System

Abstract

An object of the system according to the embodiment is to efficiently create and distribute a moving image based on information of a great person.SOLUTION: A system according to an embodiment includes an information collection unit, an analysis unit, a scenario creation unit, a moving image generation unit, an editing unit, and a distribution unit. The information collecting unit collects information of a great person using the generative AI. The analysis unit analyzes the information on the great person collected by the information collection unit. The scenario creation unit creates a scenario of the moving image based on the information analyzed by the analysis unit. The animation generation unit generates an animation based on the scenario created by the scenario creation unit. The editing unit edits the moving image generated by the moving image generation unit. The distribution unit distributes the video edited by the editing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, creating videos based on information about famous people was time-consuming and labor-intensive, making it difficult to do efficiently.

[0005] The system according to the embodiment aims to efficiently create and distribute videos based on information about great people. [Means for solving the problem]

[0006] The system according to the embodiment includes an information collection unit, an analysis unit, a scenario creation unit, a video generation unit, an editing unit, and a distribution unit. The information collection unit collects information about great people using a generation AI. The analysis unit analyzes the information about great people collected by the information collection unit. The scenario creation unit creates a video scenario based on the information analyzed by the analysis unit. The video generation unit generates a video based on the scenario created by the scenario creation unit. The editing unit edits the video generated by the video generation unit. The distribution unit distributes the video edited by the editing unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently create and distribute videos based on information about great people. [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) The great person video creation system according to an embodiment of the present invention is a system in which a generation AI collects and analyzes information about great people and generates videos of the great people based on that information. As a result, the great person video creation system can create videos that effectively convey information about great people and distribute them widely.

[0029] A great person video creation system according to an embodiment includes an information collection unit, an analysis unit, a scenario creation unit, a video generation unit, an editing unit, and a distribution unit. The information collection unit uses a generation AI to collect information about great people. For example, information about great people may be collected from the Internet or a database. Information about the great person's life, achievements, statements, photographs, video, and the like may also be collected. For example, historical documents, articles, and interview videos may serve as information sources. The analysis unit analyzes the information about great people collected by the information collection unit. For example, the generation AI extracts the great person's characteristics and important events. The generation AI may also analyze the great person's statements and episodes. For example, the generation AI may analyze the emotional nuances of the great person's statements. The scenario creation unit creates a video scenario based on the information analyzed by the analysis unit. For example, a scenario may be created that depicts the great person's life in chronological order. A scenario may also be created that focuses on a specific achievement. For example, a scenario may be created by combining the great person's statements and episodes. The video generation unit generates a video based on the scenario created by the scenario creation unit. For example, a video may be generated by combining photographs, video, audio, and text of the great person. It is also possible to animate photos of great figures and reproduce their statements using voice synthesis. The editing unit edits the videos generated by the video generation unit. For example, the editing unit adjusts the length of the videos and synchronizes the timing of audio and text. The content of the videos can also be improved based on viewer reactions and feedback. The distribution unit distributes the videos edited by the editing unit. For example, the videos are published on video sharing sites or social networking sites. The video can also be optimized to suit the characteristics of the distribution platform and distributed effectively. As a result, the great figure video creation system according to the embodiment can generate and widely distribute videos that effectively convey information about great figures. For example, the videos can be used as teaching materials in educational settings or to provide information to people interested in history and culture. Furthermore, spreading the achievements and ideas of great figures is expected to increase their influence on society.

[0030] The information collection unit can analyze handwritten documents and letters of great people and extract their personalities from their handwriting and writing style. For example, the information collection unit scans handwritten letters and notes of great people and identifies their personalities using handwriting analysis technology. For example, it analyzes changes in character shape and writing pressure to extract the great people's characteristic writing style. The information collection unit also analyzes handwritten documents of great people using natural language processing technology to extract characteristics of writing style and expression. For example, it identifies a tendency to frequently use specific phrases and expressions, revealing the great people's personalities. The information collection unit also analyzes handwritten documents of great people using image analysis technology to identify character arrangement and line spacing patterns. For example, it extracts characteristics of the great people's writing style from the size of the characters and the width of the line spacing. This makes it possible to extract personalities from handwritten documents and letters of great people and provide more detailed information.

[0031] The information collection unit analyzes interviews with people related to or family members of the great person, and is able to understand the great person's relationships and background information in detail. For example, the information collection unit analyzes interview videos of people related to or family members of the great person and extracts important information using natural language processing technology. For example, the information collection unit identifies the great person's relationships and background information from the content of the interviews. The information collection unit also analyzes audio of interviews with people related to or family members of the great person and converts the audio into text using speech recognition technology. For example, the content of the interviews is saved as text data, and the background information of the great person is understood in detail. The information collection unit also analyzes the content of interviews with people related to or family members of the great person using emotion analysis technology to track changes in emotion. For example, the intensity of emotions during the interviews is measured and emotionally important information is extracted. This allows the great person's relationships and background information to be understood in detail, providing a deeper understanding.

[0032] The Information Collection Department can 3D scan the tools and personal effects used by great people and use the data for analysis. For example, the Information Collection Department can 3D scan the tools and personal effects used by great people and analyze their shape and materials. For example, the Information Collection Department can 3D model the writing utensils and furniture used by great people and extract their characteristics. The Information Collection Department can also use the 3D scan data to recreate the living environment and usage methods of great people. For example, the Information Collection Department can analyze the placement and traces of use of tools used by great people to clarify their lifestyle. The Information Collection Department can also 3D scan the personal effects of great people and store them as a digital archive. For example, the personal effects of great people can be digitized and used as materials to pass on to future generations. This allows the Information Collection Department to 3D scan the tools and personal effects used by great people and use the detailed data for analysis.

[0033] The information collection unit collects geographic information related to the great person and can visualize the great person's range of activities and travel routes on a map. The information collection unit, for example, plots the great person's range of activities and travel routes on a map and visually displays them. For example, it maps the places the great person visited and lived on the map. The information collection unit also collects geographic information related to the great person and analyzes it using a geographic information system (GIS). For example, it displays the great person's range of activities and travel routes in chronological order to clarify the great person's behavioral patterns. The information collection unit also reproduces the great person's range of activities and travel routes on a 3D map to make them easier to visually understand. For example, it displays the route the great person took on a 3D map to relive the great person's actions. In this way, the great person's range of activities and travel routes can be visualized on a map, making them easier to visually understand.

