System

Abstract

To provide a system according to embodiments for expanding a story through a conversation with a character in a moving image content, for providing a new entertainment experience to a user.SOLUTION: A system according to embodiments comprises: a reception part; an acquisition part; a conversation part; a content expansion part; and a provision part. The reception part receives selection of a character in a moving image content. The acquisition part acquires information of the character whose selection is received by the reception part. The conversation part performs a conversation between the character and a user on the basis of the information acquired by the acquisition part. The content expansion part creates a moving image content including an additional episode of the character, on the basis of a conversation result by the conversation part. The provision part provides the created moving image content created by the content expansion part to a user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies do not adequately support character dialogue or expand the story of video content, and there is room for improvement.

[0005] The system according to the embodiment aims to expand the story and provide the user with a new entertainment experience through interaction with characters in video content. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an acquisition unit, a dialogue unit, a content expansion unit, and a provision unit. The reception unit accepts a selection of a character for video content. The acquisition unit acquires information on the character whose selection is accepted by the reception unit. The dialogue unit conducts a dialogue between the character and a user based on the information acquired by the acquisition unit. The content expansion unit generates video content including additional episodes for the character based on a dialogue result by the dialogue unit. The provision unit provides the video content generated by the content expansion unit to a user. Effect of the Invention

[0007] The system according to the embodiment can expand the story through interaction with characters in video content, providing the user with a new entertainment experience. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

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

[0028] (Example 1) The system according to the embodiment of the present invention is an AI assistant that provides conversational content with characters from television programs and movies. The AI ​​assistant allows users to select their favorite characters and enjoy conversations with the characters. The conversations are generated based on the characters' lines and personalities, providing the user with a realistic conversation experience. It is also possible to expand the original story, such as the character's background and future predictions. In addition, a virtual interview experience is provided in which the character responds to an interview in the real world. The user can ask the character questions about movies and television programs and receive answers from the character's perspective. Educational content is also provided, allowing users to learn about topics such as history, science, and literature while interacting with the characters. Entertainment elements are also included, allowing users to play games with the characters and hear jokes from the characters. For example, the user can select a favorite character and enjoy conversations with the character. The conversations are generated based on the characters' lines and personalities, providing the user with a realistic conversation experience. It is also possible to expand the original story, such as the character's background and future predictions. In addition, a virtual interview experience is provided in which the character responds to an interview in the real world. Users can ask the character questions about movies and TV shows and get answers from the character's perspective. Educational content is also provided, allowing users to learn about topics such as history, science, and literature while interacting with the character. Entertainment elements are also included, allowing users to play games with the character and hear jokes from the character. This allows the AI ​​assistant to provide a diverse range of entertainment and educational experiences for users.

[0029] The AI ​​assistant system according to the embodiment includes a reception unit, an acquisition unit, a dialogue unit, a content extension unit, and a provision unit. The reception unit accepts a character selected by a user. For example, the user can select a favorite character by clicking, tapping, voice input, or the like. The acquisition unit acquires information on the character selected by the reception unit. For example, the character's lines, personality, background information, and the like are acquired. The dialogue unit has a dialogue between the character and the user based on the information acquired by the acquisition unit. For example, the dialogue unit generates a response based on the character's lines and personality using a generation AI. The content extension unit generates video content including a new episode of the character based on the dialogue result by the dialogue unit. For example, the content extension unit generates a new episode including the character's background, future predictions, and the like using a generation AI. The provision unit provides the video content generated by the content extension unit to the user. For example, the provision unit delivers the generated video content to the user's device. As a result, the AI ​​assistant system according to the embodiment can generate and provide video content including a new episode through a dialogue with the character selected by the user.

[0030] The reception unit receives the character selected by the user. For example, the user can select a favorite character by clicking, tapping, or voice input. Specifically, the user interface is designed to be intuitive and easy to use, and displays a list of character images and names. The user can select a character using a mouse or touch screen, or can select a character by voice input using voice recognition technology. In the case of voice input, when the user speaks the name of a character, the system analyzes the voice using a voice recognition engine and identifies the corresponding character. Furthermore, the reception unit also has a function of recording the user's selection history and preferentially displaying characters previously selected by the user the next time the system is used. This allows the user to smoothly select a favorite character, improving convenience.

[0031] The acquisition unit acquires information on the character selected by the reception unit. For example, the character's lines, personality, background information, etc. are acquired. Specifically, the acquisition unit accesses a database and acquires detailed information related to the selected character. The character's lines are extracted from past dialogue logs and official dialogue collections, and the personality and background information are acquired from the character's setting materials and official website. Furthermore, the acquisition unit can also acquire the latest information and update information on the character. For example, when a new episode or event is added, the information is also acquired in real time and provided to the dialogue unit and the content expansion unit. In this way, the acquisition unit can always grasp the details of the character based on the latest information and provide the user with a consistent experience.

[0032] The dialogue unit conducts a dialogue between the character and the user based on the information acquired by the acquisition unit. For example, the dialogue unit uses a generation AI to generate a response based on the character's lines and personality. Specifically, the dialogue unit uses natural language processing technology to analyze the user's input and generate an appropriate response. The generation AI takes into account the character's personality and background information and conducts a natural dialogue in response to the user's questions and comments. For example, when a user asks a character, "How was your day?", the generation AI generates a response such as, "I had a lot of fun today! I went on a new adventure" based on the character's personality and past episodes. The dialogue unit can also analyze the user's emotions and tone and generate a response accordingly. This allows the dialogue unit to make the dialogue with the user more natural and attractive, thereby increasing the user's satisfaction.

[0033] The content extension unit generates video content including a new episode of the character based on the dialogue result by the dialogue unit. For example, a new episode including the character's background and future predictions is generated using a generation AI. Specifically, the content extension unit analyzes the dialogue content in the dialogue unit and generates episodes and scenarios that the user is likely to be interested in. The generation AI creates a new storyline taking into account the character's settings and past episodes. For example, when a user asks a character, "Where will you go on your next adventure?", the generation AI generates a new adventure scenario based on the character's personality and past adventures, and creates video content based on the scenario. Furthermore, the content extension unit generates the character's voice for the generated episode using voice synthesis technology, and creates a visually appealing video using video editing technology. As a result, the content extension unit can provide the user with high-quality video content including new episodes.

