System

Abstract

To provide an automated and efficient training animation generation system.SOLUTION: A system comprising: input means for inputting a training scenario and speech by a user; receiving means for receiving data transmitted from the input means; analyzing means for analyzing the received data; video generating means for generating video based on the analyzed data; audio generating means for generating audio based on the analyzed data; editing means for generating a training video by integrating the video and audio generated by the video generating means and the audio generating means; and storing and distributing means for storing and distributing the generated training video.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] To improve the quality and efficiency of training at companies and educational institutions, visually and audio-engaging materials are necessary. Traditional training video production methods require specialized staff to create them manually, posing significant challenges in terms of time and cost. Furthermore, because they are created manually, it is difficult to quickly generate videos tailored to individual needs. Furthermore, a lack of emotional expression in the audio can prevent participants from deepening their understanding. To solve these issues, an automated and efficient training video generation system was needed. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means. That is, a system including an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, an analysis means for analyzing the received data, a video generation means for generating video based on the analyzed data, an audio generation means for generating audio based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a storage and distribution means for saving and distributing the generated training video. Furthermore, the analysis means uses natural language processing technology to perform grammatical analysis of the scenario and lines, and the audio generation means converts text to audio using a speech synthesis engine, thereby making it possible to quickly and inexpensively generate individually tailored, high-quality training videos.

[0006] The "input means" is a device or software that provides an interface for the user to input training scenarios and lines.

[0007] The "receiving means" is a device or software having a function of receiving data transmitted from the input means.

[0008] The "analysis means" is a device or software that analyzes the received data and determines what kind of video and audio should be generated.

[0009] "Image generation means" refers to a device or software that generates an image based on the analyzed data.

[0010] "Speech generation means" refers to a device or software that generates speech based on the analyzed data.

[0011] The "editing means" is a device or software that integrates the video and audio generated by the video generation means and audio generation means into a single training video.

[0012] The "storage and distribution means" is a device or software for storing the generated training video and distributing the video to users.

[0013] "Natural language processing technology" is a technology used to perform grammatical analysis of scripts and dialogue, and to extract useful information from text.

[0014] A "speech synthesis engine" is a technology for converting text into speech, and is a device or software that artificially generates speech based on input text. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is implemented in the following specific form.

[0037] The user inputs the training scenario and dialogue into an input form on the device. This can be done on any device, such as a PC, tablet, or smartphone. For example, a user can input a scenario on the theme of "How to use a new project management tool" and enter the corresponding dialogue.

[0038] The input data is sent from the terminal to the server. After receiving the data, the server checks the integrity of the data. The received data is stored in a database and then analyzed in detail by the analysis means.

[0039] The server uses natural language processing technology to analyze the received scenario and dialogue. This allows for grammatical analysis of the scenario and dialogue and extracts keywords from the text. For example, keywords such as "project creation" and "task assignment" are extracted.

[0040] Based on the analyzed data, the server uses the image generation means to generate appropriate images, for example, for the "Project Creation" scenario, a drawing or animation of the actual project creation screen is generated.

[0041] A speech generator is used to generate speech from the analyzed data, which is then converted from text to speech by a speech synthesis engine configured to pronounce the user-entered lines with natural intonation.

[0042] The generated video and audio are integrated using editing tools. The server adjusts the video and audio so that they are synchronized, and edits them into a single training video. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to be synchronized with the video on the project creation screen.

[0043] The completed training video is stored on a server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can view the generated training video using their device. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0044] As described above, the present invention provides an efficient system that automatically generates high-quality, tailored training videos based on user-provided training scenarios and dialogue. This system solves the time and cost issues associated with traditional manual training video production and supports skill development in companies and educational institutions.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The user inputs the training scenario and lines into an input form on the terminal. For example, the user can enter a detailed description of specific operation methods for a topic such as "How to use a new project management tool."

[0048] Step 2:

[0049] The device converts the input scenario and lines into packets in JSON or XML format and sends them to the server, where the data may be encrypted.

[0050] Step 3:

[0051] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[0052] Step 4:

[0053] The server analyzes the stored data using an analytical tool. It uses natural language processing technology to analyze the grammar of the scenario and dialogue and extract important keywords. For example, keywords such as "project creation" and "task assignment" are extracted.

[0054] Step 5:

[0055] The server generates appropriate images using the image generation means based on the analysis results. For example, for the "Project Creation" scenario, a simulation or animation of an actual project creation screen is generated.

[0056] Step 6:

[0057] The server generates speech using a speech generation means based on the analysis results. Utilizing a speech synthesis engine, the lines entered by the user are converted into speech with a specific intonation. For example, the line "Click the '+' button in the upper right corner of the screen" is generated in a natural voice.

[0058] Step 7:

[0059] The server integrates the video and audio generated by the video generation means and audio generation means using the editing means, adjusts the timing so that the video and audio are properly synchronized, and edits them into a single training video.

[0060] Step 8:

[0061] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[0062] Step 9:

[0063] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[0064] Step 10:

[0065] Users can review the training videos and provide feedback as needed, including on audio pronunciation and video quality.

[0066] Step 11:

[0067] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[0068] This is a method for automatically generating high-quality training videos based on the scenario and lines provided by the user through each step.

[0069] Example 1

[0070] 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."

[0071] Existing training video creation systems require manual editing, which makes efficient video generation time-consuming and costly. They also face challenges in quickly responding to individual user needs, making it time-consuming to regenerate videos that reflect feedback. Furthermore, data consistency checks, saving, and feedback processing are often performed manually, creating complex workflows.

[0072] 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.

[0073] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving transmitted data, a consistency check means for checking the consistency of the received data and storing it in a database, an analysis means for analyzing the received data using natural language processing technology, a video generation means for generating video based on the analysis results, an audio generation means for generating audio from the analyzed data, an editing means for integrating the generated video and audio to generate a training video, a storage and distribution means for saving and distributing the generated training video, and a feedback processing means for receiving user feedback and regenerating the training video based on that. This enables the automatic generation and storage of high-quality training videos that meet user needs, and regeneration that reflects the feedback.

[0074] "Input means" refers to a device or software that allows a user to input a training scenario and lines.

[0075] The "receiving means" is a device or software that receives data sent from the input means.

[0076] The "integrity check means" refers to a device or software that has the function of checking the integrity of received data and storing it in a database after checking for errors.

[0077] "Analysis means" refers to a device or software that analyzes the received data using natural language processing technology and extracts necessary information and keywords.

[0078] "Video generation means" refers to a device or software that generates training videos based on the analyzed data.

[0079] The "speech generation means" refers to a speech synthesis engine or software that has the function of converting analyzed text data into speech.

[0080] "Editing means" refers to a device or software that synchronizes the generated video and audio and integrates them into a single training video.

[0081] The "storage and distribution means" refers to a device or software that stores the generated training video and provides an access link or distributes it to users.

[0082] A "feedback processing means" is a device or software that has the function of receiving feedback from a user and regenerating a training video based on that feedback.

[0083] "Natural language processing technology" is a technology for performing grammatical analysis and keyword extraction of scenarios and dialogue.

[0084] A "speech synthesis engine" is software or hardware that converts text data into voice data.

[0085] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is embodied in the following specific forms.

[0086] Using a device (PC, tablet, smartphone, etc.), the user enters the training scenario and dialogue into a dedicated input form. For example, the training scenario might be "How to use a new project management tool," and the corresponding dialogue might be "First, create a new project. Click the '+' button in the upper right corner of the screen."

[0087] The terminal sends the entered data to the server. This transmission uses the HTTPS protocol to send the data securely. The server checks the integrity of the received data and checks for missing fields and format errors. Once the integrity of the data has been confirmed, it is stored in a database (for example, MySQL (registered trademark) or PostgreSQL).

[0088] The server analyzes the received script and dialogue using natural language processing techniques, using natural language processing libraries such as NLTK and spaCy, to extract keywords from the text and identify key phrases such as "project creation" and "task assignment."

[0089] The server then generates video based on the analyzed data. Video generation tools such as OpenCV and Blender are used to generate the video. For example, for the "Project Creation" scenario, drawings and animations of the project creation screen are generated. For voice generation, speech synthesis engines such as Google® Text-to-Speech (TTS) API and Amazon Polly are used to generate audio files that pronounce the lines entered by the user with natural intonation.

[0090] The generated video and audio are then integrated using editing tools. The server uses a video editing tool such as FFmpeg to synchronize the video and audio and edit them into a single training video. For example, the video on the project creation screen and the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." are edited to match perfectly in time.

[0091] The completed training video is stored in cloud storage (e.g., Amazon S3) by the storage and distribution means. An access link to the video is then sent to the user's device via email or in-app notification. The user can view the generated training video by clicking the received link. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0092] For example, if a user is creating a training video for a new project management tool, here's an example prompt:

[0093] "I want to create a training video on how to use a new project management tool. The scenario should be 'How to create a new project' and the dialogue should be 'First, create a new project. Click the '+' button in the top right corner of the screen.'"

[0094] This invention allows users to efficiently create and view high-quality training videos tailored to their individual needs, solving the time and cost issues associated with traditional manual training video creation and supporting skill development in companies and educational institutions.

[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0096] Step 1:

[0097] User data entry

[0098] Input: Training scenario and dialogue

[0099] Output: Data entered in the input form

[0100] The user uses a device (PC, tablet, smartphone, etc.) to enter the training scenario and dialogue into a dedicated input form. Specifically, the user writes "How to create a new project" in the "Scenario" field of the form, and "First, create a new project. Click the '+' button in the upper right corner of the screen." in the "Dialogue" field.

[0101] Step 2:

[0102] Data transmission and reception

[0103] Input: Data entered into an input form

[0104] Output: Data sent to the server

[0105] When the user clicks the "Send" button, the device sends the scenario and dialogue data to the server in JSON format, etc. This transmission uses the HTTPS protocol to ensure secure data transmission.

[0106] Step 3:

[0107] Data integrity check and saving

[0108] Input: Data sent to the server

[0109] Output: Data stored in the database

[0110] The server checks the integrity of the received data and verifies that there are no errors. For example, it checks that the "Scenario" field is not empty and that the "Dialogue" is entered in the correct format. Once the integrity is confirmed, the data is stored in a database such as MySQL or PostgreSQL.

[0111] Step 4:

[0112] Data analysis

[0113] Input: Data stored in a database

[0114] Output: Parsed data and extracted keywords

[0115] The server analyzes the received script and dialogue using natural language processing (NLP) technology. For this analysis, it uses natural language processing libraries such as NLTK and spaCy. For example, keywords such as "project creation" and "task assignment" are extracted from the text.

[0116] Step 5:

[0117] Image Generation

[0118] Input: Parsed data, extracted keywords

[0119] Output: Generated video

[0120] The server generates images based on the analysis results. To generate images, it uses image generation tools such as OpenCV and Blender. For example, for the "Project Creation" scenario, it generates drawings and animations of the project creation screen.

[0121] Step 6:

[0122] Voice generation

[0123] Input: Parsed text data

[0124] Output: Generated audio file

[0125] The server uses a speech synthesis engine to convert the dialogue into speech. This is done using a speech synthesis engine such as the Google Text-to-Speech (TTS) API or Amazon Polly. The following dialogue, "First, create a new project. Click the '+' button in the upper right corner of the screen," is generated as an audio file with natural intonation.

[0126] Step 7:

[0127] Integrated video and audio editing

[0128] Input: Generated video and audio files

[0129] Output: Edited training video

[0130] The server uses a video editing tool such as FFmpeg to synchronize the video and audio, and then edits them into a single training video. For example, the video on the project creation screen is edited to perfectly sync with the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen."

[0131] Step 8:

[0132] Storage and distribution of training videos

[0133] Input: Edited training video

[0134] Output: Access link to the saved training video

[0135] The server saves the completed training video in cloud storage (e.g., Amazon S3), then generates a URL or access link for the storage location and sends it to the user's device via email or in-app notification. The user can view the generated training video by clicking the link.

[0136] Step 9:

[0137] Feedback and Regeneration

[0138] Input: User feedback

[0139] Output: Improved regenerated video

[0140] After watching the training video, users submit improvements and requests for additions through a feedback form. The server analyzes the feedback, regenerates the video content if necessary, and provides a new link to the improved version to the user.

[0141] (Application example 1)

[0142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0143] Conventional training for learning how to operate and maintain factory robots has the problem of being time-consuming and costly because it requires detailed explanations. Furthermore, efficiently providing such training content requires personnel with advanced expertise, and creating videos as part of the training is not easy. The present invention aims to solve these problems by providing a system that provides efficient and effective training through the automatic generation of training videos.

[0144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0145] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, an analyzing means for analyzing the received data, and a means for automatically generating a training video for learning how to operate and maintain a robot used in a factory. This makes it possible to automatically generate high-quality training videos based on the scenario and lines input by the user.

[0146] A "user" is a person or entity that inputs training scenarios and lines into the system.

[0147] A "training scenario" is a planned sequence of actions or events created for educational or training purposes.

[0148] "Dialogue" refers to the lines and explanatory text used in the training scenario.

[0149] The "input means" is an interface that the user uses to input the training scenario and lines into the system.

[0150] The "receiving means" is a device or function for receiving data sent from the input means on the system side.

[0151] "Analysis means" refers to a device or function that analyzes received data, understands the content, and extracts important information such as keywords.

[0152] The "image generating means" is a device or function for generating an appropriate image based on the information extracted by the analyzing means.

[0153] The "voice generating means" is a device or function for generating voice based on the information extracted by the analyzing means.

[0154] The "editing means" refers to a device or function for integrating the video and audio generated by the video generation means and audio generation means and editing them into a single training video.

[0155] The "storage and distribution means" refers to a device or function for storing the generated training video and distributing it as needed.

[0156] A "factory robot" is an automated mechanical device used in a factory that is programmed to perform a specific task or process.

[0157] "Operating method" means a procedure or method for using a particular machine or system.

[0158] "Maintenance procedures" are specific procedures and methods for maintaining, inspecting, and repairing machines and systems.

[0159] The system that realizes this application example automatically generates training videos on how to operate factory robots and maintenance procedures based on training scenarios and lines provided by the user. This system consists of the following main elements.

[0160] System Configuration

[0161] User Input

[0162] Users input training scenarios and lines using devices such as PCs, tablets, and smartphones. For example, they can input a scenario on the theme of "How to operate a new robot" and enter detailed lines corresponding to it.

[0163] Data reception and analysis

[0164] The data sent from the device is received by the server. After receiving this data, the server uses natural language processing technology to analyze the scenario and dialogue and extract important keywords. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted. Specifically, grammar analysis is performed using a natural language processing library called spacy.

[0165] Video and audio generation

[0166] Based on the analyzed data, the server generates appropriate video and audio using video generation and audio generation means. For video generation, the moviepy library is used to select and edit video clips that match the keywords. For audio generation, a speech synthesis engine called pyttsx3 is used to generate audio from text.

[0167] Video and audio integration and editing

[0168] The generated video and audio are then integrated using an editing tool. The video and audio are adjusted to synchronize, and finally edited into a single training video. For example, the audio "Robot arm usage procedure" is synchronized with the video of the actual robot arm operation.

[0169] Video storage and distribution

[0170] The completed training video is stored on a server using a storage and distribution method. An access link or ID for the video is then sent to the user's device. The user can then view the generated training video using their device. This solves the time and cost issues associated with traditional manual training video creation.

[0171] Examples of specific examples and prompts

[0172] As a specific example, the following scenario and dialogue could be considered for the operating procedure of a factory robot, "attaching parts."

[0173] Scenario: "To install a new part, first use the robot arm to pick it up."

[0174] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[0175] An example of a prompt is:

[0176] "Enter a scenario and lines of dialogue for how to operate a new factory robot. For example:

[0177] Scenario: "To install a new part, first use the robot arm to pick it up."

[0178] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[0179] The present invention makes it possible to automatically generate training videos that allow users to efficiently and effectively learn detailed operating methods and maintenance procedures for robots used in factories.

[0180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0181] Step 1:

[0182] This is the step where the user inputs the training scenario and lines. The user uses a device (PC, tablet, smartphone, etc.) to input a scenario and lines, such as "How to operate a new robot," into a dedicated input form. The input scenario and lines are saved on the device as data required for subsequent processing.

[0183] Step 2:

[0184] This is the step where the server receives the data sent from the terminal. When the user completes the input, the scenario and lines are sent from the terminal to the server. The server receives this data and checks the data integrity. Data in the correct format is obtained from the input scenario and lines.

[0185] Step 3:

[0186] This is the step where the server analyzes the received data. Specifically, it uses natural language processing technology (such as Spacy) to perform a grammatical analysis of the scenario and dialogue. This analysis extracts important keywords. Keywords are obtained as output data from the scenario and dialogue as input data. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted.

[0187] Step 4:

[0188] In this step, the server generates appropriate videos using a video generation means. Based on the analyzed data, it uses a video editing library called moviepy to select and combine video clips corresponding to the extracted keywords. From the keywords as input, training video clips are obtained as output.

[0189] Step 5:

[0190] In this step, the server generates speech using a speech generation means. Based on the lines extracted from the analyzed data, speech is generated using a speech synthesis engine called pyttsx3. Narration speech is obtained as output from the lines as input.

[0191] Step 6:

[0192] This is the step where the generated video and audio are edited. The server adjusts the video and audio to synchronize and integrates them into a single training video. MoviePy is used to adjust the timing of the video and audio. The input is a video clip and an audio file, and the output is an integrated training video.

[0193] Step 7:

[0194] This is the step of storing and distributing the generated training video. The server stores the completed training video and sends the user an access link or ID to the video. The user uses a terminal to view the training video by entering a specified URL or ID. The input is the integrated training video, and the output is a stored video file and an access link.

[0195] 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.

[0196] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[0197] Users input the training scenario and lines into an input form on their device. This input can be done on any device, such as a PC, tablet, or smartphone. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, a user can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while entering the corresponding lines.

[0198] The input scenario, dialogue, and emotion data are transmitted from the terminal to the server. After receiving the transmitted data, the server checks the consistency of the data. The received data is stored in a database, and then analyzed in detail by the analysis means.

[0199] The server can use natural language processing technology and an emotion engine to analyze the received scenario, dialogue, and emotion data. Natural language processing technology is used to perform a grammatical analysis of the scenario and dialogue, and to extract keywords from the text. At the same time, the emotion engine analyzes the user's emotion data and recognizes the user's intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server can determine whether the explanation evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[0200] Based on the analyzed data, the server uses the image generation means to generate appropriate images. At this time, the user's emotions recognized by the emotion engine are reflected in the generated images. For example, for a project creation scenario, if the user is feeling optimistic, images with swaying animations and bright colors are generated.