[0034] The scenario creation unit can analyze the statements and episodes of great people and create a scenario that reflects their values ​​and philosophy. For example, the scenario creation unit analyzes the statements and episodes of great people and creates a scenario that reflects their values ​​and philosophy. For example, it incorporates the beliefs and principles that the great people held dear into the scenario. The scenario creation unit also analyzes the statements and episodes of great people using natural language processing technology to extract their values ​​and philosophy. For example, it reflects phrases and expressions that the great people frequently used in the scenario. The scenario creation unit also organizes the episodes of great people in chronological order and creates a scenario that reflects their values ​​and philosophy. For example, it builds a scenario centered around turning points and important events in the great person's life. In this way, it is possible to create a scenario that reflects the great person's values ​​and philosophy.

[0035] The scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people. For example, the scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people. For example, the scenario creation unit can create a moving scenario for viewers by moving an episode in which the great person overcame difficulties. The scenario creation unit can also organize the turning points and decisions in the lives of great people in chronological order and reflect the details in the scenario. For example, the scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people. For example, the scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people.

[0036] When depicting the life of a great person, the scenario creation unit can create a multi-character scenario that also includes the people and events surrounding the great person. For example, when depicting the life of a great person, the scenario creation unit creates a multi-character scenario that also includes the people and events surrounding the great person. For example, the scenario creation unit incorporates the perspectives of the great person's family, friends, colleagues, etc. The scenario creation unit also incorporates episodes of people surrounding the great person into the scenario depicting the life of the great person. For example, it describes episodes of people who were influenced by the great person or people who influenced the great person. The scenario creation unit also describes in detail the events surrounding the great person in the scenario depicting the life of the great person. For example, it reflects historical events and social background in which the great person was involved in the scenario. In this way, when depicting the life of a great person, it is possible to create a multi-character scenario that also includes the people and events surrounding the great person.

[0037] When creating a scenario focusing on the achievements of a great person, the scenario creation unit can depict the impact that the achievements of that great person have had on the modern world. For example, the scenario creation unit creates a scenario focusing on the achievements of a great person and depicts the impact that the achievements have had on the modern world. For example, it depicts how the inventions and discoveries of the great person have influenced modern technology and society. The scenario creation unit also organizes the achievements of the great person in chronological order and depicts their impact from a modern perspective. For example, it reflects in the scenario how the achievements of the great person have contributed to modern science, technology, and culture. The scenario creation unit also analyzes the achievements of the great person and depicts their impact using specific modern examples. For example, it depicts how the achievements of the great person are being applied to modern companies and research institutions. In this way, a scenario depicting the impact that the achievements of the great person have had on the modern world can be created.

[0038] The video generation unit can analyze photographs and videos of great people and generate animations that realistically reproduce the great people's movements and gestures. The video generation unit, for example, analyzes photographs and videos of great people and generates animations that realistically reproduce the great people's movements and gestures. For example, it animates the great people's walking and waving movements. The video generation unit also uses motion analysis technology to reproduce the great people's gestures based on video data of the great people. For example, it reflects the hand movements and facial expressions of the great people when they speak in the animation. The video generation unit also creates a 3D model of the great people's photograph and generates animations that reproduce their movements and gestures based on the model. For example, it realistically reproduces the great people's sitting posture and standing up movements. This makes it possible to generate animations that realistically reproduce the great people's movements and gestures.

[0039] The video generation unit can mimic the great person's voice quality and speaking style in detail when reproducing the great person's words using voice synthesis. For example, when reproducing the great person's words using voice synthesis, the video generation unit mimics the great person's voice quality in detail. For example, it reproduces the great person's voice pitch, tone, and rhythm. The video generation unit also analyzes the great person's speaking style and reflects these characteristics in the voice synthesis. For example, it reproduces the great person's speaking style in which they emphasize certain phrases and their unique intonation. The video generation unit also uses voice synthesis technology to reproduce the great person's voice quality and speaking style in detail based on the great person's voice data. For example, it reproduces the great person's intonation and pauses in their words. This makes it possible to mimic the great person's voice quality and speaking style in detail when reproducing the great person's words using voice synthesis.

[0040] When generating a video of a great person, the video generation unit can recreate the places where the great person was active and the historical background using 3D modeling. The video generation unit, for example, recreates the places where the great person was active using 3D modeling and incorporates it into the video. For example, it creates 3D models of the houses where the great person lived and the places where they worked. The video generation unit also recreates the historical background of the great person using 3D modeling and reflects this in the video. For example, it creates 3D models of the cityscapes and scenery of the era in which the great person lived. The video generation unit also recreates the places where the great person was active and the historical background using 3D modeling to generate a visually appealing video. For example, it creates 3D models of the roads the great person walked and the places they visited and incorporates them into the video. This allows the places where the great person was active and the historical background to be recreated using 3D modeling.

[0041] The video generation unit can incorporate the achievements and inventions of great people into videos as interactive demonstrations. For example, the video generation unit incorporates the achievements and inventions of great people into videos as interactive demonstrations. For example, it can simulate the operation of a device invented by a great person. The video generation unit can also incorporate the achievements of great people into videos as demonstrations that are easy to understand visually. For example, it can recreate the process of an experiment or research conducted by a great person. The video generation unit can also incorporate the inventions of great people into videos as interactive demonstrations that can be operated by viewers. For example, it can provide an interface that allows viewers to operate a machine invented by a great person. In this way, the achievements and inventions of great people can be incorporated into videos as interactive demonstrations.

[0042] When adjusting the timing of the audio and text in a video of a great person, the editorial department can analyze the points of emphasis in the great person's words and arrange them effectively. For example, the editorial department analyzes the points of emphasis in the great person's words and adjusts the timing of the audio and text based on the results. For example, the audio volume can be increased to emphasize important statements. The editorial department can also identify the points of emphasis in the great person's words and display text to match those points. For example, the timing of text display can be adjusted to emphasize famous quotes by the great person. The editorial department can also analyze the points of emphasis in the great person's words and optimize the arrangement of the audio and text based on the results. For example, a pause can be left before and after important statements to attract the viewer's attention. In this way, the editorial department can analyze the points of emphasis in the great person's words and arrange them effectively.

[0043] When adjusting the length of videos about great people, the editorial department can calculate the optimal length to maintain viewer concentration and interest. For example, the editorial department develops an algorithm to calculate the optimal length of a video to maintain viewer concentration and interest. For example, the editorial department determines the optimal video length based on viewer viewing history and feedback. The editorial department also adjusts the length of the video to maintain viewer interest. For example, the editorial department keeps viewer concentration by shortening important scenes. The editorial department also analyzes viewer concentration and interest and optimizes the video length based on the results. For example, the editorial department frequently switches scenes to prevent viewers from getting bored. This makes it possible to calculate the optimal length to maintain viewer concentration and interest.

