system

Abstract

The system according to this embodiment aims to enable users who are not comfortable with horror or grotesque scenes to enjoy movies and dramas. [Solution] The system according to the embodiment comprises a questionnaire reception unit, an NG line measurement unit, a reading unit, a scene detection unit, a conversion unit, and a commentary generation unit. The questionnaire reception unit receives questionnaires from users. The NG line measurement unit measures the NG line based on the questionnaires received by the questionnaire reception unit. The reading unit reads movies and dramas. The scene detection unit analyzes the scenes from the movies and dramas read by the reading unit and detects horror and grotesque scenes. The conversion unit converts the scenes detected by the scene detection unit into cute images. The commentary generation unit generates commentary audio based on the scenes converted by the conversion unit.

Description

Technical Field

[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, which is 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 prior art, there was a problem that it was difficult for users who are not good at horror or grotesque scenes to enjoy movies or dramas.

[0005] The system according to the embodiment aims to enable users who are not good at horror or grotesque scenes to enjoy movies or dramas.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a questionnaire reception unit, an NG line measurement unit, a reading unit, a scene detection unit, a conversion unit, and a commentary generation unit. The questionnaire reception unit receives questionnaires from users. The NG line measurement unit measures the NG line based on the questionnaires received by the questionnaire reception unit. The reading unit reads movies and dramas. The scene detection unit analyzes the scenes from the movies and dramas read by the reading unit and detects horror and grotesque scenes. The conversion unit converts the scenes detected by the scene detection unit into cute images. The commentary generation unit generates commentary audio based on the scenes converted by the conversion unit. [Effects of the Invention]

[0007] The system according to this embodiment allows users who are not fond of horror or grotesque scenes to enjoy movies and dramas. [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, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 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 horror & gore-free software according to an embodiment of the present invention is software that allows people who are not good with horror or gore scenes to enjoy the story of movies and dramas. This software converts horror and gore scenes into cute images and commentary, allowing viewers to enjoy the content while avoiding unpleasant scenes. First, the user purchases the software and answers several questionnaires. Based on these questionnaires, the software measures the user's horror / gore tolerance level. Next, the user loads the movie or drama they want to watch into the software. The software automatically detects horror and gore scenes and converts only those parts into cute images and commentary. For example, if there is a scene in a movie where "Tanaka punches Suzuki down, and blood gushes from Tanaka's head! Then he stabs him in the neck with a knife...that's a fatal wound," the software converts this scene into an image of cute characters having fun, and changes the commentary to something like "Oh! Tanaka is having fun playing with Suzuki!" In this way, viewers can avoid horror and grotesque scenes, allowing them to enjoy movies and dramas with strong storylines. Therefore, Horror & Grotesque Bye-Bye Software allows even those who dislike horror and grotesque scenes to enjoy the storylines of movies and dramas.

[0029] The horror & gore-free software according to this embodiment comprises a survey reception unit, an NG line measurement unit, a reading unit, a scene detection unit, a conversion unit, and a live commentary generation unit. The survey reception unit receives surveys from users. The survey reception unit receives surveys, for example, through a survey form displayed when the user starts the software. The survey reception unit also allows users to answer surveys via a website. Furthermore, the survey reception unit can also receive surveys via a mobile application. For example, the survey reception unit allows users to answer surveys using their smartphones. The NG line measurement unit measures the NG line based on the surveys received by the survey reception unit. The NG line measurement unit measures the user's horror / gore NG line, for example, by analyzing the content of the survey responses. The NG line measurement unit can also analyze the content of the survey responses using AI and measure the NG line. Furthermore, the NG line measurement unit can also measure the NG line based on past survey data. For example, the NG line measurement unit analyzes past survey data and predicts the user's NG line. The reading unit reads movies and dramas that the user wants to watch. The reading unit reads, for example, movie or TV drama files specified by the user. The reading unit can also read movies and TV dramas from streaming services. Furthermore, the reading unit can read movies and TV dramas from DVDs and Blu-ray discs. For example, the reading unit can read DVDs and Blu-ray discs owned by the user. The scene detection unit analyzes scenes from the movies and TV dramas read by the reading unit and detects horror and grotesque scenes. The scene detection unit detects horror and grotesque scenes using, for example, video analysis technology. It can also analyze scenes using AI to detect horror and grotesque scenes. Furthermore, the scene detection unit can detect horror and grotesque scenes using audio analysis technology. For example, the scene detection unit can detect blood and violent scenes in the video. The conversion unit converts the scenes detected by the scene detection unit into cute videos.The conversion unit, for example, uses video conversion technology to convert horror and grotesque scenes into cute videos. The conversion unit can also use AI to convert videos. Furthermore, the conversion unit can use cute characters selected by the user to convert videos. For example, the conversion unit converts a horror scene into a scene of cute anime characters having fun. The commentary generation unit generates commentary audio based on the scenes converted by the conversion unit. The commentary generation unit generates commentary audio using, for example, speech synthesis technology. Furthermore, the commentary generation unit can also use AI to generate commentary audio. Additionally, the commentary generation unit can generate commentary audio using the voice of a voice actor selected by the user. For example, the commentary generation unit generates commentary audio in the voice of a cute character. As a result, the horror & grotesque goodbye software according to this embodiment allows users to enjoy movies and dramas while avoiding horror and grotesque scenes.

[0030] The survey department accepts user surveys. For example, it accepts surveys through a survey form displayed when a user launches the software. Specifically, the survey form includes questions about the user's age, gender, tolerance for horror and grotesque scenes, and preferred genres. The survey department also allows users to answer surveys through a website. On the website, users log in and answer the survey, and the results are saved in the user's profile. Furthermore, the survey department can accept surveys through a mobile application. For example, it allows users to answer surveys using their smartphones. The mobile application can use push notifications to prompt survey responses. This allows the survey department to accept access from a variety of user devices and collect detailed data on user preferences and tolerances. In addition, the survey department uses encryption technology to securely store user response data and protect privacy. This allows users to answer surveys with peace of mind.

