying highly rated summaries as especially recommended data. Student evaluations are based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summaries to the instructor.

[0371] Specific examples

[0372] 1. Uploading the recording data

[0373] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[0374] 2. Transcription and summary generation

[0375] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[0376] 3. Storage and management of summary data

[0377] The server stores the generated summary data and the lecture ID together in a database.

[0378] 4. Viewing summaries by other instructors

[0379] The user (lecturer) searches for the summary data of "lecture123" through the dedicated portal and checks the content on the display screen.

[0380] 5. Displaying highly rated summary data

[0381] The server analyzes the student evaluations and displays the summary data with the highest evaluations as particularly recommended data on the portal of each instructor.

[0382] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. It is also expected to increase student satisfaction.

[0383] The processing flow will be explained below.

[0384] Step 1:

[0385] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0386] Step 2:

[0387] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[0388] Step 3:

[0389] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[0390] Step 4:

[0391] Server: The server then calls the summarization tool, which converts the transcription data into summary data. The summarization tool analyzes the transcription data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0392] Step 5:

[0393] Server: The server saves the summary data in a database. When saving, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[0394] Step 6:

[0395] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The detected summary data is displayed on the screen, and the instructor can view its contents.

[0396] Step 7:

[0397] Server: The server collects and analyzes student evaluations of the summary data. Students evaluate the lecture after it is over, and the evaluation data is sent to the server and stored in a database.

[0398] Step 8:

[0399] Server: The server selects the highly rated summary data as recommended data based on the evaluation data. This recommended data is displayed specially when the user (instructor) views the summary data, and is used as a reference by other instructors.

[0400] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures, thereby improving the quality of the overall training.

[0401] Example 1

[0402] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0403] In the past, training instructors had few ways to efficiently refer to the content of other instructors' lectures and improve their own. As a result, it was difficult to improve the quality of the lecture content and share information between instructors, which often hindered efficient training management. There was also a lack of feedback based on trainee evaluations and recommended lecture information.

[0404] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0405] In this invention, the server includes means for acquiring lecture records, means for converting the lecture records into text data using a speech recognition device, means for converting the text data into concise content using a summary generation device, means for storing and managing the concise content in a storage device, and means for making the stored concise content accessible using a display device. This allows training instructors to efficiently refer to the content of other instructors' lectures, improve their own content, and provide feedback based on the students' evaluations.

[0406] "Lecture recording" refers to video or audio data of the content of a lecture given by a training instructor.

[0407] A "voice recognition device" refers to software or hardware for converting voice data into text data.

[0408] "Text data" refers to data containing character information converted by a voice recognition device.

[0409] A "summary generator" refers to software or hardware that extracts important points from long text data and converts them into concise content.

[0410] "Concise content" refers to the summary data created by the summary generator.

[0411] "Storage" refers to data storage for saving generated concise content and making it accessible when needed.

[0412] "Display device" refers to a device or software that includes an interface that allows a user to view stored concise content.

[0413] "User interface" refers to the screens and input devices through which a user interacts with a system and manipulates and views information.

[0414] "Participant evaluation" refers to the evaluation made by participants of the lecture on the lecture content and the lecturer's performance.

[0415] "Recommended information" refers to information for displaying to other users concise content that has received particularly high ratings based on participant ratings.

[0416] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[0417] Acquiring Recording Data

[0418] Device: Lecturers record their lectures using a dedicated recording application. The recording data includes both audio and video, and records the entire lecture in detail. After recording is complete, the lecturer uploads the recording data to the server via a dedicated application or web portal. For example, a lecturer records "Lecture 123" and sends the recording file "lecture123.mp4" to the server using an application.

[0419] Receiving recording data

[0420] Server: The server receives the uploaded recording data. The received data is temporarily stored in the server's storage. This allows the server to confirm the existence of the recording data. For example, the server receives a file called "lecture123.mp4" and temporarily stores it in a specified directory.

[0421] Transcription processing

[0422] Server: The server uses a speech recognition tool (e.g., Google Cloud Speech-to-Text) to convert the audio portion of the recorded data into text data. The server first extracts the audio portion and sends it to the speech recognition tool. The converted text data is temporarily stored. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[0423] Summary Generation

[0424] Server: The server inputs the transcribed text data into a summarization tool (e.g., OpenAI GPT-3) to generate summary data. The server generates a specific prompt and sends it to the summarization tool. The generated summary data is saved. For example, the server requests a summary using the following prompt:

[0425] prompt:

[0426] Summarize the following text:

[0427] "Hello, today's lecture will cover database basics. First..."

[0428] OpenAI GPT-3 provides the summary, and the server stores the summary data: "About the basics of databases..."

[0429] Summary data storage and management

[0430] Server: The server stores the generated summary data in a database (e.g., MySQL). The summary data is also stored here along with metadata such as the lecture ID and lecturer name. For example, the server stores the summary data "On the Fundamentals of Databases..." in the database along with the lecture ID "lecture123."

[0431] Viewing summary data

[0432] User (instructor): Instructors access the database through a dedicated application or web portal to search and view abstracts. The user interface is intuitive and designed to make it easy to find the information they need. The instructor types "lecture123" into the search box and the related abstract, "Database Fundamentals...," is displayed.

[0433] Reflection of participant evaluations

[0434] Server: The server collects evaluation data from students and associates it with the summary data. It analyzes the evaluation data and manages the highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When the instructor accesses the portal, the recommended data is prominently displayed.

[0435] By utilizing generative AI models and prompts, this system allows instructors to efficiently refer to other instructors' lecture content and improve the quality of their own lectures. It also provides feedback based on student evaluations, contributing to increased student satisfaction.

[0436] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0437] Step 1: Obtaining Recording Data

[0438] Terminal: The lecturer records the lecture using a dedicated recording application. After the recording is complete, the recorded data (input) is uploaded to the server (output) via the dedicated application or web portal. For example, if you record "Lecture 123," the recording file "lecture123.mp4" is sent to the server using the application.

[0439] Step 2: Receive recording data

[0440] Server: The server receives the uploaded recording data (input) and temporarily stores it in the server's storage (output). For example, a file called "lecture123.mp4" is received and temporarily stored in the specified directory " / uploads / lecture123.mp4." This allows the server to confirm the existence of the recording data.

[0441] Step 3: Transcription processing

[0442] Server: The server receives recorded data (input) and converts the audio portion into text data (output) using a speech recognition tool (e.g., Google Cloud Speech-to-Text). Specifically, the server first extracts the audio portion from the recorded data and sends it to the speech recognition tool. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[0443] Step 4: Summary generation

[0444] Server: The server inputs the transcribed text data (input) into a summarization tool (e.g., OpenAI GPT-3) and generates summary data (output). Specifically, the server generates a prompt and sends it to the summarization tool. The generated summary data is saved. For example, the following prompt can be used to request a summary:

[0445] prompt:

[0446] Summarize the following text:

[0447] "Hello, today's lecture will cover database basics. First..."

[0448] Based on the prompt, OpenAI GPT-3 provides a summary, and the server retrieves the summary data: "About the basics of databases..."

[0449] Step 5: Storing and managing summary data

[0450] Server: The server saves the generated summary data (input) in a database (e.g., MySQL) (output). Here, the summary data is saved along with metadata such as the lecture ID and lecturer name. For example, the summary data "On the Fundamentals of Databases..." is stored in the database along with the lecture ID "lecture123."

[0451] Step 6: View summary data

[0452] User (instructor): The instructor accesses the database through a dedicated application or web portal to search and view abstract data (input) (output). The user interface is intuitive and designed to make it easy to find the information needed. The instructor types "lecture123" in the search box and the related abstract data, "Database Fundamentals...," is displayed.

[0453] Step 7: Reflecting student evaluations

[0454] Server: The server collects evaluation data from students (input) and associates it with summary data (output). It analyzes the evaluation data and manages highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When a lecturer accesses the portal, the recommended data is prominently displayed.

[0455] (Application example 1)

[0456] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0457] Training personnel at factories lack the means to easily refer to the training content of other trainers and quickly and effectively improve their own training methods. Furthermore, the efficiency of improving training content by reflecting trainee evaluations is also low. This results in a decline in the quality of training and hinders improvements in production efficiency and safety.

[0458] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0459] In this invention, the server includes means for acquiring the training content of other trainers as recorded data, means for converting the recorded data into transcription data using a voice recognition tool, means for converting the transcription data into summary data using a summarization tool, means for saving and managing the summary data, means for making the saved summary data available for viewing, and means for including recorded data used for training on the operation and maintenance of industrial equipment. This allows trainers to quickly refer to the training content of other trainers and efficiently improve their own training methods. Furthermore, trainee evaluations can be efficiently reflected, improving the quality of training.

[0460] A "training instructor" is a person who is responsible for teaching other employees about the operation and maintenance of equipment within a factory.

[0461] "Recorded data" refers to digital data that records the contents of lectures and training given by training instructors in audio and video format.

[0462] A "voice recognition tool" is software or hardware that converts the audio portion of recorded data into text data.

[0463] "Transcription data" refers to text data converted from audio data using a speech recognition tool.

[0464] A "summary tool" is software that extracts important points and themes from long text data and generates a concise summary.

[0465] "Summary data" is text data generated by a summarization tool that briefly summarizes the main points of lectures or training content.

[0466] "Storage and management means" means means for safely and efficiently storing and managing Abstract Data, including databases and storage systems.

[0467] "Means for making it viewable" means means for providing a function to search and display the stored summary data through a user interface.

[0468] "Industrial equipment" refers to machines and facilities used in production and maintenance in factories.

[0469] "Participant evaluation" is an evaluation made by employees who have received training about the training content and instructor, and is provided in the form of numbers and comments.

[0470] This invention is a system that allows in-plant trainers to effectively refer to training materials and improve their own training methods. This system acquires recorded lecture data and provides functions for efficiently generating, managing, and viewing summary data using voice recognition and summarization tools.

[0471] The server performs the following main processes. First, it acquires the contents of lectures given by in-plant training instructors as recorded data. The recorded data is about the operation and maintenance of factory equipment and is usually recorded using a device equipped with a camera and microphone. After the training is completed, this recorded data is uploaded to the server via a dedicated application.

[0472] The server then converts the uploaded recordings into transcripts using a speech recognition tool (e.g., Google Cloud Speech-to-Text). The speech recognition tool analyzes the audio portion of the recordings and converts them into text. The transcripts are then stored for further processing.

[0473] The server then converts the generated transcript data into summary data using a summarization tool (e.g., OpenAI GPT-4). The summarization tool extracts key points and themes from the text data and generates a concise summary. This summary effectively captures the main content of the lecture and helps the training instructor quickly grasp the content.

[0474] The generated summary data is stored in a database. The database manages summary data for each lecture, allowing for easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed. This allows training personnel to easily search and refer to the content of lectures given by other lecturers.

[0475] Furthermore, the server has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Student evaluations are given based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summary data to training instructors. This allows instructors to efficiently improve their own training methods.

[0476] For example, if a recording called "lecture123.wav" is uploaded, the server converts the audio into text using Google Cloud Speech-to-Text. Next, OpenAI GPT-4 is used to summarize the transcript, generating a summary such as, "In this lecture, we explained basic maintenance procedures and precautions." This summary is stored in a database, and if it receives high marks from students, it will be displayed to other instructors as a recommended resource.

[0477] An example prompt might be something like, "Summarize the following text: Today we will learn about maintaining factory robots. First..."

[0478] This system allows training instructors to quickly refer to the training content of other trainers and effectively improve their own training methods. It is also possible to efficiently reflect trainee evaluations, which is expected to improve the quality of training.

[0479] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0480] Step 1:

[0481] The device's built-in camera and microphone record the lectures of the training instructor. The input is the lecture content, and the output is the recorded data. Specifically, the instructor gives an explanation on the operation and maintenance of the equipment, which is then recorded in digital format.

[0482] Step 2:

[0483] The device uploads the recorded data to the server. The input is the recorded data, and the output is the recorded data saved on the server. Specifically, after recording is completed, the data is sent to the server using a dedicated application.

[0484] Step 3:

[0485] The server uses a speech recognition tool to convert the audio portion of the recorded data into transcribed data. The input is the recorded data, and the output is the transcribed data. Specifically, Google Cloud Speech-to-Text is used to analyze the audio data and generate text data.

[0486] Step 4:

[0487] The server converts the generated transcription data into summary data using a summarization tool. The input is transcription data, and the output is summary data. Specifically, OpenAI GPT-4 is used to extract key points and generate summaries.

