system

Abstract

The system according to this embodiment aims to accumulate prompts and generate animations that reflect viewer feedback. [Solution] The system according to the embodiment comprises a prompt storage unit, a generation unit, a feedback collection unit, a feedback reflection unit, and a translation unit. The prompt storage unit stores prompts. The generation unit generates animation based on the prompts stored by the prompt storage unit. The feedback collection unit collects viewer feedback on the generated animation. The feedback reflection unit reflects the feedback collected by the feedback collection unit. The translation unit translates the generated animation into multiple languages.

Description

Technical Field

[0006] , , ,

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it depends on the capabilities of production staff in anime production and it is difficult to effectively reflect the feedback of viewers.

[0005] The system according to the embodiment aims to accumulate prompts and generate an anime reflecting the feedback of viewers.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a prompt storage unit, a generation unit, a feedback collection unit, a feedback reflection unit, and a translation unit. The prompt storage unit stores prompts. The generation unit generates animation based on the prompts stored by the prompt storage unit. The feedback collection unit collects viewer feedback on the generated animation. The feedback reflection unit reflects the feedback collected by the feedback collection unit. The translation unit translates the generated animation into multiple languages. [Effects of the Invention]

[0007] The system according to this embodiment can accumulate prompts and generate animations that reflect viewer feedback. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The platform that converts manga into anime using a generative AI according to an embodiment of the present invention provides a service in which creators use the generative AI to produce anime from manga, and viewers can enjoy and support the generated content. Through this platform, viewers can discover new appeal in the content, increase the breadth and enthusiasm of the fanbase, and support the creators, thereby creating a cycle in which even more high-quality content is mass-produced. First, on the creator's side, the capabilities of the production staff involved in adapting manga into anime are important, and the prompts (instructions) given by these production staff to the generative AI are also accumulated as learning data. This accumulated data is used to build a system that further improves the quality of content production. For example, when a creator inputs instructions to the generative AI such as "Please give this character a flashy hair color" or "Please make the voice energetic and lively," the generative AI generates anime based on those instructions. Next, on the consumer side, the preferences of highly enthusiastic fans are taken into account and weighted for creators, and further weighting is also applied to the prompts (instructions) of those creators, thereby creating a cycle that can be used to produce better content. For example, when fans provide feedback such as "I want this character's voice to be more energetic," that feedback is reflected in the generative AI and used to improve future content creation. Furthermore, by translating the generated content into multiple languages ​​and distributing it to overseas viewers, it is expected that new appeals will be discovered from an international perspective, leading to a cycle of re-importation and increased popularity in Japan. For instance, by using generative AI to provide multilingual content to overseas fans who enjoy Japanese manga and anime, it is possible to increase the number of overseas fans and enhance popularity both domestically and internationally. Thus, this invention provides a platform that converts manga into anime using generative AI, creating a beneficial cycle for both creators and viewers.

[0029] The platform for converting manga into animation using a generative AI according to this embodiment comprises a prompt storage unit, a generation unit, a feedback collection unit, a feedback reflection unit, and a translation unit. The prompt storage unit stores prompts. For example, the prompt storage unit stores prompts entered by the creator into the generative AI in a database. The prompt storage unit can also analyze the content of the prompts and efficiently store similar prompts by grouping them. The prompt storage unit can also estimate the creator's emotions, evaluate the importance of the prompts based on the estimated emotions, and determine the priority for storage. The generation unit generates animation based on the stored prompts. For example, the generation unit generates animation based on the creator's prompts using the generative AI. During generation, the generation unit can also adjust the level of detail of the generation based on the importance of the stored prompts. The generation unit can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. The feedback collection unit collects viewer feedback on the generated animation. For example, the feedback collection unit stores the feedback provided by viewers in a database. The feedback collection unit can analyze the content of the feedback and efficiently collect similar feedback by grouping it together. The feedback collection unit can also estimate the viewer's emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority for collection. The feedback reflection unit reflects the collected feedback into the generating AI. The feedback reflection unit, for example, analyzes the viewer's feedback and generates data for reflection into the generating AI. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. The feedback reflection unit can also estimate the viewer's emotions and adjust the method of reflecting the feedback based on the estimated emotions. The translation unit translates the generated animation into multiple languages. The translation unit, for example, uses the generating AI to translate the audio and subtitles of the generated animation into multiple languages. The translation unit can also estimate the viewer's emotions and adjust the expression of the translation based on the estimated emotions. The translation unit can also adjust the level of detail of the translation based on the content of the animation.As a result, the platform that converts manga into anime using the generative AI according to the embodiment can consistently perform tasks from prompt accumulation to anime generation, feedback collection and reflection, and multilingual translation.

[0030] The prompt storage unit stores prompts. For example, the prompt storage unit saves prompts that creators input into the generation AI to a database. Specifically, when a creator inputs a prompt that describes manga scenes, character movements, dialogue, etc. in detail, the prompt storage unit automatically saves this to the database. The prompt storage unit can also analyze the content of prompts and efficiently store similar prompts by grouping them. For example, by grouping prompts related to different scenes of the same character or multiple prompts based on the same theme, the subsequent generation process can be made more efficient. Furthermore, the prompt storage unit can estimate the creator's emotions, evaluate the importance of prompts based on the estimated emotions, and determine the priority for storage. For example, by prioritizing the storage of prompts that creators have written with particular emotion or prompts related to important scenes, the quality of the generated animation can be improved. The prompt storage unit analyzes the content of prompts using natural language processing technology and estimates the creator's emotions using an emotion analysis algorithm. As a result, the prompt storage unit goes beyond simple data storage and achieves advanced data management that takes into account the quality and importance of prompts.

[0031] The generation unit generates animation based on accumulated prompts. For example, the generation unit uses a generation AI to generate animation based on the creator's prompts. Specifically, the generation AI analyzes the scenes, character movements, and dialogue described in the prompts and generates animation based on that. The generation unit can also adjust the level of detail of the generation based on the importance of the accumulated prompts during generation. For example, scenes based on high-importance prompts will be generated as more detailed and high-quality animations. The generation unit can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. For example, if the creator describes an emotional scene, the generation unit will select an animation style, colors, and music that reflect those emotions. The generation AI uses deep learning technology to analyze the content of the prompts in detail and generate the optimal animation. Furthermore, the generation unit can evaluate the quality of the generated animation and make corrections or regenerations as needed. This allows the generation unit to efficiently generate high-quality animations that faithfully reflect the creator's intentions.

[0032] The feedback collection unit collects viewer feedback on the generated anime. For example, the feedback collection unit stores viewer feedback in a database. Specifically, it collects comments, ratings, and impressions that viewers provide after watching the anime and stores them in the database. The feedback collection unit can also analyze the content of the feedback and efficiently collect similar feedback by grouping them together. For example, it can group feedback from multiple viewers on the same scene and extract common opinions and impressions. The feedback collection unit can also estimate the viewer's emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority of collection. For example, by prioritizing the collection of feedback on scenes that particularly moved or dissatisfied viewers, it can clarify areas for improvement in the anime. The feedback collection unit analyzes the content of the feedback using natural language processing technology and estimates the viewer's emotions using sentiment analysis algorithms. This allows the feedback collection unit to understand viewers' opinions and emotions in detail and use this information to improve the quality of the anime.