[0031] The NG line measurement unit measures the NG line based on questionnaires received by the questionnaire reception unit. For example, the NG line measurement unit analyzes the content of the questionnaires to measure the user's horror / gore NG line. Specifically, it analyzes the content of the questionnaires using natural language processing technology to quantify the user's sensitivity and tolerance. The NG line measurement unit can also analyze the content of the questionnaires and measure the NG line using AI. The AI ​​uses machine learning algorithms to learn the user's response patterns and predict the optimal NG line for each individual user. Furthermore, the NG line measurement unit can also measure the NG line based on past questionnaire data. For example, the NG line measurement unit analyzes past questionnaire data to predict the user's NG line. This allows the NG line measurement unit to accurately measure the acceptable range of horror and gore scenes based on the user's preferences and tolerance. In addition, the NG line measurement unit can collect user feedback and continuously improve the accuracy of NG line measurement. For example, if a user encounters an unpleasant scene while watching, that information is collected and reflected in the next NG line measurement. This allows the NG line measurement unit to optimize the user experience and provide a more comfortable viewing environment.

[0032] The loading unit loads movies and TV shows that the user wants to watch. For example, the loading unit loads movie or TV show files specified by the user. Specifically, the user selects a video file saved on local storage, and the loading unit analyzes that file. The loading unit can also load movies and TV shows from streaming services. Using the streaming service's API, it searches for the content the user wants to watch and loads the selected content in real time. Furthermore, the loading unit can also load movies and TV shows from DVDs and Blu-ray discs. For example, the loading unit makes it possible to load DVDs and Blu-ray discs owned by the user. This involves the process of reading the physical media through the disc drive and converting it into digital data. The loading unit centrally manages data from these diverse sources, allowing the user to smoothly watch the content. In addition, the loading unit automatically retrieves metadata of the loaded content (title, genre, release year, cast, etc.) and provides it to the user. This allows the user to easily check detailed information about the content they are watching.

[0033] The scene detection unit analyzes scenes from movies and dramas loaded by the loading unit to detect horror and grotesque scenes. For example, the scene detection unit uses video analysis technology to detect horror and grotesque scenes. Specifically, it uses computer vision technology to identify specific patterns and features in the video to identify horror and grotesque scenes. The scene detection unit can also use AI to analyze scenes and detect horror and grotesque scenes. The AI ​​uses a deep learning model to learn complex patterns in the video and classify scenes with high accuracy. Furthermore, the scene detection unit can also use audio analysis technology to detect horror and grotesque scenes. For example, it can detect blood and violent scenes in the video. By using audio analysis technology, it can identify audio patterns specific to horror scenes, such as screams and eerie music. This allows the scene detection unit to analyze both video and audio to detect horror and grotesque scenes with high accuracy. Finally, based on the user's NG line, the scene detection unit evaluates the importance and impact of the detected scenes and provides information for appropriate processing. This allows the scene detection unit to optimize the user's viewing experience and effectively avoid horror and grotesque scenes.

[0034] The conversion unit transforms scenes detected by the scene detection unit into cute videos. For example, the conversion unit can use video conversion technology to transform horror and grotesque scenes into cute videos. Specifically, it removes horror and grotesque elements from the video and inserts cute characters or scenery in their place. The conversion unit can also use AI to transform videos. The AI ​​uses generative AI technology to automatically transform horror scenes into cute scenes. For example, the AI ​​can replace terrifying monsters in horror movies with cute animal characters. Furthermore, the conversion unit can also transform videos using cute characters selected by the user. For example, the conversion unit can transform a horror scene into a scene where cute anime characters are having fun. Users can select their favorite characters in advance and set them to appear in the video. This allows the conversion unit to provide customized video transformations tailored to the user's preferences. In addition, the conversion unit performs the video transformation process in real time, allowing the user to continue watching smoothly. This allows the conversion unit to effectively avoid horror and grotesque scenes and provide the user with an enjoyable viewing experience.

[0035] The commentary generation unit generates commentary audio based on the scene converted by the conversion unit. The commentary generation unit generates commentary audio using, for example, speech synthesis technology. Specifically, it uses a speech synthesis engine to generate narration and commentary that matches the converted scene. The commentary generation unit can also generate commentary audio using AI. The AI ​​uses natural language processing technology to generate appropriate commentary comments based on the content of the scene. Furthermore, the commentary generation unit can generate commentary audio using the voice of a voice actor selected by the user. For example, the commentary generation unit can generate commentary audio in the voice of a cute character. Users can select their preferred voice actor in advance and set the commentary to be performed in that voice actor's voice. This allows the commentary generation unit to provide customized commentary audio that matches the user's preferences. Furthermore, the commentary generation unit can generate commentary audio in real time and synchronize it with the video. This allows users to enjoy the converted scene while listening to immersive commentary. In addition, the commentary generation unit can collect user feedback and continuously improve the accuracy and effectiveness of the commentary content. This allows the commentary generation unit to provide users with an enjoyable viewing experience while effectively avoiding horror and grotesque scenes.

[0036] The survey reception unit can analyze a user's past survey response history and select the most appropriate question format. For example, if a user has previously preferred detailed answers, the survey reception unit can provide a detailed question format. For example, if a user has previously preferred concise answers, the survey reception unit can also provide a concise question format. For example, if a user has previously shown interest in a particular topic, the survey reception unit can also provide questions related to that topic. This improves the accuracy of user responses by providing the most appropriate question format based on past response history. Some or all of the above processing in the survey reception unit may be performed using AI, for example, or without AI. For example, the survey reception unit can input the user's past survey response data into a generating AI and have the generating AI select the most appropriate question format.

[0037] The NG line measurement unit can analyze the user's past viewing history to select the optimal measurement method when measuring the NG line. For example, the NG line measurement unit can provide the optimal measurement method based on the user's past viewing history of horror movies. The NG line measurement unit can also provide the optimal measurement method based on the user's past viewing history of dramas. The NG line measurement unit can also provide the optimal measurement method based on the user's past viewing history of anime. By providing the optimal measurement method based on past viewing history, the accuracy of NG line measurement is improved. Some or all of the above processing in the NG line measurement unit may be performed using AI, for example, or without AI. For example, the NG line measurement unit can input the user's past viewing history data into a generating AI and have the generating AI select the optimal measurement method.