[0201] Similarly, a speech generator generates speech based on the analyzed scenario and emotion data. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user and the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0202] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[0203] The completed training video is stored on the server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0204] As described above, the present invention provides a system that automatically generates high-quality training videos based on the user's emotional data, in addition to the scenario and dialogue provided by the user. This system improves the quality of training videos, enhances learning effectiveness, and solves the problems of traditional manual video creation.

[0205] The processing flow will be explained below.

[0206] Step 1:

[0207] The user inputs the training scenario and dialogue into the input form on the device. For example, the user inputs a scenario on the theme of "How to use a new project management tool" and the corresponding dialogue. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotional data.

[0208] Step 2:

[0209] The device converts the input scenario, dialogue, and emotional data (voice and facial expression data) into packets, encrypts them, and sends them to the server in JSON or XML format.

[0210] Step 3:

[0211] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[0212] Step 4:

[0213] The server analyzes the saved scenario, dialogue, and emotion data using an analytical means. It uses natural language processing technology to perform grammatical analysis of the scenario and dialogue and extract important keywords from the text. It also uses an emotion engine to recognize the user's emotions from their voice and facial expressions. For example, the keywords "project creation" and "task assignment" are extracted, and it is recognized that the user is expressing optimistic emotions.

[0214] Step 5:

[0215] The server generates an appropriate image using the image generation means based on the analysis results. The character's facial expression and the color tone of the background are adjusted based on the user's emotion recognized by the emotion engine. For example, if the user is expressing optimistic emotion, a simulation image of the project creation screen with bright colors is generated.

[0216] Step 6:

[0217] The server generates speech using a speech generation means based on the analysis results. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user, depending on the recognized emotion. For example, speech is generated so that the line "Click the '+' button in the upper right corner of the screen" is pronounced in an optimistic tone.

[0218] Step 7:

[0219] The server integrates the video and audio generated by the video generation means and audio generation means using an editing means. The timing is adjusted so that the video and audio are properly synchronized, and they are edited into a single training video. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited so that it is synchronized with the video of the project creation screen in an optimistic tone.

[0220] Step 8:

[0221] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[0222] Step 9:

[0223] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[0224] Step 10:

[0225] Users can review training videos and provide feedback as needed, including on audio pronunciation, video quality, and appropriateness of emotional expression.

[0226] Step 11:

[0227] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[0228] Through the above steps, high-quality, emotion-sensitive training videos are automatically generated based on the scenario, dialogue, and emotion data provided by the user.

[0229] Example 2

[0230] 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."

[0231] Traditionally, creating training videos has required a lot of time and effort, and accurate editing has been difficult, especially when creating videos that contain multiple emotional expressions. Furthermore, there is a need to accurately capture the user's emotions in order to provide more effective training to viewers. To solve these problems, an automatic and highly accurate training video generation system is needed.

[0232] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, a checking means for checking the consistency of the received data, a saving means for saving the received data, an analyzing means for analyzing the saved data, a grammar analysis means for analyzing the scenario and lines using natural language processing technology, an emotion analysis means for analyzing emotion data using emotion analysis technology, a video generation means for generating video based on the analyzed data, an audio generation means for generating audio based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a saving and distribution means for saving and distributing the generated training video. This makes it possible to accurately capture the user's emotions as well as the scenario and lines provided by the user, and automatically generate high-quality training videos based on them.

[0233] A "user" is a person or organization that inputs training scenarios and lines into a terminal and provides data to the system.

[0234] "Input means" refers to devices such as computers, tablets, and smartphones that users use to input training scenarios and lines, as well as the accompanying software.

[0235] The "receiving means" is a function that allows the server to receive data transmitted from the input means.

[0236] "Checking means" refers to a mechanism for verifying the integrity of received data and verifying that it is accurate and complete.

[0237] "Storage means" is a function for storing received data in a database or storage within the server.

[0238] "Analysis means" refers to technologies and algorithms used to analyze stored data in detail and understand its contents.

[0239] "Grammar analysis means" is a function that uses natural language processing technology to grammatically analyze the text data of the scenario and dialogue, and extracts important keywords and structures.

[0240] "Emotion analysis means" is a technology for analyzing emotional data such as the user's voice and facial expressions, and recognizing the user's intentions and emotions.

[0241] "Video generation means" refers to software and hardware for creating visual content based on the analyzed data.

[0242] "Speech generation means" refers to a function for generating speech based on analyzed data, and includes a speech synthesis engine that converts text into natural speech.

[0243] The "editing means" is a function that integrates and synchronizes the video and audio generated by the video generation means and audio generation means to complete a single training video.

[0244] The "storage and distribution means" is a mechanism for storing the generated training video and distributing it to users in a viewable format.

[0245] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[0246] Users use any device (PC, tablet, smartphone, etc.) to input the training scenario and lines. This input is done through an input form on the device. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, they can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while inputting the corresponding lines.

[0247] The device sends the input scenario, lines, and emotion data to the server. This data transmission uses the HTTPS protocol. The server checks the format and content of the received data and stores it in a database. A general relational database (e.g., MySQL) is used as the database.

[0248] To analyze the received scenario, dialogue, and emotion data, the server uses natural language processing technology (e.g., the BERT model) to perform grammatical analysis of the scenario and dialogue and extract important keywords. It then uses emotion analysis technology (e.g., AWS® Rekognition or Microsoft® Azure® Emotion API) to analyze the user's emotion data and recognize their intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server determines whether the description evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[0249] Based on the analyzed data, the server generates an appropriate image using an image generation tool (e.g., Blender or Adobe After Effects). At this time, the user's emotions recognized by the emotion engine are reflected in the image generation. For example, if the user is optimistic about the project creation scenario, a bright image will be generated.

[0250] Similarly, speech generation tools (e.g., Google Text-to-Speech or Amazon Polly) generate speech based on the analyzed scenario and emotion data. The speech synthesis engine uses the user-entered lines and adjusts intonation and emotional expression according to the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0251] The generated video and audio are then combined using an editing tool (e.g., FFmpeg or Adobe Premiere Pro) and edited into a training video. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is completed. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[0252] The completed training video is stored on the server, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server can regenerate the training video based on that feedback.

[0253] Here is an example prompt:

[0254] Analyze the following scenarios and generate text and speech with the corresponding emotions.

[0255] Scenario: First, create a new project by clicking the '+' button on the top right of the screen.

[0256] Sentiment: Optimistic

[0257] Example of text and audio output: This tool is very useful for creating projects. Click on the '+' button on the top right of the screen.

[0258] Voice characteristics: Bright tone

[0259] In this way, the system of the present invention automatically generates high-quality training videos based on the scenario and dialogue provided by the user, as well as the user's emotional data, thereby improving the quality of training videos and enhancing learning effectiveness.

[0260] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0261] Step 1:

[0262] The user inputs the training scenario and lines. Using a device such as a PC, tablet, or smartphone, the user inputs the training scenario and lines into an input form. In addition, the user can record their own voice and facial expressions using the device's microphone and camera, which are then input as emotional data. The input data is temporarily stored on the device.

[0263] Input: Training scenario, dialogue, voice recording, facial expression recording

[0264] Output: Input dataset saved on device

[0265] Specific behavior: A user opens a browser, enters a scenario with the theme "How to use a new project management tool," and enters the following dialogue: "This tool is very useful for creating projects. Click the '+' button in the upper right corner of the screen." Click the record button to record the voice, and click the camera button to record the facial expression.

[0266] Step 2:

[0267] The device sends the input data to the server. The device sends the data to the server using the HTTPS protocol. The data sent consists of the training scenario, lines, and recorded voice and facial expressions.

[0268] Input: Input dataset stored on the device

[0269] Output: The dataset sent to the server

[0270] Specific operation: The device sends data packaged in JSON format to the server as an HTTPS request.

[0271] Step 3:

[0272] The server receives the data and checks its integrity. Once the server receives the data, it checks for any omissions or errors. Once the server has confirmed that the data is complete, it stores it in the database.

[0273] Input: Dataset sent to the server

[0274] Output: Validated data stored in a database

[0275] Specific behavior: The server parses the received JSON data, verifies that all required fields are present and that the data conforms to the format, and stores data that passes validation in a database (e.g., MySQL).

[0276] Step 4:

[0277] The server analyzes the scenario and dialogue. Using natural language processing technology (e.g., the BERT model), it performs a grammatical analysis of the scenario and dialogue and extracts keywords and emotions. The results of this analysis are used for subsequent processing.

[0278] Input: Scenario and dialogue data stored in the database

[0279] Output: Syntax-analyzed text data, keyword list

[0280] Specific operation: The server uses the BERT module to analyze the scenario "How to use a new project management tool" and extract important keywords (e.g., "project creation" and "task assignment").

[0281] Step 5:

[0282] The server analyzes the emotional data. Using emotion analysis technology (e.g., AWS Rekognition or Microsoft Azure Emotion API), it identifies emotions from the user's voice and facial expressions. This identifies the emotions with which the user is speaking the scenario or lines.

[0283] Input: Voice and facial expression data stored in a database

[0284] Output: Emotion recognition result (e.g. optimistic, cautious)

[0285] What it does: The server uses the AWS Rekognition API to analyze the recorded voice and facial expressions and recognize that the user is expressing optimistic emotions.

[0286] Step 6:

[0287] The server generates the video. Based on the analysis results of the saved scenario and dialogue, as well as emotional data, an appropriate video is generated using a video generation tool (e.g., Blender or Adobe After Effects). The video's color tone and movements are reflected based on the emotional data.

[0288] Input: Grammar analysis results, keyword list, emotion recognition results

[0289] Output: Emotionally-reflected video file

[0290] What it does: The server launches Blender and generates a brightly colored animated video that corresponds to the "Create a Project" scenario.

[0291] Step 7:

[0292] The server generates the speech. Based on the analyzed scenario and emotional data, a speech generator (e.g., Google Text-to-Speech or Amazon Polly) is used to generate an audio file. The speech synthesis engine adjusts intonation and emotional expression according to the recognized emotion based on the lines entered by the user.

[0293] Input: Grammar analysis results, dialogue, emotion recognition results

[0294] Output: Emotionally-reflected audio file

[0295] What it does: The server uses the Google Text-to-Speech API to convert the following line into an audio file in an optimistic tone: "This tool is very helpful for creating your project. Click the '+' button in the top right corner of the screen."

[0296] Step 8:

[0297] The server integrates the video and audio. The video and audio generated by the video generation means and audio generation means are integrated and edited into a single training video. An editing tool (e.g., FFmpeg or Adobe Premiere Pro) is used to adjust the video and audio so that they are properly synchronized.

[0298] Input: Video files, audio files

[0299] Output: Finished training video file

[0300] Specific operation: The server starts FFmpeg, places the generated video and audio on the timeline, and combines them into a single video file. For example, it edits the scene that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." so that it plays properly.

[0301] Step 9:

[0302] The server saves the completed training video and distributes it to the user. The generated training video is saved in the server's storage, and an access link or ID for the video is sent to the user's device.

[0303] Input: Completed training video file

[0304] Output: Access link or ID of the video

[0305] Specific operation: The server uploads the video file to storage (e.g. AWS S3) and sends the user an access link via email or message. The user can use this link to watch the generated training video.

[0306] (Application example 2)

[0307] 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."

[0308] Conventional training video creation systems use uniform video and audio without considering the user's emotions, making it difficult to enhance the participants' understanding and interest. Furthermore, manually editing video and audio is time-consuming and costly, making it inefficient.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines and record the user's voice and facial expression, a receiving means for receiving data transmitted from the input means, an analysis means for analyzing the received data and recognizing emotions, a video generation means for generating video that reflects emotions based on the analyzed data, an audio generation means for generating audio that reflects emotions based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a storage and distribution means for saving and distributing the generated training video. This makes it possible to create more effective training videos that reflect the user's emotions.

[0310] "Input means" refers to a device or software that allows a user to input a training scenario and lines and record the user's voice and facial expressions.

[0311] The "receiving means" is a device or software for receiving data transmitted from the input means.

[0312] The "analysis means" is a device or software for analyzing the received data and recognizing emotions.

[0313] The "image generation means" is a device or software for generating an image that reflects emotions based on the analyzed data.

[0314] The "voice generation means" is a device or software for generating voice that reflects emotions based on the analyzed data.

[0315] The "editing means" is a device or software for generating a training video by integrating the video and audio generated by the video generation means and audio generation means.

[0316] The "storage and distribution means" is a device or software for storing and distributing the generated training video.

[0317] An "emotion engine" is software or technology for analyzing a user's emotions and generating emotion data.

[0318] "Natural language processing technology" is a technology for performing grammatical analysis of scenarios and dialogue.

[0319] A "speech synthesis engine" is a technology or device for converting text into speech.

[0320] The present invention relates to a system that recognizes the user's emotions in addition to the training scenario and lines provided by the user, and generates training videos based on these.

[0321] First, the user uses an input means to input the training scenario and lines. This input means consists of a device such as a PC, tablet, or smartphone, and text is entered using a keyboard or touch screen. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotion data. At this stage, for example, we imagine a scenario such as "How to use a new project management tool" being entered, and the tone of voice and facial expressions being recorded while entering the corresponding lines.

[0322] The input scenario, dialogue, and emotional data are then transmitted from the terminal to a server. The server has a receiving means for receiving this data. The received data is stored in a database and analyzed in detail by an analyzing means. The analysis uses natural language processing technology such as TENSORFLOW (registered trademark) and emotion engines such as DeepFace and OpenCV. This allows for grammatical analysis of the scenario and dialogue and analysis of the user's emotions. For example, in response to keywords such as "project creation" and "task assignment," the tone of voice and facial expression of the user's speech can be used to determine whether the description evokes emotional expressions such as "carefully" or "optimistic."

[0323] After the analysis is complete, the image generation means generates an appropriate image based on the analysis results. The user's emotions recognized by the emotion engine are also reflected in the image generation. For example, if the user is optimistic about the project creation scenario, an image with swaying animations and bright colors will be generated.

[0324] At the same time, speech is generated by the speech generation means. Using a speech synthesis engine, speech is generated by adding intonation and emotional expressions to the inputted lines based on the analyzed scenario and emotional data. For example, the line "Please click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0325] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen.

[0326] The completed training video is stored on a server using a storage and distribution means, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0327] As a concrete example, consider a training video that teaches how to operate and maintain a robot used in a factory. In this case, the user inputs a scenario called "Procedure for Part Replacement," then inputs lines such as "First, prepare the tools to be used... Next, remove the old part..." and records emotional data such as speaking in a calm tone during the explanation. Based on this, a training video that reflects a calm tone and appropriate procedures is generated.

[0328] An example of a prompt for a generative AI model is as follows:

[0329] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[0330] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0331] Step 1:

[0332] The user inputs the training scenario and lines using the input means of the terminal. The input data is recorded as text data of the scenario and lines. In addition, the user's voice and facial expressions are recorded using a microphone and camera, and these are input as emotion data. Specifically, the user inputs a scenario called "Procedure for Part Replacement" and the lines, "First, prepare the tools you will use. Next, remove the old part," and the user's voice and facial expressions are recorded during the explanation.

[0333] Input: Scenario, lines, voice and facial expression data

[0334] Output: Text data, emotion data

[0335] Step 2:

[0336] The terminal packages the input scenario, lines, and emotion data to send to the server. This sending uses a communication method such as the HTTP protocol. The sent data is received by the server's receiving method. Specifically, text data and emotion data are sent to the server.

[0337] Input: Text data, emotion data

[0338] Output: Send data (to server)

[0339] Step 3:

[0340] The server receives the transmitted data using the receiving means. The received data is stored in a database and analyzed by the analyzing means. The analyzing means analyzes the text data using natural language processing technology (such as TensorFlow) to extract grammar and keywords. It also analyzes the emotional data using an emotion engine (such as DeepFace or OpenCV) to recognize the user's intentions and emotions.

[0341] Input: Transmitted data (text data, emotion data)

[0342] Output: Analysis results (keywords, emotion data)

[0343] Step 4:

[0344] The server's video generation means generates videos that reflect the user's emotions based on the analysis results. Specifically, it selects video material that corresponds to the scenario entered by the user and adjusts the video to match the user's emotions (e.g., optimistic, cautious, etc.). For example, if the tone is calm, a quiet background and animation with gentle movements will be selected.

[0345] Input: Analysis results (keywords, emotion data)

[0346] Output: Emotionally-reflecting images

[0347] Step 5:

[0348] The server's speech generation means uses a speech synthesis engine to convert text data into speech that reflects emotions. Based on the analysis results, intonation and emphasis are added to the dialogue to generate a speech that corresponds to the user's emotions (e.g., optimistic, cautious, etc.). Specifically, a speech synthesis engine (e.g., gTTS) is used to convert text into speech based on pre-recorded voice samples.

[0349] Input: Analysis results (text data, emotion data)

[0350] Output: Emotionally-reflecting voice

[0351] Step 6:

[0352] The editing means on the server combines the generated video and audio. This creates the final training video. The editing means synchronizes the video and audio at the appropriate times and compiles them into a single continuous video file. Specifically, the video clips and audio clips are combined using video editing software (e.g., MoviePy).

[0353] Input: Emotionally reflective video, emotionally reflective audio

[0354] Output: Consolidated training videos

[0355] Step 7:

[0356] The server's storage and distribution means stores the generated training video in a database or file server and sends the user an access link or ID to the video. Using this link or ID, the user can view the generated training video. Specifically, a URL is generated for the stored video and sent to the user via email or other means.

[0357] Input: Integrated training videos

[0358] Output: Training video access link or ID

[0359] This allows users to watch training videos that reflect a calm tone and proper procedures. For example, the following prompt sentences can be input into the generative AI model to activate the system:

[0360] Example prompt sentence:

[0361] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[0362] 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.

[0363] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0364] 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.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 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.

[0368] 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).

[0369] 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.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0377] 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."

[0378] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is implemented in the following specific form.

[0379] The user inputs the training scenario and dialogue into an input form on the device. This can be done on any device, such as a PC, tablet, or smartphone. For example, a user can input a scenario on the theme of "How to use a new project management tool" and enter the corresponding dialogue.

[0380] The input data is sent from the terminal to the server. After receiving the data, the server checks the integrity of the data. The received data is stored in a database and then analyzed in detail by the analysis means.

[0381] The server uses natural language processing technology to analyze the received scenario and dialogue. This allows for grammatical analysis of the scenario and dialogue and extracts keywords from the text. For example, keywords such as "project creation" and "task assignment" are extracted.

