system

Abstract

The system according to the embodiment aims to efficiently provide educational content in the form of video. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit inputs educational content in text format. The analysis unit analyzes the text input by the reception unit and generates a scenario for a video. The generation unit creates a video based on the scenario generated by the analysis unit.

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] With conventional technology, it is difficult to efficiently provide educational content in video format, and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently provide educational content in the form of video. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit inputs educational content in text format. The analysis unit analyzes the text input by the reception unit and generates a scenario for a video. The generation unit creates a video based on the scenario generated by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently provide educational content in the form of video. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An educational video creation system according to an embodiment of the present invention efficiently creates videos of educational content and effectively trains personnel. The educational video creation system inputs educational content in text format, and a generation AI analyzes the text, generates a video scenario, and creates videos based on the generated scenario. For example, the educational video creation system inputs educational content in text format. For example, the content may include a "Basic Manual for Customer Service" or a "Troubleshooting Guide." This text is then input into the generation AI. The educational video creation system then analyzes the input text using the generation AI to generate a video scenario. The generation AI understands the content of the text and determines which parts to explain in the video. For example, in the case of a "Basic Manual for Customer Service," the scenario includes information such as how to greet customers and how to handle inquiries. The educational video creation system then creates videos based on the scenario generated by the generation AI. The generation AI generates each scene in the video according to the scenario and adds narration and subtitles. For example, in a greeting scene, a video shows how the person in charge greets customers, and the narration explains the process. This allows personnel in the Sapporo base to efficiently receive training by watching the educational video creation system. Videos are visually easy to understand, making it easier to understand content that is difficult to convey through text alone. Generative AI also streamlines video creation and editing, enabling the provision of high-quality training videos in a short amount of time. For example, a troubleshooting guide video shows specific examples of problems and uses narration to explain how to solve them. This allows staff to acquire the skills to deal with problems they face in their actual work. This allows the training video creation system to efficiently train staff at the Sapporo base. For example, by watching visually easy-to-understand videos, staff can more easily understand content that is difficult to convey through text alone. Generative AI also streamlines video creation and editing, enabling the provision of high-quality training videos in a short amount of time. This allows staff to acquire the skills to deal with problems they face in their actual work.

[0029] An educational video creation system according to an embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit inputs educational content in text format. The educational content may include, but is not limited to, technical education, business education, and general knowledge education. The reception unit may accept text formats such as plain text, rich text, and Markdown. The analysis unit uses a generation AI to analyze the text input by the reception unit and generate a video scenario. The analysis may be performed using, but is not limited to, natural language processing technology, keyword extraction, grammar analysis, or other methods. For example, the generation AI may analyze the text using a text generation AI (e.g., LLM) and generate a scenario. The analysis unit may also use the generation AI to understand the content of the text and determine which parts to explain in the video. The generation unit uses the generation AI to create a video based on the scenario generated by the analysis unit. The video creation is performed according to, but is not limited to, standards such as the software used, the video format, and the resolution. For example, the generation AI may generate each scene of the video according to the scenario and add narration and subtitles. As a result, the educational video creation system according to the embodiment can efficiently create videos of educational content and effectively educate personnel.

[0030] The generation unit includes a scene generation unit that generates each scene of the video according to a scenario. The scene generation unit generates each scene of the video according to the scenario. The scene may include, but is not limited to, for example, the length, content, and transitions of the scene. The scene generation unit, for example, determines the order of the scenes based on the scenario and generates each scene. The scene generation unit can also set scene transitions according to the scenario. For example, the scene generation unit adds transition effects such as fade-in and fade-out to achieve a smooth transition between scenes. This allows for the generation of detailed scenes based on the scenario, thereby improving the quality of educational videos.

[0031] The scene generation unit includes a narration adding unit that adds narration. The narration adding unit adds narration to the scenes generated by the scene generation unit. The narration includes, but is not limited to, voice synthesis technology, narration scripts, and the like. The narration adding unit generates narration based on a scenario, for example, using voice synthesis technology. The narration adding unit can also add narration using voice synthesis technology based on the narration script. For example, the narration adding unit generates narration corresponding to each scene in the scenario and adds it to the scene. By adding narration, explanations to viewers become clearer, improving the educational effect.

[0032] The scene generation unit includes a subtitle addition unit that adds subtitles. The subtitle addition unit adds subtitles to the scenes generated by the scene generation unit. The subtitles include, but are not limited to, subtitle font, display position, and timing, for example. The subtitle addition unit generates subtitle content based on a scenario, for example, and adds the content to the scenes. The subtitle addition unit can also set the subtitle font and display position. For example, the subtitle addition unit adjusts the subtitle font and display position so that the viewer can easily understand the content. As a result, adding subtitles makes it easier for the viewer to understand the content, improving the educational effect.

[0033] The analysis unit can understand the content of the text and determine which parts to explain in the video. The analysis unit uses a generation AI to understand the content of the text and determine which parts to explain in the video. Methods for understanding the content of the text include, but are not limited to, natural language processing technology, semantic analysis, and context understanding. For example, the generation AI analyzes the text using a text generation AI (e.g., LLM) and extracts important parts. The analysis unit can also use the generation AI to understand the context of the text and determine which parts to explain in the video. This makes it possible to generate an appropriate scenario by understanding the content of the text.

[0034] The generation unit can simulate specific cases in the troubleshooting guide and show the solutions. The generation unit uses the generation AI to simulate specific cases in the troubleshooting guide and show the solutions. Troubleshooting guides include, but are not limited to, procedure manuals, FAQs, visual guides, etc. For example, the generation AI can simulate troubleshooting based on a scenario and show the solutions in a video. The generation unit can also use the generation AI to simulate specific cases and explain the solutions using narration or subtitles. This enables practical education by simulating specific cases.

[0035] The reception unit can analyze the user's past input history and select the optimal input method. The reception unit uses the generation AI to analyze the user's past input history and select the optimal input method. The input history includes, but is not limited to, past input data and analysis of input patterns. For example, the generation AI preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The generation AI can also predict and suggest an input method to be used during a specific time period based on the user's past input history. The generation AI can also suggest similar input methods based on content that the user has entered in the past. In this way, the optimal input method can be provided to the user by analyzing the past input history.

[0036] The reception unit can filter text based on the user's current project and areas of interest when the text is input. The reception unit uses the generation AI to filter text based on the user's current project and areas of interest when the text is input. Areas of interest include, but are not limited to, the user's profile information and past activity history. For example, the generation AI can preferentially display text related to the user's current project. The generation AI can also filter and display related text based on the user's areas of interest. The generation AI can also suggest related text by referring to the user's past project history. This makes it possible to provide highly relevant information by filtering based on the user's areas of interest.

[0037] The reception unit can select the optimal input means depending on the user's input method (voice, text, image, etc.) when inputting text. The reception unit uses the generation AI to select the optimal input means depending on the user's input method (voice, text, image, etc.) when inputting text. Input methods include, but are not limited to, voice input, text input, image input, etc. For example, if the user desires voice input, the generation AI can provide voice input with priority. Also, if the user desires text input, the generation AI can provide text input with priority. Also, if the user desires image input, the generation AI can provide image input with priority. This improves input efficiency by providing the optimal means depending on the user's input method.

[0038] The reception unit can prioritize inputting highly relevant text by taking into account the user's geographical location information when inputting text. The reception unit uses the generation AI to prioritize inputting highly relevant text by taking into account the user's geographical location information when inputting text. Geographical location information includes, but is not limited to, GPS data, IP address, location information services, etc. For example, if the user is in a specific area, the generation AI can prioritize inputting text related to that area. Furthermore, if the user is moving, the generation AI can prioritize inputting relevant text based on the user's current location. Furthermore, if the user is in a specific location, the generation AI can prioritize inputting text related to that location. In this way, highly relevant information can be provided to the user by taking into account the geographical location information.

[0039] The reception unit can analyze the user's social media activity and input related text when text is input. The reception unit uses the generation AI to analyze the user's social media activity and input related text when text is input. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of followers. For example, the generation AI analyzes the content posted by the user on social media and inputs related text. The generation AI can also input related text by referring to the user's social media activity history. The generation AI can also input related text by referring to the activities of the user's friends on social media. In this way, information relevant to the user can be provided by analyzing social media activity.

[0040] The reception unit can customize the input method by reflecting the user's past feedback when inputting text. The reception unit uses the generation AI to customize the input method by reflecting the user's past feedback when inputting text. Feedback includes, but is not limited to, user ratings, comments, survey results, etc. For example, the generation AI customizes the input method based on feedback provided by the user in the past. The generation AI can also suggest an optimal input method based on the user's past feedback. The generation AI can also adjust the input interface by reflecting the user's feedback. In this way, the optimal input method can be provided to the user by reflecting past feedback.