[0044] When editing videos of great people, the editorial department can automatically generate multiple versions tailored to different audiences. For example, the editorial department develops a system that automatically generates multiple versions tailored to different audiences. For example, it creates versions for children, students, and professionals. The editorial department also adjusts the content and length of the video according to the viewer's age and interests. For example, it provides short, easy-to-understand content for children and detailed information for professionals. The editorial department also automatically generates versions tailored to different audiences and improves them based on viewer feedback. For example, it analyzes viewer reactions and selects the optimal version. This makes it possible to automatically generate multiple versions tailored to different audiences.

[0045] When editing videos of great people, the editorial department can reflect viewer feedback in real time and continuously improve the content of the videos. For example, the editorial department builds a system that collects viewer feedback in real time and continuously improves the content of the videos based on the results. For example, the editorial department edits videos based on viewer comments and ratings. The editorial department also analyzes viewer feedback and dynamically changes the content of the videos based on the results. For example, the order of scenes is changed to reflect viewer opinions. The editorial department also reflects viewer feedback in real time and continuously improves the content of the videos. For example, the length and content of the videos are adjusted based on viewer reactions. In this way, viewer feedback can be reflected in real time and the content of the videos can be continuously improved.

[0046] When distributing videos of great people, the distribution unit can analyze the viewer's viewing history and interests and provide personalized distribution. The distribution unit, for example, analyzes the viewer's viewing history and interests and provides personalized distribution based on the results. For example, the distribution unit distributes related content based on the content of videos the viewer has previously viewed. The distribution unit also analyzes the viewer's interests and provides personalized distribution based on the results. For example, the distribution unit prioritizes the distribution of videos related to themes that interest the viewer. The distribution unit also analyzes the viewer's viewing history and interests in real time and provides personalized distribution based on the results. For example, if the viewer's interests change, related content is immediately distributed. In this way, the viewer's viewing history and interests can be analyzed and personalized distribution can be provided.

[0047] When distributing videos of great people, the distribution unit can automatically adjust the video format and resolution to suit the characteristics of the distribution platform. The distribution unit, for example, develops a system that automatically adjusts the video format and resolution to suit the characteristics of the distribution platform. For example, the distribution unit distributes videos in a format that is optimal for YouTube or social media. The distribution unit also analyzes the characteristics of the distribution platform and adjusts the video format and resolution based on the results. For example, the distribution unit distributes videos in a resolution that is optimal for the viewer's device. The distribution unit also adjusts the video format and resolution in real time to suit the characteristics of the distribution platform. For example, the video resolution is dynamically changed depending on the viewer's network environment. This makes it possible to automatically adjust the video format and resolution to suit the characteristics of the distribution platform.

[0048] When distributing videos of great people, the distribution unit can automatically generate multilingual videos tailored to different languages ​​and cultural spheres. The distribution unit, for example, develops a system that automatically generates videos tailored to different languages. For example, the distribution unit distributes videos translated into multiple languages, such as English, French, and Chinese. The distribution unit also automatically generates videos tailored to different cultural spheres and distributes content appropriate to that culture. For example, the distribution unit creates videos that take cultural backgrounds and customs into consideration. The distribution unit also automatically generates multilingual videos and distributes them in the optimal language based on the viewer's language settings. For example, the distribution unit distributes videos based on the language settings of the viewer's device. This makes it possible to automatically generate multilingual videos tailored to different languages ​​and cultural spheres.

[0049] When distributing videos of great people, the distribution unit can dynamically change the content of the video based on the real-time reactions of viewers. The distribution unit, for example, analyzes the real-time reactions of viewers and develops a system that dynamically changes the content of the video based on the results. For example, it highlights scenes that receive good reactions from viewers. The distribution unit also dynamically changes the content of the video based on the real-time reactions of viewers. For example, it provides additional information in scenes that increase viewers' interest. The distribution unit also monitors the real-time reactions of viewers and dynamically changes the content of the video based on the results. For example, it adds new content if viewer reactions drop. This makes it possible to dynamically change the content of the video based on the real-time reactions of viewers.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The famous person video creation system may further include an interest estimation unit that estimates the user's interests and customizes the content of the video based on the estimated interests. For example, if the user is interested in a particular famous person, it can generate a video that highlights episodes and achievements related to that person. It can also analyze the user's viewing history and recommend famous people that the user may be interested in. Furthermore, it can adjust the length and content of the video based on the user's interests to increase viewer satisfaction. This allows the famous person video creation system to provide customized videos that match the user's interests and convey information more effectively.

[0052] The system for creating videos of famous people may further include a health estimation unit that estimates the health condition of the famous person and adjusts the content of the video based on the estimated health condition. For example, it may be possible to describe in detail episodes when the famous person was ill or injured. It may also be possible to analyze the impact of the famous person's health condition on their achievements and statements and reflect the results in the video. Furthermore, it may be possible to visually display information about the famous person's health condition to make it easier for viewers to understand. This makes it possible to create videos that provide a deeper understanding based on the famous person's health condition.

[0053] The system for creating videos of famous people may further include an influence estimation unit that estimates the social influence of famous people and adjusts the content of the video based on the estimated influence. For example, the system can display the influence of famous people on society over time, visually showing changes. It can also analyze how the words and actions of famous people have influenced society and reflect the results in the video. Furthermore, it can incorporate maps and graphs into the video that show how the influence of famous people has spread to specific fields or regions. This allows the creation of videos that provide more comprehensive information based on the social influence of famous people.

[0054] The system for creating videos of famous people may further include a cultural analysis unit that analyzes the cultural background of the famous person and adjusts the content of the video based on the results. For example, the culture and customs of the region where the famous person was born and raised can be reflected in the video. It can also analyze how the famous person's words and actions were influenced by their cultural background and incorporate the results into the video. Furthermore, it can visually display information about the cultural background of the famous person to make it easier for viewers to understand. This makes it possible to create videos that provide a deeper understanding of the famous person's cultural background.