[0382] Based on the analyzed data, the server uses the image generation means to generate appropriate images, for example, for the "Project Creation" scenario, a drawing or animation of the actual project creation screen is generated.

[0383] A speech generator is used to generate speech from the analyzed data, which is then converted from text to speech by a speech synthesis engine configured to pronounce the user-entered lines with natural intonation.

[0384] The generated video and audio are integrated using editing tools. The server adjusts the video and audio so that they are synchronized, and edits them into a single training video. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to be synchronized with the video on the project creation screen.

[0385] The completed training video is stored on a server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can view the generated training video using their device. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0386] As described above, the present invention provides an efficient system that automatically generates high-quality, tailored training videos based on user-provided training scenarios and dialogue. This system solves the time and cost issues associated with traditional manual training video production and supports skill development in companies and educational institutions.

[0387] The processing flow will be explained below.

[0388] Step 1:

[0389] The user inputs the training scenario and lines into an input form on the terminal. For example, the user can enter a detailed description of specific operation methods for a topic such as "How to use a new project management tool."

[0390] Step 2:

[0391] The device converts the input scenario and lines into packets in JSON or XML format and sends them to the server, where the data may be encrypted.

[0392] Step 3:

[0393] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[0394] Step 4:

[0395] The server analyzes the stored data using an analytical tool. It uses natural language processing technology to analyze the grammar of the scenario and dialogue and extract important keywords. For example, keywords such as "project creation" and "task assignment" are extracted.

[0396] Step 5:

[0397] The server generates appropriate images using the image generation means based on the analysis results. For example, for the "Project Creation" scenario, a simulation or animation of an actual project creation screen is generated.

[0398] Step 6:

[0399] The server generates speech using a speech generation means based on the analysis results. Utilizing a speech synthesis engine, the lines entered by the user are converted into speech with a specific intonation. For example, the line "Click the '+' button in the upper right corner of the screen" is generated in a natural voice.

[0400] Step 7:

[0401] The server integrates the video and audio generated by the video generation means and audio generation means using the editing means, adjusts the timing so that the video and audio are properly synchronized, and edits them into a single training video.

[0402] Step 8:

[0403] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[0404] Step 9:

[0405] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[0406] Step 10:

[0407] Users can review the training videos and provide feedback as needed, including on audio pronunciation and video quality.

[0408] Step 11:

[0409] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[0410] This is a method for automatically generating high-quality training videos based on the scenario and lines provided by the user through each step.

[0411] Example 1

[0412] 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."

[0413] Existing training video creation systems require manual editing, which makes efficient video generation time-consuming and costly. They also face challenges in quickly responding to individual user needs, making it time-consuming to regenerate videos that reflect feedback. Furthermore, data consistency checks, saving, and feedback processing are often performed manually, creating complex workflows.

[0414] 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.

[0415] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving transmitted data, a consistency check means for checking the consistency of the received data and storing it in a database, an analysis means for analyzing the received data using natural language processing technology, a video generation means for generating video based on the analysis results, an audio generation means for generating audio from the analyzed data, an editing means for integrating the generated video and audio to generate a training video, a storage and distribution means for saving and distributing the generated training video, and a feedback processing means for receiving user feedback and regenerating the training video based on that. This enables the automatic generation and storage of high-quality training videos that meet user needs, and regeneration that reflects the feedback.

[0416] "Input means" refers to a device or software that allows a user to input a training scenario and lines.

[0417] The "receiving means" is a device or software that receives data sent from the input means.

[0418] The "integrity check means" refers to a device or software that has the function of checking the integrity of received data and storing it in a database after checking for errors.

[0419] "Analysis means" refers to a device or software that analyzes the received data using natural language processing technology and extracts necessary information and keywords.

[0420] "Video generation means" refers to a device or software that generates training videos based on the analyzed data.

[0421] The "speech generation means" refers to a speech synthesis engine or software that has the function of converting analyzed text data into speech.

[0422] "Editing means" refers to a device or software that synchronizes the generated video and audio and integrates them into a single training video.

[0423] The "storage and distribution means" refers to a device or software that stores the generated training video and provides an access link or distributes it to users.

[0424] A "feedback processing means" is a device or software that has the function of receiving feedback from a user and regenerating a training video based on that feedback.

[0425] "Natural language processing technology" is a technology for performing grammatical analysis and keyword extraction of scenarios and dialogue.

[0426] A "speech synthesis engine" is software or hardware that converts text data into voice data.

[0427] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is embodied in the following specific forms.

[0428] Using a device (PC, tablet, smartphone, etc.), the user enters the training scenario and dialogue into a dedicated input form. For example, the training scenario might be "How to use a new project management tool," and the corresponding dialogue might be "First, create a new project. Click the '+' button in the upper right corner of the screen."

[0429] The terminal sends the entered data to the server. This transmission uses the HTTPS protocol to send the data securely. The server checks the integrity of the received data and checks for missing fields and format errors. Once the integrity is confirmed, the data is stored in a database (for example, MySQL or PostgreSQL).

[0430] The server analyzes the received script and dialogue using natural language processing techniques, using natural language processing libraries such as NLTK and spaCy, to extract keywords from the text and identify key phrases such as "project creation" and "task assignment."

[0431] The server then generates images based on the analyzed data. This is done using tools such as OpenCV and Blender. For example, for the "Project Creation" scenario, it generates drawings and animations of the project creation screen. For voice generation, it uses voice synthesis engines such as the Google Text-to-Speech (TTS) API and Amazon Polly to generate audio files that pronounce the lines entered by the user with natural intonation.

[0432] The generated video and audio are then integrated using editing tools. The server uses a video editing tool such as FFmpeg to synchronize the video and audio and edit them into a single training video. For example, the video on the project creation screen and the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." are edited to match perfectly in time.

[0433] The completed training video is stored in cloud storage (e.g., Amazon S3) by the storage and distribution means. An access link to the video is then sent to the user's device via email or in-app notification. The user can view the generated training video by clicking the received link. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0434] For example, if a user is creating a training video for a new project management tool, here's an example prompt:

[0435] "I want to create a training video on how to use a new project management tool. The scenario should be 'How to create a new project' and the dialogue should be 'First, create a new project. Click the '+' button in the top right corner of the screen.'"

[0436] This invention allows users to efficiently create and view high-quality training videos tailored to their individual needs, solving the time and cost issues associated with traditional manual training video creation and supporting skill development in companies and educational institutions.

[0437] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0438] Step 1:

[0439] User data entry

[0440] Input: Training scenario and dialogue

[0441] Output: Data entered in the input form

[0442] The user uses a device (PC, tablet, smartphone, etc.) to enter the training scenario and dialogue into a dedicated input form. Specifically, the user writes "How to create a new project" in the "Scenario" field of the form, and "First, create a new project. Click the '+' button in the upper right corner of the screen." in the "Dialogue" field.

[0443] Step 2:

[0444] Data transmission and reception

[0445] Input: Data entered into an input form

[0446] Output: Data sent to the server

[0447] When the user clicks the "Send" button, the device sends the scenario and dialogue data to the server in JSON format, etc. This transmission uses the HTTPS protocol to ensure secure data transmission.

[0448] Step 3:

[0449] Data integrity check and saving

[0450] Input: Data sent to the server

[0451] Output: Data stored in the database

[0452] The server checks the integrity of the received data and verifies that there are no errors. For example, it checks that the "Scenario" field is not empty and that the "Dialogue" is entered in the correct format. Once the integrity is confirmed, the data is stored in a database such as MySQL or PostgreSQL.

[0453] Step 4:

[0454] Data analysis

[0455] Input: Data stored in a database

[0456] Output: Parsed data and extracted keywords

[0457] The server analyzes the received script and dialogue using natural language processing (NLP) technology. For this analysis, it uses natural language processing libraries such as NLTK and spaCy. For example, keywords such as "project creation" and "task assignment" are extracted from the text.

[0458] Step 5:

[0459] Image Generation

[0460] Input: Parsed data, extracted keywords

[0461] Output: Generated video

[0462] The server generates images based on the analysis results. To generate images, it uses image generation tools such as OpenCV and Blender. For example, for the "Project Creation" scenario, it generates drawings and animations of the project creation screen.

[0463] Step 6:

[0464] Voice generation

[0465] Input: Parsed text data

[0466] Output: Generated audio file

[0467] The server uses a speech synthesis engine to convert the dialogue into speech. This is done using a speech synthesis engine such as the Google Text-to-Speech (TTS) API or Amazon Polly. The following dialogue, "First, create a new project. Click the '+' button in the upper right corner of the screen," is generated as an audio file with natural intonation.

[0468] Step 7:

[0469] Integrated video and audio editing

[0470] Input: Generated video and audio files

[0471] Output: Edited training video

[0472] The server uses a video editing tool such as FFmpeg to synchronize the video and audio, and then edits them into a single training video. For example, the video on the project creation screen is edited to perfectly sync with the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen."

[0473] Step 8:

[0474] Storage and distribution of training videos

[0475] Input: Edited training video

[0476] Output: Access link to the saved training video

[0477] The server saves the completed training video in cloud storage (e.g., Amazon S3), then generates a URL or access link for the storage location and sends it to the user's device via email or in-app notification. The user can view the generated training video by clicking the link.

[0478] Step 9:

[0479] Feedback and Regeneration

[0480] Input: User feedback

[0481] Output: Improved regenerated video

[0482] After watching the training video, users submit improvements and requests for additions through a feedback form. The server analyzes the feedback, regenerates the video content if necessary, and provides a new link to the improved version to the user.

[0483] (Application example 1)

[0484] 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."

[0485] Conventional training for learning how to operate and maintain factory robots has the problem of being time-consuming and costly because it requires detailed explanations. Furthermore, efficiently providing such training content requires personnel with advanced expertise, and creating videos as part of the training is not easy. The present invention aims to solve these problems by providing a system that provides efficient and effective training through the automatic generation of training videos.

[0486] 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.

[0487] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, an analyzing means for analyzing the received data, and a means for automatically generating a training video for learning how to operate and maintain a robot used in a factory. This makes it possible to automatically generate high-quality training videos based on the scenario and lines input by the user.

[0488] A "user" is a person or entity that inputs training scenarios and lines into the system.

[0489] A "training scenario" is a planned sequence of actions or events created for educational or training purposes.

[0490] "Dialogue" refers to the lines and explanatory text used in the training scenario.

[0491] The "input means" is an interface that the user uses to input the training scenario and lines into the system.

[0492] The "receiving means" is a device or function for receiving data sent from the input means on the system side.

[0493] "Analysis means" refers to a device or function that analyzes received data, understands the content, and extracts important information such as keywords.

[0494] The "image generating means" is a device or function for generating an appropriate image based on the information extracted by the analyzing means.

[0495] The "voice generating means" is a device or function for generating voice based on the information extracted by the analyzing means.

[0496] The "editing means" refers to a device or function for integrating the video and audio generated by the video generation means and audio generation means and editing them into a single training video.

[0497] The "storage and distribution means" refers to a device or function for storing the generated training video and distributing it as needed.

[0498] A "factory robot" is an automated mechanical device used in a factory that is programmed to perform a specific task or process.

[0499] "Operating method" means a procedure or method for using a particular machine or system.

[0500] "Maintenance procedures" are specific procedures and methods for maintaining, inspecting, and repairing machines and systems.

[0501] The system that realizes this application example automatically generates training videos on how to operate factory robots and maintenance procedures based on training scenarios and lines provided by the user. This system consists of the following main elements.

[0502] System Configuration

[0503] User Input

[0504] Users input training scenarios and lines using devices such as PCs, tablets, and smartphones. For example, they can input a scenario on the theme of "How to operate a new robot" and enter detailed lines corresponding to it.

[0505] Data reception and analysis

[0506] The data sent from the device is received by the server. After receiving this data, the server uses natural language processing technology to analyze the scenario and dialogue and extract important keywords. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted. Specifically, grammar analysis is performed using a natural language processing library called spacy.

[0507] Video and audio generation

[0508] Based on the analyzed data, the server generates appropriate video and audio using video generation and audio generation means. For video generation, the moviepy library is used to select and edit video clips that match the keywords. For audio generation, a speech synthesis engine called pyttsx3 is used to generate audio from text.

[0509] Video and audio integration and editing

[0510] The generated video and audio are then integrated using an editing tool. The video and audio are adjusted to synchronize, and finally edited into a single training video. For example, the audio "Robot arm usage procedure" is synchronized with the video of the actual robot arm operation.

[0511] Video storage and distribution

[0512] The completed training video is stored on a server using a storage and distribution method. An access link or ID for the video is then sent to the user's device. The user can then view the generated training video using their device. This solves the time and cost issues associated with traditional manual training video creation.

[0513] Examples of specific examples and prompts

[0514] As a specific example, the following scenario and dialogue could be considered for the operating procedure of a factory robot, "attaching parts."

[0515] Scenario: "To install a new part, first use the robot arm to pick it up."

[0516] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[0517] An example of a prompt is:

[0518] "Enter a scenario and lines of dialogue for how to operate a new factory robot. For example:

[0519] Scenario: "To install a new part, first use the robot arm to pick it up."

[0520] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[0521] The present invention makes it possible to automatically generate training videos that allow users to efficiently and effectively learn detailed operating methods and maintenance procedures for robots used in factories.

[0522] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0523] Step 1:

[0524] This is the step where the user inputs the training scenario and lines. The user uses a device (PC, tablet, smartphone, etc.) to input a scenario and lines, such as "How to operate a new robot," into a dedicated input form. The input scenario and lines are saved on the device as data required for subsequent processing.

[0525] Step 2:

[0526] This is the step where the server receives the data sent from the terminal. When the user completes the input, the scenario and lines are sent from the terminal to the server. The server receives this data and checks the data integrity. Data in the correct format is obtained from the input scenario and lines.

[0527] Step 3:

[0528] This is the step where the server analyzes the received data. Specifically, it uses natural language processing technology (such as Spacy) to perform a grammatical analysis of the scenario and dialogue. This analysis extracts important keywords. Keywords are obtained as output data from the scenario and dialogue as input data. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted.

[0529] Step 4:

[0530] In this step, the server generates appropriate videos using a video generation means. Based on the analyzed data, it uses a video editing library called moviepy to select and combine video clips corresponding to the extracted keywords. From the keywords as input, training video clips are obtained as output.

[0531] Step 5:

[0532] In this step, the server generates speech using a speech generation means. Based on the lines extracted from the analyzed data, speech is generated using a speech synthesis engine called pyttsx3. Narration speech is obtained as output from the lines as input.

[0533] Step 6:

[0534] This is the step where the generated video and audio are edited. The server adjusts the video and audio to synchronize and integrates them into a single training video. MoviePy is used to adjust the timing of the video and audio. The input is a video clip and an audio file, and the output is an integrated training video.

[0535] Step 7:

[0536] This is the step of storing and distributing the generated training video. The server stores the completed training video and sends the user an access link or ID to the video. The user uses a terminal to view the training video by entering a specified URL or ID. The input is the integrated training video, and the output is a stored video file and an access link.

[0537] 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.

[0538] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[0539] Users input the training scenario and lines into an input form on their device. This input can be done on any device, such as a PC, tablet, or smartphone. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, a user can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while entering the corresponding lines.

[0540] The input scenario, dialogue, and emotion data are transmitted from the terminal to the server. After receiving the transmitted data, the server checks the consistency of the data. The received data is stored in a database, and then analyzed in detail by the analysis means.

[0541] The server can use natural language processing technology and an emotion engine to analyze the received scenario, dialogue, and emotion data. Natural language processing technology is used to perform a grammatical analysis of the scenario and dialogue, and to extract keywords from the text. At the same time, the emotion engine analyzes the user's emotion data and recognizes the user's intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server can determine whether the explanation evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[0542] Based on the analyzed data, the server uses the image generation means to generate appropriate images. At this time, the user's emotions recognized by the emotion engine are reflected in the generated images. For example, for a project creation scenario, if the user is feeling optimistic, images with swaying animations and bright colors are generated.

[0543] Similarly, a speech generator generates speech based on the analyzed scenario and emotion data. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user and the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0544] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[0545] The completed training video is stored on the server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0546] As described above, the present invention provides a system that automatically generates high-quality training videos based on the user's emotional data, in addition to the scenario and dialogue provided by the user. This system improves the quality of training videos, enhances learning effectiveness, and solves the problems of traditional manual video creation.

[0547] The processing flow will be explained below.

[0548] Step 1:

[0549] The user inputs the training scenario and dialogue into the input form on the device. For example, the user inputs a scenario on the theme of "How to use a new project management tool" and the corresponding dialogue. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotional data.

[0550] Step 2:

[0551] The device converts the input scenario, dialogue, and emotional data (voice and facial expression data) into packets, encrypts them, and sends them to the server in JSON or XML format.

[0552] Step 3:

[0553] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[0554] Step 4:

[0555] The server analyzes the saved scenario, dialogue, and emotion data using an analytical means. It uses natural language processing technology to perform grammatical analysis of the scenario and dialogue and extract important keywords from the text. It also uses an emotion engine to recognize the user's emotions from their voice and facial expressions. For example, the keywords "project creation" and "task assignment" are extracted, and it is recognized that the user is expressing optimistic emotions.

[0556] Step 5:

[0557] The server generates an appropriate image using the image generation means based on the analysis results. The character's facial expression and the color tone of the background are adjusted based on the user's emotion recognized by the emotion engine. For example, if the user is expressing optimistic emotion, a simulation image of the project creation screen with bright colors is generated.

[0558] Step 6:

[0559] The server generates speech using a speech generation means based on the analysis results. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user, depending on the recognized emotion. For example, speech is generated so that the line "Click the '+' button in the upper right corner of the screen" is pronounced in an optimistic tone.

[0560] Step 7:

[0561] The server integrates the video and audio generated by the video generation means and audio generation means using an editing means. The timing is adjusted so that the video and audio are properly synchronized, and they are edited into a single training video. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited so that it is synchronized with the video of the project creation screen in an optimistic tone.

[0562] Step 8:

[0563] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[0564] Step 9:

[0565] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[0566] Step 10:

[0567] Users can review training videos and provide feedback as needed, including on audio pronunciation, video quality, and appropriateness of emotional expression.

[0568] Step 11:

[0569] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[0570] Through the above steps, high-quality, emotion-sensitive training videos are automatically generated based on the scenario, dialogue, and emotion data provided by the user.

[0571] Example 2

[0572] 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."