[0041] The analysis unit can adjust the level of detail of the scenario based on the importance of the text when generating a scenario. The analysis unit uses the generation AI to adjust the level of detail of the scenario based on the importance of the text when generating a scenario. Examples of the importance of the text include, but are not limited to, the frequency of appearance of keywords and the importance of the context. For example, the generation AI generates a scenario that explains important text portions in detail. The generation AI can also generate a scenario that briefly explains text portions with low importance. The generation AI can also dynamically adjust the level of detail of the scenario according to the importance of the text. As a result, important information can be explained in detail by adjusting the level of detail of the scenario based on the importance of the text.

[0042] The analysis unit can apply different analysis algorithms depending on the text category when generating a scenario. The analysis unit uses the generation AI to apply different analysis algorithms depending on the text category when generating a scenario. Text categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized analysis algorithm to technical text. The generation AI can also apply a simple analysis algorithm to general text. The generation AI can also select the optimal analysis algorithm depending on the text category. This improves the accuracy of the scenario by applying the optimal analysis algorithm depending on the text category.

[0043] When generating a scenario, the analysis unit can improve the accuracy of the scenario by referring to the user's past scenario results. When generating a scenario, the analysis unit uses the generation AI to improve the accuracy of the scenario by referring to the user's past scenario results. Past scenario results include, but are not limited to, evaluations of past scenarios and user feedback. For example, the generation AI improves the accuracy by referring to scenarios generated by the user in the past. The generation AI can also extract areas for improvement from the user's past scenario results and improve the accuracy of the scenario. The generation AI can also improve the accuracy of the scenario based on user feedback. In this way, the accuracy of the scenario is improved by referring to the past scenario results.

[0044] The analysis unit can determine the priority of scenarios based on the time of submission of text when generating a scenario. The analysis unit, using the generation AI, determines the priority of scenarios based on the time of submission of text when generating a scenario. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI prioritizes text that is submitted earlier in the scenario. The generation AI can also reflect text that is submitted later in the scenario later. The generation AI can also dynamically adjust the priority of scenarios based on the time of submission. This makes it possible to provide timely information by determining the priority of scenarios based on the time of submission.

[0045] The analysis unit can adjust the order of the scenarios based on the relevance of the text when generating a scenario. The analysis unit uses the generation AI to adjust the order of the scenarios based on the relevance of the text when generating a scenario. Examples of text relevance include, but are not limited to, keyword co-occurrence, contextual consistency, etc. For example, the generation AI prioritizes reflecting highly relevant text in the scenario. The generation AI can also reflect less relevant text in the scenario later. The generation AI can also dynamically adjust the order of the scenarios based on the relevance of the text. In this way, by adjusting the order of the scenarios based on the relevance of the text, a scenario that is easy for viewers to understand can be provided.

[0046] The analysis unit can adjust the use of technical terms in the scenario according to the user's level of expertise when generating a scenario. The analysis unit uses the generation AI to adjust the use of technical terms in the scenario according to the user's level of expertise when generating a scenario. Expertise level includes, but is not limited to, the user's work history, educational background, and past learning history. For example, the generation AI can generate a scenario that uses a lot of technical terms for a user with a high level of expertise. The generation AI can also generate a scenario that uses less technical terms for a user with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the scenario according to the user's level of expertise. This makes it possible to provide a scenario that is easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise.

[0047] The generation unit can adjust the level of detail of the video based on the importance of the scenario when generating the video. The generation unit uses the generation AI to adjust the level of detail of the video based on the importance of the scenario when generating the video. The importance of the scenario includes, but is not limited to, the number of scenes, the level of detail of each scene, and the overall resolution. For example, the generation AI generates a video that explains important parts of the scenario in detail. The generation AI can also generate a video that briefly explains less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of the video according to the importance of the scenario. As a result, important information can be explained in detail by adjusting the level of detail of the video based on the importance of the scenario.

[0048] The generation unit can apply different generation algorithms depending on the scenario category when generating a video. The generation unit uses the generation AI to apply different generation algorithms depending on the scenario category when generating a video. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized generation algorithm to technical scenarios. The generation AI can also apply a simple generation algorithm to general scenarios. The generation AI can also select the optimal generation algorithm depending on the scenario category. This improves the accuracy of the video by applying the optimal generation algorithm depending on the scenario category.

[0049] The generation unit can improve the accuracy of the video when generating the video by referring to the user's past video results. The generation unit uses the generation AI to improve the accuracy of the video when generating the video by referring to the user's past video results. Past video results include, but are not limited to, past video ratings and user feedback, for example. For example, the generation AI improves the accuracy by referring to videos generated by the user in the past. The generation AI can also extract areas for improvement from the user's past video results and improve the accuracy of the video. The generation AI can also improve the accuracy of the video based on user feedback. In this way, the accuracy of the video is improved by referring to past video results.

[0050] The generation unit can determine the priority of videos based on the submission time of the scenario when generating the videos. The generation unit uses the generation AI to determine the priority of videos based on the submission time of the scenario when generating the videos. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI prioritizes scenarios that are submitted earlier in the video. The generation AI can also reflect scenarios that are submitted later in the video later. The generation AI can also dynamically adjust the priority of videos based on the submission time. This makes it possible to provide timely information by determining the priority of videos based on the submission time.

[0051] The generation unit can adjust the order of videos based on the relevance of the scenario when generating the videos. The generation unit uses the generation AI to adjust the order of videos based on the relevance of the scenario when generating the videos. The relevance of the scenario includes, but is not limited to, for example, scene relevance and storytelling flow. For example, the generation AI prioritizes reflecting highly relevant scenarios in the videos. The generation AI can also reflect less relevant scenarios in the videos later. The generation AI can also dynamically adjust the order of videos based on the relevance of the scenario. In this way, by adjusting the order of videos based on the relevance of the scenario, it is possible to provide videos that are easy for viewers to understand.

[0052] The generation unit can adjust the use of technical terms in the video according to the user's level of expertise when generating the video. The generation unit uses the generation AI to adjust the use of technical terms in the video according to the user's level of expertise when generating the video. Expertise level includes, but is not limited to, the user's work history, educational background, and past learning history, for example. For example, the generation AI can generate a video that uses a lot of technical terms for a user with a high level of expertise. The generation AI can also generate a video that uses less technical terms for a user with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the video according to the user's level of expertise. This makes it possible to provide a video that is easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise.

[0053] The scene generation unit can adjust the level of detail of a scene based on the importance of the scenario when generating a scene. The scene generation unit uses the generation AI to adjust the level of detail of a scene based on the importance of the scenario when generating a scene. The level of detail of a scene includes, but is not limited to, the number of scenes, the level of detail of each scene, and the overall resolution. For example, the generation AI generates scenes that explain important parts of the scenario in detail. The generation AI can also generate scenes that briefly explain less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of a scene according to the importance of the scenario. As a result, important information can be explained in detail by adjusting the level of detail of a scene based on the importance of the scenario.

[0054] The scene generation unit can apply different generation algorithms depending on the category of the scenario when generating a scene. The scene generation unit uses the generation AI to apply different generation algorithms depending on the category of the scenario when generating a scene. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized generation algorithm to technical scenarios. The generation AI can also apply a simple generation algorithm to general scenarios. The generation AI can also select the optimal generation algorithm depending on the category of the scenario. This improves the accuracy of the scene by applying the optimal generation algorithm depending on the category of the scenario.

[0055] The scene generation unit can improve the accuracy of a scene when generating a scene by referring to the user's past scene results. The scene generation unit uses the generation AI to improve the accuracy of a scene when generating a scene by referring to the user's past scene results. Past scene results include, but are not limited to, evaluations of past scenes and user feedback. For example, the generation AI improves the accuracy by referring to scenes generated by the user in the past. The generation AI can also extract areas for improvement from the user's past scene results and improve the accuracy of the scene. The generation AI can also improve the accuracy of a scene based on user feedback. In this way, the accuracy of a scene is improved by referring to past scene results.

[0056] The scene generation unit can determine the priority of scenes based on the submission time of the scenario when generating the scene. The scene generation unit uses the generation AI to determine the priority of scenes based on the submission time of the scenario when generating the scene. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI preferentially reflects scenarios that are submitted earlier in the scene. The generation AI can also reflect scenarios that are submitted later in the scene later. The generation AI can also dynamically adjust the priority of scenes based on the submission time. In this way, by determining the priority of scenes based on the submission time, timely information can be provided.