[0034] The providing unit provides the video content generated by the content extension unit to the user. For example, the providing unit distributes the generated video content to the user's device. Specifically, the providing unit distributes the video content in a format optimized for the user's device, allowing the user to view the content smoothly. The providing unit can distribute the video in real time using streaming technology, and the user can instantly view the video through an Internet connection. The providing unit can also analyze the user's viewing history and preferences to provide individually customized content. For example, if the user likes a particular character or episode, new video content related to the character or episode is preferentially provided. Furthermore, the providing unit can collect feedback from the user and continuously improve the quality of the content and the method of providing the content. As a result, the providing unit can always provide the latest and attractive content to the user, thereby increasing the user's satisfaction.

[0035] The system includes an interview information generating unit that generates information on a simulated interview of a character, and the providing unit provides the information on the simulated interview to a user. The interview information generating unit generates interview content based on, for example, a question input by a user. For example, a user inputs a question to a character, and generates an answer from the character to the question. The providing unit provides the generated interview content to a user. For example, the providing unit delivers the generated interview content to a device of the user. This allows the user to enjoy a virtual interview of the character. A part or all of the above-mentioned processing in the interview information generating unit may be performed using AI, or may be performed without using AI. For example, the interview information generating unit inputs a question input by a user to a generating AI, and the generating AI can generate interview content.

[0036] The system includes an answer generation unit that generates an answer from the character's viewpoint to a question about video content, and the providing unit provides the answer to the user. For example, the answer generation unit inputs a question about video content by the user, and generates an answer from the character's viewpoint to the question. For example, the user asks the character, "What is the background of this scene?", and the character generates an answer to the question. The providing unit provides the generated answer to the user. For example, the providing unit delivers the generated answer to the user's device. This allows the user to obtain the answer from the character's viewpoint. A part or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit inputs a question input by the user to a generation AI, and the generation AI can generate an answer from the character's viewpoint.

[0037] The system includes an entertainment unit that provides a game to be played together with a character and provides jokes from the character. The entertainment unit, for example, provides a game to be played by a user together with a character. For example, the user can enjoy a puzzle game or an action game together with the character. The entertainment unit can also provide jokes from the character. For example, the character tells a humorous joke to the user. This allows the user to enjoy the game together with the character and to hear the joke. A part or all of the above-mentioned processing in the entertainment unit may be performed using an AI or may be performed without using an AI. For example, the entertainment unit can input the progress of the game and the user's reaction to the generation AI, and the generation AI can generate the next step of the game and jokes.

[0038] The content extension unit can generate video content including new episodes related to the character's background and future. The content extension unit generates new episodes based on, for example, the character's background and predictions for the future. For example, it generates episodes related to the character's past events and future goals. This allows the user to enjoy new episodes related to the character's background and future. Some or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit can input background information of the character to the generation AI, which can generate new episodes.

[0039] The content extension unit can generate video content using a video generation AI. For example, the content extension unit generates video content including a new episode of a character using a video generation AI. The video generation AI generates videos using technologies such as deep learning and generative adversarial network (GAN). As a result, the use of the video generation AI makes it possible to generate video content more efficiently. For example, the content extension unit inputs background information and dialogue results of a character into the video generation AI, which then generates video content including a new episode. This allows users to enjoy high-quality video content.

[0040] The interview information generation unit can generate interview content based on a question input by the user. The interview information generation unit generates interview content for a character based on a question input by the user, for example. For example, the user asks the character, "What is your favorite food?", and the character generates an answer to the question. This allows the user to enjoy an interview with the character. Some or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit can input a question input by the user to a generation AI, and the generation AI can generate interview content.

[0041] The content extension unit can generate video content including a new episode based on the geographical information of the user. The content extension unit generates a new episode for a character based on the geographical information of the user, for example. For example, when the user is in a specific area, an episode related to the area is generated. This allows the user to enjoy a new episode based on his / her geographical information. A part or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit can input the geographical information of the user to a generation AI, which can generate a new episode.

[0042] The dialogue unit can change the theme of the dialogue based on a specific keyword specified by the user. For example, if the user specifies the keyword "adventure", the dialogue unit changes the theme of the dialogue with the character to adventure. This allows the user to enjoy dialogue with the character on a theme that suits his or her interests. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input a keyword specified by the user to the generation AI, which then changes the theme of the dialogue.

[0043] The reception unit receives a change in the character's setting or background during a dialogue with the user, and the content extension unit can generate video content based on the change. The reception unit, for example, receives a request from the user to change the character's setting or background during a dialogue. For example, the user can make a request to change the character's personality, appearance, or background setting. The content extension unit generates a new episode based on the change in the setting or background received by the reception unit. For example, if the user changes the character's personality, a new episode is generated based on the change. This allows the user to change the character's setting or background during a dialogue and enjoy a new episode based on the change. A part or all of the above-mentioned processing in the reception unit and the content extension unit may be performed using AI, or may be performed without using AI. For example, the reception unit inputs the user's request to a generation AI, and the generation AI can generate a new episode that reflects the change in the setting or background.

[0044] The reception unit can analyze the user's past selection history and recommend the most suitable character. For example, the genre, personality, and movie or TV program series of a character previously selected by the user are analyzed, and a character of the same genre, personality, and series is recommended. This makes it possible to recommend the most suitable character based on the user's past selection history. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's past selection history to a generation AI, which can then recommend the most suitable character.

[0045] The reception unit can perform filtering based on the user's current interests and concerns when selecting a character. The reception unit, for example, filters characters based on the user's current interests and concerns. For example, the reception unit filters characters based on the genre of movies the user has recently watched, the theme of books the user has read, and the content of events the user has participated in. This makes it possible to filter characters based on the user's current interests and concerns. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's current interests and concerns to the generation AI, and the generation AI can filter the most suitable character.

[0046] When selecting a character, the reception unit can preferentially present a highly relevant character in consideration of the user's geographical location information. The reception unit, for example, selects a character based on the user's geographical location information. For example, when the user is in a specific area, characters from movies and TV programs related to that area are presented. When the user is traveling, characters related to the travel destination are presented. This makes it possible to preferentially present a highly relevant character based on the user's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to a generation AI, which can select a highly relevant character.