[0038] The loading unit can analyze the user's past viewing history and select the optimal loading method during loading. For example, the loading unit can provide the optimal loading method based on the user's history of watching horror movies. For example, the loading unit can also provide the optimal loading method based on the user's history of watching dramas. For example, the loading unit can also provide the optimal loading method based on the user's history of watching anime. This improves the accuracy of loading movies and dramas by providing the optimal loading method based on past viewing history. Some or all of the above processing in the loading unit may be performed using AI, for example, or without AI. For example, the loading unit can input the user's past viewing history data into a generating AI and have the generating AI select the optimal loading method.

[0039] The scene detection unit can apply different detection algorithms depending on the genre of the film or drama during scene detection. For example, in the case of a horror film, the scene detection unit may prioritize detecting scary scenes. In the case of a drama, for example, the scene detection unit may prioritize detecting emotional scenes. In the case of an anime, for example, the scene detection unit may prioritize detecting action scenes. By applying a detection algorithm appropriate to the genre, the accuracy of scene detection is improved. Some or all of the above processing in the scene detection unit may be performed using AI, for example, or without AI. For example, the scene detection unit can input genre data of the film or drama into a generating AI and have the generating AI select the optimal detection algorithm.

[0040] The conversion unit can apply different conversion algorithms depending on the genre of the movie or drama during the conversion process. For example, in the case of a horror movie, the conversion unit can convert scary scenes into cute images. In the case of a drama, for example, the conversion unit can convert emotional scenes into cute images. In the case of an anime, for example, the conversion unit can convert action scenes into cute images. By applying a conversion algorithm appropriate to the genre, the accuracy of the video conversion is improved. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input movie and drama genre data into a generating AI and have the generating AI select the optimal conversion algorithm.

[0041] The commentary generation unit can apply different commentary algorithms depending on the genre of the movie or drama when generating commentary. For example, in the case of a horror movie, the commentary generation unit can convert scary scenes into cute commentary voices. For example, in the case of a drama, the commentary generation unit can convert emotional scenes into cute commentary voices. For example, in the case of an anime, the commentary generation unit can convert action scenes into cute commentary voices. By applying a commentary algorithm appropriate to the genre, the accuracy of the commentary is improved. Some or all of the above processing in the commentary generation unit may be performed using AI, for example, or without using AI. For example, the commentary generation unit can input movie or drama genre data into a generation AI and have the generation AI select the optimal commentary algorithm.

[0042] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0043] The Horror & Gore Bye-Bye software analyzes a user's viewing history and can select the optimal conversion algorithm based on the genres of movies and dramas the user has watched in the past. For example, if a user has watched many horror movies in the past, the conversion algorithm for horror scenes can be enhanced. Similarly, if a user has watched many dramas in the past, the conversion algorithm for emotional scenes can be enhanced. Furthermore, if a user has watched many anime in the past, the conversion algorithm for action scenes can be enhanced. This allows for more appropriate video conversion by providing the optimal conversion algorithm based on the user's viewing history. The analysis of viewing history may be performed using AI or without AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the optimal conversion algorithm.

[0044] The Horror & Gore Bye-Bye software can automatically select characters that the user likes based on their viewing history and reflect them in the converted video. For example, it can include characters from anime the user has watched in the past in the converted video. It can also include characters from dramas the user has watched in the past in the converted video. Furthermore, it can include characters from movies the user has watched in the past in the converted video. This makes it possible to create more relatable video conversions by providing the most suitable characters based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without using AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the most suitable characters.

[0045] The Horror & Gore Bye-Bye software can automatically select music that a user likes based on their viewing history and reflect it in the converted video. For example, it can use the soundtracks of movies the user has watched in the past in the converted video. It can also use the soundtracks of dramas the user has watched in the past in the converted video. Furthermore, it can use the soundtracks of anime the user has watched in the past in the converted video. This makes it possible to create more user-friendly video conversions by providing the most suitable music based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without using AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the most suitable music.

[0046] The Horror & Gore Bye-Bye software can automatically select a narration style preferred by the user based on their viewing history and reflect it in the converted video. For example, it can use the narration style of movies the user has watched in the past in the converted video. It can also use the narration style of dramas the user has watched in the past in the converted video. Furthermore, it can use the narration style of anime the user has watched in the past in the converted video. This makes it possible to create more user-friendly video conversions by providing the optimal narration style based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without using AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the optimal narration style.

[0047] The Horror & Gore Bye-Bye software can automatically select a user's preferred subtitle style based on their viewing history and apply it to the converted video. For example, it can use the subtitle style of movies the user has watched in the past. It can also use the subtitle style of dramas the user has watched in the past. Furthermore, it can use the subtitle style of anime the user has watched in the past. This allows for more user-friendly video conversion by providing the optimal subtitle style based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the optimal subtitle style.

[0048] The following briefly describes the processing flow for example form 1.

[0049] Step 1: The survey reception unit receives user surveys. For example, surveys can be received through a survey form displayed when the user launches the software, a website, or a mobile application. Step 2: The NG line measurement unit measures the NG line based on the questionnaires received by the questionnaire reception unit. For example, it analyzes the content of the questionnaire responses to determine the user's horror / gore NG line. It can also use AI for analysis or predict the NG line based on past questionnaire data. Step 3: The loading unit loads the movies or TV shows the user wants to watch. For example, it can load movies or TV shows specified by the user from files, streaming services, or DVDs and Blu-ray discs. Step 4: The scene detection unit analyzes the movie or drama scenes loaded by the loading unit and detects horror or grotesque scenes. For example, scenes can be detected using video analysis technology, AI, or audio analysis technology. Step 5: The conversion unit converts the scene detected by the scene detection unit into a cute video. For example, it can use video conversion technology or AI for the conversion, and it can also use a cute character selected by the user. Step 6: The commentary generation unit generates commentary audio based on the scene converted by the conversion unit. For example, it is possible to generate commentary audio using speech synthesis technology or AI, and use the voice of a voice actor selected by the user.