[0033] The feedback reflection unit incorporates collected feedback into the generating AI. For example, the feedback reflection unit analyzes viewer feedback and generates data for incorporation into the generating AI. Specifically, it analyzes collected feedback and identifies which parts of the anime need improvement and what kind of improvements. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. For example, improvements based on high-importance feedback will be reflected in more detail. The feedback reflection unit can also estimate the viewer's emotions and adjust how the feedback is reflected based on the estimated emotions. For example, it may make improvements to further emphasize scenes that moved the viewer or to correct scenes that caused dissatisfaction. The feedback reflection unit analyzes the content of the feedback using natural language processing technology and estimates the viewer's emotions using sentiment analysis algorithms. This allows the feedback reflection unit to improve the anime in a way that reflects the viewer's opinions and emotions in detail. Furthermore, the feedback reflection unit provides specific improvement instructions to the generating AI, optimizing the generation process. This allows the feedback reflection unit to efficiently generate high-quality anime that reflects the viewer's opinions.

[0034] The translation department translates the generated anime into multiple languages. For example, it uses generative AI to translate the audio and subtitles of the generated anime into multiple languages. Specifically, it analyzes the dialogue and narration of the generated anime and translates them into multiple languages. The translation department can also estimate the viewer's emotions and adjust the translation's expression based on those emotions. For example, in emotional or tense scenes, it selects translation expressions that more effectively convey the viewer's emotions. The translation department can also adjust the level of detail in the translation based on the anime's content. For example, important scenes and dialogue receive more detailed and accurate translations. The translation department analyzes the content of dialogue and narration using natural language processing technology and translates them into multiple languages ​​using machine translation technology. Furthermore, the translation department can evaluate the quality of the translation results and make corrections or retranslations as needed. This enables the translation department to achieve high-quality multilingual translations that reflect the viewer's emotions and cater to the anime's international audience.

[0035] The prompt storage unit can store the creator's prompts as training data. For example, the prompt storage unit can save the prompts that the creator inputs to the generation AI into a database. The prompt storage unit can also analyze the content of the prompts and efficiently store similar prompts by grouping them together. The prompt storage unit can also estimate the creator's emotions, evaluate the importance of the prompts based on the estimated emotions, and determine the priority for storage. In this way, the accuracy of the generation AI is improved by storing the creator's prompts as training data. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can save the prompts that the creator inputs to the generation AI into a database, and then analyze those prompts with AI to group similar prompts together.

[0036] The generation unit can generate animation based on accumulated prompts. For example, the generation unit uses a generation AI to generate animation based on the creator's prompts. The generation unit can also adjust the level of detail of the generation based on the importance of the accumulated prompts during generation. The generation unit can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. This ensures that the animation generated based on accumulated prompts reflects the creator's intentions. Some or all of the above-described processes in the generation unit may be performed using a generation AI or not. For example, the generation unit can input accumulated prompts into a generation AI, which can then generate the animation.

[0037] The feedback collection unit can collect viewer feedback. For example, the feedback collection unit can store viewer feedback in a database. The feedback collection unit can also analyze the content of the feedback and group similar feedback for efficient collection. The feedback collection unit can also estimate viewer emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority for collection. This allows viewer feedback to be reflected in future content creation. Some or all of the above processes in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can store viewer feedback in a database and analyze that feedback using AI to group similar feedback.

[0038] The feedback reflection unit can reflect the collected feedback into the generating AI. For example, the feedback reflection unit can analyze viewer feedback and generate data for reflection into the generating AI. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. The feedback reflection unit can also estimate the viewer's emotions and adjust the method of reflecting the feedback based on the estimated emotions. This improves the quality of future content generation by reflecting the collected feedback into the generating AI. Some or all of the above processing in the feedback reflection unit may be performed using the generating AI or not. For example, the feedback reflection unit can analyze viewer feedback and input that data into the generating AI for reflection.

[0039] The translation unit can translate the generated anime into multiple languages. For example, the translation unit can use a generative AI to translate the audio and subtitles of the generated anime into multiple languages. The translation unit can also estimate the viewer's emotions and adjust the expression of the translation based on the estimated emotions. The translation unit can also adjust the level of detail of the translation based on the content of the anime. This allows the generated anime to be distributed to overseas viewers by translating it into multiple languages. Some or all of the above processes in the translation unit may be performed using AI or not. For example, the translation unit can input the audio and subtitles of the generated anime into a generative AI, which can then translate them into multiple languages.

[0040] The prompt storage unit can analyze the content of prompts and efficiently store similar prompts by grouping them together. For example, the prompt storage unit can analyze the content of prompts using natural language processing technology and automatically group similar prompts. The prompt storage unit can also analyze prompts entered by creators on a keyword basis and group similar prompts together. The prompt storage unit can also analyze the content of prompts using topic modeling technology and group highly relevant prompts together. This enables efficient prompt storage by analyzing the content of prompts and grouping similar prompts together. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the content of prompts using AI and store similar prompts by grouping them together.

[0041] The prompt storage unit can select the optimal storage method by referring to the creator's past prompt history when storing prompts. For example, the prompt storage unit can analyze the creator's past prompt history and prioritize storing frequently used prompts. The prompt storage unit can also automatically extract and store prompts related to a specific theme from the creator's past prompt history. The prompt storage unit can also efficiently store prompts by referring to the creator's past prompt history and eliminating duplicate prompts. This allows the optimal storage method to be selected by referring to the creator's past prompt history. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the creator's past prompt history using AI and select the optimal storage method.

[0042] The prompt storage unit can prioritize storing highly relevant prompts by considering the creator's geographical location information when storing prompts. For example, if the creator is in a specific region, the prompt storage unit will prioritize storing prompts related to that region. Based on the creator's geographical location information, the prompt storage unit can also store prompts related to the region's specific culture and customs. If the creator is on the move, the prompt storage unit can store prompts related to their current location in real time. This allows for the priority storage of highly relevant prompts by considering the creator's geographical location information. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the creator's geographical location information using AI and prioritize storing highly relevant prompts.

[0043] The prompt storage unit can analyze the creator's social media activity and store relevant prompts when storing prompts. For example, the prompt storage unit can analyze the creator's social media posts and automatically store relevant prompts. The prompt storage unit can also prioritize storing prompts related to topics mentioned by the creator on social media. The prompt storage unit can also monitor the creator's social media activity and store relevant prompts in real time. This allows for efficient storage of relevant prompts by analyzing the creator's social media activity. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the creator's social media posts using AI and store relevant prompts.

[0044] The generation unit can adjust the level of detail of the animation based on the importance of the accumulated prompts during generation. For example, the generation unit can generate a detailed animation based on a high-importance prompt. The generation unit can also generate a simplified animation based on a low-importance prompt. The generation unit can also generate an animation with a moderate level of detail based on a medium-importance prompt. This allows for efficient animation generation by adjusting the level of detail of the animation based on the importance of the accumulated prompts. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the accumulated prompts into a generation AI, which can then adjust the level of detail of the animation.

[0045] The generation unit can apply different generation algorithms depending on the anime category during generation. For example, in the case of action anime, the generation unit can apply a generation algorithm that emphasizes fast-moving scenes. In the case of romance anime, the generation unit can also apply a generation algorithm that emphasizes emotional expression. In the case of comedy anime, the generation unit can also apply a generation algorithm that emphasizes humorous scenes. In this way, by applying different generation algorithms depending on the anime category, it is possible to generate anime that is appropriate for the category. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can have the generation AI apply different algorithms depending on the anime category.

[0046] The generation unit can determine the generation priority based on the prompt submission timing during generation. For example, the generation unit may prioritize the generation of recently submitted prompts. The generation unit may also postpone the generation of older prompts. The generation unit can also adjust the generation schedule based on the submission timing. This enables efficient animation generation by determining the generation priority based on the prompt submission timing. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit may use AI to analyze the prompt submission timing and determine the generation priority.