[0047] The reception unit can analyze the user's social media activity and recommend related characters when selecting a character. The reception unit, for example, analyzes the user's social media activity and recommends related characters. For example, characters from movies and TV shows that the user follows on social media are recommended. Characters related to posts that the user has "liked" on social media are recommended. This makes it possible to recommend related characters based on the user's social media activity. Some or all of the above-mentioned processing in the reception unit may be performed using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity to the generation AI, which can then recommend related characters.

[0048] The acquisition unit can analyze the user's past dialogue history and select the optimal acquisition method. For example, the acquisition unit preferentially acquires information on characters with whom the user has previously interacted. The acquisition unit preferentially acquires information on characters in which the user has previously shown interest. This allows the optimal acquisition method to be selected based on the user's past dialogue history. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the user's past dialogue history to a generation AI, which can select the optimal acquisition method.

[0049] The acquisition unit can perform filtering based on the user's current interests and concerns when acquiring the character information. The acquisition unit, for example, filters the character information based on the user's current interests and concerns. For example, the character information is filtered based on the genre of a movie the user has recently watched, the theme of a book the user has read, or the content of an event the user has participated in. This makes it possible to filter the character information based on the user's current interests and concerns. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the user's current interests and concerns to the generation AI, and the generation AI can filter the optimal character information.

[0050] When acquiring character information, the acquisition unit can preferentially acquire highly relevant information in consideration of the geographical location information of the user. The acquisition unit acquires character information based on, for example, the geographical location information of the user. For example, when the user is in a specific area, character information of movies and TV programs related to the area is acquired. When the user is traveling, character information related to the travel destination is acquired. This makes it possible to preferentially acquire highly relevant character information based on the geographical location information of the user. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the geographical location information of the user to the generation AI, and the generation AI can acquire highly relevant character information.

[0051] The acquisition unit can analyze the user's social media activity and acquire related information when acquiring the character information. The acquisition unit, for example, analyzes the user's social media activity and acquires related character information. For example, character information of movies and TV programs that the user follows on social media is acquired. Character information related to posts that the user "liked" on social media is acquired. This makes it possible to acquire related character information based on the user's social media activity. Some or all of the above-mentioned processing in the acquisition unit may be performed using AI or may be performed without using AI. For example, the acquisition unit can input the user's social media activity to the generation AI, and the generation AI can acquire related character information.

[0052] The dialogue unit can adjust the level of detail of the dialogue based on the importance of the character during the dialogue. For example, detailed information is provided in the dialogue with the main character, and concise information is provided in the dialogue with the sub-character. This allows the level of detail of the dialogue to be adjusted based on the importance of the character. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the importance of the character to the generation AI, and the generation AI can adjust the level of detail of the dialogue.

[0053] The dialogue unit can apply different dialogue algorithms depending on the character category during dialogue. For example, a dialogue algorithm related to action is applied to a dialogue with a character in an action movie, and a dialogue algorithm related to humor is applied to a dialogue with a character in a comedy movie. This makes it possible to apply an optimal dialogue algorithm depending on the character category. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input the character category to a generation AI, which can then apply an optimal dialogue algorithm.

[0054] During dialogue, the dialogue unit can determine the priority of dialogue based on the appearance time of the character. For example, dialogue with characters from the latest movies and TV shows is prioritized, and dialogue with characters from popular past movies and TV shows is prioritized. This allows the priority of dialogue to be determined based on the appearance time of the character. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the appearance time of the character to the generation AI, and the generation AI can determine the priority of dialogue.

[0055] The dialogue unit can adjust the order of dialogue based on the relevance of the characters during dialogue. For example, it prioritizes dialogue with other characters related to the character selected by the user. It prioritizes dialogue with characters from the same movie or TV program. It prioritizes dialogue with characters from the same genre. This makes it possible to adjust the order of dialogue based on the relevance of the characters. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input the relevance of the characters to the generation AI, and the generation AI can adjust the order of dialogue.

[0056] The content expansion unit can analyze the character's past episodes and select the optimal expansion method when expanding the content. For example, the content expansion unit analyzes the character's past events, behavior patterns, and relationships, and generates new episodes based on the results. This allows the character's past episodes to be analyzed and the optimal expansion method to be selected. Some or all of the above-mentioned processing in the content expansion unit may be performed using AI, or may be performed without using AI. For example, the content expansion unit can input the character's past episodes to a generation AI, and the generation AI can select the optimal expansion method.

[0057] The content extension unit can customize the episode based on the character's current settings during content extension. The content extension unit generates a new episode based on the character's current occupation, role, relationship, situation, and environment, for example. For example, a new episode is generated based on the character's current occupation. This allows the episode to be customized based on the character's current settings. Some or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit inputs the character's current settings to the generation AI, and the generation AI can customize the episode.

[0058] The content extension unit can generate an optimal episode in consideration of the geographical location information of the user when expanding the content. The content extension unit generates an episode based on the geographical location information of the user, for example. For example, when the user is in a specific area, an episode related to the area is generated. When the user is traveling, an episode related to the travel destination is generated. In this way, it is possible to generate an optimal episode based on the geographical location information of the user. A part or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit inputs the geographical location information of the user to a generation AI, which can generate an optimal episode.

[0059] The content extension unit can analyze the user's social media activity and suggest episodes during content extension. The content extension unit, for example, analyzes the user's social media activity and generates related episodes. For example, it generates episodes related to movies and TV programs that the user follows on social media. It generates episodes related to posts that the user "likes" on social media. This makes it possible to suggest episodes based on the user's social media activity. Some or all of the above-mentioned processing in the content extension unit may be performed using AI or may be performed without using AI. For example, the content extension unit can input the user's social media activity into a generation AI, which generates related episodes.

[0060] When providing content, the providing unit can select the optimal providing method by referring to the user's past viewing history. For example, the providing method is selected based on the genre, length, and viewing time period of the content viewed by the user in the past. This makes it possible to select the optimal providing method based on the user's past viewing history. A part or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the user's past viewing history to the generating AI, which can select the optimal providing method.