[0488] Step 5:

[0489] The server stores and manages the generated summary data in a database. The input is summary data, and the output is summary data stored in the database. Specifically, the summary data is registered in the database along with the lecture ID and lecturer name.

[0490] Step 6:

[0491] Users access the database through a dedicated user interface and view the summary data. The input is a search query from the user interface, and the output is summary data as search results. Specifically, users enter a lecture ID or keyword to search for summary data.

[0492] Step 7:

[0493] The server analyzes the students' evaluation data and displays the highly rated summary data as especially recommended data. The input is the students' evaluation data, and the output is the summary data with ratings. Specifically, the server analyzes the evaluation points and comments provided by the students and displays the highly rated summary data on the user interface.

[0494] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0495] This invention combines an emotion engine with a system that allows training instructors to efficiently refer to the content of other instructors' lectures and refine their own lectures. The system performs a series of processes: recording lectures, transcribing them, and generating summaries. Furthermore, when viewing saved summaries, the emotion engine is used to recognize the user's emotions, and the display content can be flexibly adjusted based on those emotions.

[0496] Acquiring Recording Data

[0497] Device:

[0498] The lecturer records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0499] Transcription processing

[0500] server:

[0501] The server receives the recorded data and temporarily stores it. Once the recording data has been received, the transcription process begins. The server calls a speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data, and the generated transcription data is temporarily stored on the server.

[0502] Summary Generation

[0503] server:

[0504] The generated transcription data is then converted into summary data using a summarization tool. The summarization tool analyzes the transcription data, extracts important points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0505] Summary data storage and management

[0506] server:

[0507] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored.

[0508] Viewing summary data

[0509] User (instructor):

[0510] Lecturers view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to other lecturers' summaries to identify areas for improvement in their own lectures. At this time, an emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions. For example, it can identify parts that the lecturer found interesting or uncomfortable while viewing.

[0511] Reflecting emotional data

[0512] server:

[0513] The emotion engine adjusts the content of the summary data based on the emotional data it recognizes. For example, it can highlight parts that are recognized as interesting, or suggest other related materials for parts that are recognized as unpleasant. This improves the accuracy and satisfaction of the information provided to users.

[0514] Reflection of participant evaluations

[0515] server:

[0516] The system has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Students evaluate the lecture after it is over, and the data is sent to the server and stored in a database. The server analyzes this evaluation data and can recommend highly rated summary data to the instructor. Furthermore, emotional data recognized by the emotion engine is also reflected as part of the evaluation. This further improves the fairness and accuracy of the evaluation.

[0517] Specific examples

[0518] 1. Uploading the recording data

[0519] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[0520] 2. Transcription and summary generation

[0521] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[0522] 3. Storage and management of summary data

[0523] The server stores the generated summary data and the lecture ID together in a database.

[0524] 4. Viewing summaries by other instructors

[0525] The user (lecturer) searches for the summary data of "lecture123" through a dedicated portal and checks the content on the display screen. At that time, the emotion engine analyzes the user's facial expressions and tone of voice, and the emotional data is also saved.

[0526] 5. Displaying highly rated summary data

[0527] The server analyzes the student evaluations and emotion data, and displays the highly evaluated summary data as especially recommended data on each instructor's portal.

[0528] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. In addition, the flexible provision of information based on emotional data is expected to improve the quality of learning for students.

[0529] The processing flow will be explained below.

[0530] Step 1:

[0531] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0532] Step 2:

[0533] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[0534] Step 3:

[0535] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[0536] Step 4:

[0537] Server: The server then calls the summarization tool, which converts the transcript into summary data. The summarization tool analyzes the text data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0538] Step 5:

[0539] Server: The generated summary data is saved in a database. When saved, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[0540] Step 6:

[0541] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The search results are displayed, and the summary data can be viewed.

[0542] Step 7:

[0543] User (instructor): While viewing the summary data, the emotion engine analyzes the user's facial expressions and vocal tone. The emotion engine identifies the parts that the user found interesting or unpleasant, and sends the emotion data to the server.

[0544] Step 8:

[0545] Server: The server stores the emotion data recognized by the emotion engine. The emotion data is associated with the summary data and used for future analysis and display adjustments.

[0546] Step 9:

[0547] Server: Based on the emotion data, the server adjusts the content of the summary data displayed. For example, it highlights parts that the user finds interesting, and suggests other related materials for parts that are perceived as unpleasant. This adjustment allows the server to provide information that is tailored to the user's interests.

[0548] Step 10:

[0549] Server: Collects and analyzes student evaluation data, and displays highly rated summary data as especially recommended data. Based on the analysis results of student evaluations and emotion data, highly rated summary data is recommended to the instructor.

[0550] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures. It also enables flexible information provision based on user emotions, which is expected to improve the quality of learning for students.

[0551] Example 2

[0552] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0553] Conventional training systems have the drawback of requiring time and effort to refer to other lecturers' lecture content. Furthermore, they do not provide feedback that reflects the students' feelings and evaluations, making it difficult to improve the lecture content. Furthermore, there is a lack of a way to increase student satisfaction while maintaining the quality of the summary data.

[0554] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0555] In this invention, the server includes means for acquiring lecture content from other lecturers as recorded data, means for converting the recorded data into transcription data using a speech recognition device, means for converting the transcription data into summary data using a summarization device, means for making the saved summary data viewable, means for recognizing a user's emotions when viewing the summary data and adjusting the display content, and means for collecting student evaluation data on the lecture and recommending highly rated data. This allows lecturers to efficiently refer to the lecture content of other lecturers and improve their own lecture content. Furthermore, flexible feedback reflecting student emotions and evaluations is provided, thereby increasing student satisfaction.

[0556] A "lecturer" is a person who gives a lecture in an educational or training setting.

[0557] "Recorded data" refers to digital data containing video and audio recordings of lecture content.

[0558] A "voice recognition device" is a device or software that analyzes recorded speech and converts it into text data.

[0559] "Transcription data" is text data generated from speech by a speech recognition device.

[0560] A "summarization device" is a device or software that analyzes transcription data, extracts important points and themes, and generates concise summary data.

[0561] "Summary data" is text data that succinctly summarizes the important points and themes of the lecture content.

[0562] A "database" is a system that stores and manages multiple data in an organized manner, making it easy to search and access.

[0563] "Emotion recognition" refers to analyzing a user's facial expressions and tone of voice to identify their emotional state at that moment.

[0564] "Adjusting the display content" means improving the accuracy of information provision by changing or highlighting the content of the summary data in accordance with the user's emotions.

[0565] "Evaluation data" refers to data on evaluations and feedback on the content of a lecture provided by students after the lecture.

[0566] "Recommended data" is data that has been judged to have a particularly high rating from a large amount of evaluation data and is to be recommended to other users.

[0567] This invention combines an emotion engine with a system that allows users to efficiently refer to the lecture content of other lecturers and refine their own lecture content. The system acquires recorded lecture data, transcribes it, and then performs a series of processes to generate a summary. Furthermore, when viewing saved summary data, the emotion engine is used to recognize the user's emotions and provides a function to flexibly adjust the displayed content based on those emotions.

[0568] Acquiring and uploading recording data

[0569] The user (lecturer) records the lecture content and saves the recorded data on their device. Next, they access a dedicated application or web portal and use the upload function for the recorded data. By selecting the recorded data and pressing the upload button, the recorded data is sent to the server. For example, the user uploads "lecture123.mp4" to the server through the dedicated portal.

[0570] Transcription processing

[0571] The server analyzes the received recording data using a speech recognition device (e.g., Google Cloud Speech-to-Text API). The server converts the audio data into text data and temporarily stores the generated transcription data. For example, the server calls a speech recognition tool, analyzes the audio portion of "lecture123.mp4," and transcribes it.

[0572] Summary Generation

[0573] The server analyzes the generated transcript data using a summarization device (e.g., OpenAI GPT-3), extracts important points and themes, and generates summary data. The generated summary data is temporarily stored on the server. For example, the server analyzes "lecture123_transcript.txt" using a summarization tool and generates "lecture123_summary.txt," which summarizes the important points.

[0574] Summary data storage and management

[0575] The server stores the generated summary data in a database. The database manages the summary data for each lecture and also stores metadata such as the lecture ID and lecturer name. For example, the summary data "lecture123_summary.txt" along with the lecture ID and lecturer name is stored in the database.

[0576] Viewing summary data

[0577] Users (lecturers) search for and view summary data through a dedicated application or web portal. The user interface is intuitive and includes a function for viewing the summary data for each lecture. The emotion engine analyzes the user's facial expressions and tone of voice to identify parts that interest or annoy the user. For example, a user can search for "lecture123_summary" through the dedicated portal and view the summary data on the display screen.

[0578] Reflecting emotional data

[0579] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. For example, parts that the user finds interesting are displayed in bold, and parts that the user finds unpleasant are displayed as links to supplementary materials.

[0580] Reflection of participant evaluations

[0581] The server assigns the students' evaluation data to the summary data and displays the highly rated summary data as recommended data. Students evaluate the data after the lecture, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. For example, evaluation data collected from students after the lecture is analyzed, and the highly rated summary data is displayed as recommended data for other lecturers.

[0582] Prompt Sentence Examples

[0583] Use a speech recognition tool to transcribe the recording data "lecture123.mp4" and a summarization tool to generate a summary. This summary data and related metadata will be stored in a database and made available for other lecturers to view. An emotion engine will be used to analyze facial expressions and tone of voice during viewing and adjust the displayed content. Also, based on the student's evaluation, particularly recommended summary data will be displayed.

[0584] This system allows lecturers to efficiently refer to the content of other lecturers' lectures and improve their own lecture content. It also provides flexible feedback that reflects the students' feelings and evaluations, thereby improving student satisfaction.

[0585] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0586] Step 1: Obtain and upload recording data

[0587] A user (lecturer) records their own lecture and saves the recorded data (e.g., "lecture123.mp4") on their device. Next, the user accesses a dedicated application or web portal and uses the upload function for the recorded data. The user selects the recorded data and presses the upload button to send the recorded data to the server. The input is the recorded data, and the output is the recorded data uploaded to the server.

[0588] Specific operation: The user selects the recorded data on the device and clicks the "Upload" button.

[0589] Step 2: Transcription processing

[0590] The server temporarily stores the received recording data. Next, the server calls a speech recognizer (e.g., Google Cloud Speech-to-Text API) to analyze the audio portion of the recording data. The speech recognizer converts the audio data into text data, and the generated transcription data (e.g., "lecture123_transcript.txt") is temporarily stored on the server. The input is the recording data, and the output is the transcription data.

[0591] Specific operation: The server calls the speech recognition API, analyzes the voice data, and saves the generated text data.

[0592] Step 3: Summary generation

[0593] The server analyzes the generated transcription data using a summarization device (e.g., OpenAI GPT-3). The server extracts important points and themes and generates a concise summary (e.g., "lecture123_summary.txt"). The generated summary data is temporarily stored on the server. The input is the transcription data, and the output is the summary data.

[0594] Specific operation: The server calls the summarization device, summarizes the transcription data, and saves the summary data.

[0595] Step 4: Storing and managing summary data

[0596] The server saves the generated summary data in a database. The database manages summary data for each lecture, along with metadata such as lecture ID and lecturer name. The input is the summary data, lecture ID, and lecturer name, and the output is the data saved in the database.

[0597] Specific operation: The server stores and manages the summary data and related metadata in a database.

[0598] Step 5: View summary data

[0599] Users (lecturers) search and view the summary data through a dedicated application or web portal. The user interface is intuitive and has a function to display summary data for each lecture. In addition, an emotion engine analyzes the user's facial expressions and tone of voice to identify parts that showed interest or discomfort. The input is the viewing request and user behavior data, and the output is an adjusted summary display.

[0600] Specific operation: The user searches for summary data through the dedicated portal and checks the summary content on the display screen.

[0601] Step 6: Reflecting emotional data

[0602] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. The input is emotional data and summary data, and the output is a display of the adjusted summary data.

[0603] Specific operation: The server uses an emotion engine to analyze the user's emotions and adjust the displayed content.

[0604] Step 7: Reflecting student evaluations

[0605] The server adds student evaluation data to the summary data and displays the highly rated summary data as recommended data. Student evaluations are conducted after the lecture ends, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. The input is evaluation data and emotional data, and the output is summary data that is displayed as recommended data.

[0606] Specific operation: The server analyzes the evaluation data of the students and displays the summary data of the highly evaluated data as especially recommended data.

[0607] (Application example 2)

[0608] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0609] In today's brick-and-mortar stores, improving customer service quality is crucial to increasing customer satisfaction. However, there is no adequate system in place for store instructors to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, there is no function to automatically adjust the displayed content based on the user's emotions, which can lead to insufficient understanding of the training content. This issue limits each store's efforts to improve customer service quality.