[0047] The generation unit can adjust the generation order based on the relevance of the prompts during generation. For example, the generation unit can prioritize generating highly relevant prompts. The generation unit can also postpone generating less relevant prompts. The generation unit can also optimize the generation order based on the relevance of the prompts. This allows for efficient animation generation by adjusting the generation order based on the relevance of the prompts. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can analyze the relevance of prompts using AI and adjust the generation order.

[0048] The feedback collection unit can analyze the content of feedback and efficiently collect similar feedback by grouping it together. For example, the feedback collection unit can analyze the content of feedback using natural language processing technology and automatically group similar feedback. The feedback collection unit can also analyze the feedback provided by viewers on a keyword basis and group similar feedback. The feedback collection unit can also analyze the content of feedback using topic modeling technology and group highly relevant feedback. This enables efficient feedback collection by analyzing the content of feedback and grouping similar feedback. Some or all of the above processing in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can analyze the content of feedback using AI and collect similar feedback by grouping it together.

[0049] The feedback collection unit can select the optimal collection method by referring to the viewer's past feedback history when collecting feedback. For example, the feedback collection unit can analyze the viewer's past feedback history and prioritize the collection of frequently provided feedback. The feedback collection unit can also automatically extract and collect feedback related to a specific theme from the viewer's past feedback history. The feedback collection unit can also efficiently collect feedback by referring to the viewer's past feedback history and eliminating duplicate feedback. This allows the optimal collection method to be selected by referring to the viewer's past feedback history. Some or all of the above processes in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can analyze the viewer's past feedback history using AI and select the optimal collection method.

[0050] The feedback collection unit can prioritize collecting highly relevant feedback by considering the viewer's geographical location information when collecting feedback. For example, if a viewer is in a specific region, the feedback collection unit will prioritize collecting feedback related to that region. Based on the viewer's geographical location information, the feedback collection unit can also collect feedback related to the region's specific culture and customs. If a viewer is on the move, the feedback collection unit can also collect feedback related to their current location in real time. This allows for the priority collection of highly relevant feedback by considering the viewer's geographical location information. Some or all of the above processing in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can analyze the viewer's geographical location information using AI and prioritize the collection of highly relevant feedback.

[0051] The feedback reflection unit can adjust the level of detail in the reflection of feedback based on the importance of the collected feedback. For example, the feedback reflection unit can perform detailed reflection based on high-importance feedback. The feedback reflection unit can also perform simplified reflection based on low-importance feedback. The feedback reflection unit can also perform reflection with an appropriate level of detail based on medium-importance feedback. This allows for efficient feedback reflection by adjusting the level of detail in the reflection based on the importance of the collected feedback. Some or all of the above processing in the feedback reflection unit may be performed using AI or not. For example, the feedback reflection unit can analyze the importance of the collected feedback using AI and adjust the level of detail in the reflection.

[0052] The feedback reflection unit can apply different reflection algorithms depending on the category of the feedback when reflecting it. For example, in the case of technical feedback, the feedback reflection unit can apply a reflection algorithm that emphasizes technical improvements. In the case of emotional feedback, the feedback reflection unit can also apply a reflection algorithm that emphasizes emotional expression. In the case of design-related feedback, the feedback reflection unit can also apply a reflection algorithm that emphasizes design improvements. This enables efficient feedback reflection by applying different reflection algorithms depending on the category of the feedback. Some or all of the above processing in the feedback reflection unit may be performed using AI or not. For example, the feedback reflection unit can analyze the category of the feedback using AI and apply an appropriate reflection algorithm.

[0053] The feedback processing unit can determine the priority of feedback processing based on the submission date. For example, it may prioritize recently submitted feedback. It may also postpone older feedback. The feedback processing unit can also adjust the processing schedule based on the submission date. This enables efficient feedback processing by determining the priority of feedback processing based on the submission date. Some or all of the above processing in the feedback processing unit may be performed using AI or not. For example, the feedback processing unit may use AI to analyze the submission date of feedback and determine the priority of processing.

[0054] The translation unit can adjust the level of detail in the translation based on the content of the anime. For example, in the case of an action scene, the translation unit can provide a concise and easy-to-understand translation. In the case of an emotional scene, the translation unit can also provide a detailed translation that emphasizes emotional expression. In the case of a comedy scene, the translation unit can also provide a translation that emphasizes humor. By adjusting the level of detail in the translation based on the content of the anime, efficient translation becomes possible. Some or all of the above processes in the translation unit may be performed using AI, or not. For example, the translation unit can analyze the content of the anime using AI and adjust the level of detail in the translation.

[0055] The translation unit can apply different translation algorithms depending on the anime category during translation. For example, in the case of action anime, the unit may apply a translation algorithm that emphasizes fast-paced scenes. In the case of romance anime, the unit may also apply a translation algorithm that emphasizes emotional expression. In the case of comedy anime, the unit may also apply a translation algorithm that emphasizes humorous scenes. By applying different translation algorithms depending on the anime category, efficient translation becomes possible. Some or all of the above processing in the translation unit may be performed using AI or not. For example, the translation unit may use AI to analyze the anime category and apply an appropriate translation algorithm.

[0056] The translation department can prioritize translations based on the anime's submission dates. For example, it might prioritize translating recently submitted anime. It could also postpone older anime submissions. The translation department could also adjust the translation schedule based on submission dates. This allows for more efficient translation by prioritizing translations based on anime submission dates. Some or all of the above processes in the translation department may be performed using AI or not. For example, the translation department could use AI to analyze anime submission dates and determine translation priorities.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] A platform that uses generative AI to convert manga into anime can further analyze users' viewing history and recommend content best suited to each individual user. For example, it can identify a user's preferred genres and characters from their viewing history and recommend new anime based on that information. It can also collect ratings and comments on anime watched by users and use this to recommend content popular with other users. Furthermore, it can utilize information on users' viewing times and devices to deliver content at the optimal time. This can improve the user's viewing experience and increase the frequency of platform use.

[0059] A platform that uses generative AI to convert manga into anime can also incorporate the ability to insert advertisements tailored to the viewer's preferences based on user viewing data. For example, if a user prefers action anime, it can insert trailers for action movies. Similarly, if a user prefers romance anime, it can insert advertisements for romance movies. Furthermore, if a user frequently purchases products from a particular brand, it can insert advertisements introducing new products from that brand. This allows for increased advertising effectiveness by providing advertisements tailored to the user's preferences.

[0060] A platform that uses generative AI to convert manga into anime can also incorporate the ability to automatically generate relevant content that viewers might be interested in, based on their viewing history. For example, if a user likes a particular character, it can generate a spin-off anime centered around that character. It can also generate new stories related to a genre if the user prefers that genre. Furthermore, it can automatically generate sequels to anime the user has watched. This allows for an improved viewing experience by providing new content tailored to the user's interests.

[0061] A platform that uses generative AI to convert manga into anime can also incorporate a feature that suggests events likely to interest viewers based on their viewing data. For example, if a user likes a particular anime, it can suggest events or concerts related to that anime. Similarly, if a user likes a particular character, it can suggest events featuring that character's voice actor. Furthermore, if a user likes a particular genre, it can suggest events related to that genre. This allows for an improved viewing experience by suggesting events tailored to the user's interests.