[0061] The providing unit can select the optimal providing method in consideration of the user's device information when providing content. For example, if the user is using a smartphone, a providing method suited to the screen size is selected. If the user is using a tablet, a providing method optimized for a large screen is selected. This makes it possible to select the optimal providing method based on the user's device information. Some or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the user's device information to the generating AI, which can select the optimal providing method.

[0062] When generating interview information, the interview information generation unit can generate optimal interview content by referring to the user's past question history. For example, related questions are generated based on content that the user has asked in the past. Questions are generated based on topics that the user has shown interest in in the past. This makes it possible to generate optimal interview content based on the user's past question history. Some or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit can input the user's past question history into a generation AI, which can generate optimal interview content.

[0063] The interview information generation unit can generate optimal interview content in consideration of the user's geographical location information when generating interview information. The interview information generation unit generates interview content based on the user's geographical location information, for example. For example, when the user is in a specific area, the interview information generation unit generates interview content related to the area. When the user is traveling, the interview information generation unit generates interview content related to the travel destination. This makes it possible to generate optimal interview content based on the user's geographical location information. A part or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit inputs the user's geographical location information to a generation AI, which can generate optimal interview content.

[0064] The answer generation unit can adjust the level of detail of the answer based on the importance of the question when generating an answer. For example, a detailed answer is provided for an important question, and a concise answer is provided for a general question. This makes it possible to adjust the level of detail of the answer based on the importance of the question. A part or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit can input the importance of the question to the generation AI, and the generation AI can adjust the level of detail of the answer.

[0065] The answer generation unit can determine the priority of answers based on the time of question submission when generating answers. For example, the most recent question is given priority in answering. Important questions are given priority in answering. This makes it possible to determine the priority of answers based on the time of question submission. Some or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit can input the time of question submission to the generation AI, and the generation AI can determine the priority of answers.

[0066] When providing entertainment, the entertainment unit can select the optimal providing method by referring to the user's past entertainment history. For example, the providing method is selected based on the genre of games or types of jokes that the user has enjoyed in the past, and the length of entertainment. In this way, the optimal providing method can be selected based on the user's past entertainment history. Some or all of the above-mentioned processing in the entertainment unit may be performed using AI, or may be performed without using AI. For example, the entertainment unit can input the user's past entertainment history to a generation AI, which can select the optimal providing method.

[0067] When providing entertainment, the entertainment unit can select the optimal providing method in consideration of the geographical location information of the user. The entertainment unit provides entertainment, for example, based on the geographical location information of the user. For example, when the user is in a specific area, entertainment related to the area is provided. When the user is traveling, entertainment related to the travel destination is provided. In this way, optimal entertainment can be provided based on the geographical location information of the user. Some or all of the above-mentioned processing in the entertainment unit may be performed using AI, or may be performed without using AI. For example, the entertainment unit inputs the geographical location information of the user to a generation AI, which can provide optimal entertainment.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The reception unit can analyze the user's past dialogue history and recommend the most suitable character. For example, the genre and personality of a character with whom the user has previously interacted, and the series of a movie or television program are analyzed, and a character of the same genre, personality, and series is recommended. This makes it possible to recommend the most suitable character based on the user's past dialogue history. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's past dialogue history to a generation AI, and the generation AI can recommend the most suitable character.

[0070] The reception unit can filter characters based on the user's current interests and concerns. For example, the characters are filtered based on the genre of movies the user has recently watched, the theme of books the user has read, and the contents of events the user has attended. This allows the characters to be filtered based on the user's current interests and concerns. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's current interests and concerns to the generation AI, which can then filter out the most suitable characters.

[0071] The acquisition unit can analyze the user's past dialogue history and select the optimal acquisition method. For example, the acquisition unit preferentially acquires information on characters with whom the user has previously interacted. The acquisition unit preferentially acquires information on characters in which the user has previously shown interest. This allows the optimal acquisition method to be selected based on the user's past dialogue history. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the user's past dialogue history to a generation AI, which can select the optimal acquisition method.

[0072] The dialogue unit can apply different dialogue algorithms depending on the character category during dialogue. For example, a dialogue algorithm related to action is applied to a dialogue with a character in an action movie, and a dialogue algorithm related to humor is applied to a dialogue with a character in a comedy movie. This makes it possible to apply an optimal dialogue algorithm depending on the character category. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input the character category to a generation AI, which can then apply an optimal dialogue algorithm.

[0073] The content expansion unit can analyze the character's past episodes and select the optimal expansion method when expanding the content. For example, the content expansion unit analyzes the character's past events, behavior patterns, and relationships, and generates new episodes based on the results. This allows the character's past episodes to be analyzed and the optimal expansion method to be selected. Some or all of the above-mentioned processing in the content expansion unit may be performed using AI, or may be performed without using AI. For example, the content expansion unit can input the character's past episodes to a generation AI, and the generation AI can select the optimal expansion method.

[0074] When providing content, the providing unit can select the optimal providing method by referring to the user's past viewing history. For example, the providing method is selected based on the genre, length, and viewing time period of the content viewed by the user in the past. This makes it possible to select the optimal providing method based on the user's past viewing history. A part or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the user's past viewing history to the generating AI, which can select the optimal providing method.

[0075] The process flow of the first embodiment will be briefly described below.

[0076] Step 1: The reception unit receives the character selected by the user. For example, the user can select the character they like by clicking, tapping, or by voice input. Step 2: The acquisition unit acquires information about the character selected by the reception unit, such as the character's lines, personality, background information, and the like. Step 3: The dialogue unit conducts a dialogue between the character and the user based on the information acquired by the acquisition unit. For example, the dialogue unit uses a generation AI to generate a response based on the character's lines and personality. Step 4: The content expansion unit generates video content including new episodes for the character based on the dialogue results from the dialogue unit. For example, a generation AI is used to generate new episodes that include the character's background and predictions for the future. Step 5: The providing unit provides the video content generated by the content extension unit to the user. For example, the providing unit delivers the generated video content to the user's device.