[0057] The scene generation unit can adjust the order of scenes based on the relevance of the scenario when generating scenes. The scene generation unit uses the generation AI to adjust the order of scenes based on the relevance of the scenario when generating scenes. The relevance of the scenario includes, but is not limited to, for example, the relevance of the scenario, the flow of storytelling, etc. For example, the generation AI prioritizes reflecting highly relevant scenarios in the scenes. The generation AI can also reflect less relevant scenarios in the scenes later. The generation AI can also dynamically adjust the order of scenes based on the relevance of the scenario. In this way, by adjusting the order of scenes based on the relevance of the scenario, it is possible to provide scenes that are easy for viewers to understand.

[0058] The narration adding unit can adjust the level of detail of the narration based on the importance of the scenario when adding narration. The narration adding unit uses the generation AI to adjust the level of detail of the narration based on the importance of the scenario when adding narration. The level of detail of the narration includes, but is not limited to, the depth of explanation, the number of specific examples, and the use of technical terms. For example, the generation AI adds narration that explains important parts of the scenario in detail. The generation AI can also add narration that briefly explains less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of the narration according to the importance of the scenario. In this way, important information can be explained in detail by adjusting the level of detail of the narration based on the importance of the scenario.

[0059] The narration adding unit can apply different narration algorithms depending on the category of the scenario when adding narration. The narration adding unit uses the generation AI to apply different narration algorithms depending on the category of the scenario when adding narration. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized narration algorithm to technical scenarios. The generation AI can also apply a simple narration algorithm to general scenarios. The generation AI can also select the optimal narration algorithm depending on the category of the scenario. This improves the accuracy of the narration by applying the optimal narration algorithm depending on the category of the scenario.

[0060] The narration adding unit can improve the accuracy of the narration when adding a narration by referring to the user's past narration results. The narration adding unit uses the generation AI to improve the accuracy of the narration when adding a narration by referring to the user's past narration results. Past narration results include, but are not limited to, evaluations of past narrations and user feedback, for example. For example, the generation AI improves the accuracy by referring to narrations added by the user in the past. The generation AI can also extract areas for improvement from the user's past narration results and improve the accuracy of the narration. The generation AI can also improve the accuracy of the narration based on user feedback. In this way, the accuracy of the narration is improved by referring to the past narration results.

[0061] The narration adding unit can determine the priority of the narration based on the submission time of the scenario when adding the narration. The narration adding unit uses the generation AI to determine the priority of the narration based on the submission time of the scenario when adding the narration. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI can prioritize scenarios that are submitted earlier in the narration. The generation AI can also reflect scenarios that are submitted later in the narration later. The generation AI can also dynamically adjust the priority of the narration based on the submission time. In this way, by determining the priority of the narration based on the submission time, timely information can be provided.

[0062] The narration adding unit can adjust the order of the narration based on the relevance of the scenario when adding the narration. The narration adding unit uses the generation AI to adjust the order of the narration based on the relevance of the scenario when adding the narration. The relevance of the scenario includes, but is not limited to, scene relevance, storytelling flow, and the like. For example, the generation AI can prioritize reflecting highly relevant scenarios in the narration. The generation AI can also reflect less relevant scenarios in the narration later. The generation AI can also dynamically adjust the order of the narration based on the relevance of the scenario. In this way, by adjusting the order of the narration based on the relevance of the scenario, it is possible to provide narration that is easy for viewers to understand.

[0063] The narration adding unit can adjust the use of technical terms in the narration according to the user's level of expertise when adding a narration. The narration adding unit uses the generation AI to adjust the use of technical terms in the narration according to the user's level of expertise when adding a narration. Expertise level includes, but is not limited to, the user's work history, educational background, and past learning history. For example, the generation AI can add narration that uses a lot of technical terms to a user with a high level of expertise. The generation AI can also add narration that uses less technical terms to a user with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the narration according to the user's level of expertise. This allows for the provision of narration that is easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise.

[0064] The subtitle adding unit can adjust the level of detail of the subtitles based on the importance of the scenario when adding subtitles. The subtitle adding unit uses the generation AI to adjust the level of detail of the subtitles based on the importance of the scenario when adding subtitles. Examples of the level of detail of the subtitles include, but are not limited to, the depth of explanation, the number of specific examples, and the use of technical terms. For example, the generation AI adds subtitles that explain important parts of the scenario in detail. The generation AI can also add subtitles that briefly explain less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of the subtitles according to the importance of the scenario. In this way, important information can be explained in detail by adjusting the level of detail of the subtitles based on the importance of the scenario.

[0065] The subtitle adding unit can apply different subtitle algorithms depending on the scenario category when adding subtitles. The subtitle adding unit uses the generation AI to apply different subtitle algorithms depending on the scenario category when adding subtitles. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized subtitle algorithm to technical scenarios. The generation AI can also apply a simple subtitle algorithm to general scenarios. The generation AI can also select the optimal subtitle algorithm depending on the scenario category. This improves the accuracy of the subtitles by applying the optimal subtitle algorithm depending on the scenario category.

[0066] The subtitle adding unit can improve the accuracy of subtitles by referring to the user's past subtitle results when adding subtitles. The subtitle adding unit uses the generation AI to improve the accuracy of subtitles by referring to the user's past subtitle results when adding subtitles. Past subtitle results include, but are not limited to, past subtitle evaluations and user feedback, for example. For example, the generation AI improves accuracy by referring to subtitles added by the user in the past. The generation AI can also extract areas for improvement from the user's past subtitle results and improve the accuracy of the subtitles. The generation AI can also improve the accuracy of the subtitles based on user feedback. In this way, the accuracy of the subtitles is improved by referring to the past subtitle results.

[0067] The subtitle adding unit can determine the priority of subtitles based on the submission time of the scenario when adding subtitles. The subtitle adding unit uses the generation AI to determine the priority of subtitles based on the submission time of the scenario when adding subtitles. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI prioritizes scenarios that are submitted earlier in the subtitles. The generation AI can also prioritize scenarios that are submitted later in the subtitles. The generation AI can also dynamically adjust the priority of subtitles based on the submission time. In this way, by determining the priority of subtitles based on the submission time, timely information can be provided.

[0068] The subtitle adding unit can adjust the order of subtitles based on the relevance of the scenario when adding subtitles. The subtitle adding unit uses the generation AI to adjust the order of subtitles based on the relevance of the scenario when adding subtitles. The relevance of the scenario includes, but is not limited to, scene relevance, storytelling flow, and the like. For example, the generation AI prioritizes reflecting highly relevant scenarios in the subtitles. The generation AI can also reflect less relevant scenarios in the subtitles later. The generation AI can also dynamically adjust the order of subtitles based on the relevance of the scenario. In this way, by adjusting the order of subtitles based on the relevance of the scenario, subtitles that are easy for viewers to understand can be provided.

[0069] The subtitle adding unit can adjust the use of technical terms in the subtitles according to the user's level of expertise when adding subtitles. The subtitle adding unit uses the generation AI to adjust the use of technical terms in the subtitles according to the user's level of expertise when adding subtitles. Examples of the level of expertise include, but are not limited to, the user's work history, educational background, and past learning history. For example, the generation AI can add subtitles that use a lot of technical terms to users with a high level of expertise. The generation AI can also add subtitles that use less technical terms to users with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the subtitles according to the user's level of expertise. This makes it possible to provide subtitles that are easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The reception unit can analyze the user's past input history and select the optimal input method. For example, the generation AI can prioritize and suggest input methods (voice, text, etc.) that the user has frequently used in the past. The generation AI can also predict and suggest the input method that will be used at a specific time period based on the user's past input history. Furthermore, the generation AI can also suggest similar input methods by referring to content that the user has entered in the past. In this way, by analyzing the user's past input history, the optimal input method can be provided to the user.

[0072] When generating a scenario, the analysis unit can apply different analysis algorithms depending on the text category. For example, the generation AI applies a specialized analysis algorithm to technical text. The generation AI can also apply a simple analysis algorithm to general text. Furthermore, the generation AI can select the optimal analysis algorithm depending on the text category. This improves the accuracy of the scenario by applying the optimal analysis algorithm depending on the text category.

[0073] When generating a video, the generation unit can apply different generation algorithms depending on the scenario category. For example, the generation AI applies a specialized generation algorithm to technical scenarios. The generation AI can also apply a simple generation algorithm to general scenarios. Furthermore, the generation AI can select the optimal generation algorithm depending on the scenario category. This improves the accuracy of the video by applying the optimal generation algorithm depending on the scenario category.