[0055] The system for creating videos of famous people may further include an economic analysis unit that analyzes the economic circumstances of famous people and adjusts the content of the videos based on the results. For example, the economic background of the famous people can be reflected in the videos. It can also analyze how the economic circumstances of the famous people influenced their achievements and statements and incorporate the results into the videos. Furthermore, information about the economic circumstances of the famous people can be visually displayed to make it easier for viewers to understand. This allows for the creation of videos that provide more comprehensive information based on the economic circumstances of the famous people.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The information gathering unit uses the generative AI to collect information about the great person. For example, information about the great person can be collected from the internet or databases. It can also collect information about the great person's life, achievements, statements, photos, videos, etc. For example, historical documents, articles, and interview videos can be used as sources of information. Step 2: The analysis unit analyzes the information about the great person collected by the information collection unit. For example, the generation AI extracts the great person's characteristics and important events. The generation AI can also analyze the great person's statements and episodes. For example, the generation AI analyzes the emotional nuances of the great person's statements. Step 3: The scenario creation unit creates a video scenario based on the information analyzed by the analysis unit. For example, a scenario can be created that depicts the life of a great person in chronological order. It can also create a scenario that focuses on a specific achievement. For example, a scenario can be created by combining the great person's words and episodes. Step 4: The video generation unit generates a video based on the scenario created by the scenario creation unit. For example, it generates a video by combining photos, video, audio, and text of famous people. It can also animate photos of famous people or reproduce their words using voice synthesis. Step 5: The editing department edits the video generated by the video generator. For example, they can adjust the length of the video, adjust the timing of the audio and text, and improve the content of the video based on viewer reactions and feedback. Step 6: The distribution department distributes the video edited by the editorial department. For example, the video is published on a video sharing site or social media. The distribution department can also optimize the video to suit the characteristics of the distribution platform and distribute it effectively.

[0058] (Example 2) The great person video creation system according to an embodiment of the present invention is a system in which a generation AI collects and analyzes information about great people and generates videos of the great people based on that information. As a result, the great person video creation system can create videos that effectively convey information about great people and distribute them widely.

[0059] A great person video creation system according to an embodiment includes an information collection unit, an analysis unit, a scenario creation unit, a video generation unit, an editing unit, and a distribution unit. The information collection unit uses a generation AI to collect information about great people. For example, information about great people may be collected from the Internet or a database. Information about the great person's life, achievements, statements, photographs, video, and the like may also be collected. For example, historical documents, articles, and interview videos may serve as information sources. The analysis unit analyzes the information about great people collected by the information collection unit. For example, the generation AI extracts the great person's characteristics and important events. The generation AI may also analyze the great person's statements and episodes. For example, the generation AI may analyze the emotional nuances of the great person's statements. The scenario creation unit creates a video scenario based on the information analyzed by the analysis unit. For example, a scenario may be created that depicts the great person's life in chronological order. A scenario may also be created that focuses on a specific achievement. For example, a scenario may be created by combining the great person's statements and episodes. The video generation unit generates a video based on the scenario created by the scenario creation unit. For example, a video may be generated by combining photographs, video, audio, and text of the great person. It is also possible to animate photos of great figures and reproduce their statements using voice synthesis. The editing unit edits the videos generated by the video generation unit. For example, the editing unit adjusts the length of the videos and synchronizes the timing of audio and text. The content of the videos can also be improved based on viewer reactions and feedback. The distribution unit distributes the videos edited by the editing unit. For example, the videos are published on video sharing sites or social networking sites. The video can also be optimized to suit the characteristics of the distribution platform and distributed effectively. As a result, the great figure video creation system according to the embodiment can generate and widely distribute videos that effectively convey information about great figures. For example, the videos can be used as teaching materials in educational settings or to provide information to people interested in history and culture. Furthermore, spreading the achievements and ideas of great figures is expected to increase their influence on society.

[0060] The information collection unit performs emotion analysis on the collected information using an emotion estimation function to estimate the emotions and psychological state of the great person, and can filter information based on the results. The information collection unit, for example, analyzes documents such as letters and diaries of the great person and identifies the intensity and type of emotion using the emotion estimation function. For example, emotions such as joy and sadness are quantified from the writing style and expression of letters written by the great person, and documents containing important emotions are prioritized for analysis. The information collection unit also analyzes audio data of the great person's statements and speeches and tracks changes in emotion using the emotion estimation function. For example, the information collection unit measures the intensity of emotions from the tone and rhythm of the voice and extracts emotionally important statements. The information collection unit also analyzes photographs and videos of the great person and estimates emotions using facial expression recognition technology. For example, the information collection unit detects the great person's smiling or angry facial expressions, quantifies the intensity of the emotions, and filters the information. This allows the great person's emotions and psychological state to be estimated and emotionally important information to be prioritized for analysis.

[0061] The information collection unit can analyze handwritten documents and letters of great people and extract their personalities from their handwriting and writing style. For example, the information collection unit scans handwritten letters and notes of great people and identifies their personalities using handwriting analysis technology. For example, it analyzes changes in character shape and writing pressure to extract the great people's characteristic writing style. The information collection unit also analyzes handwritten documents of great people using natural language processing technology to extract characteristics of writing style and expression. For example, it identifies a tendency to frequently use specific phrases and expressions, revealing the great people's personalities. The information collection unit also analyzes handwritten documents of great people using image analysis technology to identify character arrangement and line spacing patterns. For example, it extracts characteristics of the great people's writing style from the size of the characters and the width of the line spacing. This makes it possible to extract personalities from handwritten documents and letters of great people and provide more detailed information.

[0062] The information collection unit analyzes interviews with people related to or family members of the great person, and is able to understand the great person's relationships and background information in detail. For example, the information collection unit analyzes interview videos of people related to or family members of the great person and extracts important information using natural language processing technology. For example, the information collection unit identifies the great person's relationships and background information from the content of the interviews. The information collection unit also analyzes audio of interviews with people related to or family members of the great person and converts the audio into text using speech recognition technology. For example, the content of the interviews is saved as text data, and the background information of the great person is understood in detail. The information collection unit also analyzes the content of interviews with people related to or family members of the great person using emotion analysis technology to track changes in emotion. For example, the intensity of emotions during the interviews is measured and emotionally important information is extracted. This allows the great person's relationships and background information to be understood in detail, providing a deeper understanding.

[0063] The Information Collection Department can 3D scan the tools and personal effects used by great people and use the data for analysis. For example, the Information Collection Department can 3D scan the tools and personal effects used by great people and analyze their shape and materials. For example, the Information Collection Department can 3D model the writing utensils and furniture used by great people and extract their characteristics. The Information Collection Department can also use the 3D scan data to recreate the living environment and usage methods of great people. For example, the Information Collection Department can analyze the placement and traces of use of tools used by great people to clarify their lifestyle. The Information Collection Department can also 3D scan the personal effects of great people and store them as a digital archive. For example, the personal effects of great people can be digitized and used as materials to pass on to future generations. This allows the Information Collection Department to 3D scan the tools and personal effects used by great people and use the detailed data for analysis.