[0077] (Example 2) The system according to the embodiment of the present invention is an AI assistant that provides conversational content with characters from television programs and movies. The AI ​​assistant allows users to select their favorite characters and enjoy conversations with the characters. The conversations are generated based on the characters' lines and personalities, providing the user with a realistic conversation experience. It is also possible to expand the original story, such as the character's background and future predictions. In addition, a virtual interview experience is provided in which the character responds to an interview in the real world. The user can ask the character questions about movies and television programs and receive answers from the character's perspective. Educational content is also provided, allowing users to learn about topics such as history, science, and literature while interacting with the characters. Entertainment elements are also included, allowing users to play games with the characters and hear jokes from the characters. For example, the user can select a favorite character and enjoy conversations with the character. The conversations are generated based on the characters' lines and personalities, providing the user with a realistic conversation experience. It is also possible to expand the original story, such as the character's background and future predictions. In addition, a virtual interview experience is provided in which the character responds to an interview in the real world. Users can ask the character questions about movies and TV shows and get answers from the character's perspective. Educational content is also provided, allowing users to learn about topics such as history, science, and literature while interacting with the character. Entertainment elements are also included, allowing users to play games with the character and hear jokes from the character. This allows the AI ​​assistant to provide a diverse range of entertainment and educational experiences for users.

[0078] The AI ​​assistant system according to the embodiment includes a reception unit, an acquisition unit, a dialogue unit, a content extension unit, and a provision unit. The reception unit accepts a character selected by a user. For example, the user can select a favorite character by clicking, tapping, voice input, or the like. The acquisition unit acquires information on the character selected by the reception unit. For example, the character's lines, personality, background information, and the like are acquired. The dialogue unit has a dialogue between the character and the user based on the information acquired by the acquisition unit. For example, the dialogue unit generates a response based on the character's lines and personality using a generation AI. The content extension unit generates video content including a new episode of the character based on the dialogue result by the dialogue unit. For example, the content extension unit generates a new episode including the character's background, future predictions, and the like using a generation AI. The provision unit provides the video content generated by the content extension unit to the user. For example, the provision unit delivers the generated video content to the user's device. As a result, the AI ​​assistant system according to the embodiment can generate and provide video content including a new episode through a dialogue with the character selected by the user.

[0079] The reception unit receives the character selected by the user. For example, the user can select a favorite character by clicking, tapping, or voice input. Specifically, the user interface is designed to be intuitive and easy to use, and displays a list of character images and names. The user can select a character using a mouse or touch screen, or can select a character by voice input using voice recognition technology. In the case of voice input, when the user speaks the name of a character, the system analyzes the voice using a voice recognition engine and identifies the corresponding character. Furthermore, the reception unit also has a function of recording the user's selection history and preferentially displaying characters previously selected by the user the next time the system is used. This allows the user to smoothly select a favorite character, improving convenience.

[0080] The acquisition unit acquires information on the character selected by the reception unit. For example, the character's lines, personality, background information, etc. are acquired. Specifically, the acquisition unit accesses a database and acquires detailed information related to the selected character. The character's lines are extracted from past dialogue logs and official dialogue collections, and the personality and background information are acquired from the character's setting materials and official website. Furthermore, the acquisition unit can also acquire the latest information and update information on the character. For example, when a new episode or event is added, the information is also acquired in real time and provided to the dialogue unit and the content expansion unit. In this way, the acquisition unit can always grasp the details of the character based on the latest information and provide the user with a consistent experience.

[0081] The dialogue unit conducts a dialogue between the character and the user based on the information acquired by the acquisition unit. For example, the dialogue unit uses a generation AI to generate a response based on the character's lines and personality. Specifically, the dialogue unit uses natural language processing technology to analyze the user's input and generate an appropriate response. The generation AI takes into account the character's personality and background information and conducts a natural dialogue in response to the user's questions and comments. For example, when a user asks a character, "How was your day?", the generation AI generates a response such as, "I had a lot of fun today! I went on a new adventure" based on the character's personality and past episodes. The dialogue unit can also analyze the user's emotions and tone and generate a response accordingly. This allows the dialogue unit to make the dialogue with the user more natural and attractive, thereby increasing the user's satisfaction.

[0082] The content extension unit generates video content including a new episode of the character based on the dialogue result by the dialogue unit. For example, a new episode including the character's background and future predictions is generated using a generation AI. Specifically, the content extension unit analyzes the dialogue content in the dialogue unit and generates episodes and scenarios that the user is likely to be interested in. The generation AI creates a new storyline taking into account the character's settings and past episodes. For example, when a user asks a character, "Where will you go on your next adventure?", the generation AI generates a new adventure scenario based on the character's personality and past adventures, and creates video content based on the scenario. Furthermore, the content extension unit generates the character's voice for the generated episode using voice synthesis technology, and creates a visually appealing video using video editing technology. As a result, the content extension unit can provide the user with high-quality video content including new episodes.

[0083] The providing unit provides the video content generated by the content extension unit to the user. For example, the providing unit distributes the generated video content to the user's device. Specifically, the providing unit distributes the video content in a format optimized for the user's device, allowing the user to view the content smoothly. The providing unit can distribute the video in real time using streaming technology, and the user can instantly view the video through an Internet connection. The providing unit can also analyze the user's viewing history and preferences to provide individually customized content. For example, if the user likes a particular character or episode, new video content related to the character or episode is preferentially provided. Furthermore, the providing unit can collect feedback from the user and continuously improve the quality of the content and the method of providing the content. As a result, the providing unit can always provide the latest and attractive content to the user, thereby increasing the user's satisfaction.

[0084] The system includes an interview information generating unit that generates information on a simulated interview of a character, and the providing unit provides the information on the simulated interview to a user. The interview information generating unit generates interview content based on, for example, a question input by a user. For example, a user inputs a question to a character, and generates an answer from the character to the question. The providing unit provides the generated interview content to a user. For example, the providing unit delivers the generated interview content to a device of the user. This allows the user to enjoy a virtual interview of the character. A part or all of the above-mentioned processing in the interview information generating unit may be performed using AI, or may be performed without using AI. For example, the interview information generating unit inputs a question input by a user to a generating AI, and the generating AI can generate interview content.