[0573] Traditionally, creating training videos has required a lot of time and effort, and accurate editing has been difficult, especially when creating videos that contain multiple emotional expressions. Furthermore, there is a need to accurately capture the user's emotions in order to provide more effective training to viewers. To solve these problems, an automatic and highly accurate training video generation system is needed.

[0574] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, a checking means for checking the consistency of the received data, a saving means for saving the received data, an analyzing means for analyzing the saved data, a grammar analysis means for analyzing the scenario and lines using natural language processing technology, an emotion analysis means for analyzing emotion data using emotion analysis technology, a video generation means for generating video based on the analyzed data, an audio generation means for generating audio based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a saving and distribution means for saving and distributing the generated training video. This makes it possible to accurately capture the user's emotions as well as the scenario and lines provided by the user, and automatically generate high-quality training videos based on them.

[0575] A "user" is a person or organization that inputs training scenarios and lines into a terminal and provides data to the system.

[0576] "Input means" refers to devices such as computers, tablets, and smartphones that users use to input training scenarios and lines, as well as the accompanying software.

[0577] The "receiving means" is a function that allows the server to receive data transmitted from the input means.

[0578] "Checking means" refers to a mechanism for verifying the integrity of received data and verifying that it is accurate and complete.

[0579] "Storage means" is a function for storing received data in a database or storage within the server.

[0580] "Analysis means" refers to technologies and algorithms used to analyze stored data in detail and understand its contents.

[0581] "Grammar analysis means" is a function that uses natural language processing technology to grammatically analyze the text data of the scenario and dialogue, and extracts important keywords and structures.

[0582] "Emotion analysis means" is a technology for analyzing emotional data such as the user's voice and facial expressions, and recognizing the user's intentions and emotions.

[0583] "Video generation means" refers to software and hardware for creating visual content based on the analyzed data.

[0584] "Speech generation means" refers to a function for generating speech based on analyzed data, and includes a speech synthesis engine that converts text into natural speech.

[0585] The "editing means" is a function that integrates and synchronizes the video and audio generated by the video generation means and audio generation means to complete a single training video.

[0586] The "storage and distribution means" is a mechanism for storing the generated training video and distributing it to users in a viewable format.

[0587] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[0588] Users use any device (PC, tablet, smartphone, etc.) to input the training scenario and lines. This input is done through an input form on the device. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, they can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while inputting the corresponding lines.

[0589] The device sends the input scenario, lines, and emotion data to the server. This data transmission uses the HTTPS protocol. The server checks the format and content of the received data and stores it in a database. A general relational database (e.g., MySQL) is used as the database.

[0590] To analyze the received scenario, dialogue, and emotion data, the server uses natural language processing technology (e.g., the BERT model) to perform grammatical analysis of the scenario and dialogue and extract important keywords. It then uses emotion analysis technology (e.g., AWS Rekognition or Microsoft Azure Emotion API) to analyze the user's emotion data and recognize their intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server determines whether the description evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[0591] Based on the analyzed data, the server generates an appropriate image using an image generation tool (e.g., Blender or Adobe After Effects). At this time, the user's emotions recognized by the emotion engine are reflected in the image generation. For example, if the user is optimistic about the project creation scenario, a bright image will be generated.

[0592] Similarly, speech generation tools (e.g., Google Text-to-Speech or Amazon Polly) generate speech based on the analyzed scenario and emotion data. The speech synthesis engine uses the user-entered lines and adjusts intonation and emotional expression according to the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0593] The generated video and audio are then combined using an editing tool (e.g., FFmpeg or Adobe Premiere Pro) and edited into a training video. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is completed. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[0594] The completed training video is stored on the server, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server can regenerate the training video based on that feedback.

[0595] Here is an example prompt:

[0596] Analyze the following scenarios and generate text and speech with the corresponding emotions.

[0597] Scenario: First, create a new project by clicking the '+' button on the top right of the screen.

[0598] Sentiment: Optimistic

[0599] Example of text and audio output: This tool is very useful for creating projects. Click on the '+' button on the top right of the screen.

[0600] Voice characteristics: Bright tone

[0601] In this way, the system of the present invention automatically generates high-quality training videos based on the scenario and dialogue provided by the user, as well as the user's emotional data, thereby improving the quality of training videos and enhancing learning effectiveness.

[0602] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0603] Step 1:

[0604] The user inputs the training scenario and lines. Using a device such as a PC, tablet, or smartphone, the user inputs the training scenario and lines into an input form. In addition, the user can record their own voice and facial expressions using the device's microphone and camera, which are then input as emotional data. The input data is temporarily stored on the device.

[0605] Input: Training scenario, dialogue, voice recording, facial expression recording

[0606] Output: Input dataset saved on device

[0607] Specific behavior: A user opens a browser, enters a scenario with the theme "How to use a new project management tool," and enters the following dialogue: "This tool is very useful for creating projects. Click the '+' button in the upper right corner of the screen." Click the record button to record the voice, and click the camera button to record the facial expression.

[0608] Step 2:

[0609] The device sends the input data to the server. The device sends the data to the server using the HTTPS protocol. The data sent consists of the training scenario, lines, and recorded voice and facial expressions.

[0610] Input: Input dataset stored on the device

[0611] Output: The dataset sent to the server

[0612] Specific operation: The device sends data packaged in JSON format to the server as an HTTPS request.

[0613] Step 3:

[0614] The server receives the data and checks its integrity. Once the server receives the data, it checks for any omissions or errors. Once the server has confirmed that the data is complete, it stores it in the database.

[0615] Input: Dataset sent to the server

[0616] Output: Validated data stored in a database

[0617] Specific behavior: The server parses the received JSON data, verifies that all required fields are present and that the data conforms to the format, and stores data that passes validation in a database (e.g., MySQL).

[0618] Step 4:

[0619] The server analyzes the scenario and dialogue. Using natural language processing technology (e.g., the BERT model), it performs a grammatical analysis of the scenario and dialogue and extracts keywords and emotions. The results of this analysis are used for subsequent processing.

[0620] Input: Scenario and dialogue data stored in the database

[0621] Output: Syntax-analyzed text data, keyword list

[0622] Specific operation: The server uses the BERT module to analyze the scenario "How to use a new project management tool" and extract important keywords (e.g., "project creation" and "task assignment").

[0623] Step 5:

[0624] The server analyzes the emotional data. Using emotion analysis technology (e.g., AWS Rekognition or Microsoft Azure Emotion API), it identifies emotions from the user's voice and facial expressions. This identifies the emotions with which the user is speaking the scenario or lines.

[0625] Input: Voice and facial expression data stored in a database

[0626] Output: Emotion recognition result (e.g. optimistic, cautious)

[0627] What it does: The server uses the AWS Rekognition API to analyze the recorded voice and facial expressions and recognize that the user is expressing optimistic emotions.

[0628] Step 6:

[0629] The server generates the video. Based on the analysis results of the saved scenario and dialogue, as well as emotional data, an appropriate video is generated using a video generation tool (e.g., Blender or Adobe After Effects). The video's color tone and movements are reflected based on the emotional data.

[0630] Input: Grammar analysis results, keyword list, emotion recognition results

[0631] Output: Emotionally-reflected video file

[0632] What it does: The server launches Blender and generates a brightly colored animated video that corresponds to the "Create a Project" scenario.

[0633] Step 7:

[0634] The server generates the speech. Based on the analyzed scenario and emotional data, a speech generator (e.g., Google Text-to-Speech or Amazon Polly) is used to generate an audio file. The speech synthesis engine adjusts intonation and emotional expression according to the recognized emotion based on the lines entered by the user.

[0635] Input: Grammar analysis results, dialogue, emotion recognition results

[0636] Output: Emotionally-reflected audio file

[0637] What it does: The server uses the Google Text-to-Speech API to convert the following line into an audio file in an optimistic tone: "This tool is very helpful for creating your project. Click the '+' button in the top right corner of the screen."

[0638] Step 8:

[0639] The server integrates the video and audio. The video and audio generated by the video generation means and audio generation means are integrated and edited into a single training video. An editing tool (e.g., FFmpeg or Adobe Premiere Pro) is used to adjust the video and audio so that they are properly synchronized.

[0640] Input: Video files, audio files

[0641] Output: Finished training video file

[0642] Specific operation: The server starts FFmpeg, places the generated video and audio on the timeline, and combines them into a single video file. For example, it edits the scene that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." so that it plays properly.

[0643] Step 9:

[0644] The server saves the completed training video and distributes it to the user. The generated training video is saved in the server's storage, and an access link or ID for the video is sent to the user's device.

[0645] Input: Completed training video file

[0646] Output: Access link or ID of the video

[0647] Specific operation: The server uploads the video file to storage (e.g. AWS S3) and sends the user an access link via email or message. The user can use this link to watch the generated training video.

[0648] (Application example 2)

[0649] 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."

[0650] Conventional training video creation systems use uniform video and audio without considering the user's emotions, making it difficult to enhance the participants' understanding and interest. Furthermore, manually editing video and audio is time-consuming and costly, making it inefficient.

[0651] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines and record the user's voice and facial expression, a receiving means for receiving data transmitted from the input means, an analysis means for analyzing the received data and recognizing emotions, a video generation means for generating video that reflects emotions based on the analyzed data, an audio generation means for generating audio that reflects emotions based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a storage and distribution means for saving and distributing the generated training video. This makes it possible to create more effective training videos that reflect the user's emotions.

[0652] "Input means" refers to a device or software that allows a user to input a training scenario and lines and record the user's voice and facial expressions.

[0653] The "receiving means" is a device or software for receiving data transmitted from the input means.

[0654] The "analysis means" is a device or software for analyzing the received data and recognizing emotions.

[0655] The "image generation means" is a device or software for generating an image that reflects emotions based on the analyzed data.

[0656] The "voice generation means" is a device or software for generating voice that reflects emotions based on the analyzed data.

[0657] The "editing means" is a device or software for generating a training video by integrating the video and audio generated by the video generation means and audio generation means.

[0658] The "storage and distribution means" is a device or software for storing and distributing the generated training video.

[0659] An "emotion engine" is software or technology for analyzing a user's emotions and generating emotion data.

[0660] "Natural language processing technology" is a technology for performing grammatical analysis of scenarios and dialogue.

[0661] A "speech synthesis engine" is a technology or device for converting text into speech.

[0662] The present invention relates to a system that recognizes the user's emotions in addition to the training scenario and lines provided by the user, and generates training videos based on these.

[0663] First, the user uses an input means to input the training scenario and lines. This input means consists of a device such as a PC, tablet, or smartphone, and text is entered using a keyboard or touch screen. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotion data. At this stage, for example, we imagine a scenario such as "How to use a new project management tool" being entered, and the tone of voice and facial expressions being recorded while entering the corresponding lines.

[0664] The input scenario, dialogue, and emotion data are then sent from the terminal to a server. The server has a receiving means for receiving this data. The received data is stored in a database and then analyzed in detail by an analysis means. The analysis uses natural language processing technologies such as TensorFlow and emotion engines such as DeepFace and OpenCV. This allows for grammatical analysis of the scenario and dialogue and an analysis of the user's emotions. For example, in response to keywords such as "project creation" and "task assignment," the tone of voice and facial expression of the user's voice can be used to determine whether the explanation evokes emotions such as "carefully" or "optimistic."

[0665] After the analysis is complete, the image generation means generates an appropriate image based on the analysis results. The user's emotions recognized by the emotion engine are also reflected in the image generation. For example, if the user is optimistic about the project creation scenario, an image with swaying animations and bright colors will be generated.

[0666] At the same time, speech is generated by the speech generation means. Using a speech synthesis engine, speech is generated by adding intonation and emotional expressions to the inputted lines based on the analyzed scenario and emotional data. For example, the line "Please click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0667] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen.

[0668] The completed training video is stored on a server using a storage and distribution means, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0669] As a concrete example, consider a training video that teaches how to operate and maintain a robot used in a factory. In this case, the user inputs a scenario called "Procedure for Part Replacement," then inputs lines such as "First, prepare the tools to be used... Next, remove the old part..." and records emotional data such as speaking in a calm tone during the explanation. Based on this, a training video that reflects a calm tone and appropriate procedures is generated.

[0670] An example of a prompt for a generative AI model is as follows:

[0671] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[0672] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0673] Step 1:

[0674] The user inputs the training scenario and lines using the input means of the terminal. The input data is recorded as text data of the scenario and lines. In addition, the user's voice and facial expressions are recorded using a microphone and camera, and these are input as emotion data. Specifically, the user inputs a scenario called "Procedure for Part Replacement" and the lines, "First, prepare the tools you will use. Next, remove the old part," and the user's voice and facial expressions are recorded during the explanation.

[0675] Input: Scenario, lines, voice and facial expression data

[0676] Output: Text data, emotion data

[0677] Step 2:

[0678] The terminal packages the input scenario, lines, and emotion data to send to the server. This sending uses a communication method such as the HTTP protocol. The sent data is received by the server's receiving method. Specifically, text data and emotion data are sent to the server.

[0679] Input: Text data, emotion data

[0680] Output: Send data (to server)

[0681] Step 3:

[0682] The server receives the transmitted data using the receiving means. The received data is stored in a database and analyzed by the analyzing means. The analyzing means analyzes the text data using natural language processing technology (such as TensorFlow) to extract grammar and keywords. It also analyzes the emotional data using an emotion engine (such as DeepFace or OpenCV) to recognize the user's intentions and emotions.

[0683] Input: Transmitted data (text data, emotion data)

[0684] Output: Analysis results (keywords, emotion data)

[0685] Step 4:

[0686] The server's video generation means generates videos that reflect the user's emotions based on the analysis results. Specifically, it selects video material that corresponds to the scenario entered by the user and adjusts the video to match the user's emotions (e.g., optimistic, cautious, etc.). For example, if the tone is calm, a quiet background and animation with gentle movements will be selected.

[0687] Input: Analysis results (keywords, emotion data)

[0688] Output: Emotionally-reflecting images

[0689] Step 5:

[0690] The server's speech generation means uses a speech synthesis engine to convert text data into speech that reflects emotions. Based on the analysis results, intonation and emphasis are added to the dialogue to generate a speech that corresponds to the user's emotions (e.g., optimistic, cautious, etc.). Specifically, a speech synthesis engine (e.g., gTTS) is used to convert text into speech based on pre-recorded voice samples.

[0691] Input: Analysis results (text data, emotion data)

[0692] Output: Emotionally-reflecting voice

[0693] Step 6:

[0694] The editing means on the server combines the generated video and audio. This creates the final training video. The editing means synchronizes the video and audio at the appropriate times and compiles them into a single continuous video file. Specifically, the video clips and audio clips are combined using video editing software (e.g., MoviePy).

[0695] Input: Emotionally reflective video, emotionally reflective audio

[0696] Output: Consolidated training videos

[0697] Step 7:

[0698] The server's storage and distribution means stores the generated training video in a database or file server and sends the user an access link or ID to the video. Using this link or ID, the user can view the generated training video. Specifically, a URL is generated for the stored video and sent to the user via email or other means.

[0699] Input: Integrated training videos

[0700] Output: Training video access link or ID

[0701] This allows users to watch training videos that reflect a calm tone and proper procedures. For example, the following prompt sentences can be input into the generative AI model to activate the system:

[0702] Example prompt sentence:

[0703] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[0704] 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.

[0705] 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.

[0706] 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.

[0707] [Third embodiment]

[0708] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0709] 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.

[0710] 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).

[0711] 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.

[0712] 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.

[0713] 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).

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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."

[0720] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is implemented in the following specific form.

[0721] The user inputs the training scenario and dialogue into an input form on the device. This can be done on any device, such as a PC, tablet, or smartphone. For example, a user can input a scenario on the theme of "How to use a new project management tool" and enter the corresponding dialogue.

[0722] The input data is sent from the terminal to the server. After receiving the data, the server checks the integrity of the data. The received data is stored in a database and then analyzed in detail by the analysis means.

[0723] The server uses natural language processing technology to analyze the received scenario and dialogue. This allows for grammatical analysis of the scenario and dialogue and extracts keywords from the text. For example, keywords such as "project creation" and "task assignment" are extracted.

[0724] Based on the analyzed data, the server uses the image generation means to generate appropriate images, for example, for the "Project Creation" scenario, a drawing or animation of the actual project creation screen is generated.

[0725] A speech generator is used to generate speech from the analyzed data, which is then converted from text to speech by a speech synthesis engine configured to pronounce the user-entered lines with natural intonation.

[0726] The generated video and audio are integrated using editing tools. The server adjusts the video and audio so that they are synchronized, and edits them into a single training video. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to be synchronized with the video on the project creation screen.

[0727] The completed training video is stored on a server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can view the generated training video using their device. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0728] As described above, the present invention provides an efficient system that automatically generates high-quality, tailored training videos based on user-provided training scenarios and dialogue. This system solves the time and cost issues associated with traditional manual training video production and supports skill development in companies and educational institutions.

[0729] The processing flow will be explained below.

[0730] Step 1:

[0731] The user inputs the training scenario and lines into an input form on the terminal. For example, the user can enter a detailed description of specific operation methods for a topic such as "How to use a new project management tool."

[0732] Step 2:

[0733] The device converts the input scenario and lines into packets in JSON or XML format and sends them to the server, where the data may be encrypted.

[0734] Step 3:

[0735] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[0736] Step 4:

[0737] The server analyzes the stored data using an analytical tool. It uses natural language processing technology to analyze the grammar of the scenario and dialogue and extract important keywords. For example, keywords such as "project creation" and "task assignment" are extracted.

[0738] Step 5:

[0739] The server generates appropriate images using the image generation means based on the analysis results. For example, for the "Project Creation" scenario, a simulation or animation of an actual project creation screen is generated.

[0740] Step 6:

[0741] The server generates speech using a speech generation means based on the analysis results. Utilizing a speech synthesis engine, the lines entered by the user are converted into speech with a specific intonation. For example, the line "Click the '+' button in the upper right corner of the screen" is generated in a natural voice.

[0742] Step 7:

[0743] The server integrates the video and audio generated by the video generation means and audio generation means using the editing means, adjusts the timing so that the video and audio are properly synchronized, and edits them into a single training video.

[0744] Step 8:

[0745] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[0746] Step 9:

[0747] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[0748] Step 10:

[0749] Users can review the training videos and provide feedback as needed, including on audio pronunciation and video quality.

[0750] Step 11:

[0751] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[0752] This is a method for automatically generating high-quality training videos based on the scenario and lines provided by the user through each step.

[0753] Example 1

[0754] 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."