[0050] (Example of form 2) The horror & gore-free software according to an embodiment of the present invention is software that allows people who are not good with horror or gore scenes to enjoy the story of movies and dramas. This software converts horror and gore scenes into cute images and commentary, allowing viewers to enjoy the content while avoiding unpleasant scenes. First, the user purchases the software and answers several questionnaires. Based on these questionnaires, the software measures the user's horror / gore tolerance level. Next, the user loads the movie or drama they want to watch into the software. The software automatically detects horror and gore scenes and converts only those parts into cute images and commentary. For example, if there is a scene in a movie where "Tanaka punches Suzuki down, and blood gushes from Tanaka's head! Then he stabs him in the neck with a knife...that's a fatal wound," the software converts this scene into an image of cute characters having fun, and changes the commentary to something like "Oh! Tanaka is having fun playing with Suzuki!" In this way, viewers can avoid horror and grotesque scenes, allowing them to enjoy movies and dramas with strong storylines. Therefore, Horror & Grotesque Bye-Bye Software allows even those who dislike horror and grotesque scenes to enjoy the storylines of movies and dramas.

[0051] The horror & gore-free software according to this embodiment comprises a survey reception unit, an NG line measurement unit, a reading unit, a scene detection unit, a conversion unit, and a live commentary generation unit. The survey reception unit receives surveys from users. The survey reception unit receives surveys, for example, through a survey form displayed when the user starts the software. The survey reception unit also allows users to answer surveys via a website. Furthermore, the survey reception unit can also receive surveys via a mobile application. For example, the survey reception unit allows users to answer surveys using their smartphones. The NG line measurement unit measures the NG line based on the surveys received by the survey reception unit. The NG line measurement unit measures the user's horror / gore NG line, for example, by analyzing the content of the survey responses. The NG line measurement unit can also analyze the content of the survey responses using AI and measure the NG line. Furthermore, the NG line measurement unit can also measure the NG line based on past survey data. For example, the NG line measurement unit analyzes past survey data and predicts the user's NG line. The reading unit reads movies and dramas that the user wants to watch. The reading unit reads, for example, movie or TV drama files specified by the user. The reading unit can also read movies and TV dramas from streaming services. Furthermore, the reading unit can read movies and TV dramas from DVDs and Blu-ray discs. For example, the reading unit can read DVDs and Blu-ray discs owned by the user. The scene detection unit analyzes scenes from the movies and TV dramas read by the reading unit and detects horror and grotesque scenes. The scene detection unit detects horror and grotesque scenes using, for example, video analysis technology. It can also analyze scenes using AI to detect horror and grotesque scenes. Furthermore, the scene detection unit can detect horror and grotesque scenes using audio analysis technology. For example, the scene detection unit can detect blood and violent scenes in the video. The conversion unit converts the scenes detected by the scene detection unit into cute videos.The conversion unit, for example, uses video conversion technology to convert horror and grotesque scenes into cute videos. The conversion unit can also use AI to convert videos. Furthermore, the conversion unit can use cute characters selected by the user to convert videos. For example, the conversion unit converts a horror scene into a scene of cute anime characters having fun. The commentary generation unit generates commentary audio based on the scenes converted by the conversion unit. The commentary generation unit generates commentary audio using, for example, speech synthesis technology. Furthermore, the commentary generation unit can also use AI to generate commentary audio. Additionally, the commentary generation unit can generate commentary audio using the voice of a voice actor selected by the user. For example, the commentary generation unit generates commentary audio in the voice of a cute character. As a result, the horror & grotesque goodbye software according to this embodiment allows users to enjoy movies and dramas while avoiding horror and grotesque scenes.

[0052] The survey department accepts user surveys. For example, it accepts surveys through a survey form displayed when a user launches the software. Specifically, the survey form includes questions about the user's age, gender, tolerance for horror and grotesque scenes, and preferred genres. The survey department also allows users to answer surveys through a website. On the website, users log in and answer the survey, and the results are saved in the user's profile. Furthermore, the survey department can accept surveys through a mobile application. For example, it allows users to answer surveys using their smartphones. The mobile application can use push notifications to prompt survey responses. This allows the survey department to accept access from a variety of user devices and collect detailed data on user preferences and tolerances. In addition, the survey department uses encryption technology to securely store user response data and protect privacy. This allows users to answer surveys with peace of mind.

[0053] The NG line measurement unit measures the NG line based on questionnaires received by the questionnaire reception unit. For example, the NG line measurement unit analyzes the content of the questionnaires to measure the user's horror / gore NG line. Specifically, it analyzes the content of the questionnaires using natural language processing technology to quantify the user's sensitivity and tolerance. The NG line measurement unit can also analyze the content of the questionnaires and measure the NG line using AI. The AI ​​uses machine learning algorithms to learn the user's response patterns and predict the optimal NG line for each individual user. Furthermore, the NG line measurement unit can also measure the NG line based on past questionnaire data. For example, the NG line measurement unit analyzes past questionnaire data to predict the user's NG line. This allows the NG line measurement unit to accurately measure the acceptable range of horror and gore scenes based on the user's preferences and tolerance. In addition, the NG line measurement unit can collect user feedback and continuously improve the accuracy of NG line measurement. For example, if a user encounters an unpleasant scene while watching, that information is collected and reflected in the next NG line measurement. This allows the NG line measurement unit to optimize the user experience and provide a more comfortable viewing environment.

[0054] The loading unit loads movies and TV shows that the user wants to watch. For example, the loading unit loads movie or TV show files specified by the user. Specifically, the user selects a video file saved on local storage, and the loading unit analyzes that file. The loading unit can also load movies and TV shows from streaming services. Using the streaming service's API, it searches for the content the user wants to watch and loads the selected content in real time. Furthermore, the loading unit can also load movies and TV shows from DVDs and Blu-ray discs. For example, the loading unit makes it possible to load DVDs and Blu-ray discs owned by the user. This involves the process of reading the physical media through the disc drive and converting it into digital data. The loading unit centrally manages data from these diverse sources, allowing the user to smoothly watch the content. In addition, the loading unit automatically retrieves metadata of the loaded content (title, genre, release year, cast, etc.) and provides it to the user. This allows the user to easily check detailed information about the content they are watching.