[0085] The system includes an answer generation unit that generates an answer from the character's viewpoint to a question about video content, and the providing unit provides the answer to the user. For example, the answer generation unit inputs a question about video content by the user, and generates an answer from the character's viewpoint to the question. For example, the user asks the character, "What is the background of this scene?", and the character generates an answer to the question. The providing unit provides the generated answer to the user. For example, the providing unit delivers the generated answer to the user's device. This allows the user to obtain the answer from the character's viewpoint. A part or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit inputs a question input by the user to a generation AI, and the generation AI can generate an answer from the character's viewpoint.

[0086] The system includes an entertainment unit that provides a game to be played together with a character and provides jokes from the character. The entertainment unit, for example, provides a game to be played by a user together with a character. For example, the user can enjoy a puzzle game or an action game together with the character. The entertainment unit can also provide jokes from the character. For example, the character tells a humorous joke to the user. This allows the user to enjoy the game together with the character and to hear the joke. A part or all of the above-mentioned processing in the entertainment unit may be performed using an AI or may be performed without using an AI. For example, the entertainment unit can input the progress of the game and the user's reaction to the generation AI, and the generation AI can generate the next step of the game and jokes.

[0087] The content extension unit can generate video content including new episodes related to the character's background and future. The content extension unit generates new episodes based on, for example, the character's background and predictions for the future. For example, it generates episodes related to the character's past events and future goals. This allows the user to enjoy new episodes related to the character's background and future. Some or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit can input background information of the character to the generation AI, which can generate new episodes.

[0088] The content extension unit can generate video content using a video generation AI. For example, the content extension unit generates video content including a new episode of a character using a video generation AI. The video generation AI generates videos using technologies such as deep learning and generative adversarial network (GAN). As a result, the use of the video generation AI makes it possible to generate video content more efficiently. For example, the content extension unit inputs background information and dialogue results of a character into the video generation AI, which then generates video content including a new episode. This allows users to enjoy high-quality video content.

[0089] The interview information generation unit can generate interview content based on a question input by the user. The interview information generation unit generates interview content for a character based on a question input by the user, for example. For example, the user asks the character, "What is your favorite food?", and the character generates an answer to the question. This allows the user to enjoy an interview with the character. Some or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit can input a question input by the user to a generation AI, and the generation AI can generate interview content.

[0090] The content extension unit can generate video content including a new episode based on the geographical information of the user. The content extension unit generates a new episode for a character based on the geographical information of the user, for example. For example, when the user is in a specific area, an episode related to the area is generated. This allows the user to enjoy a new episode based on his / her geographical information. A part or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit can input the geographical information of the user to a generation AI, which can generate a new episode.

[0091] The dialogue unit can change the theme of the dialogue based on a specific keyword specified by the user. For example, if the user specifies the keyword "adventure", the dialogue unit changes the theme of the dialogue with the character to adventure. This allows the user to enjoy dialogue with the character on a theme that suits his or her interests. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input a keyword specified by the user to the generation AI, which then changes the theme of the dialogue.

[0092] The reception unit receives a change in the character's setting or background during a dialogue with the user, and the content extension unit can generate video content based on the change. The reception unit, for example, receives a request from the user to change the character's setting or background during a dialogue. For example, the user can make a request to change the character's personality, appearance, or background setting. The content extension unit generates a new episode based on the change in the setting or background received by the reception unit. For example, if the user changes the character's personality, a new episode is generated based on the change. This allows the user to change the character's setting or background during a dialogue and enjoy a new episode based on the change. A part or all of the above-mentioned processing in the reception unit and the content extension unit may be performed using AI, or may be performed without using AI. For example, the reception unit inputs the user's request to a generation AI, and the generation AI can generate a new episode that reflects the change in the setting or background.

[0093] The reception unit can estimate the user's emotion and present character options based on the estimated user's emotion. The reception unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the reception unit presents optimal character options. For example, if the user is excited, action movie characters are presented preferentially. If the user is relaxed, comedy movie characters are presented preferentially. In this way, optimal character options can be presented based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's emotion data to the generation AI, and the generation AI can generate optimal character options.

[0094] The reception unit can analyze the user's past selection history and recommend the most suitable character. For example, the genre, personality, and movie or TV program series of a character previously selected by the user are analyzed, and a character of the same genre, personality, and series is recommended. This makes it possible to recommend the most suitable character based on the user's past selection history. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's past selection history to a generation AI, which can then recommend the most suitable character.

[0095] The reception unit can perform filtering based on the user's current interests and concerns when selecting a character. The reception unit, for example, filters characters based on the user's current interests and concerns. For example, the reception unit filters characters based on the genre of movies the user has recently watched, the theme of books the user has read, and the content of events the user has participated in. This makes it possible to filter characters based on the user's current interests and concerns. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's current interests and concerns to the generation AI, and the generation AI can filter the most suitable character.

[0096] The reception unit can estimate the user's emotion and adjust the selection order of the characters based on the estimated user's emotion. The reception unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, tone of voice, and text content. Based on the estimated emotion, the reception unit adjusts the selection order of the characters. For example, if the user is excited, action movie characters are presented first. If the user is relaxed, comedy movie characters are presented first. This makes it possible to adjust the selection order of the characters based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit inputs the user's emotion data to the generation AI, and the generation AI can adjust the selection order of the characters.

[0097] When selecting a character, the reception unit can preferentially present a highly relevant character in consideration of the user's geographical location information. The reception unit, for example, selects a character based on the user's geographical location information. For example, when the user is in a specific area, characters from movies and TV programs related to that area are presented. When the user is traveling, characters related to the travel destination are presented. This makes it possible to preferentially present a highly relevant character based on the user's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to a generation AI, which can select a highly relevant character.

[0098] The reception unit can analyze the user's social media activity and recommend related characters when selecting a character. The reception unit, for example, analyzes the user's social media activity and recommends related characters. For example, characters from movies and TV shows that the user follows on social media are recommended. Characters related to posts that the user has "liked" on social media are recommended. This makes it possible to recommend related characters based on the user's social media activity. Some or all of the above-mentioned processing in the reception unit may be performed using AI or may be performed without using AI. For example, the reception unit can input the user's social media activity to the generation AI, which can then recommend related characters.