[0610] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0611] In this invention, the server includes: means for acquiring the content of other instructors' lectures as recorded data; means for converting the recorded data into transcription data using a voice recognition tool; means for converting the transcription data into summary data using a summarization tool; means for saving and managing the summary data; means for making the saved summary data viewable; and means including an emotion engine that recognizes the user's emotions when viewing the summary data and adjusts the display content. This allows instructors at each store to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, because the display content is adjusted based on the user's emotions, it is expected that the user's understanding of the training content will deepen and the quality of their customer service will improve.

[0612] "Lecture content of other instructors" refers to all or part of educational materials or presentations used during training or education.

[0613] "Recorded data" refers to digital data that records audio and video.

[0614] "Speech recognition tools" refers to technology or software that converts speech into text.

[0615] "Transcription data" refers to data converted from audio into text format.

[0616] A "summary tool" refers to technology or software that extracts important points from long pieces of text and converts them into short summaries.

[0617] "Summary data" refers to concise text data generated using a summarization tool.

[0618] "Means of storage and management" refers to a system that uses a database or other means to consistently store data and keep it in a state that allows it to be searched or retrieved as needed.

[0619] "Means for making data available for viewing" refers to an interface or mechanism that allows users to easily access and display stored data.

[0620] An "emotion engine" refers to technology or software that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[0621] "User emotion" refers to the emotional state, such as interest, pleasure, or discomfort, shown by the user while browsing.

[0622] "Adjusting the display content" refers to dynamically changing the format or emphasis of displayed information based on the user's emotional state.

[0623] To implement the invention, the following details regarding the server, terminals, and users are provided.

[0624] The server has a means for acquiring lecture content from other instructors as recorded data. The recorded data is digital data containing audio and video and is stored on the server. The server also has a means for converting the recorded data into transcribed data using a speech recognition tool. This conversion uses speech recognition technology and software such as speech_recognition.

[0625] The transcription data is converted into summary data using a summarization tool. This summarization tool uses the transformers library to condense long sentences into short ones. For example, a model called t5-small is used to generate summaries. This extracts key points from the transcription data and generates concise summaries.

[0626] The server has a means for storing and managing the generated summary data, and this is managed using a database. The database stores each summary data and its corresponding metadata, and important information is kept in a state where it can be easily retrieved.

[0627] An interface is also provided that allows users to view the summary data. This interface is accessible through a dedicated application or web portal and is intuitive to use. Users can refer to other instructors' summary data and obtain information to improve their own customer service skills and teaching methods. In addition, an emotion engine analyzes the user's emotional state and dynamically adjusts the displayed content based on that. The emotion engine uses OpenCV to perform facial expression analysis and identify interesting areas and areas for improvement.

[0628] For example, store A uploads a recording of a training session, and the server transcribes it using a speech recognition tool, then uses a summarization tool to generate a concise summary. Users can view this summary through smart glasses, and the emotion engine automatically highlights points of interest.

[0629] As an example of a prompt sentence, the following sentence can be input to the generative AI model:

[0630] "Today's customer service training emphasized the importance of direct communication with customers. In particular, we are required to quickly grasp customer reactions and make suggestions that meet their needs."

[0631] This allows the server to provide optimal information to users through speech recognition, summary generation, emotion analysis, and display content adjustment. This system will help improve customer service skills in brick-and-mortar stores and contribute to increased customer satisfaction.

[0632] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0633] Step 1:

[0634] The device acquires the recording data.

[0635] Specifically, the system identifies videos of training sessions at stores that are recorded on devices and saves the data in a specific file format (e.g., .mp4). Users upload the recorded data saved on their devices to a server using a dedicated application or web portal. The input is the training recording data, and the output is the recording data sent to the server.

[0636] Step 2:

[0637] The server converts the recorded data into transcribed data using a voice recognition tool.

[0638] Specifically, the server analyzes the uploaded recording data and converts the audio portion into text data using the speech_recognition library. The input is the recording data, and the output is a text file that is saved as the transcription data.

[0639] Step 3:

[0640] The server converts the transcribed data into summary data using a summarization tool.

[0641] Specifically, the server summarizes the transcription data using a summarization tool (e.g., t5-small) from the transformers library. The input is the transcription data, and the output is a summary that extracts the important points.

[0642] Step 4:

[0643] A server stores and manages the abstract data.

[0644] Specifically, the generated summary data is stored in a database, along with metadata corresponding to each summary data (e.g., training ID, instructor name, etc.). The input is the summary data and metadata, and the output is the stored summary data.

[0645] Step 5:

[0646] The user views the summary data.

[0647] Specifically, users can access the stored summary data through a dedicated application or web portal and view the contents using an intuitive interface. The input is the search criteria for the summary data, and the output is the summary data displayed as a search result.

[0648] Step 6:

[0649] The emotion engine recognizes the user's emotions and adjusts the displayed content.

[0650] Specifically, while the user is viewing the summary data, the system uses the OpenCV library to analyze the user's facial expressions and tone of voice, highlighting the parts it finds interesting, and suggesting other related materials for areas that need improvement. The input is the user's facial expressions and voice data, and the output is the adjusted display content.

[0651] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0652] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0653] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0654] [Third embodiment]

[0655] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0656] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0657] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0658] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0659] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0660] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0661] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0662] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0663] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0664] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0665] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0666] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0667] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[0668] Acquiring Recording Data

[0669] Device:

[0670] Lecturers record their lectures and upload the recordings to a server. The recordings contain audio and video, detailing the entire lecture. The recordings are then sent to the server via a dedicated application or web portal.

[0671] Transcription processing

[0672] server:

[0673] The server receives the uploaded recording data and transcribes it using a speech recognition tool. The speech recognition tool has the function of converting the audio portion of the recording data into text data. For example, if a recording data called "lecture123.mp4" is uploaded, the server will use the speech recognition tool to convert the entire content of the lecture into text data.

[0674] Summary Generation

[0675] server:

[0676] The generated transcript data is then converted into summary data using a summarization tool. The summarization tool extracts important points and themes from long text data and generates a concise summary. This summary data compactly summarizes the main content of the lecture.

[0677] Summary data storage and management

[0678] server:

[0679] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed.

[0680] Viewing summary data

[0681] User (instructor):

[0682] Lecturers can view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to the summary data of other lecturers to identify areas for improvement in their own lectures.

[0683] Reflection of participant evaluations

[0684] server:

[0685] Furthermore, the system has the function of adding student evaluation data to the summary data and displaying highly rated summaries as especially recommended data. Student evaluations are based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summaries to the instructor.

[0686] Specific examples

[0687] 1. Uploading the recording data

[0688] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[0689] 2. Transcription and summary generation

[0690] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[0691] 3. Storage and management of summary data

[0692] The server stores the generated summary data and the lecture ID together in a database.

[0693] 4. Viewing summaries by other instructors

[0694] The user (lecturer) searches for the summary data of "lecture123" through the dedicated portal and checks the content on the display screen.

[0695] 5. Displaying highly rated summary data

[0696] The server analyzes the student evaluations and displays the summary data with the highest evaluations as particularly recommended data on the portal of each instructor.

[0697] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. It is also expected to increase student satisfaction.

[0698] The processing flow will be explained below.

[0699] Step 1:

[0700] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0701] Step 2:

[0702] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[0703] Step 3:

[0704] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[0705] Step 4:

[0706] Server: The server then calls the summarization tool, which converts the transcription data into summary data. The summarization tool analyzes the transcription data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0707] Step 5:

[0708] Server: The server saves the summary data in a database. When saving, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[0709] Step 6:

[0710] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The detected summary data is displayed on the screen, and the instructor can view its contents.

[0711] Step 7:

[0712] Server: The server collects and analyzes student evaluations of the summary data. Students evaluate the lecture after it is over, and the evaluation data is sent to the server and stored in a database.

[0713] Step 8:

[0714] Server: The server selects the highly rated summary data as recommended data based on the evaluation data. This recommended data is displayed specially when the user (instructor) views the summary data, and is used as a reference by other instructors.

[0715] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures, thereby improving the quality of the overall training.

[0716] Example 1

[0717] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0718] In the past, training instructors had few ways to efficiently refer to the content of other instructors' lectures and improve their own. As a result, it was difficult to improve the quality of the lecture content and share information between instructors, which often hindered efficient training management. There was also a lack of feedback based on trainee evaluations and recommended lecture information.

[0719] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0720] In this invention, the server includes means for acquiring lecture records, means for converting the lecture records into text data using a speech recognition device, means for converting the text data into concise content using a summary generation device, means for storing and managing the concise content in a storage device, and means for making the stored concise content accessible using a display device. This allows training instructors to efficiently refer to the content of other instructors' lectures, improve their own content, and provide feedback based on the students' evaluations.

[0721] "Lecture recording" refers to video or audio data of the content of a lecture given by a training instructor.

[0722] A "voice recognition device" refers to software or hardware for converting voice data into text data.

[0723] "Text data" refers to data containing character information converted by a voice recognition device.

[0724] A "summary generator" refers to software or hardware that extracts important points from long text data and converts them into concise content.

[0725] "Concise content" refers to the summary data created by the summary generator.

[0726] "Storage" refers to data storage for saving generated concise content and making it accessible when needed.

[0727] "Display device" refers to a device or software that includes an interface that allows a user to view stored concise content.

[0728] "User interface" refers to the screens and input devices through which a user interacts with a system and manipulates and views information.

[0729] "Participant evaluation" refers to the evaluation made by participants of the lecture on the lecture content and the lecturer's performance.

[0730] "Recommended information" refers to information for displaying to other users concise content that has received particularly high ratings based on participant ratings.

[0731] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[0732] Acquiring Recording Data

[0733] Device: Lecturers record their lectures using a dedicated recording application. The recording data includes both audio and video, and records the entire lecture in detail. After recording is complete, the lecturer uploads the recording data to the server via a dedicated application or web portal. For example, a lecturer records "Lecture 123" and sends the recording file "lecture123.mp4" to the server using an application.

[0734] Receiving recording data

[0735] Server: The server receives the uploaded recording data. The received data is temporarily stored in the server's storage. This allows the server to confirm the existence of the recording data. For example, the server receives a file called "lecture123.mp4" and temporarily stores it in a specified directory.

[0736] Transcription processing

[0737] Server: The server uses a speech recognition tool (e.g., Google Cloud Speech-to-Text) to convert the audio portion of the recorded data into text data. The server first extracts the audio portion and sends it to the speech recognition tool. The converted text data is temporarily stored. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[0738] Summary Generation

[0739] Server: The server inputs the transcribed text data into a summarization tool (e.g., OpenAI GPT-3) to generate summary data. The server generates a specific prompt and sends it to the summarization tool. The generated summary data is saved. For example, the server requests a summary using the following prompt:

[0740] prompt:

[0741] Summarize the following text:

[0742] "Hello, today's lecture will cover database basics. First..."

[0743] OpenAI GPT-3 provides the summary, and the server stores the summary data: "About the basics of databases..."

[0744] Summary data storage and management

[0745] Server: The server stores the generated summary data in a database (e.g., MySQL). The summary data is also stored here along with metadata such as the lecture ID and lecturer name. For example, the server stores the summary data "On the Fundamentals of Databases..." in the database along with the lecture ID "lecture123."

[0746] Viewing summary data

[0747] User (instructor): Instructors access the database through a dedicated application or web portal to search and view abstracts. The user interface is intuitive and designed to make it easy to find the information they need. The instructor types "lecture123" into the search box and the related abstract, "Database Fundamentals...," is displayed.

[0748] Reflection of participant evaluations

[0749] Server: The server collects evaluation data from students and associates it with the summary data. It analyzes the evaluation data and manages the highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When the instructor accesses the portal, the recommended data is prominently displayed.

[0750] By utilizing generative AI models and prompts, this system allows instructors to efficiently refer to other instructors' lecture content and improve the quality of their own lectures. It also provides feedback based on student evaluations, contributing to increased student satisfaction.

[0751] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0752] Step 1: Obtaining Recording Data

[0753] Terminal: The lecturer records the lecture using a dedicated recording application. After the recording is complete, the recorded data (input) is uploaded to the server (output) via the dedicated application or web portal. For example, if you record "Lecture 123," the recording file "lecture123.mp4" is sent to the server using the application.

[0754] Step 2: Receive recording data

[0755] Server: The server receives the uploaded recording data (input) and temporarily stores it in the server's storage (output). For example, a file called "lecture123.mp4" is received and temporarily stored in the specified directory " / uploads / lecture123.mp4." This allows the server to confirm the existence of the recording data.