[0074] The scene generation unit can adjust the level of detail of a scene based on the importance of the scenario when generating a scene. For example, the generation AI generates a scene that explains important parts of the scenario in detail. The generation AI can also generate a scene that briefly explains less important parts of the scenario. Furthermore, the generation AI can dynamically adjust the level of detail of a scene according to the importance of the scenario. This allows important information to be explained in detail by adjusting the level of detail of a scene based on the importance of the scenario.

[0075] When adding narration, the narration adding unit can apply different narration algorithms depending on the scenario category. For example, the generation AI can apply a specialized narration algorithm to technical scenarios. The generation AI can also apply a simple narration algorithm to general scenarios. Furthermore, the generation AI can select the optimal narration algorithm depending on the scenario category. This improves the accuracy of the narration by applying the optimal narration algorithm depending on the scenario category.

[0076] The processing flow of the first embodiment will be briefly explained below.

[0077] Step 1: The reception unit inputs the educational content in text format. The educational content may include technical education, business education, general knowledge education, etc. The reception unit can accept text formats such as plain text, rich text, and Markdown format. Step 2: The analysis unit uses the generation AI to analyze the text entered by the reception unit and generate a video scenario. The analysis is performed using methods such as natural language processing technology, keyword extraction, and grammar analysis. The generation AI analyzes the text using text generation AI (e.g., LLM) and generates a scenario. The analysis unit also understands the content of the text and decides which parts to explain in the video. Step 3: The generation unit uses the generation AI to create a video based on the scenario generated by the analysis unit. The video is created according to standards such as the software used, video format, and resolution. The generation AI generates each scene in the video according to the scenario and adds narration and subtitles.

[0078] (Example 2) An educational video creation system according to an embodiment of the present invention efficiently creates videos of educational content and effectively trains personnel. The educational video creation system inputs educational content in text format, and a generation AI analyzes the text, generates a video scenario, and creates videos based on the generated scenario. For example, the educational video creation system inputs educational content in text format. For example, the content may include a "Basic Manual for Customer Service" or a "Troubleshooting Guide." This text is then input into the generation AI. The educational video creation system then analyzes the input text using the generation AI to generate a video scenario. The generation AI understands the content of the text and determines which parts to explain in the video. For example, in the case of a "Basic Manual for Customer Service," the scenario includes information such as how to greet customers and how to handle inquiries. The educational video creation system then creates videos based on the scenario generated by the generation AI. The generation AI generates each scene in the video according to the scenario and adds narration and subtitles. For example, in a greeting scene, a video shows how the person in charge greets customers, and the narration explains the process. This allows personnel in the Sapporo base to efficiently receive training by watching the educational video creation system. Videos are visually easy to understand, making it easier to understand content that is difficult to convey through text alone. Generative AI also streamlines video creation and editing, enabling the provision of high-quality training videos in a short amount of time. For example, a troubleshooting guide video shows specific examples of problems and uses narration to explain how to solve them. This allows staff to acquire the skills to deal with problems they face in their actual work. This allows the training video creation system to efficiently train staff at the Sapporo base. For example, by watching visually easy-to-understand videos, staff can more easily understand content that is difficult to convey through text alone. Generative AI also streamlines video creation and editing, enabling the provision of high-quality training videos in a short amount of time. This allows staff to acquire the skills to deal with problems they face in their actual work.

[0079] An educational video creation system according to an embodiment includes a reception unit, an analysis unit, and a generation unit. The reception unit inputs educational content in text format. The educational content may include, but is not limited to, technical education, business education, and general knowledge education. The reception unit may accept text formats such as plain text, rich text, and Markdown. The analysis unit uses a generation AI to analyze the text input by the reception unit and generate a video scenario. The analysis may be performed using, but is not limited to, natural language processing technology, keyword extraction, grammar analysis, or other methods. For example, the generation AI may analyze the text using a text generation AI (e.g., LLM) and generate a scenario. The analysis unit may also use the generation AI to understand the content of the text and determine which parts to explain in the video. The generation unit uses the generation AI to create a video based on the scenario generated by the analysis unit. The video creation is performed according to, but is not limited to, standards such as the software used, the video format, and the resolution. For example, the generation AI may generate each scene of the video according to the scenario and add narration and subtitles. As a result, the educational video creation system according to the embodiment can efficiently create videos of educational content and effectively educate personnel.

[0080] The generation unit includes a scene generation unit that generates each scene of the video according to a scenario. The scene generation unit generates each scene of the video according to the scenario. The scene may include, but is not limited to, for example, the length, content, and transitions of the scene. The scene generation unit, for example, determines the order of the scenes based on the scenario and generates each scene. The scene generation unit can also set scene transitions according to the scenario. For example, the scene generation unit adds transition effects such as fade-in and fade-out to achieve a smooth transition between scenes. This allows for the generation of detailed scenes based on the scenario, thereby improving the quality of educational videos.

[0081] The scene generation unit includes a narration adding unit that adds narration. The narration adding unit adds narration to the scenes generated by the scene generation unit. The narration includes, but is not limited to, voice synthesis technology, narration scripts, and the like. The narration adding unit generates narration based on a scenario, for example, using voice synthesis technology. The narration adding unit can also add narration using voice synthesis technology based on the narration script. For example, the narration adding unit generates narration corresponding to each scene in the scenario and adds it to the scene. By adding narration, explanations to viewers become clearer, improving the educational effect.

[0082] The scene generation unit includes a subtitle addition unit that adds subtitles. The subtitle addition unit adds subtitles to the scenes generated by the scene generation unit. The subtitles include, but are not limited to, subtitle font, display position, and timing, for example. The subtitle addition unit generates subtitle content based on a scenario, for example, and adds the content to the scenes. The subtitle addition unit can also set the subtitle font and display position. For example, the subtitle addition unit adjusts the subtitle font and display position so that the viewer can easily understand the content. As a result, adding subtitles makes it easier for the viewer to understand the content, improving the educational effect.

[0083] The analysis unit can understand the content of the text and determine which parts to explain in the video. The analysis unit uses a generation AI to understand the content of the text and determine which parts to explain in the video. Methods for understanding the content of the text include, but are not limited to, natural language processing technology, semantic analysis, and context understanding. For example, the generation AI analyzes the text using a text generation AI (e.g., LLM) and extracts important parts. The analysis unit can also use the generation AI to understand the context of the text and determine which parts to explain in the video. This makes it possible to generate an appropriate scenario by understanding the content of the text.

[0084] The generation unit can simulate specific cases in the troubleshooting guide and show the solutions. The generation unit uses the generation AI to simulate specific cases in the troubleshooting guide and show the solutions. Troubleshooting guides include, but are not limited to, procedure manuals, FAQs, visual guides, etc. For example, the generation AI can simulate troubleshooting based on a scenario and show the solutions in a video. The generation unit can also use the generation AI to simulate specific cases and explain the solutions using narration or subtitles. This enables practical education by simulating specific cases.

[0085] The reception unit can estimate the user's emotions and adjust the timing of text input based on the estimated user emotions. The reception unit can use the generation AI to estimate the user's emotions and adjust the timing of text input based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. The generation AI can also analyze the user's text data to estimate the emotion. For example, if the user is feeling stressed, the timing of input prompts can be delayed to allow the user to relax. If the user is relaxed, the timing of input prompts can be advanced to allow the user to proceed smoothly. If the user is in a hurry, the timing of input prompts can be optimized to allow the user to complete the input quickly. This allows the input timing to be adjusted according to the user's emotions, reducing stress and enabling efficient input.

[0086] The reception unit can analyze the user's past input history and select the optimal input method. The reception unit uses the generation AI to analyze the user's past input history and select the optimal input method. The input history includes, but is not limited to, past input data and analysis of input patterns. For example, the generation AI preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The generation AI can also predict and suggest an input method to be used during a specific time period based on the user's past input history. The generation AI can also suggest similar input methods based on content that the user has entered in the past. In this way, the optimal input method can be provided to the user by analyzing the past input history.

[0087] The reception unit can filter text based on the user's current project and areas of interest when the text is input. The reception unit uses the generation AI to filter text based on the user's current project and areas of interest when the text is input. Areas of interest include, but are not limited to, the user's profile information and past activity history. For example, the generation AI can preferentially display text related to the user's current project. The generation AI can also filter and display related text based on the user's areas of interest. The generation AI can also suggest related text by referring to the user's past project history. This makes it possible to provide highly relevant information by filtering based on the user's areas of interest.