[0755] Existing training video creation systems require manual editing, which makes efficient video generation time-consuming and costly. They also face challenges in quickly responding to individual user needs, making it time-consuming to regenerate videos that reflect feedback. Furthermore, data consistency checks, saving, and feedback processing are often performed manually, creating complex workflows.

[0756] 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.

[0757] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving transmitted data, a consistency check means for checking the consistency of the received data and storing it in a database, an analysis means for analyzing the received data using natural language processing technology, a video generation means for generating video based on the analysis results, an audio generation means for generating audio from the analyzed data, an editing means for integrating the generated video and audio to generate a training video, a storage and distribution means for saving and distributing the generated training video, and a feedback processing means for receiving user feedback and regenerating the training video based on that. This enables the automatic generation and storage of high-quality training videos that meet user needs, and regeneration that reflects the feedback.

[0758] "Input means" refers to a device or software that allows a user to input a training scenario and lines.

[0759] The "receiving means" is a device or software that receives data sent from the input means.

[0760] The "integrity check means" refers to a device or software that has the function of checking the integrity of received data and storing it in a database after checking for errors.

[0761] "Analysis means" refers to a device or software that analyzes the received data using natural language processing technology and extracts necessary information and keywords.

[0762] "Video generation means" refers to a device or software that generates training videos based on the analyzed data.

[0763] The "speech generation means" refers to a speech synthesis engine or software that has the function of converting analyzed text data into speech.

[0764] "Editing means" refers to a device or software that synchronizes the generated video and audio and integrates them into a single training video.

[0765] The "storage and distribution means" refers to a device or software that stores the generated training video and provides an access link or distributes it to users.

[0766] A "feedback processing means" is a device or software that has the function of receiving feedback from a user and regenerating a training video based on that feedback.

[0767] "Natural language processing technology" is a technology for performing grammatical analysis and keyword extraction of scenarios and dialogue.

[0768] A "speech synthesis engine" is software or hardware that converts text data into voice data.

[0769] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is embodied in the following specific forms.

[0770] Using a device (PC, tablet, smartphone, etc.), the user enters the training scenario and dialogue into a dedicated input form. For example, the training scenario might be "How to use a new project management tool," and the corresponding dialogue might be "First, create a new project. Click the '+' button in the upper right corner of the screen."

[0771] The terminal sends the entered data to the server. This transmission uses the HTTPS protocol to send the data securely. The server checks the integrity of the received data and checks for missing fields and format errors. Once the integrity is confirmed, the data is stored in a database (for example, MySQL or PostgreSQL).

[0772] The server analyzes the received script and dialogue using natural language processing techniques, using natural language processing libraries such as NLTK and spaCy, to extract keywords from the text and identify key phrases such as "project creation" and "task assignment."

[0773] The server then generates images based on the analyzed data. This is done using tools such as OpenCV and Blender. For example, for the "Project Creation" scenario, it generates drawings and animations of the project creation screen. For voice generation, it uses voice synthesis engines such as the Google Text-to-Speech (TTS) API and Amazon Polly to generate audio files that pronounce the lines entered by the user with natural intonation.

[0774] The generated video and audio are then integrated using editing tools. The server uses a video editing tool such as FFmpeg to synchronize the video and audio and edit them into a single training video. For example, the video on the project creation screen and the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." are edited to match perfectly in time.

[0775] The completed training video is stored in cloud storage (e.g., Amazon S3) by the storage and distribution means. An access link to the video is then sent to the user's device via email or in-app notification. The user can view the generated training video by clicking the received link. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0776] For example, if a user is creating a training video for a new project management tool, here's an example prompt:

[0777] "I want to create a training video on how to use a new project management tool. The scenario should be 'How to create a new project' and the dialogue should be 'First, create a new project. Click the '+' button in the top right corner of the screen.'"

[0778] This invention allows users to efficiently create and view high-quality training videos tailored to their individual needs, solving the time and cost issues associated with traditional manual training video creation and supporting skill development in companies and educational institutions.

[0779] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0780] Step 1:

[0781] User data entry

[0782] Input: Training scenario and dialogue

[0783] Output: Data entered in the input form

[0784] The user uses a device (PC, tablet, smartphone, etc.) to enter the training scenario and dialogue into a dedicated input form. Specifically, the user writes "How to create a new project" in the "Scenario" field of the form, and "First, create a new project. Click the '+' button in the upper right corner of the screen." in the "Dialogue" field.

[0785] Step 2:

[0786] Data transmission and reception

[0787] Input: Data entered into an input form

[0788] Output: Data sent to the server

[0789] When the user clicks the "Send" button, the device sends the scenario and dialogue data to the server in JSON format, etc. This transmission uses the HTTPS protocol to ensure secure data transmission.

[0790] Step 3:

[0791] Data integrity check and saving

[0792] Input: Data sent to the server

[0793] Output: Data stored in the database

[0794] The server checks the integrity of the received data and verifies that there are no errors. For example, it checks that the "Scenario" field is not empty and that the "Dialogue" is entered in the correct format. Once the integrity is confirmed, the data is stored in a database such as MySQL or PostgreSQL.

[0795] Step 4:

[0796] Data analysis

[0797] Input: Data stored in a database

[0798] Output: Parsed data and extracted keywords

[0799] The server analyzes the received script and dialogue using natural language processing (NLP) technology. For this analysis, it uses natural language processing libraries such as NLTK and spaCy. For example, keywords such as "project creation" and "task assignment" are extracted from the text.

[0800] Step 5:

[0801] Image Generation

[0802] Input: Parsed data, extracted keywords

[0803] Output: Generated video

[0804] The server generates images based on the analysis results. To generate images, it uses image generation tools such as OpenCV and Blender. For example, for the "Project Creation" scenario, it generates drawings and animations of the project creation screen.

[0805] Step 6:

[0806] Voice generation

[0807] Input: Parsed text data

[0808] Output: Generated audio file

[0809] The server uses a speech synthesis engine to convert the dialogue into speech. This is done using a speech synthesis engine such as the Google Text-to-Speech (TTS) API or Amazon Polly. The following dialogue, "First, create a new project. Click the '+' button in the upper right corner of the screen," is generated as an audio file with natural intonation.

[0810] Step 7:

[0811] Integrated video and audio editing

[0812] Input: Generated video and audio files

[0813] Output: Edited training video

[0814] The server uses a video editing tool such as FFmpeg to synchronize the video and audio, and then edits them into a single training video. For example, the video on the project creation screen is edited to perfectly sync with the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen."

[0815] Step 8:

[0816] Storage and distribution of training videos

[0817] Input: Edited training video

[0818] Output: Access link to the saved training video

[0819] The server saves the completed training video in cloud storage (e.g., Amazon S3), then generates a URL or access link for the storage location and sends it to the user's device via email or in-app notification. The user can view the generated training video by clicking the link.

[0820] Step 9:

[0821] Feedback and Regeneration

[0822] Input: User feedback

[0823] Output: Improved regenerated video

[0824] After watching the training video, users submit improvements and requests for additions through a feedback form. The server analyzes the feedback, regenerates the video content if necessary, and provides a new link to the improved version to the user.

[0825] (Application example 1)

[0826] 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."

[0827] Conventional training for learning how to operate and maintain factory robots has the problem of being time-consuming and costly because it requires detailed explanations. Furthermore, efficiently providing such training content requires personnel with advanced expertise, and creating videos as part of the training is not easy. The present invention aims to solve these problems by providing a system that provides efficient and effective training through the automatic generation of training videos.

[0828] 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.

[0829] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, an analyzing means for analyzing the received data, and a means for automatically generating a training video for learning how to operate and maintain a robot used in a factory. This makes it possible to automatically generate high-quality training videos based on the scenario and lines input by the user.

[0830] A "user" is a person or entity that inputs training scenarios and lines into the system.

[0831] A "training scenario" is a planned sequence of actions or events created for educational or training purposes.

[0832] "Dialogue" refers to the lines and explanatory text used in the training scenario.

[0833] The "input means" is an interface that the user uses to input the training scenario and lines into the system.

[0834] The "receiving means" is a device or function for receiving data sent from the input means on the system side.

[0835] "Analysis means" refers to a device or function that analyzes received data, understands the content, and extracts important information such as keywords.

[0836] The "image generating means" is a device or function for generating an appropriate image based on the information extracted by the analyzing means.

[0837] The "voice generating means" is a device or function for generating voice based on the information extracted by the analyzing means.

[0838] The "editing means" refers to a device or function for integrating the video and audio generated by the video generation means and audio generation means and editing them into a single training video.

[0839] The "storage and distribution means" refers to a device or function for storing the generated training video and distributing it as needed.

[0840] A "factory robot" is an automated mechanical device used in a factory that is programmed to perform a specific task or process.

[0841] "Operating method" means a procedure or method for using a particular machine or system.

[0842] "Maintenance procedures" are specific procedures and methods for maintaining, inspecting, and repairing machines and systems.

[0843] The system that realizes this application example automatically generates training videos on how to operate factory robots and maintenance procedures based on training scenarios and lines provided by the user. This system consists of the following main elements.

[0844] System Configuration

[0845] User Input

[0846] Users input training scenarios and lines using devices such as PCs, tablets, and smartphones. For example, they can input a scenario on the theme of "How to operate a new robot" and enter detailed lines corresponding to it.

[0847] Data reception and analysis

[0848] The data sent from the device is received by the server. After receiving this data, the server uses natural language processing technology to analyze the scenario and dialogue and extract important keywords. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted. Specifically, grammar analysis is performed using a natural language processing library called spacy.

[0849] Video and audio generation

[0850] Based on the analyzed data, the server generates appropriate video and audio using video generation and audio generation means. For video generation, the moviepy library is used to select and edit video clips that match the keywords. For audio generation, a speech synthesis engine called pyttsx3 is used to generate audio from text.

[0851] Video and audio integration and editing

[0852] The generated video and audio are then integrated using an editing tool. The video and audio are adjusted to synchronize, and finally edited into a single training video. For example, the audio "Robot arm usage procedure" is synchronized with the video of the actual robot arm operation.

[0853] Video storage and distribution

[0854] The completed training video is stored on a server using a storage and distribution method. An access link or ID for the video is then sent to the user's device. The user can then view the generated training video using their device. This solves the time and cost issues associated with traditional manual training video creation.

[0855] Examples of specific examples and prompts

[0856] As a specific example, the following scenario and dialogue could be considered for the operating procedure of a factory robot, "attaching parts."

[0857] Scenario: "To install a new part, first use the robot arm to pick it up."

[0858] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[0859] An example of a prompt is:

[0860] "Enter a scenario and lines of dialogue for how to operate a new factory robot. For example:

[0861] Scenario: "To install a new part, first use the robot arm to pick it up."

[0862] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[0863] The present invention makes it possible to automatically generate training videos that allow users to efficiently and effectively learn detailed operating methods and maintenance procedures for robots used in factories.

[0864] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0865] Step 1:

[0866] This is the step where the user inputs the training scenario and lines. The user uses a device (PC, tablet, smartphone, etc.) to input a scenario and lines, such as "How to operate a new robot," into a dedicated input form. The input scenario and lines are saved on the device as data required for subsequent processing.

[0867] Step 2:

[0868] This is the step where the server receives the data sent from the terminal. When the user completes the input, the scenario and lines are sent from the terminal to the server. The server receives this data and checks the data integrity. Data in the correct format is obtained from the input scenario and lines.

[0869] Step 3:

[0870] This is the step where the server analyzes the received data. Specifically, it uses natural language processing technology (such as Spacy) to perform a grammatical analysis of the scenario and dialogue. This analysis extracts important keywords. Keywords are obtained as output data from the scenario and dialogue as input data. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted.

[0871] Step 4:

[0872] In this step, the server generates appropriate videos using a video generation means. Based on the analyzed data, it uses a video editing library called moviepy to select and combine video clips corresponding to the extracted keywords. From the keywords as input, training video clips are obtained as output.

[0873] Step 5:

[0874] In this step, the server generates speech using a speech generation means. Based on the lines extracted from the analyzed data, speech is generated using a speech synthesis engine called pyttsx3. Narration speech is obtained as output from the lines as input.

[0875] Step 6:

[0876] This is the step where the generated video and audio are edited. The server adjusts the video and audio to synchronize and integrates them into a single training video. MoviePy is used to adjust the timing of the video and audio. The input is a video clip and an audio file, and the output is an integrated training video.

[0877] Step 7:

[0878] This is the step of storing and distributing the generated training video. The server stores the completed training video and sends the user an access link or ID to the video. The user uses a terminal to view the training video by entering a specified URL or ID. The input is the integrated training video, and the output is a stored video file and an access link.

[0879] 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.

[0880] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[0881] Users input the training scenario and lines into an input form on their device. This input can be done on any device, such as a PC, tablet, or smartphone. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, a user can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while entering the corresponding lines.

[0882] The input scenario, dialogue, and emotion data are transmitted from the terminal to the server. After receiving the transmitted data, the server checks the consistency of the data. The received data is stored in a database, and then analyzed in detail by the analysis means.

[0883] The server can use natural language processing technology and an emotion engine to analyze the received scenario, dialogue, and emotion data. Natural language processing technology is used to perform a grammatical analysis of the scenario and dialogue, and to extract keywords from the text. At the same time, the emotion engine analyzes the user's emotion data and recognizes the user's intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server can determine whether the explanation evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[0884] Based on the analyzed data, the server uses the image generation means to generate appropriate images. At this time, the user's emotions recognized by the emotion engine are reflected in the generated images. For example, for a project creation scenario, if the user is feeling optimistic, images with swaying animations and bright colors are generated.

[0885] Similarly, a speech generator generates speech based on the analyzed scenario and emotion data. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user and the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0886] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[0887] The completed training video is stored on the server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[0888] As described above, the present invention provides a system that automatically generates high-quality training videos based on the user's emotional data, in addition to the scenario and dialogue provided by the user. This system improves the quality of training videos, enhances learning effectiveness, and solves the problems of traditional manual video creation.

[0889] The processing flow will be explained below.

[0890] Step 1:

[0891] The user inputs the training scenario and dialogue into the input form on the device. For example, the user inputs a scenario on the theme of "How to use a new project management tool" and the corresponding dialogue. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotional data.

[0892] Step 2:

[0893] The device converts the input scenario, dialogue, and emotional data (voice and facial expression data) into packets, encrypts them, and sends them to the server in JSON or XML format.

[0894] Step 3:

[0895] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[0896] Step 4:

[0897] The server analyzes the saved scenario, dialogue, and emotion data using an analytical means. It uses natural language processing technology to perform grammatical analysis of the scenario and dialogue and extract important keywords from the text. It also uses an emotion engine to recognize the user's emotions from their voice and facial expressions. For example, the keywords "project creation" and "task assignment" are extracted, and it is recognized that the user is expressing optimistic emotions.

[0898] Step 5:

[0899] The server generates an appropriate image using the image generation means based on the analysis results. The character's facial expression and the color tone of the background are adjusted based on the user's emotion recognized by the emotion engine. For example, if the user is expressing optimistic emotion, a simulation image of the project creation screen with bright colors is generated.

[0900] Step 6:

[0901] The server generates speech using a speech generation means based on the analysis results. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user, depending on the recognized emotion. For example, speech is generated so that the line "Click the '+' button in the upper right corner of the screen" is pronounced in an optimistic tone.

[0902] Step 7:

[0903] The server integrates the video and audio generated by the video generation means and audio generation means using an editing means. The timing is adjusted so that the video and audio are properly synchronized, and they are edited into a single training video. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited so that it is synchronized with the video of the project creation screen in an optimistic tone.

[0904] Step 8:

[0905] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[0906] Step 9:

[0907] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[0908] Step 10:

[0909] Users can review training videos and provide feedback as needed, including on audio pronunciation, video quality, and appropriateness of emotional expression.

[0910] Step 11:

[0911] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[0912] Through the above steps, high-quality, emotion-sensitive training videos are automatically generated based on the scenario, dialogue, and emotion data provided by the user.

[0913] Example 2

[0914] 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."

[0915] Traditionally, creating training videos has required a lot of time and effort, and accurate editing has been difficult, especially when creating videos that contain multiple emotional expressions. Furthermore, there is a need to accurately capture the user's emotions in order to provide more effective training to viewers. To solve these problems, an automatic and highly accurate training video generation system is needed.

[0916] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, a checking means for checking the consistency of the received data, a saving means for saving the received data, an analyzing means for analyzing the saved data, a grammar analysis means for analyzing the scenario and lines using natural language processing technology, an emotion analysis means for analyzing emotion data using emotion analysis technology, a video generation means for generating video based on the analyzed data, an audio generation means for generating audio based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a saving and distribution means for saving and distributing the generated training video. This makes it possible to accurately capture the user's emotions as well as the scenario and lines provided by the user, and automatically generate high-quality training videos based on them.

[0917] A "user" is a person or organization that inputs training scenarios and lines into a terminal and provides data to the system.

[0918] "Input means" refers to devices such as computers, tablets, and smartphones that users use to input training scenarios and lines, as well as the accompanying software.

[0919] The "receiving means" is a function that allows the server to receive data transmitted from the input means.

[0920] "Checking means" refers to a mechanism for verifying the integrity of received data and verifying that it is accurate and complete.

[0921] "Storage means" is a function for storing received data in a database or storage within the server.

[0922] "Analysis means" refers to technologies and algorithms used to analyze stored data in detail and understand its contents.

[0923] "Grammar analysis means" is a function that uses natural language processing technology to grammatically analyze the text data of the scenario and dialogue, and extracts important keywords and structures.

[0924] "Emotion analysis means" is a technology for analyzing emotional data such as the user's voice and facial expressions, and recognizing the user's intentions and emotions.

[0925] "Video generation means" refers to software and hardware for creating visual content based on the analyzed data.

[0926] "Speech generation means" refers to a function for generating speech based on analyzed data, and includes a speech synthesis engine that converts text into natural speech.

[0927] The "editing means" is a function that integrates and synchronizes the video and audio generated by the video generation means and audio generation means to complete a single training video.

[0928] The "storage and distribution means" is a mechanism for storing the generated training video and distributing it to users in a viewable format.

[0929] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[0930] Users use any device (PC, tablet, smartphone, etc.) to input the training scenario and lines. This input is done through an input form on the device. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, they can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while inputting the corresponding lines.

[0931] The device sends the input scenario, lines, and emotion data to the server. This data transmission uses the HTTPS protocol. The server checks the format and content of the received data and stores it in a database. A general relational database (e.g., MySQL) is used as the database.