[0756] Step 3: Transcription processing

[0757] Server: The server receives recorded data (input) and converts the audio portion into text data (output) using a speech recognition tool (e.g., Google Cloud Speech-to-Text). Specifically, the server first extracts the audio portion from the recorded data and sends it to the speech recognition tool. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[0758] Step 4: Summary generation

[0759] Server: The server inputs the transcribed text data (input) into a summarization tool (e.g., OpenAI GPT-3) and generates summary data (output). Specifically, the server generates a prompt and sends it to the summarization tool. The generated summary data is saved. For example, the following prompt can be used to request a summary:

[0760] prompt:

[0761] Summarize the following text:

[0762] "Hello, today's lecture will cover database basics. First..."

[0763] Based on the prompt, OpenAI GPT-3 provides a summary, and the server retrieves the summary data: "About the basics of databases..."

[0764] Step 5: Storing and managing summary data

[0765] Server: The server saves the generated summary data (input) in a database (e.g., MySQL) (output). Here, the summary data is saved along with metadata such as the lecture ID and lecturer name. For example, the summary data "On the Fundamentals of Databases..." is stored in the database along with the lecture ID "lecture123."

[0766] Step 6: View summary data

[0767] User (instructor): The instructor accesses the database through a dedicated application or web portal to search and view abstract data (input) (output). The user interface is intuitive and designed to make it easy to find the information needed. The instructor types "lecture123" in the search box and the related abstract data, "Database Fundamentals...," is displayed.

[0768] Step 7: Reflecting student evaluations

[0769] Server: The server collects evaluation data from students (input) and associates it with summary data (output). It analyzes the evaluation data and manages highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When a lecturer accesses the portal, the recommended data is prominently displayed.

[0770] (Application example 1)

[0771] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0772] Training personnel at factories lack the means to easily refer to the training content of other trainers and quickly and effectively improve their own training methods. Furthermore, the efficiency of improving training content by reflecting trainee evaluations is also low. This results in a decline in the quality of training and hinders improvements in production efficiency and safety.

[0773] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0774] In this invention, the server includes means for acquiring the training content of other trainers as recorded data, means for converting the recorded data into transcription data using a voice recognition tool, means for converting the transcription data into summary data using a summarization tool, means for saving and managing the summary data, means for making the saved summary data available for viewing, and means for including recorded data used for training on the operation and maintenance of industrial equipment. This allows trainers to quickly refer to the training content of other trainers and efficiently improve their own training methods. Furthermore, trainee evaluations can be efficiently reflected, improving the quality of training.

[0775] A "training instructor" is a person who is responsible for teaching other employees about the operation and maintenance of equipment within a factory.

[0776] "Recorded data" refers to digital data that records the contents of lectures and training given by training instructors in audio and video format.

[0777] A "voice recognition tool" is software or hardware that converts the audio portion of recorded data into text data.

[0778] "Transcription data" refers to text data converted from audio data using a speech recognition tool.

[0779] A "summary tool" is software that extracts important points and themes from long text data and generates a concise summary.

[0780] "Summary data" is text data generated by a summarization tool that briefly summarizes the main points of lectures or training content.

[0781] "Storage and management means" means means for safely and efficiently storing and managing Abstract Data, including databases and storage systems.

[0782] "Means for making it viewable" means means for providing a function to search and display the stored summary data through a user interface.

[0783] "Industrial equipment" refers to machines and facilities used in production and maintenance in factories.

[0784] "Participant evaluation" is an evaluation made by employees who have received training about the training content and instructor, and is provided in the form of numbers and comments.

[0785] This invention is a system that allows in-plant trainers to effectively refer to training materials and improve their own training methods. This system acquires recorded lecture data and provides functions for efficiently generating, managing, and viewing summary data using voice recognition and summarization tools.

[0786] The server performs the following main processes. First, it acquires the contents of lectures given by in-plant training instructors as recorded data. The recorded data is about the operation and maintenance of factory equipment and is usually recorded using a device equipped with a camera and microphone. After the training is completed, this recorded data is uploaded to the server via a dedicated application.

[0787] The server then converts the uploaded recordings into transcripts using a speech recognition tool (e.g., Google Cloud Speech-to-Text). The speech recognition tool analyzes the audio portion of the recordings and converts them into text. The transcripts are then stored for further processing.

[0788] The server then converts the generated transcript data into summary data using a summarization tool (e.g., OpenAI GPT-4). The summarization tool extracts key points and themes from the text data and generates a concise summary. This summary effectively captures the main content of the lecture and helps the training instructor quickly grasp the content.

[0789] The generated summary data is stored in a database. The database manages summary data for each lecture, allowing for easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed. This allows training personnel to easily search and refer to the content of lectures given by other lecturers.

[0790] Furthermore, the server has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Student evaluations are given based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summary data to training instructors. This allows instructors to efficiently improve their own training methods.

[0791] For example, if a recording called "lecture123.wav" is uploaded, the server converts the audio into text using Google Cloud Speech-to-Text. Next, OpenAI GPT-4 is used to summarize the transcript, generating a summary such as, "In this lecture, we explained basic maintenance procedures and precautions." This summary is stored in a database, and if it receives high marks from students, it will be displayed to other instructors as a recommended resource.

[0792] An example prompt might be something like, "Summarize the following text: Today we will learn about maintaining factory robots. First..."

[0793] This system allows training instructors to quickly refer to the training content of other trainers and effectively improve their own training methods. It is also possible to efficiently reflect trainee evaluations, which is expected to improve the quality of training.

[0794] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0795] Step 1:

[0796] The device's built-in camera and microphone record the lectures of the training instructor. The input is the lecture content, and the output is the recorded data. Specifically, the instructor gives an explanation on the operation and maintenance of the equipment, which is then recorded in digital format.

[0797] Step 2:

[0798] The device uploads the recorded data to the server. The input is the recorded data, and the output is the recorded data saved on the server. Specifically, after recording is completed, the data is sent to the server using a dedicated application.

[0799] Step 3:

[0800] The server uses a speech recognition tool to convert the audio portion of the recorded data into transcribed data. The input is the recorded data, and the output is the transcribed data. Specifically, Google Cloud Speech-to-Text is used to analyze the audio data and generate text data.

[0801] Step 4:

[0802] The server converts the generated transcription data into summary data using a summarization tool. The input is transcription data, and the output is summary data. Specifically, OpenAI GPT-4 is used to extract key points and generate summaries.

[0803] Step 5:

[0804] The server stores and manages the generated summary data in a database. The input is summary data, and the output is summary data stored in the database. Specifically, the summary data is registered in the database along with the lecture ID and lecturer name.

[0805] Step 6:

[0806] Users access the database through a dedicated user interface and view the summary data. The input is a search query from the user interface, and the output is summary data as search results. Specifically, users enter a lecture ID or keyword to search for summary data.

[0807] Step 7:

[0808] The server analyzes the students' evaluation data and displays the highly rated summary data as especially recommended data. The input is the students' evaluation data, and the output is the summary data with ratings. Specifically, the server analyzes the evaluation points and comments provided by the students and displays the highly rated summary data on the user interface.

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

[0810] This invention combines an emotion engine with a system that allows training instructors to efficiently refer to the content of other instructors' lectures and refine their own lectures. The system performs a series of processes: recording lectures, transcribing them, and generating summaries. Furthermore, when viewing saved summaries, the emotion engine is used to recognize the user's emotions, and the display content can be flexibly adjusted based on those emotions.

[0811] Acquiring Recording Data

[0812] Device:

[0813] The lecturer records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0814] Transcription processing

[0815] server:

[0816] The server receives the recorded data and temporarily stores it. Once the recording data has been received, the transcription process begins. The server calls a speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data, and the generated transcription data is temporarily stored on the server.

[0817] Summary Generation

[0818] server:

[0819] The generated transcription data is then converted into summary data using a summarization tool. The summarization tool analyzes the transcription data, extracts important points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0820] Summary data storage and management

[0821] server:

[0822] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored.

[0823] Viewing summary data

[0824] User (instructor):

[0825] Lecturers view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to other lecturers' summaries to identify areas for improvement in their own lectures. At this time, an emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions. For example, it can identify parts that the lecturer found interesting or uncomfortable while viewing.

[0826] Reflecting emotional data

[0827] server:

[0828] The emotion engine adjusts the content of the summary data based on the emotional data it recognizes. For example, it can highlight parts that are recognized as interesting, or suggest other related materials for parts that are recognized as unpleasant. This improves the accuracy and satisfaction of the information provided to users.

[0829] Reflection of participant evaluations

[0830] server:

[0831] The system has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Students evaluate the lecture after it is over, and the data is sent to the server and stored in a database. The server analyzes this evaluation data and can recommend highly rated summary data to the instructor. Furthermore, emotional data recognized by the emotion engine is also reflected as part of the evaluation. This further improves the fairness and accuracy of the evaluation.

[0832] Specific examples

[0833] 1. Uploading the recording data

[0834] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[0835] 2. Transcription and summary generation

[0836] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[0837] 3. Storage and management of summary data

[0838] The server stores the generated summary data and the lecture ID together in a database.

[0839] 4. Viewing summaries by other instructors

[0840] The user (lecturer) searches for the summary data of "lecture123" through a dedicated portal and checks the content on the display screen. At that time, the emotion engine analyzes the user's facial expressions and tone of voice, and the emotional data is also saved.

[0841] 5. Displaying highly rated summary data

[0842] The server analyzes the student evaluations and emotion data, and displays the highly evaluated summary data as especially recommended data on each instructor's portal.

[0843] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. In addition, the flexible provision of information based on emotional data is expected to improve the quality of learning for students.

[0844] The processing flow will be explained below.

[0845] Step 1:

[0846] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[0847] Step 2:

[0848] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[0849] Step 3:

[0850] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[0851] Step 4:

[0852] Server: The server then calls the summarization tool, which converts the transcript into summary data. The summarization tool analyzes the text data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[0853] Step 5:

[0854] Server: The generated summary data is saved in a database. When saved, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[0855] Step 6:

[0856] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The search results are displayed, and the summary data can be viewed.

[0857] Step 7:

[0858] User (instructor): While viewing the summary data, the emotion engine analyzes the user's facial expressions and vocal tone. The emotion engine identifies the parts that the user found interesting or unpleasant, and sends the emotion data to the server.

[0859] Step 8:

[0860] Server: The server stores the emotion data recognized by the emotion engine. The emotion data is associated with the summary data and used for future analysis and display adjustments.

[0861] Step 9:

[0862] Server: Based on the emotion data, the server adjusts the content of the summary data displayed. For example, it highlights parts that the user finds interesting, and suggests other related materials for parts that are perceived as unpleasant. This adjustment allows the server to provide information that is tailored to the user's interests.

[0863] Step 10:

[0864] Server: Collects and analyzes student evaluation data, and displays highly rated summary data as especially recommended data. Based on the analysis results of student evaluations and emotion data, highly rated summary data is recommended to the instructor.

[0865] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures. It also enables flexible information provision based on user emotions, which is expected to improve the quality of learning for students.

[0866] Example 2

[0867] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0868] Conventional training systems have the drawback of requiring time and effort to refer to other lecturers' lecture content. Furthermore, they do not provide feedback that reflects the students' feelings and evaluations, making it difficult to improve the lecture content. Furthermore, there is a lack of a way to increase student satisfaction while maintaining the quality of the summary data.

[0869] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0870] In this invention, the server includes means for acquiring lecture content from other lecturers as recorded data, means for converting the recorded data into transcription data using a speech recognition device, means for converting the transcription data into summary data using a summarization device, means for making the saved summary data viewable, means for recognizing a user's emotions when viewing the summary data and adjusting the display content, and means for collecting student evaluation data on the lecture and recommending highly rated data. This allows lecturers to efficiently refer to the lecture content of other lecturers and improve their own lecture content. Furthermore, flexible feedback reflecting student emotions and evaluations is provided, thereby increasing student satisfaction.

[0871] A "lecturer" is a person who gives a lecture in an educational or training setting.

[0872] "Recorded data" refers to digital data containing video and audio recordings of lecture content.

[0873] A "voice recognition device" is a device or software that analyzes recorded speech and converts it into text data.

[0874] "Transcription data" is text data generated from speech by a speech recognition device.

[0875] A "summarization device" is a device or software that analyzes transcription data, extracts important points and themes, and generates concise summary data.

[0876] "Summary data" is text data that succinctly summarizes the important points and themes of the lecture content.

[0877] A "database" is a system that stores and manages multiple data in an organized manner, making it easy to search and access.