[0055] The scene detection unit analyzes scenes from movies and dramas loaded by the loading unit to detect horror and grotesque scenes. For example, the scene detection unit uses video analysis technology to detect horror and grotesque scenes. Specifically, it uses computer vision technology to identify specific patterns and features in the video to identify horror and grotesque scenes. The scene detection unit can also use AI to analyze scenes and detect horror and grotesque scenes. The AI ​​uses a deep learning model to learn complex patterns in the video and classify scenes with high accuracy. Furthermore, the scene detection unit can also use audio analysis technology to detect horror and grotesque scenes. For example, it can detect blood and violent scenes in the video. By using audio analysis technology, it can identify audio patterns specific to horror scenes, such as screams and eerie music. This allows the scene detection unit to analyze both video and audio to detect horror and grotesque scenes with high accuracy. Finally, based on the user's NG line, the scene detection unit evaluates the importance and impact of the detected scenes and provides information for appropriate processing. This allows the scene detection unit to optimize the user's viewing experience and effectively avoid horror and grotesque scenes.

[0056] The conversion unit transforms scenes detected by the scene detection unit into cute videos. For example, the conversion unit can use video conversion technology to transform horror and grotesque scenes into cute videos. Specifically, it removes horror and grotesque elements from the video and inserts cute characters or scenery in their place. The conversion unit can also use AI to transform videos. The AI ​​uses generative AI technology to automatically transform horror scenes into cute scenes. For example, the AI ​​can replace terrifying monsters in horror movies with cute animal characters. Furthermore, the conversion unit can also transform videos using cute characters selected by the user. For example, the conversion unit can transform a horror scene into a scene where cute anime characters are having fun. Users can select their favorite characters in advance and set them to appear in the video. This allows the conversion unit to provide customized video transformations tailored to the user's preferences. In addition, the conversion unit performs the video transformation process in real time, allowing the user to continue watching smoothly. This allows the conversion unit to effectively avoid horror and grotesque scenes and provide the user with an enjoyable viewing experience.

[0057] The commentary generation unit generates commentary audio based on the scene converted by the conversion unit. The commentary generation unit generates commentary audio using, for example, speech synthesis technology. Specifically, it uses a speech synthesis engine to generate narration and commentary that matches the converted scene. The commentary generation unit can also generate commentary audio using AI. The AI ​​uses natural language processing technology to generate appropriate commentary comments based on the content of the scene. Furthermore, the commentary generation unit can generate commentary audio using the voice of a voice actor selected by the user. For example, the commentary generation unit can generate commentary audio in the voice of a cute character. Users can select their preferred voice actor in advance and set the commentary to be performed in that voice actor's voice. This allows the commentary generation unit to provide customized commentary audio that matches the user's preferences. Furthermore, the commentary generation unit can generate commentary audio in real time and synchronize it with the video. This allows users to enjoy the converted scene while listening to immersive commentary. In addition, the commentary generation unit can collect user feedback and continuously improve the accuracy and effectiveness of the commentary content. This allows the commentary generation unit to provide users with an enjoyable viewing experience while effectively avoiding horror and grotesque scenes.

[0058] The survey reception unit can estimate the user's emotions and adjust the survey questions based on the estimated emotions. For example, if the user is nervous, the survey reception unit can provide questions that help them relax. For example, if the user is relaxed, the survey reception unit can also provide detailed questions. For example, if the user is in a hurry, the survey reception unit can also provide concise questions. This allows for a more appropriate survey by providing questions that match the user'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 survey reception unit may be performed using AI, or not using AI. For example, the survey reception unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0059] The survey reception unit can analyze a user's past survey response history and select the most appropriate question format. For example, if a user has previously preferred detailed answers, the survey reception unit can provide a detailed question format. For example, if a user has previously preferred concise answers, the survey reception unit can also provide a concise question format. For example, if a user has previously shown interest in a particular topic, the survey reception unit can also provide questions related to that topic. This improves the accuracy of user responses by providing the most appropriate question format based on past response history. Some or all of the above processing in the survey reception unit may be performed using AI, for example, or without AI. For example, the survey reception unit can input the user's past survey response data into a generating AI and have the generating AI select the most appropriate question format.

[0060] The survey reception unit can adjust the order of questions based on the user's current psychological state when a survey is received. For example, if the user is nervous, the survey reception unit can start with questions that help them relax. For example, if the user is relaxed, the survey reception unit can also start with detailed questions. For example, if the user is in a hurry, the survey reception unit can also start with important questions. This allows for a more effective survey by providing a question order that is appropriate to the user's psychological state. The estimation of psychological state is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 survey reception unit may be performed using AI, for example, or not using AI. For example, the survey reception unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's psychological state.

[0061] The NG line measurement unit can estimate the user's emotions and adjust the NG line measurement method based on the estimated emotions. For example, if the user is tense, the NG line measurement unit can provide a relaxing measurement method. For example, if the user is relaxed, the NG line measurement unit can also provide a detailed measurement method. For example, if the user is in a hurry, the NG line measurement unit can also provide a concise measurement method. By providing a measurement method that suits the user's emotions, a more accurate NG line can be measured. Emotion estimation is achieved using an emotion estimation function, for example, using 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 NG line measurement unit may be performed using AI, for example, or without AI. For example, the NG line measurement unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0062] The NG line measurement unit can analyze the user's past viewing history to select the optimal measurement method when measuring the NG line. For example, the NG line measurement unit can provide the optimal measurement method based on the user's past viewing history of horror movies. The NG line measurement unit can also provide the optimal measurement method based on the user's past viewing history of dramas. The NG line measurement unit can also provide the optimal measurement method based on the user's past viewing history of anime. By providing the optimal measurement method based on past viewing history, the accuracy of NG line measurement is improved. Some or all of the above processing in the NG line measurement unit may be performed using AI, for example, or without AI. For example, the NG line measurement unit can input the user's past viewing history data into a generating AI and have the generating AI select the optimal measurement method.

[0063] The NG line measurement unit can improve the accuracy of NG line measurement based on the user's current psychological state. For example, if the user is tense, the NG line measurement unit can perform the measurement in a relaxing environment. For example, if the user is relaxed, the NG line measurement unit can also perform a detailed measurement. For example, if the user is in a hurry, the NG line measurement unit can also perform a concise measurement. This improves the accuracy of NG line measurement by performing measurements according to the user's psychological state. Estimation of the psychological state is achieved using an emotion estimation function, for example, using 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 NG line measurement unit may be performed using AI, for example, or without AI. For example, the NG line measurement unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's psychological state.