[0932] To analyze the received scenario, dialogue, and emotion data, the server uses natural language processing technology (e.g., the BERT model) to perform grammatical analysis of the scenario and dialogue and extract important keywords. It then uses emotion analysis technology (e.g., AWS Rekognition or Microsoft Azure Emotion API) to analyze the user's emotion data and recognize their intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server determines whether the description evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[0933] Based on the analyzed data, the server generates an appropriate image using an image generation tool (e.g., Blender or Adobe After Effects). At this time, the user's emotions recognized by the emotion engine are reflected in the image generation. For example, if the user is optimistic about the project creation scenario, a bright image will be generated.

[0934] Similarly, speech generation tools (e.g., Google Text-to-Speech or Amazon Polly) generate speech based on the analyzed scenario and emotion data. The speech synthesis engine uses the user-entered lines and adjusts intonation and emotional expression according to the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[0935] The generated video and audio are then combined using an editing tool (e.g., FFmpeg or Adobe Premiere Pro) and edited into a training video. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is completed. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[0936] The completed training video is stored on the server, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server can regenerate the training video based on that feedback.

[0937] Here is an example prompt:

[0938] Analyze the following scenarios and generate text and speech with the corresponding emotions.

[0939] Scenario: First, create a new project by clicking the '+' button on the top right of the screen.

[0940] Sentiment: Optimistic

[0941] Example of text and audio output: This tool is very useful for creating projects. Click on the '+' button on the top right of the screen.

[0942] Voice characteristics: Bright tone

[0943] In this way, the system of the present invention automatically generates high-quality training videos based on the scenario and dialogue provided by the user, as well as the user's emotional data, thereby improving the quality of training videos and enhancing learning effectiveness.

[0944] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0945] Step 1:

[0946] The user inputs the training scenario and lines. Using a device such as a PC, tablet, or smartphone, the user inputs the training scenario and lines into an input form. In addition, the user can record their own voice and facial expressions using the device's microphone and camera, which are then input as emotional data. The input data is temporarily stored on the device.

[0947] Input: Training scenario, dialogue, voice recording, facial expression recording

[0948] Output: Input dataset saved on device

[0949] Specific behavior: A user opens a browser, enters a scenario with the theme "How to use a new project management tool," and enters the following dialogue: "This tool is very useful for creating projects. Click the '+' button in the upper right corner of the screen." Click the record button to record the voice, and click the camera button to record the facial expression.

[0950] Step 2:

[0951] The device sends the input data to the server. The device sends the data to the server using the HTTPS protocol. The data sent consists of the training scenario, lines, and recorded voice and facial expressions.

[0952] Input: Input dataset stored on the device

[0953] Output: The dataset sent to the server

[0954] Specific operation: The device sends data packaged in JSON format to the server as an HTTPS request.

[0955] Step 3:

[0956] The server receives the data and checks its integrity. Once the server receives the data, it checks for any omissions or errors. Once the server has confirmed that the data is complete, it stores it in the database.

[0957] Input: Dataset sent to the server

[0958] Output: Validated data stored in a database

[0959] Specific behavior: The server parses the received JSON data, verifies that all required fields are present and that the data conforms to the format, and stores data that passes validation in a database (e.g., MySQL).

[0960] Step 4:

[0961] The server analyzes the scenario and dialogue. Using natural language processing technology (e.g., the BERT model), it performs a grammatical analysis of the scenario and dialogue and extracts keywords and emotions. The results of this analysis are used for subsequent processing.

[0962] Input: Scenario and dialogue data stored in the database

[0963] Output: Syntax-analyzed text data, keyword list

[0964] Specific operation: The server uses the BERT module to analyze the scenario "How to use a new project management tool" and extract important keywords (e.g., "project creation" and "task assignment").

[0965] Step 5:

[0966] The server analyzes the emotional data. Using emotion analysis technology (e.g., AWS Rekognition or Microsoft Azure Emotion API), it identifies emotions from the user's voice and facial expressions. This identifies the emotions with which the user is speaking the scenario or lines.

[0967] Input: Voice and facial expression data stored in a database

[0968] Output: Emotion recognition result (e.g. optimistic, cautious)

[0969] What it does: The server uses the AWS Rekognition API to analyze the recorded voice and facial expressions and recognize that the user is expressing optimistic emotions.

[0970] Step 6:

[0971] The server generates the video. Based on the analysis results of the saved scenario and dialogue, as well as emotional data, an appropriate video is generated using a video generation tool (e.g., Blender or Adobe After Effects). The video's color tone and movements are reflected based on the emotional data.

[0972] Input: Grammar analysis results, keyword list, emotion recognition results

[0973] Output: Emotionally-reflected video file

[0974] What it does: The server launches Blender and generates a brightly colored animated video that corresponds to the "Create a Project" scenario.

[0975] Step 7:

[0976] The server generates the speech. Based on the analyzed scenario and emotional data, a speech generator (e.g., Google Text-to-Speech or Amazon Polly) is used to generate an audio file. The speech synthesis engine adjusts intonation and emotional expression according to the recognized emotion based on the lines entered by the user.

[0977] Input: Grammar analysis results, dialogue, emotion recognition results

[0978] Output: Emotionally-reflected audio file

[0979] What it does: The server uses the Google Text-to-Speech API to convert the following line into an audio file in an optimistic tone: "This tool is very helpful for creating your project. Click the '+' button in the top right corner of the screen."

[0980] Step 8:

[0981] The server integrates the video and audio. The video and audio generated by the video generation means and audio generation means are integrated and edited into a single training video. An editing tool (e.g., FFmpeg or Adobe Premiere Pro) is used to adjust the video and audio so that they are properly synchronized.

[0982] Input: Video files, audio files

[0983] Output: Finished training video file

[0984] Specific operation: The server starts FFmpeg, places the generated video and audio on the timeline, and combines them into a single video file. For example, it edits the scene that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." so that it plays properly.

[0985] Step 9:

[0986] The server saves the completed training video and distributes it to the user. The generated training video is saved in the server's storage, and an access link or ID for the video is sent to the user's device.

[0987] Input: Completed training video file

[0988] Output: Access link or ID of the video

[0989] Specific operation: The server uploads the video file to storage (e.g. AWS S3) and sends the user an access link via email or message. The user can use this link to watch the generated training video.

[0990] (Application example 2)

[0991] 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."

[0992] Conventional training video creation systems use uniform video and audio without considering the user's emotions, making it difficult to enhance the participants' understanding and interest. Furthermore, manually editing video and audio is time-consuming and costly, making it inefficient.

[0993] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines and record the user's voice and facial expression, a receiving means for receiving data transmitted from the input means, an analysis means for analyzing the received data and recognizing emotions, a video generation means for generating video that reflects emotions based on the analyzed data, an audio generation means for generating audio that reflects emotions based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a storage and distribution means for saving and distributing the generated training video. This makes it possible to create more effective training videos that reflect the user's emotions.

[0994] "Input means" refers to a device or software that allows a user to input a training scenario and lines and record the user's voice and facial expressions.

[0995] The "receiving means" is a device or software for receiving data transmitted from the input means.

[0996] The "analysis means" is a device or software for analyzing the received data and recognizing emotions.

[0997] The "image generation means" is a device or software for generating an image that reflects emotions based on the analyzed data.

[0998] The "voice generation means" is a device or software for generating voice that reflects emotions based on the analyzed data.

[0999] The "editing means" is a device or software for generating a training video by integrating the video and audio generated by the video generation means and audio generation means.

[1000] The "storage and distribution means" is a device or software for storing and distributing the generated training video.

[1001] An "emotion engine" is software or technology for analyzing a user's emotions and generating emotion data.

[1002] "Natural language processing technology" is a technology for performing grammatical analysis of scenarios and dialogue.

[1003] A "speech synthesis engine" is a technology or device for converting text into speech.

[1004] The present invention relates to a system that recognizes the user's emotions in addition to the training scenario and lines provided by the user, and generates training videos based on these.

[1005] First, the user uses an input means to input the training scenario and lines. This input means consists of a device such as a PC, tablet, or smartphone, and text is entered using a keyboard or touch screen. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotion data. At this stage, for example, we imagine a scenario such as "How to use a new project management tool" being entered, and the tone of voice and facial expressions being recorded while entering the corresponding lines.

[1006] The input scenario, dialogue, and emotion data are then sent from the terminal to a server. The server has a receiving means for receiving this data. The received data is stored in a database and then analyzed in detail by an analysis means. The analysis uses natural language processing technologies such as TensorFlow and emotion engines such as DeepFace and OpenCV. This allows for grammatical analysis of the scenario and dialogue and an analysis of the user's emotions. For example, in response to keywords such as "project creation" and "task assignment," the tone of voice and facial expression of the user's voice can be used to determine whether the explanation evokes emotions such as "carefully" or "optimistic."

[1007] After the analysis is complete, the image generation means generates an appropriate image based on the analysis results. The user's emotions recognized by the emotion engine are also reflected in the image generation. For example, if the user is optimistic about the project creation scenario, an image with swaying animations and bright colors will be generated.

[1008] At the same time, speech is generated by the speech generation means. Using a speech synthesis engine, speech is generated by adding intonation and emotional expressions to the inputted lines based on the analyzed scenario and emotional data. For example, the line "Please click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[1009] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen.

[1010] The completed training video is stored on a server using a storage and distribution means, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[1011] As a concrete example, consider a training video that teaches how to operate and maintain a robot used in a factory. In this case, the user inputs a scenario called "Procedure for Part Replacement," then inputs lines such as "First, prepare the tools to be used... Next, remove the old part..." and records emotional data such as speaking in a calm tone during the explanation. Based on this, a training video that reflects a calm tone and appropriate procedures is generated.

[1012] An example of a prompt for a generative AI model is as follows:

[1013] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[1014] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1015] Step 1:

[1016] The user inputs the training scenario and lines using the input means of the terminal. The input data is recorded as text data of the scenario and lines. In addition, the user's voice and facial expressions are recorded using a microphone and camera, and these are input as emotion data. Specifically, the user inputs a scenario called "Procedure for Part Replacement" and the lines, "First, prepare the tools you will use. Next, remove the old part," and the user's voice and facial expressions are recorded during the explanation.

[1017] Input: Scenario, lines, voice and facial expression data

[1018] Output: Text data, emotion data

[1019] Step 2:

[1020] The terminal packages the input scenario, lines, and emotion data to send to the server. This sending uses a communication method such as the HTTP protocol. The sent data is received by the server's receiving method. Specifically, text data and emotion data are sent to the server.

[1021] Input: Text data, emotion data

[1022] Output: Send data (to server)

[1023] Step 3:

[1024] The server receives the transmitted data using the receiving means. The received data is stored in a database and analyzed by the analyzing means. The analyzing means analyzes the text data using natural language processing technology (such as TensorFlow) to extract grammar and keywords. It also analyzes the emotional data using an emotion engine (such as DeepFace or OpenCV) to recognize the user's intentions and emotions.

[1025] Input: Transmitted data (text data, emotion data)

[1026] Output: Analysis results (keywords, emotion data)

[1027] Step 4:

[1028] The server's video generation means generates videos that reflect the user's emotions based on the analysis results. Specifically, it selects video material that corresponds to the scenario entered by the user and adjusts the video to match the user's emotions (e.g., optimistic, cautious, etc.). For example, if the tone is calm, a quiet background and animation with gentle movements will be selected.

[1029] Input: Analysis results (keywords, emotion data)

[1030] Output: Emotionally-reflecting images

[1031] Step 5:

[1032] The server's speech generation means uses a speech synthesis engine to convert text data into speech that reflects emotions. Based on the analysis results, intonation and emphasis are added to the dialogue to generate a speech that corresponds to the user's emotions (e.g., optimistic, cautious, etc.). Specifically, a speech synthesis engine (e.g., gTTS) is used to convert text into speech based on pre-recorded voice samples.

[1033] Input: Analysis results (text data, emotion data)

[1034] Output: Emotionally-reflecting voice

[1035] Step 6:

[1036] The editing means on the server combines the generated video and audio. This creates the final training video. The editing means synchronizes the video and audio at the appropriate times and compiles them into a single continuous video file. Specifically, the video clips and audio clips are combined using video editing software (e.g., MoviePy).

[1037] Input: Emotionally reflective video, emotionally reflective audio

[1038] Output: Consolidated training videos

[1039] Step 7:

[1040] The server's storage and distribution means stores the generated training video in a database or file server and sends the user an access link or ID to the video. Using this link or ID, the user can view the generated training video. Specifically, a URL is generated for the stored video and sent to the user via email or other means.

[1041] Input: Integrated training videos

[1042] Output: Training video access link or ID

[1043] This allows users to watch training videos that reflect a calm tone and proper procedures. For example, the following prompt sentences can be input into the generative AI model to activate the system:

[1044] Example prompt sentence:

[1045] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[1046] 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.

[1047] 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.

[1048] 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.

[1049] [Fourth embodiment]

[1050] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1051] 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.

[1052] 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).

[1053] 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.

[1054] 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.

[1055] 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).

[1056] 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.

[1057] 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.

[1058] 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.

[1059] 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.

[1060] 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.

[1061] 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.

[1062] 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."

[1063] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is implemented in the following specific form.

[1064] The user inputs the training scenario and dialogue into an input form on the device. This can be done on any device, such as a PC, tablet, or smartphone. For example, a user can input a scenario on the theme of "How to use a new project management tool" and enter the corresponding dialogue.

[1065] The input data is sent from the terminal to the server. After receiving the data, the server checks the integrity of the data. The received data is stored in a database and then analyzed in detail by the analysis means.

[1066] The server uses natural language processing technology to analyze the received scenario and dialogue. This allows for grammatical analysis of the scenario and dialogue and extracts keywords from the text. For example, keywords such as "project creation" and "task assignment" are extracted.

[1067] Based on the analyzed data, the server uses the image generation means to generate appropriate images, for example, for the "Project Creation" scenario, a drawing or animation of the actual project creation screen is generated.

[1068] A speech generator is used to generate speech from the analyzed data, which is then converted from text to speech by a speech synthesis engine configured to pronounce the user-entered lines with natural intonation.

[1069] The generated video and audio are integrated using editing tools. The server adjusts the video and audio so that they are synchronized, and edits them into a single training video. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to be synchronized with the video on the project creation screen.

[1070] The completed training video is stored on a server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can view the generated training video using their device. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[1071] As described above, the present invention provides an efficient system that automatically generates high-quality, tailored training videos based on user-provided training scenarios and dialogue. This system solves the time and cost issues associated with traditional manual training video production and supports skill development in companies and educational institutions.

[1072] The processing flow will be explained below.

[1073] Step 1:

[1074] The user inputs the training scenario and lines into an input form on the terminal. For example, the user can enter a detailed description of specific operation methods for a topic such as "How to use a new project management tool."

[1075] Step 2:

[1076] The device converts the input scenario and lines into packets in JSON or XML format and sends them to the server, where the data may be encrypted.

[1077] Step 3:

[1078] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[1079] Step 4:

[1080] The server analyzes the stored data using an analytical tool. It uses natural language processing technology to analyze the grammar of the scenario and dialogue and extract important keywords. For example, keywords such as "project creation" and "task assignment" are extracted.

[1081] Step 5:

[1082] The server generates appropriate images using the image generation means based on the analysis results. For example, for the "Project Creation" scenario, a simulation or animation of an actual project creation screen is generated.

[1083] Step 6:

[1084] The server generates speech using a speech generation means based on the analysis results. Utilizing a speech synthesis engine, the lines entered by the user are converted into speech with a specific intonation. For example, the line "Click the '+' button in the upper right corner of the screen" is generated in a natural voice.

[1085] Step 7:

[1086] The server integrates the video and audio generated by the video generation means and audio generation means using the editing means, adjusts the timing so that the video and audio are properly synchronized, and edits them into a single training video.

[1087] Step 8:

[1088] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[1089] Step 9:

[1090] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[1091] Step 10:

[1092] Users can review the training videos and provide feedback as needed, including on audio pronunciation and video quality.

[1093] Step 11:

[1094] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[1095] This is a method for automatically generating high-quality training videos based on the scenario and lines provided by the user through each step.

[1096] Example 1

[1097] 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."

[1098] Existing training video creation systems require manual editing, which makes efficient video generation time-consuming and costly. They also face challenges in quickly responding to individual user needs, making it time-consuming to regenerate videos that reflect feedback. Furthermore, data consistency checks, saving, and feedback processing are often performed manually, creating complex workflows.

[1099] 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.

[1100] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving transmitted data, a consistency check means for checking the consistency of the received data and storing it in a database, an analysis means for analyzing the received data using natural language processing technology, a video generation means for generating video based on the analysis results, an audio generation means for generating audio from the analyzed data, an editing means for integrating the generated video and audio to generate a training video, a storage and distribution means for saving and distributing the generated training video, and a feedback processing means for receiving user feedback and regenerating the training video based on that. This enables the automatic generation and storage of high-quality training videos that meet user needs, and regeneration that reflects the feedback.

[1101] "Input means" refers to a device or software that allows a user to input a training scenario and lines.

[1102] The "receiving means" is a device or software that receives data sent from the input means.

[1103] The "integrity check means" refers to a device or software that has the function of checking the integrity of received data and storing it in a database after checking for errors.

[1104] "Analysis means" refers to a device or software that analyzes the received data using natural language processing technology and extracts necessary information and keywords.

[1105] "Video generation means" refers to a device or software that generates training videos based on the analyzed data.

[1106] The "speech generation means" refers to a speech synthesis engine or software that has the function of converting analyzed text data into speech.

[1107] "Editing means" refers to a device or software that synchronizes the generated video and audio and integrates them into a single training video.

[1108] The "storage and distribution means" refers to a device or software that stores the generated training video and provides an access link or distributes it to users.

[1109] A "feedback processing means" is a device or software that has the function of receiving feedback from a user and regenerating a training video based on that feedback.

[1110] "Natural language processing technology" is a technology for performing grammatical analysis and keyword extraction of scenarios and dialogue.

[1111] A "speech synthesis engine" is software or hardware that converts text data into voice data.

[1112] The present invention relates to a system for automatically generating training videos based on training scenarios and lines provided by users. This system is embodied in the following specific forms.

[1113] Using a device (PC, tablet, smartphone, etc.), the user enters the training scenario and dialogue into a dedicated input form. For example, the training scenario might be "How to use a new project management tool," and the corresponding dialogue might be "First, create a new project. Click the '+' button in the upper right corner of the screen."

[1114] The terminal sends the entered data to the server. This transmission uses the HTTPS protocol to send the data securely. The server checks the integrity of the received data and checks for missing fields and format errors. Once the integrity is confirmed, the data is stored in a database (for example, MySQL or PostgreSQL).