[0878] "Emotion recognition" refers to analyzing a user's facial expressions and tone of voice to identify their emotional state at that moment.

[0879] "Adjusting the display content" means improving the accuracy of information provision by changing or highlighting the content of the summary data in accordance with the user's emotions.

[0880] "Evaluation data" refers to data on evaluations and feedback on the content of a lecture provided by students after the lecture.

[0881] "Recommended data" is data that has been judged to have a particularly high rating from a large amount of evaluation data and is to be recommended to other users.

[0882] This invention combines an emotion engine with a system that allows users to efficiently refer to the lecture content of other lecturers and refine their own lecture content. The system acquires recorded lecture data, transcribes it, and then performs a series of processes to generate a summary. Furthermore, when viewing saved summary data, the emotion engine is used to recognize the user's emotions and provides a function to flexibly adjust the displayed content based on those emotions.

[0883] Acquiring and uploading recording data

[0884] The user (lecturer) records the lecture content and saves the recorded data on their device. Next, they access a dedicated application or web portal and use the upload function for the recorded data. By selecting the recorded data and pressing the upload button, the recorded data is sent to the server. For example, the user uploads "lecture123.mp4" to the server through the dedicated portal.

[0885] Transcription processing

[0886] The server analyzes the received recording data using a speech recognition device (e.g., Google Cloud Speech-to-Text API). The server converts the audio data into text data and temporarily stores the generated transcription data. For example, the server calls a speech recognition tool, analyzes the audio portion of "lecture123.mp4," and transcribes it.

[0887] Summary Generation

[0888] The server analyzes the generated transcript data using a summarization device (e.g., OpenAI GPT-3), extracts important points and themes, and generates summary data. The generated summary data is temporarily stored on the server. For example, the server analyzes "lecture123_transcript.txt" using a summarization tool and generates "lecture123_summary.txt," which summarizes the important points.

[0889] Summary data storage and management

[0890] The server stores the generated summary data in a database. The database manages the summary data for each lecture and also stores metadata such as the lecture ID and lecturer name. For example, the summary data "lecture123_summary.txt" along with the lecture ID and lecturer name is stored in the database.

[0891] Viewing summary data

[0892] Users (lecturers) search for and view summary data through a dedicated application or web portal. The user interface is intuitive and includes a function for viewing the summary data for each lecture. The emotion engine analyzes the user's facial expressions and tone of voice to identify parts that interest or annoy the user. For example, a user can search for "lecture123_summary" through the dedicated portal and view the summary data on the display screen.

[0893] Reflecting emotional data

[0894] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. For example, parts that the user finds interesting are displayed in bold, and parts that the user finds unpleasant are displayed as links to supplementary materials.

[0895] Reflection of participant evaluations

[0896] The server assigns the students' evaluation data to the summary data and displays the highly rated summary data as recommended data. Students evaluate the data after the lecture, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. For example, evaluation data collected from students after the lecture is analyzed, and the highly rated summary data is displayed as recommended data for other lecturers.

[0897] Prompt Sentence Examples

[0898] Use a speech recognition tool to transcribe the recording data "lecture123.mp4" and a summarization tool to generate a summary. This summary data and related metadata will be stored in a database and made available for other lecturers to view. An emotion engine will be used to analyze facial expressions and tone of voice during viewing and adjust the displayed content. Also, based on the student's evaluation, particularly recommended summary data will be displayed.

[0899] This system allows lecturers to efficiently refer to the content of other lecturers' lectures and improve their own lecture content. It also provides flexible feedback that reflects the students' feelings and evaluations, thereby improving student satisfaction.

[0900] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0901] Step 1: Obtain and upload recording data

[0902] A user (lecturer) records their own lecture and saves the recorded data (e.g., "lecture123.mp4") on their device. Next, the user accesses a dedicated application or web portal and uses the upload function for the recorded data. The user selects the recorded data and presses the upload button to send the recorded data to the server. The input is the recorded data, and the output is the recorded data uploaded to the server.

[0903] Specific operation: The user selects the recorded data on the device and clicks the "Upload" button.

[0904] Step 2: Transcription processing

[0905] The server temporarily stores the received recording data. Next, the server calls a speech recognizer (e.g., Google Cloud Speech-to-Text API) to analyze the audio portion of the recording data. The speech recognizer converts the audio data into text data, and the generated transcription data (e.g., "lecture123_transcript.txt") is temporarily stored on the server. The input is the recording data, and the output is the transcription data.

[0906] Specific operation: The server calls the speech recognition API, analyzes the voice data, and saves the generated text data.

[0907] Step 3: Summary generation

[0908] The server analyzes the generated transcription data using a summarization device (e.g., OpenAI GPT-3). The server extracts important points and themes and generates a concise summary (e.g., "lecture123_summary.txt"). The generated summary data is temporarily stored on the server. The input is the transcription data, and the output is the summary data.

[0909] Specific operation: The server calls the summarization device, summarizes the transcription data, and saves the summary data.

[0910] Step 4: Storing and managing summary data

[0911] The server saves the generated summary data in a database. The database manages summary data for each lecture, along with metadata such as lecture ID and lecturer name. The input is the summary data, lecture ID, and lecturer name, and the output is the data saved in the database.

[0912] Specific operation: The server stores and manages the summary data and related metadata in a database.

[0913] Step 5: View summary data

[0914] Users (lecturers) search and view the summary data through a dedicated application or web portal. The user interface is intuitive and has a function to display summary data for each lecture. In addition, an emotion engine analyzes the user's facial expressions and tone of voice to identify parts that showed interest or discomfort. The input is the viewing request and user behavior data, and the output is an adjusted summary display.

[0915] Specific operation: The user searches for summary data through the dedicated portal and checks the summary content on the display screen.

[0916] Step 6: Reflecting emotional data

[0917] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. The input is emotional data and summary data, and the output is a display of the adjusted summary data.

[0918] Specific operation: The server uses an emotion engine to analyze the user's emotions and adjust the displayed content.

[0919] Step 7: Reflecting student evaluations

[0920] The server adds student evaluation data to the summary data and displays the highly rated summary data as recommended data. Student evaluations are conducted after the lecture ends, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. The input is evaluation data and emotional data, and the output is summary data that is displayed as recommended data.

[0921] Specific operation: The server analyzes the evaluation data of the students and displays the summary data of the highly evaluated data as especially recommended data.

[0922] (Application example 2)

[0923] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0924] In today's brick-and-mortar stores, improving customer service quality is crucial to increasing customer satisfaction. However, there is no adequate system in place for store instructors to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, there is no function to automatically adjust the displayed content based on the user's emotions, which can lead to insufficient understanding of the training content. This issue limits each store's efforts to improve customer service quality.

[0925] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0926] In this invention, the server includes: means for acquiring the content of other instructors' lectures as recorded data; means for converting the recorded data into transcription data using a voice recognition tool; means for converting the transcription data into summary data using a summarization tool; means for saving and managing the summary data; means for making the saved summary data viewable; and means including an emotion engine that recognizes the user's emotions when viewing the summary data and adjusts the display content. This allows instructors at each store to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, because the display content is adjusted based on the user's emotions, it is expected that the user's understanding of the training content will deepen and the quality of their customer service will improve.

[0927] "Lecture content of other instructors" refers to all or part of educational materials or presentations used during training or education.

[0928] "Recorded data" refers to digital data that records audio and video.

[0929] "Speech recognition tools" refers to technology or software that converts speech into text.

[0930] "Transcription data" refers to data converted from audio into text format.

[0931] A "summary tool" refers to technology or software that extracts important points from long pieces of text and converts them into short summaries.

[0932] "Summary data" refers to concise text data generated using a summarization tool.

[0933] "Means of storage and management" refers to a system that uses a database or other means to consistently store data and keep it in a state that allows it to be searched or retrieved as needed.

[0934] "Means for making data available for viewing" refers to an interface or mechanism that allows users to easily access and display stored data.

[0935] An "emotion engine" refers to technology or software that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[0936] "User emotion" refers to the emotional state, such as interest, pleasure, or discomfort, shown by the user while browsing.

[0937] "Adjusting the display content" refers to dynamically changing the format or emphasis of displayed information based on the user's emotional state.

[0938] To implement the invention, the following details regarding the server, terminals, and users are provided.

[0939] The server has a means for acquiring lecture content from other instructors as recorded data. The recorded data is digital data containing audio and video and is stored on the server. The server also has a means for converting the recorded data into transcribed data using a speech recognition tool. This conversion uses speech recognition technology and software such as speech_recognition.

[0940] The transcription data is converted into summary data using a summarization tool. This summarization tool uses the transformers library to condense long sentences into short ones. For example, a model called t5-small is used to generate summaries. This extracts key points from the transcription data and generates concise summaries.

[0941] The server has a means for storing and managing the generated summary data, and this is managed using a database. The database stores each summary data and its corresponding metadata, and important information is kept in a state where it can be easily retrieved.

[0942] An interface is also provided that allows users to view the summary data. This interface is accessible through a dedicated application or web portal and is intuitive to use. Users can refer to other instructors' summary data and obtain information to improve their own customer service skills and teaching methods. In addition, an emotion engine analyzes the user's emotional state and dynamically adjusts the displayed content based on that. The emotion engine uses OpenCV to perform facial expression analysis and identify interesting areas and areas for improvement.

[0943] For example, store A uploads a recording of a training session, and the server transcribes it using a speech recognition tool, then uses a summarization tool to generate a concise summary. Users can view this summary through smart glasses, and the emotion engine automatically highlights points of interest.

[0944] As an example of a prompt sentence, the following sentence can be input to the generative AI model:

[0945] "Today's customer service training emphasized the importance of direct communication with customers. In particular, we are required to quickly grasp customer reactions and make suggestions that meet their needs."

[0946] This allows the server to provide optimal information to users through speech recognition, summary generation, emotion analysis, and display content adjustment. This system will help improve customer service skills in brick-and-mortar stores and contribute to increased customer satisfaction.

[0947] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0948] Step 1:

[0949] The device acquires the recording data.

[0950] Specifically, the system identifies videos of training sessions at stores that are recorded on devices and saves the data in a specific file format (e.g., .mp4). Users upload the recorded data saved on their devices to a server using a dedicated application or web portal. The input is the training recording data, and the output is the recording data sent to the server.

[0951] Step 2:

[0952] The server converts the recorded data into transcribed data using a voice recognition tool.

[0953] Specifically, the server analyzes the uploaded recording data and converts the audio portion into text data using the speech_recognition library. The input is the recording data, and the output is a text file that is saved as the transcription data.

[0954] Step 3:

[0955] The server converts the transcribed data into summary data using a summarization tool.

[0956] Specifically, the server summarizes the transcription data using a summarization tool (e.g., t5-small) from the transformers library. The input is the transcription data, and the output is a summary that extracts the important points.

[0957] Step 4:

[0958] A server stores and manages the abstract data.

[0959] Specifically, the generated summary data is stored in a database, along with metadata corresponding to each summary data (e.g., training ID, instructor name, etc.). The input is the summary data and metadata, and the output is the stored summary data.

[0960] Step 5:

[0961] The user views the summary data.

[0962] Specifically, users can access the stored summary data through a dedicated application or web portal and view the contents using an intuitive interface. The input is the search criteria for the summary data, and the output is the summary data displayed as a search result.

[0963] Step 6:

[0964] The emotion engine recognizes the user's emotions and adjusts the displayed content.

[0965] Specifically, while the user is viewing the summary data, the system uses the OpenCV library to analyze the user's facial expressions and tone of voice, highlighting the parts it finds interesting, and suggesting other related materials for areas that need improvement. The input is the user's facial expressions and voice data, and the output is the adjusted display content.

[0966] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0967] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0968] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0969] [Fourth embodiment]

[0970] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0971] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0972] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0973] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0974] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0975] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0976] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0977] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0978] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0979] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0980] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0981] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0982] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0983] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[0984] Acquiring Recording Data

[0985] Device:

[0986] Lecturers record their lectures and upload the recordings to a server. The recordings contain audio and video, detailing the entire lecture. The recordings are then sent to the server via a dedicated application or web portal.

[0987] Transcription processing

[0988] server:

[0989] The server receives the uploaded recording data and transcribes it using a speech recognition tool. The speech recognition tool has the function of converting the audio portion of the recording data into text data. For example, if a recording data called "lecture123.mp4" is uploaded, the server will use the speech recognition tool to convert the entire content of the lecture into text data.

[0990] Summary Generation

[0991] server:

[0992] The generated transcript data is then converted into summary data using a summarization tool. The summarization tool extracts important points and themes from long text data and generates a concise summary. This summary data compactly summarizes the main content of the lecture.