[0064] The information collection unit collects geographic information related to the great person and can visualize the great person's range of activities and travel routes on a map. The information collection unit, for example, plots the great person's range of activities and travel routes on a map and visually displays them. For example, it maps the places the great person visited and lived on the map. The information collection unit also collects geographic information related to the great person and analyzes it using a geographic information system (GIS). For example, it displays the great person's range of activities and travel routes in chronological order to clarify the great person's behavioral patterns. The information collection unit also reproduces the great person's range of activities and travel routes on a 3D map to make them easier to visually understand. For example, it displays the route the great person took on a 3D map to relive the great person's actions. In this way, the great person's range of activities and travel routes can be visualized on a map, making them easier to visually understand.

[0065] The information collection unit uses the emotion estimation function to analyze the emotional background of the great person's statements and actions when collecting information about the great person, thereby identifying emotionally significant events. The information collection unit, for example, analyzes the great person's statements and actions using the emotion estimation function to identify emotionally significant events. For example, it measures the intensity of emotions from the content of the great person's speeches and letters and extracts emotionally significant statements. The information collection unit also analyzes the great person's behavioral history and tracks changes in emotions using the emotion estimation function. For example, it analyzes how the great person felt about specific events and identifies emotionally significant events. The information collection unit also analyzes the emotional background of the great person's statements and actions and filters information based on the emotion estimation data. For example, it prioritizes analysis of events with high emotion scores to reveal the great person's emotional aspects. This makes it possible to analyze the emotional background of the great person's statements and actions and identify emotionally significant events.

[0066] The scenario creation unit can estimate the emotions and psychological state of the great person and adjust the tone and atmosphere of the scenario based on those emotions. The scenario creation unit, for example, estimates the emotions and psychological state of the great person and adjusts the tone of the scenario based on those emotions. For example, a bright tone is set in a scene in which the great person felt joy, and a dark tone is set in a scene in which the great person felt sad. The scenario creation unit also adjusts the atmosphere of the scenario based on the emotion estimation data of the great person. For example, the tempo or music of the scenario is changed depending on the intensity of the emotion to convey the emotion to the viewer. The scenario creation unit also analyzes the psychological state of the great person and adjusts the tone and atmosphere of the scenario based on the results. For example, a tense atmosphere is increased in a scene in which the great person felt tense, and a calm atmosphere is set in a scene in which the great person felt relaxed. In this way, the tone and atmosphere of the scenario can be adjusted based on the emotions and psychological state of the great person.

[0067] The scenario creation unit can analyze the statements and episodes of great people and create a scenario that reflects their values ​​and philosophy. For example, the scenario creation unit analyzes the statements and episodes of great people and creates a scenario that reflects their values ​​and philosophy. For example, it incorporates the beliefs and principles that the great people held dear into the scenario. The scenario creation unit also analyzes the statements and episodes of great people using natural language processing technology to extract their values ​​and philosophy. For example, it reflects phrases and expressions that the great people frequently used in the scenario. The scenario creation unit also organizes the episodes of great people in chronological order and creates a scenario that reflects their values ​​and philosophy. For example, it builds a scenario centered around turning points and important events in the great person's life. In this way, it is possible to create a scenario that reflects the great person's values ​​and philosophy.

[0068] The scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people. For example, the scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people. For example, the scenario creation unit can create a moving scenario for viewers by moving an episode in which the great person overcame difficulties. The scenario creation unit can also organize the turning points and decisions in the lives of great people in chronological order and reflect the details in the scenario. For example, the scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people. For example, the scenario creation unit can create a moving scenario for viewers by describing in detail important turning points and decisions in the lives of great people.

[0069] When depicting the life of a great person, the scenario creation unit can create a multi-character scenario that also includes the people and events surrounding the great person. For example, when depicting the life of a great person, the scenario creation unit creates a multi-character scenario that also includes the people and events surrounding the great person. For example, the scenario creation unit incorporates the perspectives of the great person's family, friends, colleagues, etc. The scenario creation unit also incorporates episodes of people surrounding the great person into the scenario depicting the life of the great person. For example, it describes episodes of people who were influenced by the great person or people who influenced the great person. The scenario creation unit also describes in detail the events surrounding the great person in the scenario depicting the life of the great person. For example, it reflects historical events and social background in which the great person was involved in the scenario. In this way, when depicting the life of a great person, it is possible to create a multi-character scenario that also includes the people and events surrounding the great person.

[0070] When creating a scenario focusing on the achievements of a great person, the scenario creation unit can depict the impact that the achievements of that great person have had on the modern world. For example, the scenario creation unit creates a scenario focusing on the achievements of a great person and depicts the impact that the achievements have had on the modern world. For example, it depicts how the inventions and discoveries of the great person have influenced modern technology and society. The scenario creation unit also organizes the achievements of the great person in chronological order and depicts their impact from a modern perspective. For example, it reflects in the scenario how the achievements of the great person have contributed to modern science, technology, and culture. The scenario creation unit also analyzes the achievements of the great person and depicts their impact using specific modern examples. For example, it depicts how the achievements of the great person are being applied to modern companies and research institutions. In this way, a scenario depicting the impact that the achievements of the great person have had on the modern world can be created.

[0071] The scenario creation unit can use the emotion estimation function to predict the emotional response of the viewer and create a scenario that the viewer can easily empathize with emotionally. The scenario creation unit, for example, uses the emotion estimation function to predict the emotional response of the viewer and create a scenario that the viewer can easily empathize with emotionally. For example, it incorporates scenes that are likely to move the viewer into the scenario. The scenario creation unit also builds a scenario that the viewer can easily empathize with emotionally based on the viewer's emotional response data. For example, it reflects scenes that evoke positive emotions in the scenario. The scenario creation unit also uses the emotion estimation function to analyze the viewer's emotional response in real time and adjust the scenario based on the results. For example, it performs a production that emphasizes scenes that heighten the viewer's emotions. In this way, the scenario creation unit can predict the emotional response of the viewer and create a scenario that the viewer can easily empathize with emotionally.

[0072] The video generation unit can generate the facial expressions and voice tones of the great person using the emotion estimation function to reproduce the emotions and psychological state of the great person. For example, the video generation unit generates the facial expressions of the great person using the emotion estimation function to reproduce the emotions and psychological state of the great person. For example, it generates a smiling expression when the great person is happy and a tearful expression when the great person is sad. The video generation unit also reproduces the tone of the great person's voice using the emotion estimation function to emphasize emotional expressions. For example, it raises the tone of the voice when the great person is angry and lowers the tone of the voice when the great person is calm. The video generation unit also adjusts the facial expressions and voice tones in real time based on the emotion estimation data of the great person. For example, it dynamically changes the facial expressions and voice tones when the great person's emotions change. In this way, the facial expressions and voice tones can be generated to reproduce the emotions and psychological state of the great person.