[1115] The server analyzes the received script and dialogue using natural language processing techniques, using natural language processing libraries such as NLTK and spaCy, to extract keywords from the text and identify key phrases such as "project creation" and "task assignment."

[1116] The server then generates images based on the analyzed data. This is done using tools such as OpenCV and Blender. For example, for the "Project Creation" scenario, it generates drawings and animations of the project creation screen. For voice generation, it uses voice synthesis engines such as the Google Text-to-Speech (TTS) API and Amazon Polly to generate audio files that pronounce the lines entered by the user with natural intonation.

[1117] The generated video and audio are then integrated using editing tools. The server uses a video editing tool such as FFmpeg to synchronize the video and audio and edit them into a single training video. For example, the video on the project creation screen and the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." are edited to match perfectly in time.

[1118] The completed training video is stored in cloud storage (e.g., Amazon S3) by the storage and distribution means. An access link to the video is then sent to the user's device via email or in-app notification. The user can view the generated training video by clicking the received link. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[1119] For example, if a user is creating a training video for a new project management tool, here's an example prompt:

[1120] "I want to create a training video on how to use a new project management tool. The scenario should be 'How to create a new project' and the dialogue should be 'First, create a new project. Click the '+' button in the top right corner of the screen.'"

[1121] This invention allows users to efficiently create and view high-quality training videos tailored to their individual needs, solving the time and cost issues associated with traditional manual training video creation and supporting skill development in companies and educational institutions.

[1122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1123] Step 1:

[1124] User data entry

[1125] Input: Training scenario and dialogue

[1126] Output: Data entered in the input form

[1127] The user uses a device (PC, tablet, smartphone, etc.) to enter the training scenario and dialogue into a dedicated input form. Specifically, the user writes "How to create a new project" in the "Scenario" field of the form, and "First, create a new project. Click the '+' button in the upper right corner of the screen." in the "Dialogue" field.

[1128] Step 2:

[1129] Data transmission and reception

[1130] Input: Data entered into an input form

[1131] Output: Data sent to the server

[1132] When the user clicks the "Send" button, the device sends the scenario and dialogue data to the server in JSON format, etc. This transmission uses the HTTPS protocol to ensure secure data transmission.

[1133] Step 3:

[1134] Data integrity check and saving

[1135] Input: Data sent to the server

[1136] Output: Data stored in the database

[1137] The server checks the integrity of the received data and verifies that there are no errors. For example, it checks that the "Scenario" field is not empty and that the "Dialogue" is entered in the correct format. Once the integrity is confirmed, the data is stored in a database such as MySQL or PostgreSQL.

[1138] Step 4:

[1139] Data analysis

[1140] Input: Data stored in a database

[1141] Output: Parsed data and extracted keywords

[1142] The server analyzes the received script and dialogue using natural language processing (NLP) technology. For this analysis, it uses natural language processing libraries such as NLTK and spaCy. For example, keywords such as "project creation" and "task assignment" are extracted from the text.

[1143] Step 5:

[1144] Image Generation

[1145] Input: Parsed data, extracted keywords

[1146] Output: Generated video

[1147] The server generates images based on the analysis results. To generate images, it uses image generation tools such as OpenCV and Blender. For example, for the "Project Creation" scenario, it generates drawings and animations of the project creation screen.

[1148] Step 6:

[1149] Voice generation

[1150] Input: Parsed text data

[1151] Output: Generated audio file

[1152] The server uses a speech synthesis engine to convert the dialogue into speech. This is done using a speech synthesis engine such as the Google Text-to-Speech (TTS) API or Amazon Polly. The following dialogue, "First, create a new project. Click the '+' button in the upper right corner of the screen," is generated as an audio file with natural intonation.

[1153] Step 7:

[1154] Integrated video and audio editing

[1155] Input: Generated video and audio files

[1156] Output: Edited training video

[1157] The server uses a video editing tool such as FFmpeg to synchronize the video and audio, and then edits them into a single training video. For example, the video on the project creation screen is edited to perfectly sync with the audio that says, "First, create a new project. Click the '+' button in the upper right corner of the screen."

[1158] Step 8:

[1159] Storage and distribution of training videos

[1160] Input: Edited training video

[1161] Output: Access link to the saved training video

[1162] The server saves the completed training video in cloud storage (e.g., Amazon S3), then generates a URL or access link for the storage location and sends it to the user's device via email or in-app notification. The user can view the generated training video by clicking the link.

[1163] Step 9:

[1164] Feedback and Regeneration

[1165] Input: User feedback

[1166] Output: Improved regenerated video

[1167] After watching the training video, users submit improvements and requests for additions through a feedback form. The server analyzes the feedback, regenerates the video content if necessary, and provides a new link to the improved version to the user.

[1168] (Application example 1)

[1169] 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."

[1170] Conventional training for learning how to operate and maintain factory robots has the problem of being time-consuming and costly because it requires detailed explanations. Furthermore, efficiently providing such training content requires personnel with advanced expertise, and creating videos as part of the training is not easy. The present invention aims to solve these problems by providing a system that provides efficient and effective training through the automatic generation of training videos.

[1171] 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.

[1172] In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, an analyzing means for analyzing the received data, and a means for automatically generating a training video for learning how to operate and maintain a robot used in a factory. This makes it possible to automatically generate high-quality training videos based on the scenario and lines input by the user.

[1173] A "user" is a person or entity that inputs training scenarios and lines into the system.

[1174] A "training scenario" is a planned sequence of actions or events created for educational or training purposes.

[1175] "Dialogue" refers to the lines and explanatory text used in the training scenario.

[1176] The "input means" is an interface that the user uses to input the training scenario and lines into the system.

[1177] The "receiving means" is a device or function for receiving data sent from the input means on the system side.

[1178] "Analysis means" refers to a device or function that analyzes received data, understands the content, and extracts important information such as keywords.

[1179] The "image generating means" is a device or function for generating an appropriate image based on the information extracted by the analyzing means.

[1180] The "voice generating means" is a device or function for generating voice based on the information extracted by the analyzing means.

[1181] The "editing means" refers to a device or function for integrating the video and audio generated by the video generation means and audio generation means and editing them into a single training video.

[1182] The "storage and distribution means" refers to a device or function for storing the generated training video and distributing it as needed.

[1183] A "factory robot" is an automated mechanical device used in a factory that is programmed to perform a specific task or process.

[1184] "Operating method" means a procedure or method for using a particular machine or system.

[1185] "Maintenance procedures" are specific procedures and methods for maintaining, inspecting, and repairing machines and systems.

[1186] The system that realizes this application example automatically generates training videos on how to operate factory robots and maintenance procedures based on training scenarios and lines provided by the user. This system consists of the following main elements.

[1187] System Configuration

[1188] User Input

[1189] Users input training scenarios and lines using devices such as PCs, tablets, and smartphones. For example, they can input a scenario on the theme of "How to operate a new robot" and enter detailed lines corresponding to it.

[1190] Data reception and analysis

[1191] The data sent from the device is received by the server. After receiving this data, the server uses natural language processing technology to analyze the scenario and dialogue and extract important keywords. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted. Specifically, grammar analysis is performed using a natural language processing library called spacy.

[1192] Video and audio generation

[1193] Based on the analyzed data, the server generates appropriate video and audio using video generation and audio generation means. For video generation, the moviepy library is used to select and edit video clips that match the keywords. For audio generation, a speech synthesis engine called pyttsx3 is used to generate audio from text.

[1194] Video and audio integration and editing

[1195] The generated video and audio are then integrated using an editing tool. The video and audio are adjusted to synchronize, and finally edited into a single training video. For example, the audio "Robot arm usage procedure" is synchronized with the video of the actual robot arm operation.

[1196] Video storage and distribution

[1197] The completed training video is stored on a server using a storage and distribution method. An access link or ID for the video is then sent to the user's device. The user can then view the generated training video using their device. This solves the time and cost issues associated with traditional manual training video creation.

[1198] Examples of specific examples and prompts

[1199] As a specific example, the following scenario and dialogue could be considered for the operating procedure of a factory robot, "attaching parts."

[1200] Scenario: "To install a new part, first use the robot arm to pick it up."

[1201] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[1202] An example of a prompt is:

[1203] "Enter a scenario and lines of dialogue for how to operate a new factory robot. For example:

[1204] Scenario: "To install a new part, first use the robot arm to pick it up."

[1205] Quote: "First, we'll use the robot arm to pick up the part. Control the arm..."

[1206] The present invention makes it possible to automatically generate training videos that allow users to efficiently and effectively learn detailed operating methods and maintenance procedures for robots used in factories.

[1207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1208] Step 1:

[1209] This is the step where the user inputs the training scenario and lines. The user uses a device (PC, tablet, smartphone, etc.) to input a scenario and lines, such as "How to operate a new robot," into a dedicated input form. The input scenario and lines are saved on the device as data required for subsequent processing.

[1210] Step 2:

[1211] This is the step where the server receives the data sent from the terminal. When the user completes the input, the scenario and lines are sent from the terminal to the server. The server receives this data and checks the data integrity. Data in the correct format is obtained from the input scenario and lines.

[1212] Step 3:

[1213] This is the step where the server analyzes the received data. Specifically, it uses natural language processing technology (such as Spacy) to perform a grammatical analysis of the scenario and dialogue. This analysis extracts important keywords. Keywords are obtained as output data from the scenario and dialogue as input data. For example, keywords such as "use of the robot arm" and "attaching parts" are extracted.

[1214] Step 4:

[1215] In this step, the server generates appropriate videos using a video generation means. Based on the analyzed data, it uses a video editing library called moviepy to select and combine video clips corresponding to the extracted keywords. From the keywords as input, training video clips are obtained as output.

[1216] Step 5:

[1217] In this step, the server generates speech using a speech generation means. Based on the lines extracted from the analyzed data, speech is generated using a speech synthesis engine called pyttsx3. Narration speech is obtained as output from the lines as input.

[1218] Step 6:

[1219] This is the step where the generated video and audio are edited. The server adjusts the video and audio to synchronize and integrates them into a single training video. MoviePy is used to adjust the timing of the video and audio. The input is a video clip and an audio file, and the output is an integrated training video.

[1220] Step 7:

[1221] This is the step of storing and distributing the generated training video. The server stores the completed training video and sends the user an access link or ID to the video. The user uses a terminal to view the training video by entering a specified URL or ID. The input is the integrated training video, and the output is a stored video file and an access link.

[1222] 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.

[1223] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[1224] Users input the training scenario and lines into an input form on their device. This input can be done on any device, such as a PC, tablet, or smartphone. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, a user can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while entering the corresponding lines.

[1225] The input scenario, dialogue, and emotion data are transmitted from the terminal to the server. After receiving the transmitted data, the server checks the consistency of the data. The received data is stored in a database, and then analyzed in detail by the analysis means.

[1226] The server can use natural language processing technology and an emotion engine to analyze the received scenario, dialogue, and emotion data. Natural language processing technology is used to perform a grammatical analysis of the scenario and dialogue, and to extract keywords from the text. At the same time, the emotion engine analyzes the user's emotion data and recognizes the user's intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server can determine whether the explanation evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[1227] Based on the analyzed data, the server uses the image generation means to generate appropriate images. At this time, the user's emotions recognized by the emotion engine are reflected in the generated images. For example, for a project creation scenario, if the user is feeling optimistic, images with swaying animations and bright colors are generated.

[1228] Similarly, a speech generator generates speech based on the analyzed scenario and emotion data. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user and the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[1229] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[1230] The completed training video is stored on the server using a storage and distribution means. An access link or ID for the video is then sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[1231] As described above, the present invention provides a system that automatically generates high-quality training videos based on the user's emotional data, in addition to the scenario and dialogue provided by the user. This system improves the quality of training videos, enhances learning effectiveness, and solves the problems of traditional manual video creation.

[1232] The processing flow will be explained below.

[1233] Step 1:

[1234] The user inputs the training scenario and dialogue into the input form on the device. For example, the user inputs a scenario on the theme of "How to use a new project management tool" and the corresponding dialogue. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotional data.

[1235] Step 2:

[1236] The device converts the input scenario, dialogue, and emotional data (voice and facial expression data) into packets, encrypts them, and sends them to the server in JSON or XML format.

[1237] Step 3:

[1238] The server receives data packets sent from the terminal, checks the integrity of the data upon reception, and stores correctly received data in a database.

[1239] Step 4:

[1240] The server analyzes the saved scenario, dialogue, and emotion data using an analytical means. It uses natural language processing technology to perform grammatical analysis of the scenario and dialogue and extract important keywords from the text. It also uses an emotion engine to recognize the user's emotions from their voice and facial expressions. For example, the keywords "project creation" and "task assignment" are extracted, and it is recognized that the user is expressing optimistic emotions.

[1241] Step 5:

[1242] The server generates an appropriate image using the image generation means based on the analysis results. The character's facial expression and the color tone of the background are adjusted based on the user's emotion recognized by the emotion engine. For example, if the user is expressing optimistic emotion, a simulation image of the project creation screen with bright colors is generated.

[1243] Step 6:

[1244] The server generates speech using a speech generation means based on the analysis results. The speech synthesis engine adjusts intonation and emotional expression based on the lines entered by the user, depending on the recognized emotion. For example, speech is generated so that the line "Click the '+' button in the upper right corner of the screen" is pronounced in an optimistic tone.

[1245] Step 7:

[1246] The server integrates the video and audio generated by the video generation means and audio generation means using an editing means. The timing is adjusted so that the video and audio are properly synchronized, and they are edited into a single training video. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited so that it is synchronized with the video of the project creation screen in an optimistic tone.

[1247] Step 8:

[1248] The server stores the completed training video in storage using a storage and distribution means. An access link and ID are generated for the stored video, and it is set up so that users can easily access it.

[1249] Step 9:

[1250] The server sends an access link or ID to the generated video to the user's device, and the user can use this link or ID to watch the training video.

[1251] Step 10:

[1252] Users can review training videos and provide feedback as needed, including on audio pronunciation, video quality, and appropriateness of emotional expression.

[1253] Step 11:

[1254] The server receives feedback from the user, and if there are any new improvements to be made, starts the process of generating the video again.The server uses the analysis means and generation means again to generate a training video with higher accuracy.

[1255] Through the above steps, high-quality, emotion-sensitive training videos are automatically generated based on the scenario, dialogue, and emotion data provided by the user.

[1256] Example 2

[1257] 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."

[1258] Traditionally, creating training videos has required a lot of time and effort, and accurate editing has been difficult, especially when creating videos that contain multiple emotional expressions. Furthermore, there is a need to accurately capture the user's emotions in order to provide more effective training to viewers. To solve these problems, an automatic and highly accurate training video generation system is needed.

[1259] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines, a receiving means for receiving data transmitted from the input means, a checking means for checking the consistency of the received data, a saving means for saving the received data, an analyzing means for analyzing the saved data, a grammar analysis means for analyzing the scenario and lines using natural language processing technology, an emotion analysis means for analyzing emotion data using emotion analysis technology, a video generation means for generating video based on the analyzed data, an audio generation means for generating audio based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a saving and distribution means for saving and distributing the generated training video. This makes it possible to accurately capture the user's emotions as well as the scenario and lines provided by the user, and automatically generate high-quality training videos based on them.

[1260] A "user" is a person or organization that inputs training scenarios and lines into a terminal and provides data to the system.

[1261] "Input means" refers to devices such as computers, tablets, and smartphones that users use to input training scenarios and lines, as well as the accompanying software.

[1262] The "receiving means" is a function that allows the server to receive data transmitted from the input means.

[1263] "Checking means" refers to a mechanism for verifying the integrity of received data and verifying that it is accurate and complete.

[1264] "Storage means" is a function for storing received data in a database or storage within the server.

[1265] "Analysis means" refers to technologies and algorithms used to analyze stored data in detail and understand its contents.

[1266] "Grammar analysis means" is a function that uses natural language processing technology to grammatically analyze the text data of the scenario and dialogue, and extracts important keywords and structures.

[1267] "Emotion analysis means" is a technology for analyzing emotional data such as the user's voice and facial expressions, and recognizing the user's intentions and emotions.

[1268] "Video generation means" refers to software and hardware for creating visual content based on the analyzed data.

[1269] "Speech generation means" refers to a function for generating speech based on analyzed data, and includes a speech synthesis engine that converts text into natural speech.

[1270] The "editing means" is a function that integrates and synchronizes the video and audio generated by the video generation means and audio generation means to complete a single training video.

[1271] The "storage and distribution means" is a mechanism for storing the generated training video and distributing it to users in a viewable format.

[1272] The present invention relates to a system that recognizes the emotions of a user in addition to a training scenario and lines provided by the user, and generates a training video based on the emotions. This system is embodied in the following specific form.

[1273] Users use any device (PC, tablet, smartphone, etc.) to input the training scenario and lines. This input is done through an input form on the device. Users can also record their own voice and facial expressions using the device's microphone and camera and input them as emotional data. For example, they can input a scenario on the theme of "How to use a new project management tool" and record their tone of voice and facial expressions while inputting the corresponding lines.

[1274] The device sends the input scenario, lines, and emotion data to the server. This data transmission uses the HTTPS protocol. The server checks the format and content of the received data and stores it in a database. A general relational database (e.g., MySQL) is used as the database.

[1275] To analyze the received scenario, dialogue, and emotion data, the server uses natural language processing technology (e.g., the BERT model) to perform grammatical analysis of the scenario and dialogue and extract important keywords. It then uses emotion analysis technology (e.g., AWS Rekognition or Microsoft Azure Emotion API) to analyze the user's emotion data and recognize their intentions and emotions. For example, for keywords such as "project creation" and "task assignment," the server determines whether the description evokes emotions such as "carefully" or "optimistic" based on the user's tone of voice and facial expression.

[1276] Based on the analyzed data, the server generates an appropriate image using an image generation tool (e.g., Blender or Adobe After Effects). At this time, the user's emotions recognized by the emotion engine are reflected in the image generation. For example, if the user is optimistic about the project creation scenario, a bright image will be generated.

[1277] Similarly, speech generation tools (e.g., Google Text-to-Speech or Amazon Polly) generate speech based on the analyzed scenario and emotion data. The speech synthesis engine uses the user-entered lines and adjusts intonation and emotional expression according to the recognized emotion. For example, the line "Click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[1278] The generated video and audio are then combined using an editing tool (e.g., FFmpeg or Adobe Premiere Pro) and edited into a training video. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is completed. For example, the audio "First, create a new project. Click the '+' button in the upper right corner of the screen" is edited to synchronize with the video on the project creation screen. The tone and facial expressions of this audio are also reflected in the characters in the video.