[0993] Summary data storage and management

[0994] server:

[0995] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed.

[0996] Viewing summary data

[0997] User (instructor):

[0998] Lecturers can view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to the summary data of other lecturers to identify areas for improvement in their own lectures.

[0999] Reflection of participant evaluations

[1000] server:

[1001] Furthermore, the system has the function of adding student evaluation data to the summary data and displaying highly rated summaries as especially recommended data. Student evaluations are based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summaries to the instructor.

[1002] Specific examples

[1003] 1. Uploading the recording data

[1004] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[1005] 2. Transcription and summary generation

[1006] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[1007] 3. Storage and management of summary data

[1008] The server stores the generated summary data and the lecture ID together in a database.

[1009] 4. Viewing summaries by other instructors

[1010] The user (lecturer) searches for the summary data of "lecture123" through the dedicated portal and checks the content on the display screen.

[1011] 5. Displaying highly rated summary data

[1012] The server analyzes the student evaluations and displays the summary data with the highest evaluations as particularly recommended data on the portal of each instructor.

[1013] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. It is also expected to increase student satisfaction.

[1014] The processing flow will be explained below.

[1015] Step 1:

[1016] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[1017] Step 2:

[1018] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[1019] Step 3:

[1020] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[1021] Step 4:

[1022] Server: The server then calls the summarization tool, which converts the transcription data into summary data. The summarization tool analyzes the transcription data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[1023] Step 5:

[1024] Server: The server saves the summary data in a database. When saving, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[1025] Step 6:

[1026] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The detected summary data is displayed on the screen, and the instructor can view its contents.

[1027] Step 7:

[1028] Server: The server collects and analyzes student evaluations of the summary data. Students evaluate the lecture after it is over, and the evaluation data is sent to the server and stored in a database.

[1029] Step 8:

[1030] Server: The server selects the highly rated summary data as recommended data based on the evaluation data. This recommended data is displayed specially when the user (instructor) views the summary data, and is used as a reference by other instructors.

[1031] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures, thereby improving the quality of the overall training.

[1032] Example 1

[1033] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1034] In the past, training instructors had few ways to efficiently refer to the content of other instructors' lectures and improve their own. As a result, it was difficult to improve the quality of the lecture content and share information between instructors, which often hindered efficient training management. There was also a lack of feedback based on trainee evaluations and recommended lecture information.

[1035] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1036] In this invention, the server includes means for acquiring lecture records, means for converting the lecture records into text data using a speech recognition device, means for converting the text data into concise content using a summary generation device, means for storing and managing the concise content in a storage device, and means for making the stored concise content accessible using a display device. This allows training instructors to efficiently refer to the content of other instructors' lectures, improve their own content, and provide feedback based on the students' evaluations.

[1037] "Lecture recording" refers to video or audio data of the content of a lecture given by a training instructor.

[1038] A "voice recognition device" refers to software or hardware for converting voice data into text data.

[1039] "Text data" refers to data containing character information converted by a voice recognition device.

[1040] A "summary generator" refers to software or hardware that extracts important points from long text data and converts them into concise content.

[1041] "Concise content" refers to the summary data created by the summary generator.

[1042] "Storage" refers to data storage for saving generated concise content and making it accessible when needed.

[1043] "Display device" refers to a device or software that includes an interface that allows a user to view stored concise content.

[1044] "User interface" refers to the screens and input devices through which a user interacts with a system and manipulates and views information.

[1045] "Participant evaluation" refers to the evaluation made by participants of the lecture on the lecture content and the lecturer's performance.

[1046] "Recommended information" refers to information for displaying to other users concise content that has received particularly high ratings based on participant ratings.

[1047] The present invention provides a system that enables training instructors to efficiently refer to the content of other instructors' lectures and to improve their own lectures. Specific embodiments for carrying out the invention will be described below.

[1048] Acquiring Recording Data

[1049] Device: Lecturers record their lectures using a dedicated recording application. The recording data includes both audio and video, and records the entire lecture in detail. After recording is complete, the lecturer uploads the recording data to the server via a dedicated application or web portal. For example, a lecturer records "Lecture 123" and sends the recording file "lecture123.mp4" to the server using an application.

[1050] Receiving recording data

[1051] Server: The server receives the uploaded recording data. The received data is temporarily stored in the server's storage. This allows the server to confirm the existence of the recording data. For example, the server receives a file called "lecture123.mp4" and temporarily stores it in a specified directory.

[1052] Transcription processing

[1053] Server: The server uses a speech recognition tool (e.g., Google Cloud Speech-to-Text) to convert the audio portion of the recorded data into text data. The server first extracts the audio portion and sends it to the speech recognition tool. The converted text data is temporarily stored. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[1054] Summary Generation

[1055] Server: The server inputs the transcribed text data into a summarization tool (e.g., OpenAI GPT-3) to generate summary data. The server generates a specific prompt and sends it to the summarization tool. The generated summary data is saved. For example, the server requests a summary using the following prompt:

[1056] prompt:

[1057] Summarize the following text:

[1058] "Hello, today's lecture will cover database basics. First..."

[1059] OpenAI GPT-3 provides the summary, and the server stores the summary data: "About the basics of databases..."

[1060] Summary data storage and management

[1061] Server: The server stores the generated summary data in a database (e.g., MySQL). The summary data is also stored here along with metadata such as the lecture ID and lecturer name. For example, the server stores the summary data "On the Fundamentals of Databases..." in the database along with the lecture ID "lecture123."

[1062] Viewing summary data

[1063] User (instructor): Instructors access the database through a dedicated application or web portal to search and view abstracts. The user interface is intuitive and designed to make it easy to find the information they need. The instructor types "lecture123" into the search box and the related abstract, "Database Fundamentals...," is displayed.

[1064] Reflection of participant evaluations

[1065] Server: The server collects evaluation data from students and associates it with the summary data. It analyzes the evaluation data and manages the highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When the instructor accesses the portal, the recommended data is prominently displayed.

[1066] By utilizing generative AI models and prompts, this system allows instructors to efficiently refer to other instructors' lecture content and improve the quality of their own lectures. It also provides feedback based on student evaluations, contributing to increased student satisfaction.

[1067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1068] Step 1: Obtaining Recording Data

[1069] Terminal: The lecturer records the lecture using a dedicated recording application. After the recording is complete, the recorded data (input) is uploaded to the server (output) via the dedicated application or web portal. For example, if you record "Lecture 123," the recording file "lecture123.mp4" is sent to the server using the application.

[1070] Step 2: Receive recording data

[1071] Server: The server receives the uploaded recording data (input) and temporarily stores it in the server's storage (output). For example, a file called "lecture123.mp4" is received and temporarily stored in the specified directory " / uploads / lecture123.mp4." This allows the server to confirm the existence of the recording data.

[1072] Step 3: Transcription processing

[1073] Server: The server receives recorded data (input) and converts the audio portion into text data (output) using a speech recognition tool (e.g., Google Cloud Speech-to-Text). Specifically, the server first extracts the audio portion from the recorded data and sends it to the speech recognition tool. For example, the server sends "lecture123.mp4" to the speech recognition tool and obtains the text data "Hello, today's lecture is..."

[1074] Step 4: Summary generation

[1075] Server: The server inputs the transcribed text data (input) into a summarization tool (e.g., OpenAI GPT-3) and generates summary data (output). Specifically, the server generates a prompt and sends it to the summarization tool. The generated summary data is saved. For example, the following prompt can be used to request a summary:

[1076] prompt:

[1077] Summarize the following text:

[1078] "Hello, today's lecture will cover database basics. First..."

[1079] Based on the prompt, OpenAI GPT-3 provides a summary, and the server retrieves the summary data: "About the basics of databases..."

[1080] Step 5: Storing and managing summary data

[1081] Server: The server saves the generated summary data (input) in a database (e.g., MySQL) (output). Here, the summary data is saved along with metadata such as the lecture ID and lecturer name. For example, the summary data "On the Fundamentals of Databases..." is stored in the database along with the lecture ID "lecture123."

[1082] Step 6: View summary data

[1083] User (instructor): The instructor accesses the database through a dedicated application or web portal to search and view abstract data (input) (output). The user interface is intuitive and designed to make it easy to find the information needed. The instructor types "lecture123" in the search box and the related abstract data, "Database Fundamentals...," is displayed.

[1084] Step 7: Reflecting student evaluations

[1085] Server: The server collects evaluation data from students (input) and associates it with summary data (output). It analyzes the evaluation data and manages highly rated summaries as recommended data. For example, the evaluation system detects that the summary of "lecture123" is highly rated and registers that summary as recommended data. When a lecturer accesses the portal, the recommended data is prominently displayed.

[1086] (Application example 1)

[1087] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1088] Training personnel at factories lack the means to easily refer to the training content of other trainers and quickly and effectively improve their own training methods. Furthermore, the efficiency of improving training content by reflecting trainee evaluations is also low. This results in a decline in the quality of training and hinders improvements in production efficiency and safety.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1090] In this invention, the server includes means for acquiring the training content of other trainers as recorded data, means for converting the recorded data into transcription data using a voice recognition tool, means for converting the transcription data into summary data using a summarization tool, means for saving and managing the summary data, means for making the saved summary data available for viewing, and means for including recorded data used for training on the operation and maintenance of industrial equipment. This allows trainers to quickly refer to the training content of other trainers and efficiently improve their own training methods. Furthermore, trainee evaluations can be efficiently reflected, improving the quality of training.

[1091] A "training instructor" is a person who is responsible for teaching other employees about the operation and maintenance of equipment within a factory.

[1092] "Recorded data" refers to digital data that records the contents of lectures and training given by training instructors in audio and video format.

[1093] A "voice recognition tool" is software or hardware that converts the audio portion of recorded data into text data.

[1094] "Transcription data" refers to text data converted from audio data using a speech recognition tool.

[1095] A "summary tool" is software that extracts important points and themes from long text data and generates a concise summary.

[1096] "Summary data" is text data generated by a summarization tool that briefly summarizes the main points of lectures or training content.

[1097] "Storage and management means" means means for safely and efficiently storing and managing Abstract Data, including databases and storage systems.

[1098] "Means for making it viewable" means means for providing a function to search and display the stored summary data through a user interface.

[1099] "Industrial equipment" refers to machines and facilities used in production and maintenance in factories.

[1100] "Participant evaluation" is an evaluation made by employees who have received training about the training content and instructor, and is provided in the form of numbers and comments.

[1101] This invention is a system that allows in-plant trainers to effectively refer to training materials and improve their own training methods. This system acquires recorded lecture data and provides functions for efficiently generating, managing, and viewing summary data using voice recognition and summarization tools.

[1102] The server performs the following main processes. First, it acquires the contents of lectures given by in-plant training instructors as recorded data. The recorded data is about the operation and maintenance of factory equipment and is usually recorded using a device equipped with a camera and microphone. After the training is completed, this recorded data is uploaded to the server via a dedicated application.

[1103] The server then converts the uploaded recordings into transcripts using a speech recognition tool (e.g., Google Cloud Speech-to-Text). The speech recognition tool analyzes the audio portion of the recordings and converts them into text. The transcripts are then stored for further processing.

[1104] The server then converts the generated transcript data into summary data using a summarization tool (e.g., OpenAI GPT-4). The summarization tool extracts key points and themes from the text data and generates a concise summary. This summary effectively captures the main content of the lecture and helps the training instructor quickly grasp the content.

[1105] The generated summary data is stored in a database. The database manages summary data for each lecture, allowing for easy access when needed. Metadata such as lecture ID and lecturer name are also stored as needed. This allows training personnel to easily search and refer to the content of lectures given by other lecturers.

[1106] Furthermore, the server has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Student evaluations are given based on the quality of the lecture and the instructor's ability to explain. The server can analyze this evaluation data and recommend highly rated summary data to training instructors. This allows instructors to efficiently improve their own training methods.

[1107] For example, if a recording called "lecture123.wav" is uploaded, the server converts the audio into text using Google Cloud Speech-to-Text. Next, OpenAI GPT-4 is used to summarize the transcript, generating a summary such as, "In this lecture, we explained basic maintenance procedures and precautions." This summary is stored in a database, and if it receives high marks from students, it will be displayed to other instructors as a recommended resource.

[1108] An example prompt might be something like, "Summarize the following text: Today we will learn about maintaining factory robots. First..."

[1109] This system allows training instructors to quickly refer to the training content of other trainers and effectively improve their own training methods. It is also possible to efficiently reflect trainee evaluations, which is expected to improve the quality of training.