[0099] The acquisition unit can estimate the user's emotion and adjust the timing of acquiring character information based on the estimated user's emotion. The acquisition unit estimates emotion from, for example, the user's facial expression, voice, text input, and the like. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the acquisition unit adjusts the timing of acquiring character information. For example, when the user is excited, the character information is acquired and presented immediately. When the user is relaxed, the character information is acquired and presented slowly. This makes it possible to adjust the timing of acquiring character information based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit inputs the user's emotion data to the generation AI, and the generation AI can adjust the timing of acquiring character information.

[0100] The acquisition unit can analyze the user's past dialogue history and select the optimal acquisition method. For example, the acquisition unit preferentially acquires information on characters with whom the user has previously interacted. The acquisition unit preferentially acquires information on characters in which the user has previously shown interest. This allows the optimal acquisition method to be selected based on the user's past dialogue history. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the user's past dialogue history to a generation AI, which can select the optimal acquisition method.

[0101] The acquisition unit can perform filtering based on the user's current interests and concerns when acquiring the character information. The acquisition unit, for example, filters the character information based on the user's current interests and concerns. For example, the character information is filtered based on the genre of a movie the user has recently watched, the theme of a book the user has read, or the content of an event the user has participated in. This makes it possible to filter the character information based on the user's current interests and concerns. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the user's current interests and concerns to the generation AI, and the generation AI can filter the optimal character information.

[0102] The acquisition unit can estimate the user's emotion and determine the priority of the character information to be acquired based on the estimated user's emotion. The acquisition unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the acquisition unit determines the priority of the character information. For example, when the user is excited, the character information of an action movie is preferentially acquired. When the user is relaxed, the character information of a comedy movie is preferentially acquired. This allows the priority of the character information to be determined based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit inputs the user's emotion data to the generation AI, and the generation AI can determine the priority of the character information.

[0103] When acquiring character information, the acquisition unit can preferentially acquire highly relevant information in consideration of the geographical location information of the user. The acquisition unit acquires character information based on, for example, the geographical location information of the user. For example, when the user is in a specific area, character information of movies and TV programs related to the area is acquired. When the user is traveling, character information related to the travel destination is acquired. This makes it possible to preferentially acquire highly relevant character information based on the geographical location information of the user. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the geographical location information of the user to the generation AI, and the generation AI can acquire highly relevant character information.

[0104] The acquisition unit can analyze the user's social media activity and acquire related information when acquiring the character information. The acquisition unit, for example, analyzes the user's social media activity and acquires related character information. For example, character information of movies and TV programs that the user follows on social media is acquired. Character information related to posts that the user "liked" on social media is acquired. This makes it possible to acquire related character information based on the user's social media activity. Some or all of the above-mentioned processing in the acquisition unit may be performed using AI or may be performed without using AI. For example, the acquisition unit can input the user's social media activity to the generation AI, and the generation AI can acquire related character information.

[0105] The dialogue unit can estimate the user's emotion and adjust the dialogue expression method based on the estimated user's emotion. The dialogue unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the dialogue unit adjusts the dialogue expression method. For example, when the user is excited, the dialogue is performed in an energetic expression method. When the user is relaxed, the dialogue is performed in a calm expression method. This makes it possible to adjust the dialogue expression method based on the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit inputs the user's emotion data to the generation AI, and the generation AI can adjust the dialogue expression method.

[0106] The dialogue unit can adjust the level of detail of the dialogue based on the importance of the character during the dialogue. For example, detailed information is provided in the dialogue with the main character, and concise information is provided in the dialogue with the sub-character. This allows the level of detail of the dialogue to be adjusted based on the importance of the character. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the importance of the character to the generation AI, and the generation AI can adjust the level of detail of the dialogue.

[0107] The dialogue unit can apply different dialogue algorithms depending on the character category during dialogue. For example, a dialogue algorithm related to action is applied to a dialogue with a character in an action movie, and a dialogue algorithm related to humor is applied to a dialogue with a character in a comedy movie. This makes it possible to apply an optimal dialogue algorithm depending on the character category. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input the character category to a generation AI, which can then apply an optimal dialogue algorithm.

[0108] The dialogue unit can estimate the user's emotion and adjust the length of the dialogue based on the estimated user's emotion. The dialogue unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the dialogue unit adjusts the length of the dialogue. For example, when the user is excited, a short dialogue that focuses on the main points is performed. When the user is relaxed, a longer dialogue is performed. This makes it possible to adjust the length of the dialogue based on the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dialogue unit may be performed using an AI, or may be performed without using an AI. For example, the dialogue unit inputs the user's emotion data into the generation AI, and the generation AI can adjust the length of the dialogue.

[0109] During dialogue, the dialogue unit can determine the priority of dialogue based on the appearance time of the character. For example, dialogue with characters from the latest movies and TV shows is prioritized, and dialogue with characters from popular past movies and TV shows is prioritized. This allows the priority of dialogue to be determined based on the appearance time of the character. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI, or may be performed without using AI. For example, the dialogue unit can input the appearance time of the character to the generation AI, and the generation AI can determine the priority of dialogue.

[0110] The dialogue unit can adjust the order of dialogue based on the relevance of the characters during dialogue. For example, it prioritizes dialogue with other characters related to the character selected by the user. It prioritizes dialogue with characters from the same movie or TV program. It prioritizes dialogue with characters from the same genre. This makes it possible to adjust the order of dialogue based on the relevance of the characters. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input the relevance of the characters to the generation AI, and the generation AI can adjust the order of dialogue.

[0111] The content extension unit can estimate the user's emotion and adjust the generation method of a new episode based on the estimated user's emotion. The content extension unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the content extension unit adjusts the generation method of a new episode. For example, when the user is excited, an episode including many action scenes is generated. When the user is relaxed, an episode including many calm scenes is generated. This makes it possible to adjust the generation method of a new episode based on the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit inputs the user's emotion data into the generation AI, and the generation AI adjusts the generation method of a new episode.

[0112] The content expansion unit can analyze the character's past episodes and select the optimal expansion method when expanding the content. For example, the content expansion unit analyzes the character's past events, behavior patterns, and relationships, and generates new episodes based on the results. This allows the character's past episodes to be analyzed and the optimal expansion method to be selected. Some or all of the above-mentioned processing in the content expansion unit may be performed using AI, or may be performed without using AI. For example, the content expansion unit can input the character's past episodes to a generation AI, and the generation AI can select the optimal expansion method.