[0064] The loading unit can estimate the user's emotions and adjust how movies and dramas are loaded based on the estimated emotions. For example, if the user is tense, the loading unit will prioritize loading relaxing movies and dramas. If the user is relaxed, the loading unit may also prioritize loading detailed movies and dramas. If the user is in a hurry, the loading unit may also prioritize loading concise movies and dramas. This allows for more appropriate movie and drama loading by providing a loading method that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 loading unit may be performed using AI or not using AI. For example, the loading unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0065] The loading unit can analyze the user's past viewing history and select the optimal loading method during loading. For example, the loading unit can provide the optimal loading method based on the user's history of watching horror movies. For example, the loading unit can also provide the optimal loading method based on the user's history of watching dramas. For example, the loading unit can also provide the optimal loading method based on the user's history of watching anime. This improves the accuracy of loading movies and dramas by providing the optimal loading method based on past viewing history. Some or all of the above processing in the loading unit may be performed using AI, for example, or without AI. For example, the loading unit can input the user's past viewing history data into a generating AI and have the generating AI select the optimal loading method.

[0066] The scene detection unit can estimate the user's emotions and adjust the scene detection criteria based on the estimated emotions. For example, if the user is tense, the scene detection unit may prioritize detecting relaxing scenes. For example, if the user is relaxed, the scene detection unit may also prioritize detecting detailed scenes. For example, if the user is in a hurry, the scene detection unit may also prioritize detecting concise scenes. This enables more appropriate scene detection by providing scene detection criteria that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 scene detection unit may be performed using AI, for example, or without AI. For example, the scene detection unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0067] The scene detection unit can apply different detection algorithms depending on the genre of the film or drama during scene detection. For example, in the case of a horror film, the scene detection unit may prioritize detecting scary scenes. In the case of a drama, for example, the scene detection unit may prioritize detecting emotional scenes. In the case of an anime, for example, the scene detection unit may prioritize detecting action scenes. By applying a detection algorithm appropriate to the genre, the accuracy of scene detection is improved. Some or all of the above processing in the scene detection unit may be performed using AI, for example, or without AI. For example, the scene detection unit can input genre data of the film or drama into a generating AI and have the generating AI select the optimal detection algorithm.

[0068] The transformation unit can estimate the user's emotions and adjust the style of the transformed video based on the estimated emotions. For example, if the user is tense, the transformation unit can transform the video into a relaxing style. For example, if the user is relaxed, the transformation unit can also transform the video into a detailed style. For example, if the user is in a hurry, the transformation unit can also transform the video into a concise style. This allows for more appropriate video transformation by providing a video style that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 transformation unit may be performed using AI, for example, or without AI. For example, the transformation unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0069] The conversion unit can apply different conversion algorithms depending on the genre of the movie or drama during the conversion process. For example, in the case of a horror movie, the conversion unit can convert scary scenes into cute images. In the case of a drama, for example, the conversion unit can convert emotional scenes into cute images. In the case of an anime, for example, the conversion unit can convert action scenes into cute images. By applying a conversion algorithm appropriate to the genre, the accuracy of the video conversion is improved. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input movie and drama genre data into a generating AI and have the generating AI select the optimal conversion algorithm.

[0070] The commentary generation unit can estimate the user's emotions and adjust the tone of the commentary audio based on the estimated emotions. For example, if the user is tense, the commentary generation unit can generate commentary audio in a relaxing tone. For example, if the user is relaxed, the commentary generation unit can also generate commentary audio in a detailed tone. For example, if the user is in a hurry, the commentary generation unit can also generate commentary audio in a concise tone. This enables more appropriate commentary by providing commentary audio tones that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 commentary generation unit may be performed using AI, for example, or without AI. For example, the commentary generation unit can input user facial expression data into the generation AI and have the generation AI perform the estimation of the user's emotions.

[0071] The commentary generation unit can apply different commentary algorithms depending on the genre of the movie or drama when generating commentary. For example, in the case of a horror movie, the commentary generation unit can convert scary scenes into cute commentary voices. For example, in the case of a drama, the commentary generation unit can convert emotional scenes into cute commentary voices. For example, in the case of an anime, the commentary generation unit can convert action scenes into cute commentary voices. By applying a commentary algorithm appropriate to the genre, the accuracy of the commentary is improved. Some or all of the above processing in the commentary generation unit may be performed using AI, for example, or without using AI. For example, the commentary generation unit can input movie or drama genre data into a generation AI and have the generation AI select the optimal commentary algorithm.

[0072] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0073] The Horror & Gore Bye-Bye software analyzes a user's viewing history and can select the optimal conversion algorithm based on the genres of movies and dramas the user has watched in the past. For example, if a user has watched many horror movies in the past, the conversion algorithm for horror scenes can be enhanced. Similarly, if a user has watched many dramas in the past, the conversion algorithm for emotional scenes can be enhanced. Furthermore, if a user has watched many anime in the past, the conversion algorithm for action scenes can be enhanced. This allows for more appropriate video conversion by providing the optimal conversion algorithm based on the user's viewing history. The analysis of viewing history may be performed using AI or without AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the optimal conversion algorithm.

[0074] The Horror & Gore Bye-Bye software can estimate the user's emotions and transform movie and drama scenes in real time based on those emotions. For example, if the user is tense, it can transform the scene into a relaxing one. If the user is relaxed, it can transform the scene into a more detailed one. Furthermore, if the user is in a hurry, it can transform the scene into a more concise one. This allows for a more appropriate viewing experience by providing scene transformations that match the user'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 scene transformation may be performed using AI, or not using AI. For example, user facial expression data can be input into a generative AI, and the generative AI can be made to estimate the user's emotions.

[0075] The Horror & Gore Bye-Bye software can automatically select characters that the user likes based on their viewing history and reflect them in the converted video. For example, it can include characters from anime the user has watched in the past in the converted video. It can also include characters from dramas the user has watched in the past in the converted video. Furthermore, it can include characters from movies the user has watched in the past in the converted video. This makes it possible to create more relatable video conversions by providing the most suitable characters based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without using AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the most suitable characters.