[1110] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1111] Step 1:

[1112] The device's built-in camera and microphone record the lectures of the training instructor. The input is the lecture content, and the output is the recorded data. Specifically, the instructor gives an explanation on the operation and maintenance of the equipment, which is then recorded in digital format.

[1113] Step 2:

[1114] The device uploads the recorded data to the server. The input is the recorded data, and the output is the recorded data saved on the server. Specifically, after recording is completed, the data is sent to the server using a dedicated application.

[1115] Step 3:

[1116] The server uses a speech recognition tool to convert the audio portion of the recorded data into transcribed data. The input is the recorded data, and the output is the transcribed data. Specifically, Google Cloud Speech-to-Text is used to analyze the audio data and generate text data.

[1117] Step 4:

[1118] The server converts the generated transcription data into summary data using a summarization tool. The input is transcription data, and the output is summary data. Specifically, OpenAI GPT-4 is used to extract key points and generate summaries.

[1119] Step 5:

[1120] The server stores and manages the generated summary data in a database. The input is summary data, and the output is summary data stored in the database. Specifically, the summary data is registered in the database along with the lecture ID and lecturer name.

[1121] Step 6:

[1122] Users access the database through a dedicated user interface and view the summary data. The input is a search query from the user interface, and the output is summary data as search results. Specifically, users enter a lecture ID or keyword to search for summary data.

[1123] Step 7:

[1124] The server analyzes the students' evaluation data and displays the highly rated summary data as especially recommended data. The input is the students' evaluation data, and the output is the summary data with ratings. Specifically, the server analyzes the evaluation points and comments provided by the students and displays the highly rated summary data on the user interface.

[1125] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1126] This invention combines an emotion engine with a system that allows training instructors to efficiently refer to the content of other instructors' lectures and refine their own lectures. The system performs a series of processes: recording lectures, transcribing them, and generating summaries. Furthermore, when viewing saved summaries, the emotion engine is used to recognize the user's emotions, and the display content can be flexibly adjusted based on those emotions.

[1127] Acquiring Recording Data

[1128] Device:

[1129] The lecturer records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[1130] Transcription processing

[1131] server:

[1132] The server receives the recorded data and temporarily stores it. Once the recording data has been received, the transcription process begins. The server calls a speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data, and the generated transcription data is temporarily stored on the server.

[1133] Summary Generation

[1134] server:

[1135] The generated transcription data is then converted into summary data using a summarization tool. The summarization tool analyzes the transcription data, extracts important points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[1136] Summary data storage and management

[1137] server:

[1138] The generated summary data is stored in a database on the server. The database manages the summary data for each lecture and allows easy access when needed. Metadata such as lecture ID and lecturer name are also stored.

[1139] Viewing summary data

[1140] User (instructor):

[1141] Lecturers view the summary data through a dedicated application or web portal. The user interface is intuitive and includes functions for searching and displaying the summary data for each lecture. Lecturers can also refer to other lecturers' summaries to identify areas for improvement in their own lectures. At this time, an emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions. For example, it can identify parts that the lecturer found interesting or uncomfortable while viewing.

[1142] Reflecting emotional data

[1143] server:

[1144] The emotion engine adjusts the content of the summary data displayed based on the emotion data recognized by the engine. For example, it can highlight parts that are recognized as interesting, or suggest other related materials for parts that are recognized as unpleasant. This improves the accuracy and satisfaction of the information provided to users.

[1145] Reflection of participant evaluations

[1146] server:

[1147] The system has the function of adding student evaluation data to the summary data and displaying highly rated summary data as especially recommended data. Students evaluate the lecture after it is over, and the data is sent to the server and stored in a database. The server analyzes this evaluation data and can recommend highly rated summary data to the instructor. Furthermore, emotional data recognized by the emotion engine is also reflected as part of the evaluation. This further improves the fairness and accuracy of the evaluation.

[1148] Specific examples

[1149] 1. Uploading the recording data

[1150] The instructor uploads the recorded data of "Lecture 123" to the server on the terminal using a dedicated application.

[1151] 2. Transcription and summary generation

[1152] The server transcribes "lecture123.mp4" using a speech recognition tool, and then generates summary data using a summarization tool.

[1153] 3. Storage and management of summary data

[1154] The server stores the generated summary data and the lecture ID together in a database.

[1155] 4. Viewing summaries by other instructors

[1156] The user (lecturer) searches for the summary data of "lecture123" through a dedicated portal and checks the content on the display screen. At that time, the emotion engine analyzes the user's facial expressions and tone of voice, and the emotional data is also saved.

[1157] 5. Displaying highly rated summary data

[1158] The server analyzes the student evaluations and emotion data, and displays the highly evaluated summary data as especially recommended data on each instructor's portal.

[1159] This system allows instructors to easily understand the content of other instructors' lectures and improve the quality of their own lectures. In addition, the flexible provision of information based on emotional data is expected to improve the quality of learning for students.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] Device: The instructor records their lecture and saves the recording on their device. Next, they access a dedicated application or web portal and select the upload function for the recorded data. After selecting the recorded data and pressing the upload button, the recorded data is sent to the server.

[1163] Step 2:

[1164] Server: The server receives the recording data and temporarily stores it. Once the recording data has been received, the transcription process begins.

[1165] Step 3:

[1166] Server: The server calls the speech recognition tool and analyzes the audio portion of the recorded data. The speech recognition tool converts the audio data into text data and temporarily stores the generated transcription data on the server.

[1167] Step 4:

[1168] Server: The server then calls the summarization tool, which converts the transcript into summary data. The summarization tool analyzes the text data, extracts key points and themes, and generates a concise summary. The generated summary data is temporarily stored on the server.

[1169] Step 5:

[1170] Server: The generated summary data is saved in a database. When saved, metadata such as the lecture ID and lecturer name are also registered. This makes it easy to search and manage data for each lecture later.

[1171] Step 6:

[1172] User (instructor): The instructor views the summary data through a dedicated application or web portal. After logging in, the instructor enters the lecture ID they wish to view and searches for the summary data. The search results are displayed, and the summary data can be viewed.

[1173] Step 7:

[1174] User (instructor): While viewing the summary data, the emotion engine analyzes the user's facial expressions and vocal tone. The emotion engine identifies the parts that the user found interesting or unpleasant, and sends the emotion data to the server.

[1175] Step 8:

[1176] Server: The server stores the emotion data recognized by the emotion engine. The emotion data is associated with the summary data and used for future analysis and display adjustments.

[1177] Step 9:

[1178] Server: Based on the emotion data, the server adjusts the content of the summary data displayed. For example, it highlights parts that the user finds interesting, and suggests other related materials for parts that are perceived as unpleasant. This adjustment allows the server to provide information that is tailored to the user's interests.

[1179] Step 10:

[1180] Server: Collects and analyzes student evaluation data, and displays highly rated summary data as especially recommended data. Based on the analysis results of student evaluations and emotion data, highly rated summary data is recommended to the instructor.

[1181] Through specific processing at each step, this system allows instructors to effectively refer to the content of other instructors' lectures and improve their own lectures. It also enables flexible information provision based on user emotions, which is expected to improve the quality of learning for students.

[1182] Example 2

[1183] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1184] Conventional training systems have the drawback of requiring time and effort to refer to other lecturers' lecture content. Furthermore, they do not provide feedback that reflects the students' feelings and evaluations, making it difficult to improve the lecture content. Furthermore, there is a lack of a way to increase student satisfaction while maintaining the quality of the summary data.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1186] In this invention, the server includes means for acquiring lecture content from other lecturers as recorded data, means for converting the recorded data into transcription data using a speech recognition device, means for converting the transcription data into summary data using a summarization device, means for making the saved summary data viewable, means for recognizing a user's emotions when viewing the summary data and adjusting the display content, and means for collecting student evaluation data on the lecture and recommending highly rated data. This allows lecturers to efficiently refer to the lecture content of other lecturers and improve their own lecture content. Furthermore, flexible feedback reflecting student emotions and evaluations is provided, thereby increasing student satisfaction.

[1187] A "lecturer" is a person who gives a lecture in an educational or training setting.

[1188] "Recorded data" refers to digital data containing video and audio recordings of lecture content.

[1189] A "voice recognition device" is a device or software that analyzes recorded speech and converts it into text data.

[1190] "Transcription data" is text data generated from speech by a speech recognition device.

[1191] A "summarization device" is a device or software that analyzes transcription data, extracts important points and themes, and generates concise summary data.

[1192] "Summary data" is text data that succinctly summarizes the important points and themes of the lecture content.

[1193] A "database" is a system that stores and manages multiple data in an organized manner, making it easy to search and access.

[1194] "Emotion recognition" refers to analyzing a user's facial expressions and tone of voice to identify their emotional state at that moment.

[1195] "Adjusting the display content" means improving the accuracy of information provision by changing or highlighting the content of the summary data in accordance with the user's emotions.

[1196] "Evaluation data" refers to data on evaluations and feedback on the content of a lecture provided by students after the lecture.

[1197] "Recommended data" is data that has been judged to have a particularly high rating from a large amount of evaluation data and is to be recommended to other users.

[1198] This invention combines an emotion engine with a system that allows users to efficiently refer to the lecture content of other lecturers and refine their own lecture content. The system acquires recorded lecture data, transcribes it, and then performs a series of processes to generate a summary. Furthermore, when viewing saved summary data, the emotion engine is used to recognize the user's emotions and provides a function to flexibly adjust the displayed content based on those emotions.

[1199] Acquiring and uploading recording data

[1200] The user (lecturer) records the lecture content and saves the recorded data on their device. Next, they access a dedicated application or web portal and use the upload function for the recorded data. By selecting the recorded data and pressing the upload button, the recorded data is sent to the server. For example, the user uploads "lecture123.mp4" to the server through the dedicated portal.

[1201] Transcription processing

[1202] The server analyzes the received recording data using a speech recognition device (e.g., Google Cloud Speech-to-Text API). The server converts the audio data into text data and temporarily stores the generated transcription data. For example, the server calls a speech recognition tool, analyzes the audio portion of "lecture123.mp4," and transcribes it.

[1203] Summary Generation

[1204] The server analyzes the generated transcript data using a summarization device (e.g., OpenAI GPT-3), extracts important points and themes, and generates summary data. The generated summary data is temporarily stored on the server. For example, the server analyzes "lecture123_transcript.txt" using a summarization tool and generates "lecture123_summary.txt," which summarizes the important points.

[1205] Summary data storage and management

[1206] The server stores the generated summary data in a database. The database manages the summary data for each lecture and also stores metadata such as the lecture ID and lecturer name. For example, the summary data "lecture123_summary.txt" along with the lecture ID and lecturer name is stored in the database.

[1207] Viewing summary data

[1208] Users (lecturers) search for and view summary data through a dedicated application or web portal. The user interface is intuitive and includes a function for viewing the summary data for each lecture. The emotion engine analyzes the user's facial expressions and tone of voice to identify parts that interest or annoy the user. For example, a user can search for "lecture123_summary" through the dedicated portal and view the summary data on the display screen.

[1209] Reflecting emotional data

[1210] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. For example, parts that the user finds interesting are displayed in bold, and parts that the user finds unpleasant are displayed as links to supplementary materials.

[1211] Reflection of participant evaluations

[1212] The server assigns the students' evaluation data to the summary data and displays the highly rated summary data as recommended data. Students evaluate the data after the lecture, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. For example, evaluation data collected from students after the lecture is analyzed, and the highly rated summary data is displayed as recommended data for other lecturers.

[1213] Prompt Sentence Examples

[1214] Use a speech recognition tool to transcribe the recording data "lecture123.mp4" and a summarization tool to generate a summary. This summary data and related metadata will be stored in a database and made available for other lecturers to view. An emotion engine will be used to analyze facial expressions and tone of voice during viewing and adjust the displayed content. Also, based on the student's evaluation, particularly recommended summary data will be displayed.

[1215] This system allows lecturers to efficiently refer to the content of other lecturers' lectures and improve their own lecture content. It also provides flexible feedback that reflects the students' feelings and evaluations, thereby improving student satisfaction.

[1216] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1217] Step 1: Obtain and upload recording data

[1218] A user (lecturer) records their own lecture and saves the recorded data (e.g., "lecture123.mp4") on their device. Next, the user accesses a dedicated application or web portal and uses the upload function for the recorded data. The user selects the recorded data and presses the upload button to send the recorded data to the server. The input is the recorded data, and the output is the recorded data uploaded to the server.

[1219] Specific operation: The user selects the recorded data on the device and clicks the "Upload" button.