[0062] A platform that uses generative AI to convert manga into anime can also incorporate a feature that suggests merchandise that viewers might be interested in, based on their viewing data. For example, if a user likes a particular character, it can suggest figurines or posters of that character. Similarly, if a user likes a particular anime, it can suggest merchandise related to that anime. Furthermore, if a user likes a particular genre, it can suggest merchandise related to that genre. This allows for an improved viewing experience by suggesting merchandise tailored to the user's interests.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The prompt storage unit stores prompts. For example, it saves prompts entered by the creator into the generation AI to a database. The prompt storage unit can also analyze the content of the prompts and group similar prompts for efficient storage. It can also estimate the creator's emotions, evaluate the importance of the prompts based on the estimated emotions, and determine the priority for storage. Step 2: The generation unit generates animation based on the accumulated prompts. For example, it uses a generation AI to generate animation based on the creator's prompts. The generation unit can also adjust the level of detail of the generation based on the importance of the accumulated prompts. It can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. Step 3: The feedback collection unit collects viewer feedback on the generated animation. For example, it stores viewer feedback in a database. The feedback collection unit can also analyze the content of the feedback and group similar feedback for efficient collection. It can also estimate the viewer's emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority for collection. Step 4: The feedback reflection unit reflects the collected feedback into the generating AI. For example, it analyzes viewer feedback and generates data to reflect it into the generating AI. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. It can also estimate the viewer's emotions and adjust the way the feedback is reflected based on the estimated emotions. Step 5: The translation unit translates the generated animation into multiple languages. For example, it uses a generation AI to translate the audio and subtitles of the generated animation into multiple languages. The translation unit can also estimate the viewer's emotions and adjust the translation's expression based on those emotions. It can also adjust the level of detail in the translation based on the content of the animation.

[0065] (Example of form 2) The platform that converts manga into anime using a generative AI according to an embodiment of the present invention provides a service in which creators use the generative AI to produce anime from manga, and viewers can enjoy and support the generated content. Through this platform, viewers can discover new appeal in the content, increase the breadth and enthusiasm of the fanbase, and support the creators, thereby creating a cycle in which even more high-quality content is mass-produced. First, on the creator's side, the capabilities of the production staff involved in adapting manga into anime are important, and the prompts (instructions) given by these production staff to the generative AI are also accumulated as learning data. This accumulated data is used to build a system that further improves the quality of content production. For example, when a creator inputs instructions to the generative AI such as "Please give this character a flashy hair color" or "Please make the voice energetic and lively," the generative AI generates anime based on those instructions. Next, on the consumer side, the preferences of highly enthusiastic fans are taken into account and weighted for creators, and further weighting is also applied to the prompts (instructions) of those creators, thereby creating a cycle that can be used to produce better content. For example, when fans provide feedback such as "I want this character's voice to be more energetic," that feedback is reflected in the generative AI and used to improve future content creation. Furthermore, by translating the generated content into multiple languages ​​and distributing it to overseas viewers, it is expected that new appeals will be discovered from an international perspective, leading to a cycle of re-importation and increased popularity in Japan. For instance, by using generative AI to provide multilingual content to overseas fans who enjoy Japanese manga and anime, it is possible to increase the number of overseas fans and enhance popularity both domestically and internationally. Thus, this invention provides a platform that converts manga into anime using generative AI, creating a beneficial cycle for both creators and viewers.

[0066] The platform for converting manga into animation using a generative AI according to this embodiment comprises a prompt storage unit, a generation unit, a feedback collection unit, a feedback reflection unit, and a translation unit. The prompt storage unit stores prompts. For example, the prompt storage unit stores prompts entered by the creator into the generative AI in a database. The prompt storage unit can also analyze the content of the prompts and efficiently store similar prompts by grouping them. The prompt storage unit can also estimate the creator's emotions, evaluate the importance of the prompts based on the estimated emotions, and determine the priority for storage. The generation unit generates animation based on the stored prompts. For example, the generation unit generates animation based on the creator's prompts using the generative AI. During generation, the generation unit can also adjust the level of detail of the generation based on the importance of the stored prompts. The generation unit can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. The feedback collection unit collects viewer feedback on the generated animation. For example, the feedback collection unit stores the feedback provided by viewers in a database. The feedback collection unit can analyze the content of the feedback and efficiently collect similar feedback by grouping it together. The feedback collection unit can also estimate the viewer's emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority for collection. The feedback reflection unit reflects the collected feedback into the generating AI. The feedback reflection unit, for example, analyzes the viewer's feedback and generates data for reflection into the generating AI. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. The feedback reflection unit can also estimate the viewer's emotions and adjust the method of reflecting the feedback based on the estimated emotions. The translation unit translates the generated animation into multiple languages. The translation unit, for example, uses the generating AI to translate the audio and subtitles of the generated animation into multiple languages. The translation unit can also estimate the viewer's emotions and adjust the expression of the translation based on the estimated emotions. The translation unit can also adjust the level of detail of the translation based on the content of the animation.As a result, the platform that converts manga into anime using the generative AI according to the embodiment can consistently perform tasks from prompt accumulation to anime generation, feedback collection and reflection, and multilingual translation.

[0067] The prompt storage unit stores prompts. For example, the prompt storage unit saves prompts that creators input into the generation AI to a database. Specifically, when a creator inputs a prompt that describes manga scenes, character movements, dialogue, etc. in detail, the prompt storage unit automatically saves this to the database. The prompt storage unit can also analyze the content of prompts and efficiently store similar prompts by grouping them. For example, by grouping prompts related to different scenes of the same character or multiple prompts based on the same theme, the subsequent generation process can be made more efficient. Furthermore, the prompt storage unit can estimate the creator's emotions, evaluate the importance of prompts based on the estimated emotions, and determine the priority for storage. For example, by prioritizing the storage of prompts that creators have written with particular emotion or prompts related to important scenes, the quality of the generated animation can be improved. The prompt storage unit analyzes the content of prompts using natural language processing technology and estimates the creator's emotions using an emotion analysis algorithm. As a result, the prompt storage unit goes beyond simple data storage and achieves advanced data management that takes into account the quality and importance of prompts.

[0068] The generation unit generates animation based on accumulated prompts. For example, the generation unit uses a generation AI to generate animation based on the creator's prompts. Specifically, the generation AI analyzes the scenes, character movements, and dialogue described in the prompts and generates animation based on that. The generation unit can also adjust the level of detail of the generation based on the importance of the accumulated prompts during generation. For example, scenes based on high-importance prompts will be generated as more detailed and high-quality animations. The generation unit can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. For example, if the creator describes an emotional scene, the generation unit will select an animation style, colors, and music that reflect those emotions. The generation AI uses deep learning technology to analyze the content of the prompts in detail and generate the optimal animation. Furthermore, the generation unit can evaluate the quality of the generated animation and make corrections or regenerations as needed. This allows the generation unit to efficiently generate high-quality animations that faithfully reflect the creator's intentions.

[0069] The feedback collection unit collects viewer feedback on the generated anime. For example, the feedback collection unit stores viewer feedback in a database. Specifically, it collects comments, ratings, and impressions that viewers provide after watching the anime and stores them in the database. The feedback collection unit can also analyze the content of the feedback and efficiently collect similar feedback by grouping them together. For example, it can group feedback from multiple viewers on the same scene and extract common opinions and impressions. The feedback collection unit can also estimate the viewer's emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority of collection. For example, by prioritizing the collection of feedback on scenes that particularly moved or dissatisfied viewers, it can clarify areas for improvement in the anime. The feedback collection unit analyzes the content of the feedback using natural language processing technology and estimates the viewer's emotions using sentiment analysis algorithms. This allows the feedback collection unit to understand viewers' opinions and emotions in detail and use this information to improve the quality of the anime.

[0070] The feedback reflection unit incorporates collected feedback into the generating AI. For example, the feedback reflection unit analyzes viewer feedback and generates data for incorporation into the generating AI. Specifically, it analyzes collected feedback and identifies which parts of the anime need improvement and what kind of improvements. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. For example, improvements based on high-importance feedback will be reflected in more detail. The feedback reflection unit can also estimate the viewer's emotions and adjust how the feedback is reflected based on the estimated emotions. For example, it may make improvements to further emphasize scenes that moved the viewer or to correct scenes that caused dissatisfaction. The feedback reflection unit analyzes the content of the feedback using natural language processing technology and estimates the viewer's emotions using sentiment analysis algorithms. This allows the feedback reflection unit to improve the anime in a way that reflects the viewer's opinions and emotions in detail. Furthermore, the feedback reflection unit provides specific improvement instructions to the generating AI, optimizing the generation process. This allows the feedback reflection unit to efficiently generate high-quality anime that reflects the viewer's opinions.