[0073] The video generation unit can analyze photographs and videos of great people and generate animations that realistically reproduce the great people's movements and gestures. The video generation unit, for example, analyzes photographs and videos of great people and generates animations that realistically reproduce the great people's movements and gestures. For example, it animates the great people's walking and waving movements. The video generation unit also uses motion analysis technology to reproduce the great people's gestures based on video data of the great people. For example, it reflects the hand movements and facial expressions of the great people when they speak in the animation. The video generation unit also creates a 3D model of the great people's photograph and generates animations that reproduce their movements and gestures based on the model. For example, it realistically reproduces the great people's sitting posture and standing up movements. This makes it possible to generate animations that realistically reproduce the great people's movements and gestures.

[0074] The video generation unit can mimic the great person's voice quality and speaking style in detail when reproducing the great person's words using voice synthesis. For example, when reproducing the great person's words using voice synthesis, the video generation unit mimics the great person's voice quality in detail. For example, it reproduces the great person's voice pitch, tone, and rhythm. The video generation unit also analyzes the great person's speaking style and reflects these characteristics in the voice synthesis. For example, it reproduces the great person's speaking style in which they emphasize certain phrases and their unique intonation. The video generation unit also uses voice synthesis technology to reproduce the great person's voice quality and speaking style in detail based on the great person's voice data. For example, it reproduces the great person's intonation and pauses in their words. This makes it possible to mimic the great person's voice quality and speaking style in detail when reproducing the great person's words using voice synthesis.

[0075] When generating a video of a great person, the video generation unit can recreate the places where the great person was active and the historical background using 3D modeling. The video generation unit, for example, recreates the places where the great person was active using 3D modeling and incorporates it into the video. For example, it creates 3D models of the houses where the great person lived and the places where they worked. The video generation unit also recreates the historical background of the great person using 3D modeling and reflects this in the video. For example, it creates 3D models of the cityscapes and scenery of the era in which the great person lived. The video generation unit also recreates the places where the great person was active and the historical background using 3D modeling to generate a visually appealing video. For example, it creates 3D models of the roads the great person walked and the places they visited and incorporates them into the video. This allows the places where the great person was active and the historical background to be recreated using 3D modeling.

[0076] The video generation unit can incorporate the achievements and inventions of great people into videos as interactive demonstrations. For example, the video generation unit incorporates the achievements and inventions of great people into videos as interactive demonstrations. For example, it can simulate the operation of a device invented by a great person. The video generation unit can also incorporate the achievements of great people into videos as demonstrations that are easy to understand visually. For example, it can recreate the process of an experiment or research conducted by a great person. The video generation unit can also incorporate the inventions of great people into videos as interactive demonstrations that can be operated by viewers. For example, it can provide an interface that allows viewers to operate a machine invented by a great person. In this way, the achievements and inventions of great people can be incorporated into videos as interactive demonstrations.

[0077] The video generation unit uses the emotion estimation function to reflect the viewer's emotional reaction to a video of a great person in real time, thereby generating a video that emotionally draws the viewer in. The video generation unit, for example, uses the emotion estimation function to analyze the viewer's emotional reaction in real time and reflects the results in the video. For example, the emotional presentation is enhanced in scenes that move the viewer. The video generation unit also adjusts the content of the video in real time based on the viewer's emotional reaction data. For example, the tempo is increased in scenes where the viewer is excited. The video generation unit also uses the emotion estimation function to monitor the viewer's emotional reaction in real time and dynamically change the video presentation based on the results. For example, music and sound effects are enhanced in scenes where the viewer's emotions are heightened. In this way, the viewer's emotional reaction can be reflected in real time, generating a video that emotionally draws the viewer in.

[0078] When editing videos of great people, the editing department can use the emotion estimation function to take into account the flow of viewers' emotions and perform optimal editing. For example, the editing department uses the emotion estimation function to analyze the flow of viewers' emotions and edit the video based on the results. For example, the order of scenes can be adjusted to maintain emotional intensity. The editing department also identifies editing points in the video based on the viewer's emotional response data and performs editing that is likely to resonate emotionally. For example, the timing of cuts can be adjusted to emphasize moving scenes. The editing department also uses the emotion estimation function to monitor the flow of viewers' emotions in real time and dynamically change the editing of the video based on the results. For example, music and sound effects can be added at scenes where the viewer's emotions are heightened. This allows the editing department to take into account the flow of viewers' emotions and perform optimal editing.

[0079] When adjusting the timing of the audio and text in a video of a great person, the editorial department can analyze the points of emphasis in the great person's words and arrange them effectively. For example, the editorial department analyzes the points of emphasis in the great person's words and adjusts the timing of the audio and text based on the results. For example, the audio volume can be increased to emphasize important statements. The editorial department can also identify the points of emphasis in the great person's words and display text to match those points. For example, the timing of text display can be adjusted to emphasize famous quotes by the great person. The editorial department can also analyze the points of emphasis in the great person's words and optimize the arrangement of the audio and text based on the results. For example, a pause can be left before and after important statements to attract the viewer's attention. In this way, the editorial department can analyze the points of emphasis in the great person's words and arrange them effectively.

[0080] When adjusting the length of videos about great people, the editorial department can calculate the optimal length to maintain viewer concentration and interest. For example, the editorial department develops an algorithm to calculate the optimal length of a video to maintain viewer concentration and interest. For example, the editorial department determines the optimal video length based on viewer viewing history and feedback. The editorial department also adjusts the length of the video to maintain viewer interest. For example, the editorial department keeps viewer concentration by shortening important scenes. The editorial department also analyzes viewer concentration and interest and optimizes the video length based on the results. For example, the editorial department frequently switches scenes to prevent viewers from getting bored. This makes it possible to calculate the optimal length to maintain viewer concentration and interest.

[0081] When editing videos of great people, the editorial department can automatically generate multiple versions tailored to different audiences. For example, the editorial department develops a system that automatically generates multiple versions tailored to different audiences. For example, it creates versions for children, students, and professionals. The editorial department also adjusts the content and length of the video according to the viewer's age and interests. For example, it provides short, easy-to-understand content for children and detailed information for professionals. The editorial department also automatically generates versions tailored to different audiences and improves them based on viewer feedback. For example, it analyzes viewer reactions and selects the optimal version. This makes it possible to automatically generate multiple versions tailored to different audiences.