[0088] The reception unit can select the optimal input means depending on the user's input method (voice, text, image, etc.) when inputting text. The reception unit uses the generation AI to select the optimal input means depending on the user's input method (voice, text, image, etc.) when inputting text. Input methods include, but are not limited to, voice input, text input, image input, etc. For example, if the user desires voice input, the generation AI can provide voice input with priority. Also, if the user desires text input, the generation AI can provide text input with priority. Also, if the user desires image input, the generation AI can provide image input with priority. This improves input efficiency by providing the optimal means depending on the user's input method.

[0089] The reception unit can estimate the user's emotions and determine the priority of text to be input based on the estimated user emotions. The reception unit can use the generation AI to estimate the user's emotions and determine the priority of text to be input based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. Furthermore, the generation AI can analyze the user's text data to estimate the emotion. For example, if the user is stressed, important text can be input with priority. If the user is relaxed, detailed text can be input with priority. If the user is in a hurry, brief text can be input with priority. In this way, important information can be input with priority by determining the priority of text according to the user's emotions.

[0090] The reception unit can prioritize inputting highly relevant text by taking into account the user's geographical location information when inputting text. The reception unit uses the generation AI to prioritize inputting highly relevant text by taking into account the user's geographical location information when inputting text. Geographical location information includes, but is not limited to, GPS data, IP address, location information services, etc. For example, if the user is in a specific area, the generation AI can prioritize inputting text related to that area. Furthermore, if the user is moving, the generation AI can prioritize inputting relevant text based on the user's current location. Furthermore, if the user is in a specific location, the generation AI can prioritize inputting text related to that location. In this way, highly relevant information can be provided to the user by taking into account the geographical location information.

[0091] The reception unit can analyze the user's social media activity and input related text when text is input. The reception unit uses the generation AI to analyze the user's social media activity and input related text when text is input. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of followers. For example, the generation AI analyzes the content posted by the user on social media and inputs related text. The generation AI can also input related text by referring to the user's social media activity history. The generation AI can also input related text by referring to the activities of the user's friends on social media. In this way, information relevant to the user can be provided by analyzing social media activity.

[0092] The reception unit can customize the input method by reflecting the user's past feedback when inputting text. The reception unit uses the generation AI to customize the input method by reflecting the user's past feedback when inputting text. Feedback includes, but is not limited to, user ratings, comments, survey results, etc. For example, the generation AI customizes the input method based on feedback provided by the user in the past. The generation AI can also suggest an optimal input method based on the user's past feedback. The generation AI can also adjust the input interface by reflecting the user's feedback. In this way, the optimal input method can be provided to the user by reflecting past feedback.

[0093] The analysis unit can estimate the user's emotions and adjust the way the scenario is presented based on the estimated user emotions. The analysis unit uses the generation AI to estimate the user's emotions and adjust the way the scenario is presented based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI analyzes the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. Furthermore, the generation AI can analyze the user's text data to estimate the emotion. For example, if the user is relaxed, a scenario using gentle expressions can be generated. If the user is nervous, a scenario using concise and clear expressions can be generated. If the user is excited, a scenario using visually stimulating expressions can be generated. In this way, by adjusting the way the scenario is presented based on the user's emotions, a scenario that is easy for viewers to understand can be provided.

[0094] The analysis unit can adjust the level of detail of the scenario based on the importance of the text when generating a scenario. The analysis unit uses the generation AI to adjust the level of detail of the scenario based on the importance of the text when generating a scenario. Examples of the importance of the text include, but are not limited to, the frequency of appearance of keywords and the importance of the context. For example, the generation AI generates a scenario that explains important text portions in detail. The generation AI can also generate a scenario that briefly explains text portions with low importance. The generation AI can also dynamically adjust the level of detail of the scenario according to the importance of the text. As a result, important information can be explained in detail by adjusting the level of detail of the scenario based on the importance of the text.

[0095] The analysis unit can apply different analysis algorithms depending on the text category when generating a scenario. The analysis unit uses the generation AI to apply different analysis algorithms depending on the text category when generating a scenario. Text categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized analysis algorithm to technical text. The generation AI can also apply a simple analysis algorithm to general text. The generation AI can also select the optimal analysis algorithm depending on the text category. This improves the accuracy of the scenario by applying the optimal analysis algorithm depending on the text category.

[0096] When generating a scenario, the analysis unit can improve the accuracy of the scenario by referring to the user's past scenario results. When generating a scenario, the analysis unit uses the generation AI to improve the accuracy of the scenario by referring to the user's past scenario results. Past scenario results include, but are not limited to, evaluations of past scenarios and user feedback. For example, the generation AI improves the accuracy by referring to scenarios generated by the user in the past. The generation AI can also extract areas for improvement from the user's past scenario results and improve the accuracy of the scenario. The generation AI can also improve the accuracy of the scenario based on user feedback. In this way, the accuracy of the scenario is improved by referring to the past scenario results.

[0097] The analysis unit can estimate the user's emotions and adjust the length of the scenario based on the estimated user emotions. The analysis unit can use the generation AI to estimate the user's emotions and adjust the length of the scenario based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. Furthermore, the generation AI can analyze the user's text data to estimate the emotion. For example, if the user is in a hurry, a short scenario can be generated. If the user is relaxed, a detailed scenario can be generated. If the user is excited, a visually stimulating scenario can be generated. This allows the length of the scenario to be adjusted according to the user's emotions, thereby providing the viewer with an optimal scenario.

[0098] The analysis unit can determine the priority of scenarios based on the time of submission of text when generating a scenario. The analysis unit, using the generation AI, determines the priority of scenarios based on the time of submission of text when generating a scenario. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI prioritizes text that is submitted earlier in the scenario. The generation AI can also reflect text that is submitted later in the scenario later. The generation AI can also dynamically adjust the priority of scenarios based on the time of submission. This makes it possible to provide timely information by determining the priority of scenarios based on the time of submission.

[0099] The analysis unit can adjust the order of the scenarios based on the relevance of the text when generating a scenario. The analysis unit uses the generation AI to adjust the order of the scenarios based on the relevance of the text when generating a scenario. Examples of text relevance include, but are not limited to, keyword co-occurrence, contextual consistency, etc. For example, the generation AI prioritizes reflecting highly relevant text in the scenario. The generation AI can also reflect less relevant text in the scenario later. The generation AI can also dynamically adjust the order of the scenarios based on the relevance of the text. In this way, by adjusting the order of the scenarios based on the relevance of the text, a scenario that is easy for viewers to understand can be provided.

[0100] The analysis unit can adjust the use of technical terms in the scenario according to the user's level of expertise when generating a scenario. The analysis unit uses the generation AI to adjust the use of technical terms in the scenario according to the user's level of expertise when generating a scenario. Expertise level includes, but is not limited to, the user's work history, educational background, and past learning history. For example, the generation AI can generate a scenario that uses a lot of technical terms for a user with a high level of expertise. The generation AI can also generate a scenario that uses less technical terms for a user with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the scenario according to the user's level of expertise. This makes it possible to provide a scenario that is easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise.

[0101] The generation unit can estimate the user's emotions and adjust the video generation method based on the estimated user emotions. The generation unit uses a generation AI to estimate the user's emotions and adjust the video generation method based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI analyzes the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. Furthermore, the generation AI can analyze the user's text data to estimate the emotion. For example, if the user is relaxed, a video that progresses at a leisurely pace can be generated. If the user is in a hurry, a video that emphasizes the shortest route can be generated. If the user is excited, a video that adds visually stimulating effects can be generated. This allows the video generation method to be adjusted according to the user's emotions, providing the viewer with the optimal video.

[0102] The generation unit can adjust the level of detail of the video based on the importance of the scenario when generating the video. The generation unit uses the generation AI to adjust the level of detail of the video based on the importance of the scenario when generating the video. The importance of the scenario includes, but is not limited to, the number of scenes, the level of detail of each scene, and the overall resolution. For example, the generation AI generates a video that explains important parts of the scenario in detail. The generation AI can also generate a video that briefly explains less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of the video according to the importance of the scenario. As a result, important information can be explained in detail by adjusting the level of detail of the video based on the importance of the scenario.

[0103] The generation unit can apply different generation algorithms depending on the scenario category when generating a video. The generation unit uses the generation AI to apply different generation algorithms depending on the scenario category when generating a video. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized generation algorithm to technical scenarios. The generation AI can also apply a simple generation algorithm to general scenarios. The generation AI can also select the optimal generation algorithm depending on the scenario category. This improves the accuracy of the video by applying the optimal generation algorithm depending on the scenario category.