[0071] The translation department translates the generated anime into multiple languages. For example, it uses generative AI to translate the audio and subtitles of the generated anime into multiple languages. Specifically, it analyzes the dialogue and narration of the generated anime and translates them into multiple languages. The translation department can also estimate the viewer's emotions and adjust the translation's expression based on those emotions. For example, in emotional or tense scenes, it selects translation expressions that more effectively convey the viewer's emotions. The translation department can also adjust the level of detail in the translation based on the anime's content. For example, important scenes and dialogue receive more detailed and accurate translations. The translation department analyzes the content of dialogue and narration using natural language processing technology and translates them into multiple languages ​​using machine translation technology. Furthermore, the translation department can evaluate the quality of the translation results and make corrections or retranslations as needed. This enables the translation department to achieve high-quality multilingual translations that reflect the viewer's emotions and cater to the anime's international audience.

[0072] The prompt storage unit can store the creator's prompts as training data. For example, the prompt storage unit can save the prompts that the creator inputs to the generation AI into a database. The prompt storage unit can also analyze the content of the prompts and efficiently store similar prompts by grouping them together. The prompt storage unit can also estimate the creator's emotions, evaluate the importance of the prompts based on the estimated emotions, and determine the priority for storage. In this way, the accuracy of the generation AI is improved by storing the creator's prompts as training data. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can save the prompts that the creator inputs to the generation AI into a database, and then analyze those prompts with AI to group similar prompts together.

[0073] The generation unit can generate animation based on accumulated prompts. For example, the generation unit uses a generation AI to generate animation based on the creator's prompts. The generation unit can also adjust the level of detail of the generation based on the importance of the accumulated prompts during generation. The generation unit can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. This ensures that the animation generated based on accumulated prompts reflects the creator's intentions. Some or all of the above-described processes in the generation unit may be performed using a generation AI or not. For example, the generation unit can input accumulated prompts into a generation AI, which can then generate the animation.

[0074] The feedback collection unit can collect viewer feedback. For example, the feedback collection unit can store viewer feedback in a database. The feedback collection unit can also analyze the content of the feedback and group similar feedback for efficient collection. The feedback collection unit can also estimate viewer emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority for collection. This allows viewer feedback to be reflected in future content creation. Some or all of the above processes in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can store viewer feedback in a database and analyze that feedback using AI to group similar feedback.

[0075] The feedback reflection unit can reflect the collected feedback into the generating AI. For example, the feedback reflection unit can analyze viewer feedback and generate data for reflection into the generating AI. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. The feedback reflection unit can also estimate the viewer's emotions and adjust the method of reflecting the feedback based on the estimated emotions. This improves the quality of future content generation by reflecting the collected feedback into the generating AI. Some or all of the above processing in the feedback reflection unit may be performed using the generating AI or not. For example, the feedback reflection unit can analyze viewer feedback and input that data into the generating AI for reflection.

[0076] The translation unit can translate the generated anime into multiple languages. For example, the translation unit can use a generative AI to translate the audio and subtitles of the generated anime into multiple languages. The translation unit can also estimate the viewer's emotions and adjust the expression of the translation based on the estimated emotions. The translation unit can also adjust the level of detail of the translation based on the content of the anime. This allows the generated anime to be distributed to overseas viewers by translating it into multiple languages. Some or all of the above processes in the translation unit may be performed using AI or not. For example, the translation unit can input the audio and subtitles of the generated anime into a generative AI, which can then translate them into multiple languages.

[0077] The prompt storage unit can estimate the creator's emotions, evaluate the importance of prompts based on the estimated emotions, and determine the priority for storage. For example, if the creator is excited, the prompt storage unit can evaluate the importance of prompts highly based on that emotion and prioritize their storage. If the creator is tired, the prompt storage unit can evaluate the importance of prompts lower based on that emotion and postpone them. If the creator is relaxed, the prompt storage unit can evaluate the importance of prompts to a moderate level based on that emotion and store them at an appropriate time. This enables efficient prompt storage by evaluating the importance of prompts and determining the priority for storage based on the creator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can input the creator's emotional data into a generating AI, which can then evaluate the importance of the prompts and determine the priority for storage.

[0078] The prompt storage unit can analyze the content of prompts and efficiently store similar prompts by grouping them together. For example, the prompt storage unit can analyze the content of prompts using natural language processing technology and automatically group similar prompts. The prompt storage unit can also analyze prompts entered by creators on a keyword basis and group similar prompts together. The prompt storage unit can also analyze the content of prompts using topic modeling technology and group highly relevant prompts together. This enables efficient prompt storage by analyzing the content of prompts and grouping similar prompts together. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the content of prompts using AI and store similar prompts by grouping them together.

[0079] The prompt storage unit can select the optimal storage method by referring to the creator's past prompt history when storing prompts. For example, the prompt storage unit can analyze the creator's past prompt history and prioritize storing frequently used prompts. The prompt storage unit can also automatically extract and store prompts related to a specific theme from the creator's past prompt history. The prompt storage unit can also efficiently store prompts by referring to the creator's past prompt history and eliminating duplicate prompts. This allows the optimal storage method to be selected by referring to the creator's past prompt history. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the creator's past prompt history using AI and select the optimal storage method.

[0080] The prompt storage unit can estimate the creator's emotions and adjust the prompt storage frequency based on the estimated emotions. For example, if the creator is excited, the prompt storage unit can increase the prompt storage frequency to store prompts quickly. If the creator is tired, the prompt storage unit can also decrease the prompt storage frequency to reduce the burden. If the creator is relaxed, the prompt storage unit can adjust the prompt storage frequency to a moderate level. This allows for efficient prompt storage by adjusting the prompt storage frequency based on the creator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can input the creator's emotion data into the generative AI, which can then adjust the prompt storage frequency.

[0081] The prompt storage unit can prioritize storing highly relevant prompts by considering the creator's geographical location information when storing prompts. For example, if the creator is in a specific region, the prompt storage unit will prioritize storing prompts related to that region. Based on the creator's geographical location information, the prompt storage unit can also store prompts related to the region's specific culture and customs. If the creator is on the move, the prompt storage unit can store prompts related to their current location in real time. This allows for the priority storage of highly relevant prompts by considering the creator's geographical location information. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the creator's geographical location information using AI and prioritize storing highly relevant prompts.

[0082] The prompt storage unit can analyze the creator's social media activity and store relevant prompts when storing prompts. For example, the prompt storage unit can analyze the creator's social media posts and automatically store relevant prompts. The prompt storage unit can also prioritize storing prompts related to topics mentioned by the creator on social media. The prompt storage unit can also monitor the creator's social media activity and store relevant prompts in real time. This allows for efficient storage of relevant prompts by analyzing the creator's social media activity. Some or all of the above processing in the prompt storage unit may be performed using AI or not. For example, the prompt storage unit can analyze the creator's social media posts using AI and store relevant prompts.

[0083] The generation unit can estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. For example, if the creator is excited, the generation unit can generate an animation in a bright and energetic style. If the creator is relaxed, the generation unit can also generate an animation in a calm tone. If the creator is sad, the generation unit can also generate an animation in an emotional and deep tone. This allows for the generation of animations that better reflect the emotions by adjusting the style and tone based on the creator's feelings. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using or without a generation AI. For example, the generation unit can input the creator's emotion data into a generation AI, which can then adjust the style and tone of the animation.