[0082] When editing videos of great people, the editorial department can reflect viewer feedback in real time and continuously improve the content of the videos. For example, the editorial department builds a system that collects viewer feedback in real time and continuously improves the content of the videos based on the results. For example, the editorial department edits videos based on viewer comments and ratings. The editorial department also analyzes viewer feedback and dynamically changes the content of the videos based on the results. For example, the order of scenes is changed to reflect viewer opinions. The editorial department also reflects viewer feedback in real time and continuously improves the content of the videos. For example, the length and content of the videos are adjusted based on viewer reactions. In this way, viewer feedback can be reflected in real time and the content of the videos can be continuously improved.

[0083] The editing department can use the emotion estimation function to identify editing points in a video based on the viewer's emotional response and perform editing that is likely to evoke emotional empathy. The editing department, for example, uses the emotion estimation function to analyze the viewer's emotional response and identify editing points in a video based on the results. For example, cutting is performed in scenes where emotions are heightened. The editing department also performs editing that is likely to evoke emotional empathy based on the viewer's emotional response data. For example, music and sound effects are added to emphasize moving scenes. The editing department also uses the emotion estimation function to monitor the viewer's emotional response in real time and dynamically change the editing of the video based on the results. For example, switching scenes in scenes where viewers' emotions are heightened. In this way, it is possible to identify editing points in a video based on the viewer's emotional response and perform editing that is likely to evoke emotional empathy.

[0084] When distributing videos of great people, the distribution unit can use the emotion estimation function to monitor viewers' emotional reactions in real time and optimize the distribution content. The distribution unit, for example, uses the emotion estimation function to monitor viewers' emotional reactions in real time and optimize the distribution content based on the results. For example, the distribution unit adjusts the timing of distribution in scenes where viewers' emotions are heightened. The distribution unit also dynamically changes the distribution content based on the viewer's emotional reaction data. For example, it distributes additional content when viewers' emotions drop. The distribution unit also uses the emotion estimation function to analyze viewers' emotional reactions in real time and optimize the distribution content based on the results. For example, it distributes special content in scenes where viewers' emotions are heightened. In this way, the distribution unit can monitor viewers' emotional reactions in real time and optimize the distribution content.

[0085] When distributing videos of great people, the distribution unit can analyze the viewer's viewing history and interests and provide personalized distribution. The distribution unit, for example, analyzes the viewer's viewing history and interests and provides personalized distribution based on the results. For example, the distribution unit distributes related content based on the content of videos the viewer has previously viewed. The distribution unit also analyzes the viewer's interests and provides personalized distribution based on the results. For example, the distribution unit prioritizes the distribution of videos related to themes that interest the viewer. The distribution unit also analyzes the viewer's viewing history and interests in real time and provides personalized distribution based on the results. For example, if the viewer's interests change, related content is immediately distributed. In this way, the viewer's viewing history and interests can be analyzed and personalized distribution can be provided.

[0086] When distributing videos of great people, the distribution unit can automatically adjust the video format and resolution to suit the characteristics of the distribution platform. The distribution unit, for example, develops a system that automatically adjusts the video format and resolution to suit the characteristics of the distribution platform. For example, the distribution unit distributes videos in a format that is optimal for YouTube or social media. The distribution unit also analyzes the characteristics of the distribution platform and adjusts the video format and resolution based on the results. For example, the distribution unit distributes videos in a resolution that is optimal for the viewer's device. The distribution unit also adjusts the video format and resolution in real time to suit the characteristics of the distribution platform. For example, the video resolution is dynamically changed depending on the viewer's network environment. This makes it possible to automatically adjust the video format and resolution to suit the characteristics of the distribution platform.

[0087] When distributing videos of great people, the distribution unit can automatically generate multilingual videos tailored to different languages ​​and cultural spheres. The distribution unit, for example, develops a system that automatically generates videos tailored to different languages. For example, the distribution unit distributes videos translated into multiple languages, such as English, French, and Chinese. The distribution unit also automatically generates videos tailored to different cultural spheres and distributes content appropriate to that culture. For example, the distribution unit creates videos that take cultural backgrounds and customs into consideration. The distribution unit also automatically generates multilingual videos and distributes them in the optimal language based on the viewer's language settings. For example, the distribution unit distributes videos based on the language settings of the viewer's device. This makes it possible to automatically generate multilingual videos tailored to different languages ​​and cultural spheres.

[0088] When distributing videos of great people, the distribution unit can dynamically change the content of the video based on the real-time reactions of viewers. The distribution unit, for example, analyzes the real-time reactions of viewers and develops a system that dynamically changes the content of the video based on the results. For example, it highlights scenes that receive good reactions from viewers. The distribution unit also dynamically changes the content of the video based on the real-time reactions of viewers. For example, it provides additional information in scenes that increase viewers' interest. The distribution unit also monitors the real-time reactions of viewers and dynamically changes the content of the video based on the results. For example, it adds new content if viewer reactions drop. This makes it possible to dynamically change the content of the video based on the real-time reactions of viewers.

[0089] The distribution unit uses the emotion estimation function to identify the optimal distribution timing based on the viewer's emotional response, thereby enabling effective distribution. The distribution unit, for example, uses the emotion estimation function to analyze the viewer's emotional response and identify the optimal distribution timing based on the results. For example, the distribution unit distributes videos during times when the viewer's emotions are at their highest. The distribution unit also identifies the optimal distribution timing based on the viewer's emotional response data and enables effective distribution. For example, the distribution unit distributes videos during times when the viewer is most emotionally reactive. The distribution unit also uses the emotion estimation function to monitor the viewer's emotional response in real time and identify the optimal distribution timing based on the results. For example, the distribution unit distributes videos at the moment when the viewer's emotions are at their highest. This allows the optimal distribution timing to be identified based on the viewer's emotional response, enabling effective distribution.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The famous person video creation system may further include an interest estimation unit that estimates the user's interests and customizes the content of the video based on the estimated interests. For example, if the user is interested in a particular famous person, it can generate a video that highlights episodes and achievements related to that person. It can also analyze the user's viewing history and recommend famous people that the user may be interested in. Furthermore, it can adjust the length and content of the video based on the user's interests to increase viewer satisfaction. This allows the famous person video creation system to provide customized videos that match the user's interests and convey information more effectively.

[0092] The system for creating videos of famous people may further include a health estimation unit that estimates the health condition of the famous person and adjusts the content of the video based on the estimated health condition. For example, it may be possible to describe in detail episodes when the famous person was ill or injured. It may also be possible to analyze the impact of the famous person's health condition on their achievements and statements and reflect the results in the video. Furthermore, it may be possible to visually display information about the famous person's health condition to make it easier for viewers to understand. This makes it possible to create videos that provide a deeper understanding based on the famous person's health condition.