[1220] Step 2: Transcription processing

[1221] The server temporarily stores the received recording data. Next, the server calls a speech recognizer (e.g., Google Cloud Speech-to-Text API) to analyze the audio portion of the recording data. The speech recognizer converts the audio data into text data, and the generated transcription data (e.g., "lecture123_transcript.txt") is temporarily stored on the server. The input is the recording data, and the output is the transcription data.

[1222] Specific operation: The server calls the speech recognition API, analyzes the voice data, and saves the generated text data.

[1223] Step 3: Summary generation

[1224] The server analyzes the generated transcription data using a summarization device (e.g., OpenAI GPT-3). The server extracts important points and themes and generates a concise summary (e.g., "lecture123_summary.txt"). The generated summary data is temporarily stored on the server. The input is the transcription data, and the output is the summary data.

[1225] Specific operation: The server calls the summarization device, summarizes the transcription data, and saves the summary data.

[1226] Step 4: Storing and managing summary data

[1227] The server saves the generated summary data in a database. The database manages summary data for each lecture, along with metadata such as lecture ID and lecturer name. The input is the summary data, lecture ID, and lecturer name, and the output is the data saved in the database.

[1228] Specific operation: The server stores and manages the summary data and related metadata in a database.

[1229] Step 5: View summary data

[1230] Users (lecturers) search and view the summary data through a dedicated application or web portal. The user interface is intuitive and has a function to display summary data for each lecture. In addition, an emotion engine analyzes the user's facial expressions and tone of voice to identify parts that showed interest or discomfort. The input is the viewing request and user behavior data, and the output is an adjusted summary display.

[1231] Specific operation: The user searches for summary data through the dedicated portal and checks the summary content on the display screen.

[1232] Step 6: Reflecting emotional data

[1233] The server adjusts the display of the summary data based on the emotional data analyzed using the emotion engine. Specifically, it highlights parts that are recognized as interesting and suggests related materials for parts that are recognized as unpleasant. The input is emotional data and summary data, and the output is a display of the adjusted summary data.

[1234] Specific operation: The server uses an emotion engine to analyze the user's emotions and adjust the displayed content.

[1235] Step 7: Reflecting student evaluations

[1236] The server adds student evaluation data to the summary data and displays the highly rated summary data as recommended data. Student evaluations are conducted after the lecture ends, and the data is sent to the server and stored in a database. Emotional data recognized by the emotion engine is also reflected in the evaluation. The input is evaluation data and emotional data, and the output is summary data that is displayed as recommended data.

[1237] Specific operation: The server analyzes the evaluation data of the students and displays the summary data of the highly evaluated data as especially recommended data.

[1238] (Application example 2)

[1239] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1240] In today's brick-and-mortar stores, improving customer service quality is crucial to increasing customer satisfaction. However, there is no adequate system in place for store instructors to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, there is no function to automatically adjust the displayed content based on the user's emotions, which can lead to insufficient understanding of the training content. This issue limits each store's efforts to improve customer service quality.

[1241] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1242] In this invention, the server includes: means for acquiring the content of other instructors' lectures as recorded data; means for converting the recorded data into transcription data using a voice recognition tool; means for converting the transcription data into summary data using a summarization tool; means for saving and managing the summary data; means for making the saved summary data viewable; and means including an emotion engine that recognizes the user's emotions when viewing the summary data and adjusts the display content. This allows instructors at each store to efficiently refer to training content from other stores and improve their own customer service skills. Furthermore, because the display content is adjusted based on the user's emotions, it is expected that the user's understanding of the training content will deepen and the quality of their customer service will improve.

[1243] "Lecture content of other instructors" refers to all or part of educational materials or presentations used during training or education.

[1244] "Recorded data" refers to digital data that records audio and video.

[1245] "Speech recognition tools" refers to technology or software that converts speech into text.

[1246] "Transcription data" refers to data converted from audio into text format.

[1247] A "summary tool" refers to technology or software that extracts important points from long pieces of text and converts them into short summaries.

[1248] "Summary data" refers to concise text data generated using a summarization tool.

[1249] "Means of storage and management" refers to a system that uses a database or other means to consistently store data and keep it in a state that allows it to be searched or retrieved as needed.

[1250] "Means for making data available for viewing" refers to an interface or mechanism that allows users to easily access and display stored data.

[1251] An "emotion engine" refers to technology or software that analyzes a user's facial expressions and tone of voice to recognize their emotional state.

[1252] "User emotion" refers to the emotional state, such as interest, pleasure, or discomfort, shown by the user while browsing.

[1253] "Adjusting the display content" refers to dynamically changing the format or emphasis of displayed information based on the user's emotional state.

[1254] To implement the invention, the following details regarding the server, terminals, and users are provided.

[1255] The server has a means for acquiring lecture content from other instructors as recorded data. The recorded data is digital data containing audio and video and is stored on the server. The server also has a means for converting the recorded data into transcribed data using a speech recognition tool. This conversion uses speech recognition technology and software such as speech_recognition.

[1256] The transcription data is converted into summary data using a summarization tool. This summarization tool uses the transformers library to condense long sentences into short ones. For example, a model called t5-small is used to generate summaries. This extracts key points from the transcription data and generates concise summaries.

[1257] The server has a means for storing and managing the generated summary data, and this is managed using a database. The database stores each summary data and its corresponding metadata, and important information is kept in a state where it can be easily retrieved.

[1258] An interface is also provided that allows users to view the summary data. This interface is accessible through a dedicated application or web portal and is intuitive to use. Users can refer to other instructors' summary data and obtain information to improve their own customer service skills and teaching methods. In addition, an emotion engine analyzes the user's emotional state and dynamically adjusts the displayed content based on that. The emotion engine uses OpenCV to perform facial expression analysis and identify interesting areas and areas for improvement.

[1259] For example, store A uploads a recording of a training session, and the server transcribes it using a speech recognition tool, then uses a summarization tool to generate a concise summary. Users can view this summary through smart glasses, and the emotion engine automatically highlights points of interest.

[1260] As an example of a prompt sentence, the following sentence can be input to the generative AI model:

[1261] "Today's customer service training emphasized the importance of direct communication with customers. In particular, we are required to quickly grasp customer reactions and make suggestions that meet their needs."

[1262] This allows the server to provide optimal information to users through speech recognition, summary generation, emotion analysis, and display content adjustment. This system will help improve customer service skills in brick-and-mortar stores and contribute to increased customer satisfaction.

[1263] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1264] Step 1:

[1265] The device acquires the recording data.

[1266] Specifically, the system identifies videos of training sessions at stores that are recorded on devices and saves the data in a specific file format (e.g., .mp4). Users upload the recorded data saved on their devices to a server using a dedicated application or web portal. The input is the training recording data, and the output is the recording data sent to the server.

[1267] Step 2:

[1268] The server converts the recorded data into transcribed data using a voice recognition tool.

[1269] Specifically, the server analyzes the uploaded recording data and converts the audio portion into text data using the speech_recognition library. The input is the recording data, and the output is a text file that is saved as the transcription data.

[1270] Step 3:

[1271] The server converts the transcribed data into summary data using a summarization tool.

[1272] Specifically, the server summarizes the transcription data using a summarization tool (e.g., t5-small) from the transformers library. The input is the transcription data, and the output is a summary that extracts the important points.

[1273] Step 4:

[1274] A server stores and manages the abstract data.

[1275] Specifically, the generated summary data is stored in a database, along with metadata corresponding to each summary data (e.g., training ID, instructor name, etc.). The input is the summary data and metadata, and the output is the stored summary data.

[1276] Step 5:

[1277] The user views the summary data.

[1278] Specifically, users can access the stored summary data through a dedicated application or web portal and view the contents using an intuitive interface. The input is the search criteria for the summary data, and the output is the summary data displayed as a search result.

[1279] Step 6:

[1280] The emotion engine recognizes the user's emotions and adjusts the displayed content.

[1281] Specifically, while the user is viewing the summary data, the system uses the OpenCV library to analyze the user's facial expressions and tone of voice, highlighting the parts it finds interesting, and suggesting other related materials for areas that need improvement. The input is the user's facial expressions and voice data, and the output is the adjusted display content.

[1282] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1283] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1284] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1285] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1286] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1287] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1288] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1289] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1290] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1291] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1292] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1293] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1294] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1295] 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.

[1296] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1297] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1298] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1299] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1300] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1301] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1302] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1303] The following is further disclosed regarding the above embodiment.

[1304] (Claim 1)

[1305] A means of obtaining recording data of lectures by other training instructors;

[1306] A means for converting the recorded data into transcription data using a voice recognition tool;

[1307] means for converting the transcription data into summary data using a summarization tool;

[1308] means for storing and managing the summary data;

[1309] means for making the stored summary data viewable;

[1310] A system including:

[1311] (Claim 2)

[1312] 2. The system according to claim 1, further comprising a user interface for viewing the summary data, and means for supporting the lecture instructor in improving the content of the lecture.

[1313] (Claim 3)

[1314] 2. The system according to claim 1, further comprising means for assigning a student rating to the summary data and displaying highly rated summary data as recommended data.

[1315] "Example 1"

[1316] (Claim 1)

[1317] a means for obtaining lecture notes;

[1318] means for converting the lecture records into text data using a voice recognition device;

[1319] means for converting the text data into a concise summary using a summary generator;

[1320] means for storing and managing said concise content in a storage device;

[1321] means for making the stored concise content accessible using a display device;

[1322] A system including:

[1323] (Claim 2)

[1324] 10. The system of claim 1, further comprising a user interface for viewing the brief content, and means for assisting the speaker in improving the content of the lecture.

[1325] (Claim 3)

[1326] The system of claim 1 , further comprising means for assigning participant ratings to the concise content and displaying highly rated concise content as recommended information.

[1327] "Application Example 1"

[1328] (Claim 1)

[1329] A means of obtaining recording data of lectures by other training instructors;

[1330] A means for converting the recorded data into transcription data using a voice recognition tool;

[1331] means for converting the transcription data into summary data using a summarization tool;

[1332] means for storing and managing the summary data;

[1333] means for making the stored summary data viewable;

[1334] a means for including video recordings used for training on the operation and maintenance of industrial equipment;

[1335] A system including:

[1336] (Claim 2)

[1337] 2. The system according to claim 1, further comprising a user interface for viewing the summary data, and means for supporting the lecture instructor in improving the content of the lecture.

[1338] (Claim 3)

[1339] 2. The system according to claim 1, further comprising means for assigning a student rating to the summary data and displaying highly rated summary data as recommended data.

[1340] "Example 2: Combining Emotion Engines"

[1341] (Claim 1)

[1342] A means for acquiring the contents of other lecturers' lectures as recording data;

[1343] means for converting the recorded data into transcription data using a voice recognition device;

[1344] means for converting the transcription data into summary data using a summarization device;

[1345] means for storing and managing the summary data;

[1346] means for making the stored summary data viewable;

[1347] means for recognizing a user's emotion when viewing the summary data and adjusting the display content;

[1348] means for collecting evaluation data of students regarding the lecture and recommending highly evaluated data;

[1349] A system including:

[1350] (Claim 2)

[1351] 2. The system of claim 1, further comprising a user interface for viewing the summary data, and means for improving the lecture content of the lecturer.

[1352] (Claim 3)

[1353] 2. The system according to claim 1, further comprising means for assigning a student rating to the summary data and displaying highly rated summary data as recommended data.

[1354] "Application example 2 when combining emotion engines"

[1355] (Claim 1)

[1356] A means of obtaining recording data of lectures by other instructors,

[1357] A means for converting the recorded data into transcription data using a voice recognition tool;

[1358] means for converting the transcription data into summary data using a summarization tool;

[1359] means for storing and managing the summary data;

[1360] means for making the stored summary data viewable;

[1361] means for recognizing a user's emotion when viewing the summary data and adjusting the display content;

[1362] A system including:

[1363] (Claim 2)

[1364] 2. The system according to claim 1, further comprising a user interface for viewing the summary data, and means for supporting the lecture instructor in improving the content of the lecture.

[1365] (Claim 3)

[1366] 2. The system according to claim 1, further comprising means for assigning a student rating to the summary data and displaying highly rated summary data as recommended data. [Explanation of symbols]

[1367] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining recording data of lectures by other training instructors; A means for converting the recorded data into transcription data using a voice recognition tool; means for converting the transcription data into summary data using a summarization tool; means for storing and managing the summary data; means for making the stored summary data viewable; A system including:

2. The system according to claim 1 , further comprising a user interface for viewing the summary data, and means for supporting the lecturer in improving the content of the lecture.

3. 2. The system according to claim 1, further comprising means for assigning a student rating to the summary data and displaying highly rated summary data as recommended data.

Images