[0076] The horror & gore-removing software can estimate the user's emotions and adjust the color tone of the converted video based on those emotions. For example, if the user is tense, the color tone can be converted to a relaxing one. If the user is relaxed, the color tone can be converted to a more detailed one. Furthermore, if the user is in a hurry, the color tone can be converted to a more concise one. This allows for more appropriate video conversion by providing a color tone that matches the user'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. Color tone adjustment may be performed using AI or not. For example, user facial expression data can be input into a generative AI, and the generative AI can be made to estimate the user's emotions.

[0077] The Horror & Gore Bye-Bye software can automatically select music that a user likes based on their viewing history and reflect it in the converted video. For example, it can use the soundtracks of movies the user has watched in the past in the converted video. It can also use the soundtracks of dramas the user has watched in the past in the converted video. Furthermore, it can use the soundtracks of anime the user has watched in the past in the converted video. This makes it possible to create more user-friendly video conversions by providing the most suitable music based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without using AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the most suitable music.

[0078] The horror & gore-reducing software can estimate the user's emotions and adjust the speed of the converted video based on those emotions. For example, if the user is tense, the video speed can be slowed down to help them relax. If the user is relaxed, the video speed can be returned to normal so they can enjoy the detailed scenes. Furthermore, if the user is in a hurry, the video speed can be sped up so they can quickly grasp the scene. This allows for a more appropriate viewing experience by providing video speeds that match the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AIs include, but are not limited to, text generation AIs (e.g., LLM) or multimodal generation AIs. Adjusting the video speed may be done using AI or not. For example, user facial expression data can be input into a generative AI, and the generative AI can be made to estimate the user's emotions.

[0079] The Horror & Gore Bye-Bye software can automatically select a narration style preferred by the user based on their viewing history and reflect it in the converted video. For example, it can use the narration style of movies the user has watched in the past in the converted video. It can also use the narration style of dramas the user has watched in the past in the converted video. Furthermore, it can use the narration style of anime the user has watched in the past in the converted video. This makes it possible to create more user-friendly video conversions by providing the optimal narration style based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without using AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the optimal narration style.

[0080] The horror & gore-reducing software can estimate the user's emotions and adjust the volume of the converted video based on those emotions. For example, if the user is tense, the volume can be lowered to help them relax. If the user is relaxed, the volume can be set to normal so they can enjoy the detailed scenes. Furthermore, if the user is in a hurry, the volume can be increased so they can quickly grasp the scene. This allows for a more appropriate viewing experience by providing volume levels that match the user'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. Volume adjustment may be performed using AI or not. For example, user facial expression data can be input into a generative AI, and the generative AI can be used to estimate the user's emotions.

[0081] The Horror & Gore Bye-Bye software can automatically select a user's preferred subtitle style based on their viewing history and apply it to the converted video. For example, it can use the subtitle style of movies the user has watched in the past. It can also use the subtitle style of dramas the user has watched in the past. Furthermore, it can use the subtitle style of anime the user has watched in the past. This allows for more user-friendly video conversion by providing the optimal subtitle style based on the user's viewing history. The analysis of viewing history may be performed using AI, or it may be performed without AI. For example, viewing history data can be input into a generating AI, and the generating AI can be made to select the optimal subtitle style.

[0082] The horror & gore removal software can estimate the user's emotions and adjust the effects of the converted video based on those emotions. For example, if the user is tense, a relaxing effect can be added. If the user is relaxed, a more detailed effect can be added. Furthermore, if the user is in a hurry, a concise effect can be added. This allows for more appropriate video conversion by providing effects that match the user'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. Effect adjustment may be performed using AI or not. For example, user facial expression data can be input into a generative AI, and the generative AI can be made to estimate the user's emotions.

[0083] The following briefly describes the processing flow for example form 2.

[0084] Step 1: The survey reception unit receives user surveys. For example, surveys can be received through a survey form displayed when the user launches the software, a website, or a mobile application. Step 2: The NG line measurement unit measures the NG line based on the questionnaires received by the questionnaire reception unit. For example, it analyzes the content of the questionnaire responses to determine the user's horror / gore NG line. It can also use AI for analysis or predict the NG line based on past questionnaire data. Step 3: The loading unit loads the movies or TV shows the user wants to watch. For example, it can load movies or TV shows specified by the user from files, streaming services, or DVDs and Blu-ray discs. Step 4: The scene detection unit analyzes the movie or drama scenes loaded by the loading unit and detects horror or grotesque scenes. For example, scenes can be detected using video analysis technology, AI, or audio analysis technology. Step 5: The conversion unit converts the scene detected by the scene detection unit into a cute video. For example, it can use video conversion technology or AI for the conversion, and it can also use a cute character selected by the user. Step 6: The commentary generation unit generates commentary audio based on the scene converted by the conversion unit. For example, it is possible to generate commentary audio using speech synthesis technology or AI, and use the voice of a voice actor selected by the user.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] Each of the multiple elements described above, including the survey reception unit, NG line measurement unit, reading unit, scene detection unit, conversion unit, and live commentary generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the survey reception unit is implemented by the control unit 46A of the smart device 14, enabling the user to answer the survey using a smartphone. The NG line measurement unit is implemented by the specific processing unit 290 of the data processing unit 12, analyzing the content of the survey responses and measuring the user's horror / grotesque NG line. The reading unit is implemented by the control unit 46A of the smart device 14, loading movie or drama files specified by the user. The scene detection unit is implemented by the specific processing unit 290 of the data processing unit 12, detecting horror or grotesque scenes using video analysis technology. The conversion unit is implemented by the control unit 46A of the smart device 14, converting horror or grotesque scenes into cute videos. The commentary generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates commentary audio using speech synthesis technology. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0089] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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).

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.).

[0101] 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.

[0102] 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.

[0103] 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.