[0084] The generation unit can adjust the level of detail of the animation based on the importance of the accumulated prompts during generation. For example, the generation unit can generate a detailed animation based on a high-importance prompt. The generation unit can also generate a simplified animation based on a low-importance prompt. The generation unit can also generate an animation with a moderate level of detail based on a medium-importance prompt. This allows for efficient animation generation by adjusting the level of detail of the animation based on the importance of the accumulated prompts. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the accumulated prompts into a generation AI, which can then adjust the level of detail of the animation.

[0085] The generation unit can apply different generation algorithms depending on the anime category during generation. For example, in the case of action anime, the generation unit can apply a generation algorithm that emphasizes fast-moving scenes. In the case of romance anime, the generation unit can also apply a generation algorithm that emphasizes emotional expression. In the case of comedy anime, the generation unit can also apply a generation algorithm that emphasizes humorous scenes. In this way, by applying different generation algorithms depending on the anime category, it is possible to generate anime that is appropriate for the category. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can have the generation AI apply different algorithms depending on the anime category.

[0086] The generation unit can estimate the creator's emotions and adjust the length of the generated animation based on the estimated emotions. For example, if the creator is in a hurry, the generation unit will generate a short animation. If the creator is relaxed, the generation unit can also generate a longer animation. If the creator is excited, the generation unit can adjust the length of the episode before generating it. This allows for efficient animation generation by adjusting the length of the animation based on the creator's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using the generation AI or not. For example, the generation unit can input the creator's emotion data into the generation AI, which can then adjust the length of the animation.

[0087] The generation unit can determine the generation priority based on the prompt submission timing during generation. For example, the generation unit may prioritize the generation of recently submitted prompts. The generation unit may also postpone the generation of older prompts. The generation unit can also adjust the generation schedule based on the submission timing. This enables efficient animation generation by determining the generation priority based on the prompt submission timing. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit may use AI to analyze the prompt submission timing and determine the generation priority.

[0088] The generation unit can adjust the generation order based on the relevance of the prompts during generation. For example, the generation unit can prioritize generating highly relevant prompts. The generation unit can also postpone generating less relevant prompts. The generation unit can also optimize the generation order based on the relevance of the prompts. This allows for efficient animation generation by adjusting the generation order based on the relevance of the prompts. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can analyze the relevance of prompts using AI and adjust the generation order.

[0089] The feedback collection unit can estimate the viewer's emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority of collection. For example, if the viewer is excited, the feedback collection unit can evaluate the importance of the feedback based on that emotion and prioritize its collection. If the viewer is relaxed, the feedback collection unit can evaluate the importance of the feedback based on that emotion to a moderate level and collect it at an appropriate time. If the viewer is sad, the feedback collection unit can evaluate the importance of the feedback based on that emotion and postpone its collection. This enables efficient feedback collection by evaluating the importance of feedback and determining the priority of collection based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can input viewer emotion data into a generating AI, which can then evaluate the importance of the feedback and determine the priority for collection.

[0090] The feedback collection unit can analyze the content of feedback and efficiently collect similar feedback by grouping it together. For example, the feedback collection unit can analyze the content of feedback using natural language processing technology and automatically group similar feedback. The feedback collection unit can also analyze the feedback provided by viewers on a keyword basis and group similar feedback. The feedback collection unit can also analyze the content of feedback using topic modeling technology and group highly relevant feedback. This enables efficient feedback collection by analyzing the content of feedback and grouping similar feedback. Some or all of the above processing in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can analyze the content of feedback using AI and collect similar feedback by grouping it together.

[0091] The feedback collection unit can select the optimal collection method by referring to the viewer's past feedback history when collecting feedback. For example, the feedback collection unit can analyze the viewer's past feedback history and prioritize the collection of frequently provided feedback. The feedback collection unit can also automatically extract and collect feedback related to a specific theme from the viewer's past feedback history. The feedback collection unit can also efficiently collect feedback by referring to the viewer's past feedback history and eliminating duplicate feedback. This allows the optimal collection method to be selected by referring to the viewer's past feedback history. Some or all of the above processes in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can analyze the viewer's past feedback history using AI and select the optimal collection method.

[0092] The feedback collection unit can estimate the viewer's emotions and adjust the frequency of feedback collection based on the estimated emotions. For example, if the viewer is excited, the feedback collection unit can increase the frequency of feedback collection to collect it quickly. If the viewer is relaxed, the feedback collection unit can also adjust the frequency of feedback collection to a moderate level. If the viewer is sad, the feedback collection unit can also decrease the frequency of feedback collection to reduce the burden. This allows for efficient feedback collection by adjusting the frequency of feedback collection based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can input viewer emotion data into a generative AI, which can then adjust the frequency of feedback collection.

[0093] The feedback collection unit can prioritize collecting highly relevant feedback by considering the viewer's geographical location information when collecting feedback. For example, if a viewer is in a specific region, the feedback collection unit will prioritize collecting feedback related to that region. Based on the viewer's geographical location information, the feedback collection unit can also collect feedback related to the region's specific culture and customs. If a viewer is on the move, the feedback collection unit can also collect feedback related to their current location in real time. This allows for the priority collection of highly relevant feedback by considering the viewer's geographical location information. Some or all of the above processing in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can analyze the viewer's geographical location information using AI and prioritize the collection of highly relevant feedback.

[0094] The feedback reflection unit can estimate the viewer's emotions and adjust the method of reflecting feedback based on the estimated emotions. For example, if the viewer is excited, the feedback reflection unit can quickly reflect feedback based on that emotion. If the viewer is relaxed, the feedback reflection unit can also reflect feedback moderately based on that emotion. If the viewer is sad, the feedback reflection unit can also carefully reflect feedback based on that emotion. This allows for efficient feedback reflection by adjusting the method of reflecting feedback based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the feedback reflection unit may be performed using AI or not. For example, the feedback reflection unit can input viewer emotion data into a generative AI, which can then adjust the method of reflecting feedback.

[0095] The feedback reflection unit can adjust the level of detail in the reflection of feedback based on the importance of the collected feedback. For example, the feedback reflection unit can perform detailed reflection based on high-importance feedback. The feedback reflection unit can also perform simplified reflection based on low-importance feedback. The feedback reflection unit can also perform reflection with an appropriate level of detail based on medium-importance feedback. This allows for efficient feedback reflection by adjusting the level of detail in the reflection based on the importance of the collected feedback. Some or all of the above processing in the feedback reflection unit may be performed using AI or not. For example, the feedback reflection unit can analyze the importance of the collected feedback using AI and adjust the level of detail in the reflection.

[0096] The feedback reflection unit can apply different reflection algorithms depending on the category of the feedback when reflecting it. For example, in the case of technical feedback, the feedback reflection unit can apply a reflection algorithm that emphasizes technical improvements. In the case of emotional feedback, the feedback reflection unit can also apply a reflection algorithm that emphasizes emotional expression. In the case of design-related feedback, the feedback reflection unit can also apply a reflection algorithm that emphasizes design improvements. This enables efficient feedback reflection by applying different reflection algorithms depending on the category of the feedback. Some or all of the above processing in the feedback reflection unit may be performed using AI or not. For example, the feedback reflection unit can analyze the category of the feedback using AI and apply an appropriate reflection algorithm.