[1279] The completed training video is stored on the server, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server can regenerate the training video based on that feedback.

[1280] Here is an example prompt:

[1281] Analyze the following scenarios and generate text and speech with the corresponding emotions.

[1282] Scenario: First, create a new project by clicking the '+' button on the top right of the screen.

[1283] Sentiment: Optimistic

[1284] Example of text and audio output: This tool is very useful for creating projects. Click on the '+' button on the top right of the screen.

[1285] Voice characteristics: Bright tone

[1286] In this way, the system of the present invention automatically generates high-quality training videos based on the scenario and dialogue provided by the user, as well as the user's emotional data, thereby improving the quality of training videos and enhancing learning effectiveness.

[1287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1288] Step 1:

[1289] The user inputs the training scenario and lines. Using a device such as a PC, tablet, or smartphone, the user inputs the training scenario and lines into an input form. In addition, the user can record their own voice and facial expressions using the device's microphone and camera, which are then input as emotional data. The input data is temporarily stored on the device.

[1290] Input: Training scenario, dialogue, voice recording, facial expression recording

[1291] Output: Input dataset saved on device

[1292] Specific behavior: A user opens a browser, enters a scenario with the theme "How to use a new project management tool," and enters the following dialogue: "This tool is very useful for creating projects. Click the '+' button in the upper right corner of the screen." Click the record button to record the voice, and click the camera button to record the facial expression.

[1293] Step 2:

[1294] The device sends the input data to the server. The device sends the data to the server using the HTTPS protocol. The data sent consists of the training scenario, lines, and recorded voice and facial expressions.

[1295] Input: Input dataset stored on the device

[1296] Output: The dataset sent to the server

[1297] Specific operation: The device sends data packaged in JSON format to the server as an HTTPS request.

[1298] Step 3:

[1299] The server receives the data and checks its integrity. Once the server receives the data, it checks for any omissions or errors. Once the server has confirmed that the data is complete, it stores it in the database.

[1300] Input: Dataset sent to the server

[1301] Output: Validated data stored in a database

[1302] Specific behavior: The server parses the received JSON data, verifies that all required fields are present and that the data conforms to the format, and stores data that passes validation in a database (e.g., MySQL).

[1303] Step 4:

[1304] The server analyzes the scenario and dialogue. Using natural language processing technology (e.g., the BERT model), it performs a grammatical analysis of the scenario and dialogue and extracts keywords and emotions. The results of this analysis are used for subsequent processing.

[1305] Input: Scenario and dialogue data stored in the database

[1306] Output: Syntax-analyzed text data, keyword list

[1307] Specific operation: The server uses the BERT module to analyze the scenario "How to use a new project management tool" and extract important keywords (e.g., "project creation" and "task assignment").

[1308] Step 5:

[1309] The server analyzes the emotional data. Using emotion analysis technology (e.g., AWS Rekognition or Microsoft Azure Emotion API), it identifies emotions from the user's voice and facial expressions. This identifies the emotions with which the user is speaking the scenario or lines.

[1310] Input: Voice and facial expression data stored in a database

[1311] Output: Emotion recognition result (e.g. optimistic, cautious)

[1312] What it does: The server uses the AWS Rekognition API to analyze the recorded voice and facial expressions and recognize that the user is expressing optimistic emotions.

[1313] Step 6:

[1314] The server generates the video. Based on the analysis results of the saved scenario and dialogue, as well as emotional data, an appropriate video is generated using a video generation tool (e.g., Blender or Adobe After Effects). The video's color tone and movements are reflected based on the emotional data.

[1315] Input: Grammar analysis results, keyword list, emotion recognition results

[1316] Output: Emotionally-reflected video file

[1317] What it does: The server launches Blender and generates a brightly colored animated video that corresponds to the "Create a Project" scenario.

[1318] Step 7:

[1319] The server generates the speech. Based on the analyzed scenario and emotional data, a speech generator (e.g., Google Text-to-Speech or Amazon Polly) is used to generate an audio file. The speech synthesis engine adjusts intonation and emotional expression according to the recognized emotion based on the lines entered by the user.

[1320] Input: Grammar analysis results, dialogue, emotion recognition results

[1321] Output: Emotionally-reflected audio file

[1322] What it does: The server uses the Google Text-to-Speech API to convert the following line into an audio file in an optimistic tone: "This tool is very helpful for creating your project. Click the '+' button in the top right corner of the screen."

[1323] Step 8:

[1324] The server integrates the video and audio. The video and audio generated by the video generation means and audio generation means are integrated and edited into a single training video. An editing tool (e.g., FFmpeg or Adobe Premiere Pro) is used to adjust the video and audio so that they are properly synchronized.

[1325] Input: Video files, audio files

[1326] Output: Finished training video file

[1327] Specific operation: The server starts FFmpeg, places the generated video and audio on the timeline, and combines them into a single video file. For example, it edits the scene that says, "First, create a new project. Click the '+' button in the upper right corner of the screen." so that it plays properly.

[1328] Step 9:

[1329] The server saves the completed training video and distributes it to the user. The generated training video is saved in the server's storage, and an access link or ID for the video is sent to the user's device.

[1330] Input: Completed training video file

[1331] Output: Access link or ID of the video

[1332] Specific operation: The server uploads the video file to storage (e.g. AWS S3) and sends the user an access link via email or message. The user can use this link to watch the generated training video.

[1333] (Application example 2)

[1334] 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."

[1335] Conventional training video creation systems use uniform video and audio without considering the user's emotions, making it difficult to enhance the participants' understanding and interest. Furthermore, manually editing video and audio is time-consuming and costly, making it inefficient.

[1336] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes an input means for a user to input a training scenario and lines and record the user's voice and facial expression, a receiving means for receiving data transmitted from the input means, an analysis means for analyzing the received data and recognizing emotions, a video generation means for generating video that reflects emotions based on the analyzed data, an audio generation means for generating audio that reflects emotions based on the analyzed data, an editing means for integrating the video and audio generated by the video generation means and the audio generation means to generate a training video, and a storage and distribution means for saving and distributing the generated training video. This makes it possible to create more effective training videos that reflect the user's emotions.

[1337] "Input means" refers to a device or software that allows a user to input a training scenario and lines and record the user's voice and facial expressions.

[1338] The "receiving means" is a device or software for receiving data transmitted from the input means.

[1339] The "analysis means" is a device or software for analyzing the received data and recognizing emotions.

[1340] The "image generation means" is a device or software for generating an image that reflects emotions based on the analyzed data.

[1341] The "voice generation means" is a device or software for generating voice that reflects emotions based on the analyzed data.

[1342] The "editing means" is a device or software for generating a training video by integrating the video and audio generated by the video generation means and audio generation means.

[1343] The "storage and distribution means" is a device or software for storing and distributing the generated training video.

[1344] An "emotion engine" is software or technology for analyzing a user's emotions and generating emotion data.

[1345] "Natural language processing technology" is a technology for performing grammatical analysis of scenarios and dialogue.

[1346] A "speech synthesis engine" is a technology or device for converting text into speech.

[1347] The present invention relates to a system that recognizes the user's emotions in addition to the training scenario and lines provided by the user, and generates training videos based on these.

[1348] First, the user uses an input means to input the training scenario and lines. This input means consists of a device such as a PC, tablet, or smartphone, and text is entered using a keyboard or touch screen. The user also uses the device's microphone and camera to record their own voice and facial expressions, which are then input as emotion data. At this stage, for example, we imagine a scenario such as "How to use a new project management tool" being entered, and the tone of voice and facial expressions being recorded while entering the corresponding lines.

[1349] The input scenario, dialogue, and emotion data are then sent from the terminal to a server. The server has a receiving means for receiving this data. The received data is stored in a database and then analyzed in detail by an analysis means. The analysis uses natural language processing technologies such as TensorFlow and emotion engines such as DeepFace and OpenCV. This allows for grammatical analysis of the scenario and dialogue and an analysis of the user's emotions. For example, in response to keywords such as "project creation" and "task assignment," the tone of voice and facial expression of the user's voice can be used to determine whether the explanation evokes emotions such as "carefully" or "optimistic."

[1350] After the analysis is complete, the image generation means generates an appropriate image based on the analysis results. The user's emotions recognized by the emotion engine are also reflected in the image generation. For example, if the user is optimistic about the project creation scenario, an image with swaying animations and bright colors will be generated.

[1351] At the same time, speech is generated by the speech generation means. Using a speech synthesis engine, speech is generated by adding intonation and emotional expressions to the inputted lines based on the analyzed scenario and emotional data. For example, the line "Please click the '+' button in the upper right corner of the screen" may be pronounced in an optimistic tone or in a cautious tone.

[1352] The generated video and audio are then integrated using an editing tool. The timing is adjusted to ensure proper synchronization between the video and audio, and the resulting training video is edited. For example, the audio, "First, create a new project. Click the '+' button in the upper right corner of the screen," is edited to synchronize with the video on the project creation screen.

[1353] The completed training video is stored on a server using a storage and distribution means, and an access link or ID for the video is sent to the user's device. The user can use this link or ID to view the generated training video. If necessary, the user can provide feedback, and the server will regenerate the training video based on that feedback.

[1354] As a concrete example, consider a training video that teaches how to operate and maintain a robot used in a factory. In this case, the user inputs a scenario called "Procedure for Part Replacement," then inputs lines such as "First, prepare the tools to be used... Next, remove the old part..." and records emotional data such as speaking in a calm tone during the explanation. Based on this, a training video that reflects a calm tone and appropriate procedures is generated.

[1355] An example of a prompt for a generative AI model is as follows:

[1356] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[1357] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1358] Step 1:

[1359] The user inputs the training scenario and lines using the input means of the terminal. The input data is recorded as text data of the scenario and lines. In addition, the user's voice and facial expressions are recorded using a microphone and camera, and these are input as emotion data. Specifically, the user inputs a scenario called "Procedure for Part Replacement" and the lines, "First, prepare the tools you will use. Next, remove the old part," and the user's voice and facial expressions are recorded during the explanation.

[1360] Input: Scenario, lines, voice and facial expression data

[1361] Output: Text data, emotion data

[1362] Step 2:

[1363] The terminal packages the input scenario, lines, and emotion data to send to the server. This sending uses a communication method such as the HTTP protocol. The sent data is received by the server's receiving method. Specifically, text data and emotion data are sent to the server.

[1364] Input: Text data, emotion data

[1365] Output: Send data (to server)

[1366] Step 3:

[1367] The server receives the transmitted data using the receiving means. The received data is stored in a database and analyzed by the analyzing means. The analyzing means analyzes the text data using natural language processing technology (such as TensorFlow) to extract grammar and keywords. It also analyzes the emotional data using an emotion engine (such as DeepFace or OpenCV) to recognize the user's intentions and emotions.

[1368] Input: Transmitted data (text data, emotion data)

[1369] Output: Analysis results (keywords, emotion data)

[1370] Step 4:

[1371] The server's video generation means generates videos that reflect the user's emotions based on the analysis results. Specifically, it selects video material that corresponds to the scenario entered by the user and adjusts the video to match the user's emotions (e.g., optimistic, cautious, etc.). For example, if the tone is calm, a quiet background and animation with gentle movements will be selected.

[1372] Input: Analysis results (keywords, emotion data)

[1373] Output: Emotionally-reflecting images

[1374] Step 5:

[1375] The server's speech generation means uses a speech synthesis engine to convert text data into speech that reflects emotions. Based on the analysis results, intonation and emphasis are added to the dialogue to generate a speech that corresponds to the user's emotions (e.g., optimistic, cautious, etc.). Specifically, a speech synthesis engine (e.g., gTTS) is used to convert text into speech based on pre-recorded voice samples.

[1376] Input: Analysis results (text data, emotion data)

[1377] Output: Emotionally-reflecting voice

[1378] Step 6:

[1379] The editing means on the server combines the generated video and audio. This creates the final training video. The editing means synchronizes the video and audio at the appropriate times and compiles them into a single continuous video file. Specifically, the video clips and audio clips are combined using video editing software (e.g., MoviePy).

[1380] Input: Emotionally reflective video, emotionally reflective audio

[1381] Output: Consolidated training videos

[1382] Step 7:

[1383] The server's storage and distribution means stores the generated training video in a database or file server and sends the user an access link or ID to the video. Using this link or ID, the user can view the generated training video. Specifically, a URL is generated for the stored video and sent to the user via email or other means.

[1384] Input: Integrated training videos

[1385] Output: Training video access link or ID

[1386] This allows users to watch training videos that reflect a calm tone and proper procedures. For example, the following prompt sentences can be input into the generative AI model to activate the system:

[1387] Example prompt sentence:

[1388] "Scenario: "Procedure for Part Replacement"" "Line: "First, prepare the tools you will use. Then remove the old part."" "Emotional Data: Calm Tone"

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1394] 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.

[1395] 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).

[1396] 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.

[1397] 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."

[1398] 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.

[1399] 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).

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] The following is further disclosed regarding the above embodiment.

[1411] (Claim 1)

[1412] an input means for a user to input a training scenario and lines;

[1413] receiving means for receiving data transmitted from the input means;

[1414] analysis means for analyzing the received data;

[1415] an image generating means for generating an image based on the analyzed data;

[1416] a voice generating means for generating a voice based on the analyzed data;

[1417] an editing means for integrating the video and audio generated by the video generating means and the audio generating means to generate a training video;

[1418] The system includes a storage and distribution means for storing and distributing the generated training videos.

[1419] (Claim 2)

[1420] 2. The system according to claim 1, wherein the analyzing means performs a grammatical analysis of the scenario and the dialogue using natural language processing technology.

[1421] (Claim 3)

[1422] 2. The system of claim 1, wherein the speech generating means converts text to speech using a speech synthesis engine.

[1423] "Example 1"

[1424] (Claim 1)

[1425] an input means for a user to input a training scenario and lines;

[1426] receiving means for receiving data transmitted from the input means;

[1427] integrity checking means for checking the integrity of the received data and storing it in a database;

[1428] analysis means for analyzing the received data using natural language processing technology;

[1429] an image generating means for generating an image based on the analyzed data;

[1430] a voice generating means for generating a voice based on the analyzed data;

[1431] an editing means for integrating the video and audio generated by the video generating means and the audio generating means to generate a training video;

[1432] a storage and distribution means for storing and distributing the generated training video;

[1433] The system includes a feedback processing means for receiving user feedback and regenerating the training video based on the feedback.

[1434] (Claim 2)

[1435] 2. The system according to claim 1, wherein the analyzing means performs a grammatical analysis of the scenario and the dialogue using natural language processing technology to extract keywords.

[1436] (Claim 3)

[1437] 2. The system of claim 1, wherein the speech generating means converts text to speech using a speech synthesis engine.

[1438] "Application Example 1"

[1439] (Claim 1)

[1440] an input means for a user to input a training scenario and lines;

[1441] receiving means for receiving data transmitted from the input means;

[1442] analysis means for analyzing the received data;

[1443] an image generating means for generating an image based on the analyzed data;

[1444] a voice generating means for generating a voice based on the analyzed data;

[1445] an editing means for integrating the video and audio generated by the video generating means and the audio generating means to generate a training video;

[1446] a storage and distribution means for storing and distributing the generated training video;

[1447] A means to automatically generate training videos to teach how to operate and maintain robots used in factories, and

[1448] A system including:

[1449] (Claim 2)

[1450] 2. The system according to claim 1, wherein the analyzing means performs a grammatical analysis of the scenario and the dialogue using natural language processing technology to extract keywords.

[1451] (Claim 3)

[1452] 2. The system of claim 1, wherein the speech generating means converts text to speech using a speech synthesis engine.

[1453] (Claim 4)

[1454] 2. The system according to claim 1, wherein the video generating means selects and integrates appropriate video clips based on the extracted keywords.

[1455] "Example 2: Combining Emotion Engines"

[1456] (Claim 1)

[1457] an input means for a user to input a training scenario and lines;

[1458] receiving means for receiving data transmitted from the input means;

[1459] checking means for checking the integrity of the received data;

[1460] a storage means for storing the received data;

[1461] analysis means for analyzing the stored data;

[1462] a grammar analysis means for analyzing the scenario and dialogue using natural language processing technology;

[1463] emotion analysis means for analyzing emotion data using emotion analysis technology;

[1464] an image generating means for generating an image based on the analyzed data;

[1465] a voice generating means for generating a voice based on the analyzed data;

[1466] an editing means for integrating the video and audio generated by the video generating means and the audio generating means to generate a training video;

[1467] The system includes a storage and distribution means for storing and distributing the generated training videos.

[1468] (Claim 2)

[1469] 2. The system according to claim 1, wherein the grammar analysis means performs grammar analysis of the scenario and the dialogue using natural language processing technology.

[1470] (Claim 3)

[1471] 2. The system of claim 1, wherein the speech generating means converts text to speech using a speech synthesis engine.

[1472] "Application example 2 when combining emotion engines"

[1473] (Claim 1)

[1474] an input means for a user to input a training scenario and lines and record the user's voice and facial expression;

[1475] receiving means for receiving data transmitted from the input means;

[1476] analysis means for analyzing the received data and recognizing emotions;

[1477] an image generating means for generating an image reflecting emotions based on the analyzed data;

[1478] a voice generating means for generating a voice that reflects emotion based on the analyzed data;

[1479] an editing means for integrating the video and audio generated by the video generating means and the audio generating means to generate a training video;

[1480] The system includes a storage and distribution means for storing and distributing the generated training videos.

[1481] (Claim 2)

[1482] 2. The system according to claim 1, wherein the analysis means performs grammatical analysis and emotional analysis of the scenario and dialogue using natural language processing technology and an emotional engine.

[1483] (Claim 3)

[1484] 2. The system according to claim 1, wherein the speech generating means converts text into speech while reflecting emotional expressions using a speech synthesis engine. [Explanation of symbols]

[1485] 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. an input means for a user to input a training scenario and lines; receiving means for receiving data transmitted from the input means; analysis means for analyzing the received data; an image generating means for generating an image based on the analyzed data; a voice generating means for generating a voice based on the analyzed data; an editing means for integrating the video and audio generated by the video generating means and the audio generating means to generate a training video; The system includes a storage and distribution means for storing and distributing the generated training videos.

2. 2. The system according to claim 1, wherein the analyzing means performs a grammatical analysis of the scenario and the dialogue using natural language processing technology.

3. 2. The system of claim 1, wherein the speech generating means converts text to speech using a speech synthesis engine.

Images