[0104] Each of the multiple elements described above, including the survey reception unit, NG line measurement unit, reading unit, scene detection unit, conversion unit, and live commentary generation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the survey reception unit is implemented by the control unit 46A of the smart glasses 214, enabling the user to answer the survey using a smartphone. The NG line measurement unit is implemented by the specific processing unit 290 of the data processing unit 12, analyzing the content of the survey answers and measuring the user's horror / grotesque NG line. The reading unit is implemented by the control unit 46A of the smart glasses 214, loading movie or drama files specified by the user. The scene detection unit is implemented by the specific processing unit 290 of the data processing unit 12, detecting horror or grotesque scenes using video analysis technology. The conversion unit is implemented by the control unit 46A of the smart glasses 214, converting horror or grotesque scenes into cute images. The commentary generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates commentary audio using speech synthesis technology. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0105] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] Each of the multiple elements described above, including the survey reception unit, NG line measurement unit, reading unit, scene detection unit, conversion unit, and live commentary generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the survey reception unit is implemented by the control unit 46A of the headset terminal 314, enabling the user to answer the survey using a smartphone. The NG line measurement unit is implemented by the specific processing unit 290 of the data processing unit 12, analyzing the content of the survey responses and measuring the user's horror / grotesque NG line. The reading unit is implemented by the control unit 46A of the headset terminal 314, loading movie or drama files specified by the user. The scene detection unit is implemented by the specific processing unit 290 of the data processing unit 12, detecting horror or grotesque scenes using video analysis technology. The conversion unit is implemented by the control unit 46A of the headset terminal 314, converting horror or grotesque scenes into cute videos. The commentary generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates commentary audio using speech synthesis technology. 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] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0122] 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.

[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 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.

[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 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).

[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] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] Each of the multiple elements described above, including the questionnaire reception unit, NG line measurement unit, reading unit, scene detection unit, conversion unit, and live commentary generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the questionnaire reception unit is implemented by the control unit 46A of the robot 414, enabling the user to answer the questionnaire using a smartphone. The NG line measurement unit is implemented by the specific processing unit 290 of the data processing unit 12, for example, analyzing the content of the questionnaire responses and measuring the user's horror / grotesque NG line. The reading unit is implemented by the control unit 46A of the robot 414, for example, reading movie or drama files specified by the user. The scene detection unit is implemented by the specific processing unit 290 of the data processing unit 12, for example, detecting horror or grotesque scenes using video analysis technology. The conversion unit is implemented by the control unit 46A of the robot 414, for example, converting horror or grotesque scenes into cute videos. The commentary generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates commentary audio using speech synthesis technology. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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."

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] (Note 1) The survey reception department accepts user surveys, An NG line measurement unit that measures the NG line based on the questionnaire received by the aforementioned questionnaire reception unit, A loading unit that loads movies and dramas, A scene detection unit analyzes movie and drama scenes read by the aforementioned reading unit and detects horror and grotesque scenes, A conversion unit that converts the scene detected by the scene detection unit into a cute video, The system includes a commentary generation unit that generates commentary audio based on the scene converted by the conversion unit. A system characterized by the following features. (Note 2) The aforementioned questionnaire reception department, The system estimates the user's emotions and adjusts the survey questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned questionnaire reception department, Analyze the user's past survey response history to select the most suitable question format. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned questionnaire reception department, When submitting a survey, the order of questions is adjusted based on the user's current psychological state. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned NG line measurement unit is The system estimates the user's emotions and adjusts the measurement method for the "NG" line based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned NG line measurement unit is When measuring the NG line, the system analyzes the user's past viewing history to select the optimal measurement method. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned NG line measurement unit is When measuring the NG line, the accuracy of the measurement is improved based on the user's current psychological state. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reading unit, It estimates the user's emotions and adjusts how movies and TV shows are loaded based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reading unit, During loading, the system analyzes the user's past viewing history to select the optimal loading method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned scene detection unit, It estimates the user's emotions and adjusts the scene detection criteria based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned scene detection unit, When detecting a scene, different detection algorithms are applied depending on the genre of the movie or drama. The system described in Appendix 1, characterized by the features described herein. (Note 12) The conversion unit is It estimates the user's emotions and adjusts the style of the video based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The conversion unit is During conversion, different conversion algorithms are applied depending on the genre of the movie or TV show. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned live commentary generation unit, It estimates the user's emotions and adjusts the tone of the commentary audio based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned live commentary generation unit, When generating commentary, different commentary algorithms are applied depending on the genre of the movie or drama. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0157] 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. The survey reception department accepts user surveys, An NG line measurement unit that measures the NG line based on the questionnaire received by the aforementioned questionnaire reception unit, A loading unit that loads movies and dramas, A scene detection unit analyzes movie and drama scenes read by the aforementioned reading unit and detects horror and grotesque scenes, A conversion unit that converts the scene detected by the scene detection unit into a cute video, The system includes a commentary generation unit that generates commentary audio based on the scene converted by the conversion unit. A system characterized by the following features.

2. The aforementioned questionnaire reception department, The system estimates the user's emotions and adjusts the survey questions based on those estimated emotions. The system according to feature 1.

3. The aforementioned questionnaire reception department, Analyze the user's past survey response history to select the most suitable question format. The system according to feature 1.

4. The aforementioned questionnaire reception department, When submitting a survey, the order of questions is adjusted based on the user's current psychological state. The system according to feature 1.

5. The aforementioned NG line measurement unit is The system estimates the user's emotions and adjusts the measurement method for the "NG" line based on those estimated emotions. The system according to feature 1.

6. The aforementioned NG line measurement unit is When measuring the NG line, the system analyzes the user's past viewing history to select the optimal measurement method. The system according to feature 1.

7. The aforementioned NG line measurement unit is When measuring the NG line, the accuracy of the measurement is improved based on the user's current psychological state. The system according to feature 1.

8. The aforementioned reading unit, It estimates the user's emotions and adjusts how movies and TV shows are loaded based on those estimated emotions. The system according to feature 1.

9. The aforementioned reading unit, During loading, the system analyzes the user's past viewing history to select the optimal loading method. The system according to feature 1.

10. The aforementioned scene detection unit, It estimates the user's emotions and adjusts the scene detection criteria based on the estimated emotions. The system according to feature 1.

Images