[0097] The feedback reflection unit can estimate the viewer's emotions and adjust the frequency of feedback reflection based on the estimated emotions. For example, if the viewer is excited, the feedback reflection unit can increase the frequency of feedback reflection and reflect it quickly. If the viewer is relaxed, the feedback reflection unit can also adjust the frequency of feedback reflection to a moderate level. If the viewer is sad, the feedback reflection unit can also decrease the frequency of feedback reflection and reflect it cautiously. This allows for efficient feedback reflection by adjusting the frequency of feedback reflection based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the feedback reflection unit may be performed using AI or not. For example, the feedback reflection unit can input viewer emotion data into a generative AI, which can then adjust the frequency of feedback reflection.

[0098] The feedback processing unit can determine the priority of feedback processing based on the submission date. For example, it may prioritize recently submitted feedback. It may also postpone older feedback. The feedback processing unit can also adjust the processing schedule based on the submission date. This enables efficient feedback processing by determining the priority of feedback processing based on the submission date. Some or all of the above processing in the feedback processing unit may be performed using AI or not. For example, the feedback processing unit may use AI to analyze the submission date of feedback and determine the priority of processing.

[0099] The translation unit can estimate the viewer's emotions and adjust the translation's expression based on those emotions. For example, if the viewer is excited, the translation unit can make the translation more energetic based on that emotion. If the viewer is relaxed, the translation unit can make the translation calmer based on that emotion. If the viewer is sad, the translation unit can make the translation more emotional based on that emotion. This allows for more efficient translation by adjusting the translation's expression based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI or not. For example, the translation unit can input viewer emotion data into a generative AI, which can then adjust the translation's expression.

[0100] The translation unit can adjust the level of detail in the translation based on the content of the anime. For example, in the case of an action scene, the translation unit can provide a concise and easy-to-understand translation. In the case of an emotional scene, the translation unit can also provide a detailed translation that emphasizes emotional expression. In the case of a comedy scene, the translation unit can also provide a translation that emphasizes humor. By adjusting the level of detail in the translation based on the content of the anime, efficient translation becomes possible. Some or all of the above processes in the translation unit may be performed using AI, or not. For example, the translation unit can analyze the content of the anime using AI and adjust the level of detail in the translation.

[0101] The translation unit can apply different translation algorithms depending on the anime category during translation. For example, in the case of action anime, the unit may apply a translation algorithm that emphasizes fast-paced scenes. In the case of romance anime, the unit may also apply a translation algorithm that emphasizes emotional expression. In the case of comedy anime, the unit may also apply a translation algorithm that emphasizes humorous scenes. By applying different translation algorithms depending on the anime category, efficient translation becomes possible. Some or all of the above processing in the translation unit may be performed using AI or not. For example, the translation unit may use AI to analyze the anime category and apply an appropriate translation algorithm.

[0102] The translation unit can estimate the viewer's emotions and adjust the length of the translation based on those emotions. For example, if the viewer is in a hurry, the translation unit can provide a short, concise translation. If the viewer is relaxed, the translation unit can also provide a longer translation with more detailed explanations. If the viewer is excited, the translation unit can also provide a translation with visually stimulating effects. This allows for efficient translation by adjusting the length of the translation based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI or not. For example, the translation unit can input viewer emotion data into a generative AI, which can then adjust the length of the translation.

[0103] The translation department can prioritize translations based on the anime's submission dates. For example, it might prioritize translating recently submitted anime. It could also postpone older anime submissions. The translation department could also adjust the translation schedule based on submission dates. This allows for more efficient translation by prioritizing translations based on anime submission dates. Some or all of the above processes in the translation department may be performed using AI or not. For example, the translation department could use AI to analyze anime submission dates and determine translation priorities.

[0104] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0105] A platform that uses generative AI to convert manga into anime can further analyze users' viewing history and recommend content best suited to each individual user. For example, it can identify a user's preferred genres and characters from their viewing history and recommend new anime based on that information. It can also collect ratings and comments on anime watched by users and use this to recommend content popular with other users. Furthermore, it can utilize information on users' viewing times and devices to deliver content at the optimal time. This can improve the user's viewing experience and increase the frequency of platform use.

[0106] A platform that uses generative AI to convert manga into anime can also be equipped with the ability to estimate the user's emotions and dynamically adjust anime scenes based on those emotions. For example, if the user is excited, the anime can be re-edited to emphasize action scenes. If the user is relaxed, the viewing experience can be improved by adding more calming scenes. Furthermore, if the user is sad, emotional scenes can be added to provide an anime that resonates with their feelings. This allows for a customized viewing experience tailored to the user's emotions.

[0107] A platform that uses generative AI to convert manga into anime can also incorporate real-time user feedback and dynamically update the anime's content. For example, if a user provides feedback during viewing, such as "I want this scene to be more emotionally impactful," the platform can immediately incorporate that feedback and regenerate the scene. Similarly, if a user requests a change in a character's voice, the voice actor's voice can be altered accordingly. Furthermore, if a user requests more action scenes, action scenes can be added. This allows for the provision of customized anime that instantly reflects user feedback.

[0108] A platform that uses generative AI to convert manga into anime can also incorporate the ability to insert advertisements tailored to the viewer's preferences based on user viewing data. For example, if a user prefers action anime, it can insert trailers for action movies. Similarly, if a user prefers romance anime, it can insert advertisements for romance movies. Furthermore, if a user frequently purchases products from a particular brand, it can insert advertisements introducing new products from that brand. This allows for increased advertising effectiveness by providing advertisements tailored to the user's preferences.

[0109] A platform that uses generative AI to convert manga into anime can also be equipped with the ability to estimate the user's emotions and dynamically change the content of advertisements based on those emotions. For example, if the user is excited, it can display energetic advertisements. If the user is relaxed, it can display calming advertisements. Furthermore, if the user is sad, it can empathize with their emotions by displaying emotionally moving advertisements. This maximizes the effectiveness of advertisements by providing ads that are tailored to the user's emotions.

[0110] A platform that uses generative AI to convert manga into anime can also incorporate the ability to automatically generate relevant content that viewers might be interested in, based on their viewing history. For example, if a user likes a particular character, it can generate a spin-off anime centered around that character. It can also generate new stories related to a genre if the user prefers that genre. Furthermore, it can automatically generate sequels to anime the user has watched. This allows for an improved viewing experience by providing new content tailored to the user's interests.

[0111] A platform that uses generative AI to convert manga into anime can also be equipped with the ability to estimate the user's emotions and dynamically change the anime's ending based on those emotions. For example, if the user is excited, it can provide a happy ending. If the user is relaxed, it can provide a calm ending. Furthermore, if the user is sad, it can empathize with their emotions by providing an emotionally moving ending. In this way, the viewing experience can be improved by providing an ending that matches the user's emotions.

[0112] A platform that uses generative AI to convert manga into anime can also incorporate a feature that suggests events likely to interest viewers based on their viewing data. For example, if a user likes a particular anime, it can suggest events or concerts related to that anime. Similarly, if a user likes a particular character, it can suggest events featuring that character's voice actor. Furthermore, if a user likes a particular genre, it can suggest events related to that genre. This allows for an improved viewing experience by suggesting events tailored to the user's interests.

[0113] A platform that uses generative AI to convert manga into anime can also be equipped with the ability to estimate the user's emotions and dynamically change the anime's music based on those emotions. For example, if the user is excited, it can provide energetic music. If the user is relaxed, it can provide calming music. Furthermore, if the user is sad, it can provide emotionally resonant music to empathize with their feelings. In this way, the viewing experience can be improved by providing music that matches the user's emotions.

[0114] A platform that uses generative AI to convert manga into anime can also incorporate a feature that suggests merchandise that viewers might be interested in, based on their viewing data. For example, if a user likes a particular character, it can suggest figurines or posters of that character. Similarly, if a user likes a particular anime, it can suggest merchandise related to that anime. Furthermore, if a user likes a particular genre, it can suggest merchandise related to that genre. This allows for an improved viewing experience by suggesting merchandise tailored to the user's interests.