[0104] The generation unit can improve the accuracy of the video when generating the video by referring to the user's past video results. The generation unit uses the generation AI to improve the accuracy of the video when generating the video by referring to the user's past video results. Past video results include, but are not limited to, past video ratings and user feedback, for example. For example, the generation AI improves the accuracy by referring to videos generated by the user in the past. The generation AI can also extract areas for improvement from the user's past video results and improve the accuracy of the video. The generation AI can also improve the accuracy of the video based on user feedback. In this way, the accuracy of the video is improved by referring to past video results.

[0105] The generation unit can estimate the user's emotions and adjust the length of the video based on the estimated user emotions. The generation unit can use a generation AI to estimate the user's emotions and adjust the length of the video based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. The generation AI can also analyze the user's text data to estimate the emotion. For example, if the user is in a hurry, a short video can be generated. If the user is relaxed, a detailed video can be generated. If the user is excited, a visually stimulating video can be generated. This allows the length of the video to be adjusted according to the user's emotions, thereby providing the viewer with the optimal video.

[0106] The generation unit can determine the priority of videos based on the submission time of the scenario when generating the videos. The generation unit uses the generation AI to determine the priority of videos based on the submission time of the scenario when generating the videos. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI prioritizes scenarios that are submitted earlier in the video. The generation AI can also reflect scenarios that are submitted later in the video later. The generation AI can also dynamically adjust the priority of videos based on the submission time. This makes it possible to provide timely information by determining the priority of videos based on the submission time.

[0107] The generation unit can adjust the order of videos based on the relevance of the scenario when generating the videos. The generation unit uses the generation AI to adjust the order of videos based on the relevance of the scenario when generating the videos. The relevance of the scenario includes, but is not limited to, for example, scene relevance and storytelling flow. For example, the generation AI prioritizes reflecting highly relevant scenarios in the videos. The generation AI can also reflect less relevant scenarios in the videos later. The generation AI can also dynamically adjust the order of videos based on the relevance of the scenario. In this way, by adjusting the order of videos based on the relevance of the scenario, it is possible to provide videos that are easy for viewers to understand.

[0108] The generation unit can adjust the use of technical terms in the video according to the user's level of expertise when generating the video. The generation unit uses the generation AI to adjust the use of technical terms in the video according to the user's level of expertise when generating the video. Expertise level includes, but is not limited to, the user's work history, educational background, and past learning history, for example. For example, the generation AI can generate a video that uses a lot of technical terms for a user with a high level of expertise. The generation AI can also generate a video that uses less technical terms for a user with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the video according to the user's level of expertise. This makes it possible to provide a video that is easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise.

[0109] The scene generation unit can estimate the user's emotions and adjust the scene generation method based on the estimated user emotions. The scene generation unit uses a generation AI to estimate the user's emotions and adjust the scene generation method based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI analyzes the user's facial expression data to estimate the emotions. The generation AI can also analyze the user's voice data to estimate the emotions. Furthermore, the generation AI can analyze the user's text data to estimate the emotions. For example, if the user is relaxed, a relaxed scene can be generated. If the user is in a hurry, a short and to-the-point scene can be generated. If the user is excited, a visually stimulating scene can be generated. In this way, by adjusting the scene generation method according to the user's emotions, the optimal scene can be provided to the viewer.

[0110] The scene generation unit can adjust the level of detail of a scene based on the importance of the scenario when generating a scene. The scene generation unit uses the generation AI to adjust the level of detail of a scene based on the importance of the scenario when generating a scene. The level of detail of a scene includes, but is not limited to, the number of scenes, the level of detail of each scene, and the overall resolution. For example, the generation AI generates scenes that explain important parts of the scenario in detail. The generation AI can also generate scenes that briefly explain less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of a scene according to the importance of the scenario. As a result, important information can be explained in detail by adjusting the level of detail of a scene based on the importance of the scenario.

[0111] The scene generation unit can apply different generation algorithms depending on the category of the scenario when generating a scene. The scene generation unit uses the generation AI to apply different generation algorithms depending on the category of the scenario when generating a scene. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized generation algorithm to technical scenarios. The generation AI can also apply a simple generation algorithm to general scenarios. The generation AI can also select the optimal generation algorithm depending on the category of the scenario. This improves the accuracy of the scene by applying the optimal generation algorithm depending on the category of the scenario.

[0112] The scene generation unit can improve the accuracy of a scene when generating a scene by referring to the user's past scene results. The scene generation unit uses the generation AI to improve the accuracy of a scene when generating a scene by referring to the user's past scene results. Past scene results include, but are not limited to, evaluations of past scenes and user feedback. For example, the generation AI improves the accuracy by referring to scenes generated by the user in the past. The generation AI can also extract areas for improvement from the user's past scene results and improve the accuracy of the scene. The generation AI can also improve the accuracy of a scene based on user feedback. In this way, the accuracy of a scene is improved by referring to past scene results.

[0113] The scene generation unit can estimate the user's emotions and adjust the length of a scene based on the estimated user's emotions. The scene generation unit uses a generation AI to estimate the user's emotions and adjust the length of a scene based on the estimated user's emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. The generation AI can also analyze the user's text data to estimate the emotion. For example, if the user is in a hurry, a short scene can be generated. If the user is relaxed, a detailed scene can be generated. If the user is excited, a visually stimulating scene can be generated. This allows the length of a scene to be adjusted according to the user's emotions, providing the viewer with the optimal scene.

[0114] The scene generation unit can determine the priority of scenes based on the submission time of the scenario when generating the scene. The scene generation unit uses the generation AI to determine the priority of scenes based on the submission time of the scenario when generating the scene. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI preferentially reflects scenarios that are submitted earlier in the scene. The generation AI can also reflect scenarios that are submitted later in the scene later. The generation AI can also dynamically adjust the priority of scenes based on the submission time. In this way, by determining the priority of scenes based on the submission time, timely information can be provided.

[0115] The scene generation unit can adjust the order of scenes based on the relevance of the scenario when generating scenes. The scene generation unit uses the generation AI to adjust the order of scenes based on the relevance of the scenario when generating scenes. The relevance of the scenario includes, but is not limited to, for example, the relevance of the scenario, the flow of storytelling, etc. For example, the generation AI prioritizes reflecting highly relevant scenarios in the scenes. The generation AI can also reflect less relevant scenarios in the scenes later. The generation AI can also dynamically adjust the order of scenes based on the relevance of the scenario. In this way, by adjusting the order of scenes based on the relevance of the scenario, it is possible to provide scenes that are easy for viewers to understand.

[0116] The narration adding unit can estimate the user's emotions and adjust the way the narration is expressed based on the estimated user emotions. The narration adding unit can use the generation AI to estimate the user's emotions and adjust the way the narration is expressed based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. Furthermore, the generation AI can analyze the user's text data to estimate the emotion. For example, if the user is relaxed, the narration can be given in a soft voice. If the user is nervous, the narration can be given in a clear and concise voice. If the user is excited, the narration can be given in a visually stimulating voice. By adjusting the way the narration is expressed based on the user's emotions, the optimal narration can be provided to the viewer.

[0117] The narration adding unit can adjust the level of detail of the narration based on the importance of the scenario when adding narration. The narration adding unit uses the generation AI to adjust the level of detail of the narration based on the importance of the scenario when adding narration. The level of detail of the narration includes, but is not limited to, the depth of explanation, the number of specific examples, and the use of technical terms. For example, the generation AI adds narration that explains important parts of the scenario in detail. The generation AI can also add narration that briefly explains less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of the narration according to the importance of the scenario. In this way, important information can be explained in detail by adjusting the level of detail of the narration based on the importance of the scenario.

[0118] The narration adding unit can apply different narration algorithms depending on the category of the scenario when adding narration. The narration adding unit uses the generation AI to apply different narration algorithms depending on the category of the scenario when adding narration. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized narration algorithm to technical scenarios. The generation AI can also apply a simple narration algorithm to general scenarios. The generation AI can also select the optimal narration algorithm depending on the category of the scenario. This improves the accuracy of the narration by applying the optimal narration algorithm depending on the category of the scenario.

[0119] The narration adding unit can improve the accuracy of the narration when adding a narration by referring to the user's past narration results. The narration adding unit uses the generation AI to improve the accuracy of the narration when adding a narration by referring to the user's past narration results. Past narration results include, but are not limited to, evaluations of past narrations and user feedback, for example. For example, the generation AI improves the accuracy by referring to narrations added by the user in the past. The generation AI can also extract areas for improvement from the user's past narration results and improve the accuracy of the narration. The generation AI can also improve the accuracy of the narration based on user feedback. In this way, the accuracy of the narration is improved by referring to the past narration results.