[0093] The system for creating videos of famous people may further include an influence estimation unit that estimates the social influence of famous people and adjusts the content of the video based on the estimated influence. For example, the system can display the influence of famous people on society over time, visually showing changes. It can also analyze how the words and actions of famous people have influenced society and reflect the results in the video. Furthermore, it can incorporate maps and graphs into the video that show how the influence of famous people has spread to specific fields or regions. This allows the creation of videos that provide more comprehensive information based on the social influence of famous people.

[0094] The system for creating videos of famous people may further include a cultural analysis unit that analyzes the cultural background of the famous person and adjusts the content of the video based on the results. For example, the culture and customs of the region where the famous person was born and raised can be reflected in the video. It can also analyze how the famous person's words and actions were influenced by their cultural background and incorporate the results into the video. Furthermore, it can visually display information about the cultural background of the famous person to make it easier for viewers to understand. This makes it possible to create videos that provide a deeper understanding of the famous person's cultural background.

[0095] The system for creating videos of famous people may further include an economic analysis unit that analyzes the economic circumstances of famous people and adjusts the content of the videos based on the results. For example, the economic background of the famous people can be reflected in the videos. It can also analyze how the economic circumstances of the famous people influenced their achievements and statements and incorporate the results into the videos. Furthermore, information about the economic circumstances of the famous people can be visually displayed to make it easier for viewers to understand. This allows for the creation of videos that provide more comprehensive information based on the economic circumstances of the famous people.

[0096] The famous person video creation system may further include an emotion estimation unit that estimates the emotions of the famous person and adjusts the content of the video based on the estimated emotions. For example, it can analyze the emotions that the famous person had toward a specific event and reflect the results in the video. It can also display the changes in the famous person's emotions in chronological order, visually showing the changes. Furthermore, it can visually display information about the famous person's emotions, making it easier for viewers to understand. This makes it possible to generate videos that are more likely to resonate emotionally with viewers based on the emotions of the famous person.

[0097] The famous person video creation system may further include a psychological estimation unit that estimates the famous person's psychological state and adjusts the content of the video based on the estimated psychological state. For example, the system can analyze the famous person's psychological state in a specific situation and reflect the results in the video. It can also display changes in the famous person's psychological state in chronological order, visually showing the changes. Furthermore, it can visually display information about the famous person's psychological state, making it easier for viewers to understand. This makes it possible to generate videos that provide a deeper understanding based on the famous person's psychological state.

[0098] The famous person video creation system may further include an emotional scenario unit that estimates the emotions of the famous person and adjusts the video scenario based on the estimated emotions. For example, a bright tone can be set for scenes in which the famous person felt joy, and a dark tone can be set for scenes in which the famous person felt sadness. The tempo and music of the scenario can also be changed depending on the intensity of the famous person's emotions to convey the emotions to the viewer. Furthermore, the atmosphere of the scenario can be adjusted based on the emotions of the famous person, creating a scenario that is more likely to resonate with the viewer emotionally. This makes it possible to provide a scenario that is more likely to resonate with the viewer emotionally based on the emotions of the famous person.

[0099] The famous person video creation system may further include an emotion editing unit that estimates the emotions of the famous person and edits the video based on the estimated emotions. For example, by inserting a cut at a scene where the great person's emotions are heightened, it is possible to draw in the viewer's emotions. It is also possible to add music and sound effects according to the changes in the great person's emotions to enhance the emotional presentation. Furthermore, it is possible to adjust the order of scenes based on the great person's emotions and perform editing that takes into account the flow of the viewer's emotions. This makes it possible to provide editing that is more likely to resonate emotionally with the viewer based on the great person's emotions.

[0100] The great person video creation system may further include an emotion distribution unit that estimates the emotions of the great person and optimizes video distribution based on the estimated emotions. For example, by distributing videos at times when viewers' emotions are strongest, it is possible to maximize the viewers' emotional responses. It is also possible to monitor viewers' emotional responses in real time and dynamically change the content of distribution based on the results. Furthermore, it is possible to distribute special content based on the viewers' emotions and increase the viewers' emotional satisfaction. This makes it possible to provide more effective distribution based on the emotions of the great person.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The information gathering unit uses the generative AI to collect information about the great person. For example, information about the great person can be collected from the internet or databases. It can also collect information about the great person's life, achievements, statements, photos, videos, etc. For example, historical documents, articles, and interview videos can be used as sources of information. Step 2: The analysis unit analyzes the information about the great person collected by the information collection unit. For example, the generation AI extracts the great person's characteristics and important events. The generation AI can also analyze the great person's statements and episodes. For example, the generation AI analyzes the emotional nuances of the great person's statements. Step 3: The scenario creation unit creates a video scenario based on the information analyzed by the analysis unit. For example, a scenario can be created that depicts the life of a great person in chronological order. It can also create a scenario that focuses on a specific achievement. For example, a scenario can be created by combining the great person's words and episodes. Step 4: The video generation unit generates a video based on the scenario created by the scenario creation unit. For example, it generates a video by combining photos, video, audio, and text of famous people. It can also animate photos of famous people or reproduce their words using voice synthesis. Step 5: The editing department edits the video generated by the video generator. For example, they can adjust the length of the video, adjust the timing of the audio and text, and improve the content of the video based on viewer reactions and feedback. Step 6: The distribution department distributes the video edited by the editorial department. For example, the video is published on a video sharing site or social media. The distribution department can also optimize the video to suit the characteristics of the distribution platform and distribute it effectively.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] In the robot 414, 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 robot 414 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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. [Explanation of symbols]

[0170] 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. An information gathering department that uses generative AI to collect information on great people, an analysis unit that analyzes the information on the great person collected by the information collection unit; a scenario creation unit that creates a scenario for a video based on the information analyzed by the analysis unit; a moving image generating unit that generates a moving image based on the scenario created by the scenario creating unit; an editing unit that edits the video generated by the video generation unit; a distribution unit that distributes the video edited by the editing unit. A system characterized by:

2. The information collecting unit To estimate the emotions and psychological state of the person, emotional analysis is performed on the collected information, and the information is filtered based on the results.

2. The system of claim 1.

3. The information collecting unit Analyzing the handwritten documents and letters of the great person and extracting the personality of the great person from their handwriting and writing style 2. The system of claim 1.

4. The information collecting unit Analyze interviews with people close to or close to the great person to gain a detailed understanding of their relationships and background information.

2. The system of claim 1.

5. The information collecting unit 3D scan the tools and personal effects used by the great man and use the data for analysis.

2. The system of claim 1.

6. The information collecting unit Collecting geographical information related to the great person and visualizing the area of ​​activity and travel route of the great person on a map 2. The system of claim 1.

Images