[0115] The following briefly describes the processing flow for example form 2.

[0116] Step 1: The prompt storage unit stores prompts. For example, it saves prompts entered by the creator into the generation AI to a database. The prompt storage unit can also analyze the content of the prompts and group similar prompts for efficient storage. It can also estimate the creator's emotions, evaluate the importance of the prompts based on the estimated emotions, and determine the priority for storage. Step 2: The generation unit generates animation based on the accumulated prompts. For example, it uses a generation AI to generate animation based on the creator's prompts. The generation unit can also adjust the level of detail of the generation based on the importance of the accumulated prompts. It can also estimate the creator's emotions and adjust the style and tone of the generated animation based on the estimated emotions. Step 3: The feedback collection unit collects viewer feedback on the generated animation. For example, it stores viewer feedback in a database. The feedback collection unit can also analyze the content of the feedback and group similar feedback for efficient collection. It can also estimate the viewer's emotions, evaluate the importance of the feedback based on the estimated emotions, and determine the priority for collection. Step 4: The feedback reflection unit reflects the collected feedback into the generating AI. For example, it analyzes viewer feedback and generates data to reflect it into the generating AI. The feedback reflection unit can also adjust the level of detail of the reflection based on the importance of the feedback. It can also estimate the viewer's emotions and adjust the way the feedback is reflected based on the estimated emotions. Step 5: The translation unit translates the generated animation into multiple languages. For example, it uses a generation AI to translate the audio and subtitles of the generated animation into multiple languages. The translation unit can also estimate the viewer's emotions and adjust the translation's expression based on those emotions. It can also adjust the level of detail in the translation based on the content of the animation.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0119] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0120] Each of the multiple elements described above, including the prompt storage unit, generation unit, feedback collection unit, feedback reflection unit, and translation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the prompt storage unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the specific processing unit 290 of the data processing device 12. The feedback collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The feedback reflection unit is implemented by the specific processing unit 290 of the data processing device 12. The translation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0121] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0122] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0124] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0125] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0127] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0128] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0129] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0130] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0131] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0135] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements described above, including the prompt storage unit, generation unit, feedback collection unit, feedback reflection unit, and translation unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the prompt storage unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the specific processing unit 290 of the data processing device 12. The feedback collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The feedback reflection unit is implemented by the specific processing unit 290 of the data processing device 12. The translation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0137] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0138] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the prompt storage unit, generation unit, feedback collection unit, feedback reflection unit, and translation unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the prompt storage unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The generation unit is implemented by the specific processing unit 290 of the data processing device 12. The feedback collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The feedback reflection unit is implemented by the specific processing unit 290 of the data processing device 12. The translation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0153] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0154] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0161] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0162] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0163] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0164] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0165] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0166] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0167] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0168] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0169] Each of the multiple elements described above, including the prompt storage unit, generation unit, feedback collection unit, feedback reflection unit, and translation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the prompt storage unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12. The feedback collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The feedback reflection unit is implemented by the specific processing unit 290 of the data processing unit 12. The translation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0170] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0171] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0172] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0173] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0174] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0175] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0176] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0177] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0178] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0179] 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.

[0180] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0181] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0182] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0183] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0184] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0185] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0186] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0187] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0188] (Note 1) A prompt storage unit that stores prompts, A generation unit that generates animations based on prompts accumulated by the prompt accumulation unit, A feedback collection unit that collects viewer feedback on the generated animation, A feedback reflection unit that reflects the feedback collected by the aforementioned feedback collection unit, It includes a translation unit that translates the generated animation into multiple languages. A system characterized by the following features. (Note 2) The prompt storage unit is, The creator's prompts are stored as training data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Generate animations based on accumulated prompts. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned feedback collection unit is Collect viewer feedback The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned feedback reflection unit is The collected feedback is incorporated into the generating AI. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned translation department, Translate the generated animation into multiple languages. The system described in Appendix 1, characterized by the features described herein. (Note 7) The prompt storage unit is, It estimates the creator's emotions, evaluates the importance of prompts based on those emotions, and determines the priority of accumulation. The system described in Appendix 1, characterized by the features described herein. (Note 8) The prompt storage unit is, Analyze the content of prompts, group similar prompts together, and store them efficiently. The system described in Appendix 1, characterized by the features described herein. (Note 9) The prompt storage unit is, When accumulating prompts, the optimal accumulation method is selected by referring to the creator's past prompt history. The system described in Appendix 1, characterized by the features described herein. (Note 10) The prompt storage unit is, It estimates the creator's emotions and adjusts the frequency of prompt accumulation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The prompt storage unit is, When accumulating prompts, the system prioritizes accumulating highly relevant prompts by considering the creator's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The prompt storage unit is, When accumulating prompts, the system analyzes the creator's social media activity and collects relevant prompts. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is It estimates the creator's emotions and adjusts the style and tone of the generated animation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is During generation, adjust the level of detail based on the importance of the accumulated prompts. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is During generation, different generation algorithms are applied depending on the anime category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the creator's emotions and adjusts the length of the generated animation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is During generation, the generation priority is determined based on when the prompt was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is During generation, the generation order is adjusted based on the relevance of the prompts. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned feedback collection unit is The system estimates the audience's emotions, evaluates the importance of feedback based on those emotions, and determines the priority of collection. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned feedback collection unit is Analyze the content of the feedback, group similar feedback together, and collect it efficiently. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned feedback collection unit is When collecting feedback, refer to the viewer's past feedback history to select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned feedback collection unit is We estimate the viewer's emotions and adjust the frequency of feedback collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned feedback collection unit is When collecting feedback, the system prioritizes collecting highly relevant feedback by considering the viewer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned feedback reflection unit is We estimate the viewer's emotions and adjust how feedback is reflected based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned feedback reflection unit is When incorporating feedback, adjust the level of detail based on the importance of the collected feedback. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned feedback reflection unit is When incorporating feedback, different implementation algorithms are applied depending on the feedback category. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned feedback reflection unit is It estimates the viewer's emotions and adjusts the frequency of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned feedback reflection unit is When incorporating feedback, we prioritize its implementation based on when the feedback was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned translation department, The system estimates the viewer's emotions and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned translation department, During translation, adjust the level of detail based on the content of the anime. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned translation department, When translating, different translation algorithms are applied depending on the anime category. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned translation department, It estimates the viewer's emotions and adjusts the translation length based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned translation department, During translation, translation priorities are determined based on the anime's submission deadline. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A prompt storage unit that stores prompts, A generation unit that generates animations based on prompts accumulated by the prompt accumulation unit, A feedback collection unit that collects viewer feedback on the generated animation, A feedback reflection unit that reflects the feedback collected by the aforementioned feedback collection unit, It includes a translation unit that translates the generated animation into multiple languages. A system characterized by the following features.

2. The prompt storage unit is, The creator's prompts are stored as training data. The system according to feature 1.

3. The generating unit is Generate animations based on accumulated prompts. The system according to feature 1.

4. The aforementioned feedback collection unit is Collect viewer feedback The system according to feature 1.

5. The aforementioned feedback reflection unit is The collected feedback is incorporated into the generating AI. The system according to feature 1.

6. The aforementioned translation department, Translate the generated animation into multiple languages. The system according to feature 1.

7. The prompt storage unit is, It estimates the creator's emotions, evaluates the importance of prompts based on those emotions, and determines the priority of accumulation. The system according to feature 1.

8. The prompt storage unit is, Analyze the content of prompts, group similar prompts together, and store them efficiently. The system according to feature 1.

Images