[0120] The narration adding unit can estimate the user's emotions and adjust the length of the narration based on the estimated user emotions. The narration adding unit can use the generation AI to estimate the user's emotions and adjust the length of the narration based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotion. The generation AI can also analyze the user's voice data to estimate the emotion. The generation AI can also analyze the user's text data to estimate the emotion. For example, if the user is in a hurry, a short narration can be added. If the user is relaxed, a detailed narration can be added. If the user is excited, a visually stimulating narration can be added. This allows the length of the narration to be adjusted according to the user's emotions, thereby providing the optimal narration for the viewer.

[0121] The narration adding unit can determine the priority of the narration based on the submission time of the scenario when adding the narration. The narration adding unit uses the generation AI to determine the priority of the narration based on the submission time of the scenario when adding the narration. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI can prioritize scenarios that are submitted earlier in the narration. The generation AI can also reflect scenarios that are submitted later in the narration later. The generation AI can also dynamically adjust the priority of the narration based on the submission time. In this way, by determining the priority of the narration based on the submission time, timely information can be provided.

[0122] The narration adding unit can adjust the order of the narration based on the relevance of the scenario when adding the narration. The narration adding unit uses the generation AI to adjust the order of the narration based on the relevance of the scenario when adding the narration. The relevance of the scenario includes, but is not limited to, scene relevance, storytelling flow, and the like. For example, the generation AI can prioritize reflecting highly relevant scenarios in the narration. The generation AI can also reflect less relevant scenarios in the narration later. The generation AI can also dynamically adjust the order of the narration based on the relevance of the scenario. In this way, by adjusting the order of the narration based on the relevance of the scenario, it is possible to provide narration that is easy for viewers to understand.

[0123] The narration adding unit can adjust the use of technical terms in the narration according to the user's level of expertise when adding a narration. The narration adding unit uses the generation AI to adjust the use of technical terms in the narration according to the user's level of expertise when adding a narration. Expertise level includes, but is not limited to, the user's work history, educational background, and past learning history. For example, the generation AI can add narration that uses a lot of technical terms to a user with a high level of expertise. The generation AI can also add narration that uses less technical terms to a user with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the narration according to the user's level of expertise. This allows for the provision of narration that is easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise.

[0124] The subtitle adding unit can estimate the user's emotions and adjust the subtitle expression method based on the estimated user emotions. The subtitle adding unit can use the generation AI to estimate the user's emotions and adjust the subtitle expression method based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotions. The generation AI can also analyze the user's voice data to estimate the emotions. Furthermore, the generation AI can analyze the user's text data to estimate the emotions. For example, if the user is relaxed, subtitles using gentle expressions can be added. If the user is nervous, subtitles using clear and concise expressions can be added. If the user is excited, subtitles using visually stimulating expressions can be added. In this way, the subtitle expression method can be adjusted according to the user's emotions, thereby providing optimal subtitles for the viewer.

[0125] The subtitle adding unit can adjust the level of detail of the subtitles based on the importance of the scenario when adding subtitles. The subtitle adding unit uses the generation AI to adjust the level of detail of the subtitles based on the importance of the scenario when adding subtitles. Examples of the level of detail of the subtitles include, but are not limited to, the depth of explanation, the number of specific examples, and the use of technical terms. For example, the generation AI adds subtitles that explain important parts of the scenario in detail. The generation AI can also add subtitles that briefly explain less important parts of the scenario. The generation AI can also dynamically adjust the level of detail of the subtitles according to the importance of the scenario. In this way, important information can be explained in detail by adjusting the level of detail of the subtitles based on the importance of the scenario.

[0126] The subtitle adding unit can apply different subtitle algorithms depending on the scenario category when adding subtitles. The subtitle adding unit uses the generation AI to apply different subtitle algorithms depending on the scenario category when adding subtitles. Scenario categories include, but are not limited to, technical documents, business documents, and educational documents. For example, the generation AI applies a specialized subtitle algorithm to technical scenarios. The generation AI can also apply a simple subtitle algorithm to general scenarios. The generation AI can also select the optimal subtitle algorithm depending on the scenario category. This improves the accuracy of the subtitles by applying the optimal subtitle algorithm depending on the scenario category.

[0127] The subtitle adding unit can improve the accuracy of subtitles by referring to the user's past subtitle results when adding subtitles. The subtitle adding unit uses the generation AI to improve the accuracy of subtitles by referring to the user's past subtitle results when adding subtitles. Past subtitle results include, but are not limited to, past subtitle evaluations and user feedback, for example. For example, the generation AI improves accuracy by referring to subtitles added by the user in the past. The generation AI can also extract areas for improvement from the user's past subtitle results and improve the accuracy of the subtitles. The generation AI can also improve the accuracy of the subtitles based on user feedback. In this way, the accuracy of the subtitles is improved by referring to the past subtitle results.

[0128] The subtitle adding unit can estimate the user's emotions and adjust the length of the subtitles based on the estimated user emotions. The subtitle adding unit can use the generation AI to estimate the user's emotions and adjust the length of the subtitles based on the estimated user emotions. Methods for estimating emotions include, but are not limited to, facial expression recognition, voice analysis, and text analysis. For example, the generation AI can analyze the user's facial expression data to estimate the emotions. The generation AI can also analyze the user's voice data to estimate the emotions. Furthermore, the generation AI can analyze the user's text data to estimate the emotions. For example, if the user is in a hurry, short subtitles can be added. If the user is relaxed, detailed subtitles can be added. If the user is excited, visually stimulating subtitles can be added. In this way, the length of the subtitles can be adjusted according to the user's emotions, thereby providing optimal subtitles for the viewer.

[0129] The subtitle adding unit can determine the priority of subtitles based on the submission time of the scenario when adding subtitles. The subtitle adding unit uses the generation AI to determine the priority of subtitles based on the submission time of the scenario when adding subtitles. The submission time includes, but is not limited to, for example, a submission deadline, urgency, importance, etc. For example, the generation AI prioritizes scenarios that are submitted earlier in the subtitles. The generation AI can also prioritize scenarios that are submitted later in the subtitles. The generation AI can also dynamically adjust the priority of subtitles based on the submission time. In this way, by determining the priority of subtitles based on the submission time, timely information can be provided.

[0130] The subtitle adding unit can adjust the order of subtitles based on the relevance of the scenario when adding subtitles. The subtitle adding unit uses the generation AI to adjust the order of subtitles based on the relevance of the scenario when adding subtitles. The relevance of the scenario includes, but is not limited to, scene relevance, storytelling flow, and the like. For example, the generation AI prioritizes reflecting highly relevant scenarios in the subtitles. The generation AI can also reflect less relevant scenarios in the subtitles later. The generation AI can also dynamically adjust the order of subtitles based on the relevance of the scenario. In this way, by adjusting the order of subtitles based on the relevance of the scenario, subtitles that are easy for viewers to understand can be provided.

[0131] The subtitle adding unit can adjust the use of technical terms in the subtitles according to the user's level of expertise when adding subtitles. The subtitle adding unit uses the generation AI to adjust the use of technical terms in the subtitles according to the user's level of expertise when adding subtitles. Examples of the level of expertise include, but are not limited to, the user's work history, educational background, and past learning history. For example, the generation AI can add subtitles that use a lot of technical terms to users with a high level of expertise. The generation AI can also add subtitles that use less technical terms to users with a low level of expertise. The generation AI can also dynamically adjust the use of technical terms in the subtitles according to the user's level of expertise. This makes it possible to provide subtitles that are easy for viewers to understand by adjusting the use of technical terms according to the user's level of expertise. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, scene generation unit, narration addition unit, and subtitle addition unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and inputs educational content in text format. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input text using a generation AI to generate a video scenario. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and creates a video based on the generated scenario. The scene generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates each scene of the video according to the scenario. The narration addition unit is realized by the control unit 46A of the smart device 14 and adds narration to scenes. The subtitle addition unit is realized by the control unit 46A of the smart device 14 and adds subtitles to scenes. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, generation unit, scene generation unit, narration addition unit, and subtitle addition unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and inputs educational content in text format. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input text using a generation AI to generate a video scenario. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and creates a video based on the generated scenario. The scene generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates each scene of the video according to the scenario. The narration addition unit is realized by the control unit 46A of the smart glasses 214 and adds narration to scenes. The subtitle addition unit is realized by the control unit 46A of the smart glasses 214 and adds subtitles to scenes. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, scene generation unit, narration addition unit, and subtitle addition unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and inputs educational content in text format. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input text using a generation AI to generate a scenario for a video. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and creates a video based on the generated scenario. The scene generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates each scene of the video according to the scenario. The narration addition unit is realized by the control unit 46A of the headset-type terminal 314 and adds narration to scenes. The subtitle addition unit is realized by the control unit 46A of the headset-type terminal 314 and adds subtitles to scenes. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, scene generation unit, narration addition unit, and subtitle addition unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and inputs educational content in text format. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the input text using a generation AI to generate a video scenario. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and creates a video based on the generated scenario. The scene generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates each scene of the video according to the scenario. The narration addition unit is realized by the control unit 46A of the robot 414 and adds narration to scenes. The subtitle addition unit is realized by the control unit 46A of the robot 414 and adds subtitles to scenes.

[0132] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0133] The reception unit can analyze the user's past input history and select the optimal input method. For example, the generation AI can prioritize and suggest input methods (voice, text, etc.) that the user has frequently used in the past. The generation AI can also predict and suggest the input method that will be used at a specific time period based on the user's past input history. Furthermore, the generation AI can also suggest similar input methods by referring to content that the user has entered in the past. In this way, by analyzing the user's past input history, the optimal input method can be provided to the user.

[0134] When generating a scenario, the analysis unit can apply different analysis algorithms depending on the text category. For example, the generation AI applies a specialized analysis algorithm to technical text. The generation AI can also apply a simple analysis algorithm to general text. Furthermore, the generation AI can select the optimal analysis algorithm depending on the text category. This improves the accuracy of the scenario by applying the optimal analysis algorithm depending on the text category.

[0135] When generating a video, the generation unit can apply different generation algorithms depending on the scenario category. For example, the generation AI applies a specialized generation algorithm to technical scenarios. The generation AI can also apply a simple generation algorithm to general scenarios. Furthermore, the generation AI can select the optimal generation algorithm depending on the scenario category. This improves the accuracy of the video by applying the optimal generation algorithm depending on the scenario category.

[0136] The scene generation unit can adjust the level of detail of a scene based on the importance of the scenario when generating a scene. For example, the generation AI generates a scene that explains important parts of the scenario in detail. The generation AI can also generate a scene that briefly explains less important parts of the scenario. Furthermore, the generation AI can dynamically adjust the level of detail of a scene according to the importance of the scenario. This allows important information to be explained in detail by adjusting the level of detail of a scene based on the importance of the scenario.

[0137] When adding narration, the narration adding unit can apply different narration algorithms depending on the scenario category. For example, the generation AI can apply a specialized narration algorithm to technical scenarios. The generation AI can also apply a simple narration algorithm to general scenarios. Furthermore, the generation AI can select the optimal narration algorithm depending on the scenario category. This improves the accuracy of the narration by applying the optimal narration algorithm depending on the scenario category.

[0138] The reception unit can estimate the user's emotions and adjust the timing of text input based on the estimated user emotions. For example, the generation AI can analyze the user's facial expression data to estimate emotions. The generation AI can also analyze the user's voice data to estimate emotions. The generation AI can also analyze the user's text data to estimate emotions. For example, if the user is feeling stressed, the timing of input prompts can be delayed to allow the user to relax. If the user is relaxed, the timing of input prompts can be accelerated to allow the user to proceed smoothly. If the user is in a hurry, the timing of input prompts can be optimized to allow the user to complete input quickly. In this way, adjusting the input timing according to the user's emotions reduces stress and enables efficient input.

[0139] The analysis unit can estimate the user's emotions and adjust the way the scenario is presented based on the estimated user emotions. For example, the generation AI can analyze the user's facial expression data to estimate emotions. The generation AI can also analyze the user's voice data to estimate emotions. The generation AI can also analyze the user's text data to estimate emotions. For example, if the user is relaxed, a scenario using gentle expressions can be generated. If the user is nervous, a scenario using concise and clear expressions can be generated. If the user is excited, a scenario using visually stimulating expressions can be generated. In this way, by adjusting the way the scenario is presented according to the user's emotions, it is possible to provide a scenario that is easy for viewers to understand.

[0140] The generation unit can estimate the user's emotions and adjust the video generation method based on the estimated user emotions. For example, the generation AI can analyze the user's facial expression data to estimate emotions. The generation AI can also analyze the user's voice data to estimate emotions. Furthermore, the generation AI can analyze the user's text data to estimate emotions. For example, if the user is relaxed, a video that progresses at a leisurely pace can be generated. If the user is in a hurry, a video that emphasizes the shortest route can be generated. If the user is excited, a video that adds visually stimulating effects can be generated. In this way, by adjusting the video generation method according to the user's emotions, the optimal video can be provided to the viewer.

[0141] The scene generation unit can estimate the user's emotions and adjust the scene generation method based on the estimated user emotions. For example, the generation AI can analyze the user's facial expression data to estimate emotions. The generation AI can also analyze the user's voice data to estimate emotions. The generation AI can also analyze the user's text data to estimate emotions. For example, if the user is relaxed, a leisurely scene can be generated. If the user is in a hurry, a short and to-the-point scene can be generated. If the user is excited, a visually stimulating scene can be generated. This allows the scene generation method to be adjusted according to the user's emotions, providing the viewer with the optimal scene.

[0142] The subtitle adding unit can estimate the user's emotions and adjust the way the subtitles are expressed based on the estimated user emotions. For example, the generation AI can analyze the user's facial expression data to estimate emotions. The generation AI can also analyze the user's voice data to estimate emotions. The generation AI can also analyze the user's text data to estimate emotions. For example, if the user is relaxed, subtitles using gentle expressions can be added. If the user is nervous, subtitles using clear and concise expressions can be added. If the user is excited, subtitles using visually stimulating expressions can be added. In this way, by adjusting the way the subtitles are expressed according to the user's emotions, it is possible to provide the viewer with subtitles that are optimal for them.

[0143] The processing flow of the second embodiment will be briefly explained below.

[0144] Step 1: The reception unit inputs the educational content in text format. The educational content may include technical education, business education, general knowledge education, etc. The reception unit can accept text formats such as plain text, rich text, and Markdown format. Step 2: The analysis unit uses the generation AI to analyze the text entered by the reception unit and generate a video scenario. The analysis is performed using methods such as natural language processing technology, keyword extraction, and grammar analysis. The generation AI analyzes the text using text generation AI (e.g., LLM) and generates a scenario. The analysis unit also understands the content of the text and decides which parts to explain in the video. Step 3: The generation unit uses the generation AI to create a video based on the scenario generated by the analysis unit. The video is created according to standards such as the software used, video format, and resolution. The generation AI generates each scene in the video according to the scenario and adds narration and subtitles.

[0145] 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.

[0146] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0150] 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.

[0151] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0152] 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.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0154] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0159] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0161] 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.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0163] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0164] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0165] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0166] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0167] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0168] 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.

[0169] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0170] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0175] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0176] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0177] 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.

[0178] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0179] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0180] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0181] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0182] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0183] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0184] 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.

[0185] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0186] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0187] 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.

[0188] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0189] 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.

[0190] 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.

[0191] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0192] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0193] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0194] 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.

[0195] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0196] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0197] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0198] 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.

[0199] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0200] 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.

[0201] 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).

[0202] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0203] 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."

[0204] 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.

[0205] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0210] The hardware resource that executes the specific process 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 process may be a single processor.

[0211] 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.

[0212] 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.

[0213] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0214] 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.

[0215] 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.

[0216] [Explanation of symbols]

[0217] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception section for inputting educational content in text format; an analysis unit that analyzes the text input by the reception unit and generates a scenario for a video; a generation unit that generates a video based on the scenario generated by the analysis unit; Equipped with A system characterized by:

2. The generation unit It has a scene generation unit that generates each scene of the video according to the scenario.

2. The system of claim 1.

3. The scene generation unit Includes a narration adding section for adding narration 3. The system of claim 2.

4. The scene generation unit Equipped with a subtitle adding section to add subtitles 3. The system of claim 2.

5. The analysis unit Understand the content of the text and decide which parts to explain in the video 2. The system of claim 1.

6. The generation unit Simulate specific cases from the troubleshooting guide and show how to solve them 2. The system of claim 1.

7. The reception unit Estimate the user's emotions and adjust the timing of text input based on the estimated user emotions.

2. The system of claim 1.

8. The reception unit Analyze the user's past input history and select the optimal input method 2. The system of claim 1.

9. The reception unit As you type, it filters based on your current projects and interests.

2. The system of claim 1.

Images