[0113] The content extension unit can customize the episode based on the character's current settings during content extension. The content extension unit generates a new episode based on the character's current occupation, role, relationship, situation, and environment, for example. For example, a new episode is generated based on the character's current occupation. This allows the episode to be customized based on the character's current settings. Some or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit inputs the character's current settings to the generation AI, and the generation AI can customize the episode.

[0114] The content extension unit can estimate the user's emotion and determine the priority of new episodes based on the estimated user's emotion. The content extension unit estimates emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the content extension unit determines the priority of new episodes. For example, when the user is excited, episodes including many action scenes are preferentially generated. When the user is relaxed, episodes including many calm scenes are preferentially generated. This makes it possible to determine the priority of new episodes based on the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit inputs the user's emotion data into the generation AI, and the generation AI can determine the priority of new episodes.

[0115] The content extension unit can generate an optimal episode in consideration of the geographical location information of the user when expanding the content. The content extension unit generates an episode based on the geographical location information of the user, for example. For example, when the user is in a specific area, an episode related to the area is generated. When the user is traveling, an episode related to the travel destination is generated. In this way, it is possible to generate an optimal episode based on the geographical location information of the user. A part or all of the above-mentioned processing in the content extension unit may be performed using AI, or may be performed without using AI. For example, the content extension unit inputs the geographical location information of the user to a generation AI, which can generate an optimal episode.

[0116] The content extension unit can analyze the user's social media activity and suggest episodes during content extension. The content extension unit, for example, analyzes the user's social media activity and generates related episodes. For example, it generates episodes related to movies and TV programs that the user follows on social media. It generates episodes related to posts that the user "likes" on social media. This makes it possible to suggest episodes based on the user's social media activity. Some or all of the above-mentioned processing in the content extension unit may be performed using AI or may be performed without using AI. For example, the content extension unit can input the user's social media activity into a generation AI, which generates related episodes.

[0117] The providing unit can estimate the user's emotion and adjust the content providing method based on the estimated user's emotion. The providing unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the providing unit adjusts the content providing method. For example, if the user is excited, the content is provided with energetic music. If the user is relaxed, the content is provided with calm music. This makes it possible to adjust the content providing method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit inputs the user's emotion data into the generation AI, and the generation AI can adjust the content providing method.

[0118] When providing content, the providing unit can select the optimal providing method by referring to the user's past viewing history. For example, the providing method is selected based on the genre, length, and viewing time period of the content viewed by the user in the past. This makes it possible to select the optimal providing method based on the user's past viewing history. A part or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the user's past viewing history to the generating AI, which can select the optimal providing method.

[0119] The providing unit can estimate the user's emotion and adjust the content provision order based on the estimated user's emotion. The providing unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the providing unit adjusts the content provision order. For example, if the user is excited, content including an action scene is provided first. If the user is relaxed, content including a calm scene is provided first. This makes it possible to adjust the content provision order based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit inputs the user's emotion data into the generation AI, and the generation AI can adjust the content provision order.

[0120] The providing unit can select the optimal providing method in consideration of the user's device information when providing content. For example, if the user is using a smartphone, a providing method suited to the screen size is selected. If the user is using a tablet, a providing method optimized for a large screen is selected. This makes it possible to select the optimal providing method based on the user's device information. Some or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the user's device information to the generating AI, which can select the optimal providing method.

[0121] The interview information generation unit can estimate the user's emotion and adjust the generation method of the interview content based on the estimated user's emotion. The interview information generation unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the interview information generation unit adjusts the generation method of the interview content. For example, if the user is excited, an energetic question is generated. If the user is relaxed, a gentle question is generated. This makes it possible to adjust the generation method of the interview content based on the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit inputs the user's emotion data into the generation AI, and the generation AI can adjust the generation method of the interview content.

[0122] When generating interview information, the interview information generation unit can generate optimal interview content by referring to the user's past question history. For example, related questions are generated based on content that the user has asked in the past. Questions are generated based on topics that the user has shown interest in in the past. This makes it possible to generate optimal interview content based on the user's past question history. Some or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit can input the user's past question history into a generation AI, which can generate optimal interview content.

[0123] The interview information generation unit can estimate the user's emotion and determine the priority of the interview contents based on the estimated user's emotion. The interview information generation unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the interview information generation unit determines the priority of the interview contents. For example, if the user is excited, energetic questions are preferentially generated. If the user is relaxed, calm questions are preferentially generated. This makes it possible to determine the priority of the interview contents based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit inputs the user's emotion data into the generation AI, and the generation AI can determine the priority of the interview contents.

[0124] The interview information generation unit can generate optimal interview content in consideration of the user's geographical location information when generating interview information. The interview information generation unit generates interview content based on the user's geographical location information, for example. For example, when the user is in a specific area, the interview information generation unit generates interview content related to the area. When the user is traveling, the interview information generation unit generates interview content related to the travel destination. This makes it possible to generate optimal interview content based on the user's geographical location information. A part or all of the above-mentioned processing in the interview information generation unit may be performed using AI, or may be performed without using AI. For example, the interview information generation unit inputs the user's geographical location information to a generation AI, which can generate optimal interview content.

[0125] The answer generation unit can estimate the user's emotion and adjust the way of expressing the answer based on the estimated user's emotion. The answer generation unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, tone of voice, and text content. Based on the estimated emotion, the answer generation unit adjusts the way of expressing the answer. For example, if the user is excited, the answer is given in an energetic way of expression. If the user is relaxed, the answer is given in a calm way of expression. This makes it possible to adjust the way of expressing the answer based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit inputs the user's emotion data into the generation AI, and the generation AI can adjust the way of expressing the answer.

[0126] The answer generation unit can adjust the level of detail of the answer based on the importance of the question when generating an answer. For example, a detailed answer is provided for an important question, and a concise answer is provided for a general question. This makes it possible to adjust the level of detail of the answer based on the importance of the question. A part or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit can input the importance of the question to the generation AI, and the generation AI can adjust the level of detail of the answer.

[0127] The answer generation unit can estimate the user's emotion and adjust the length of the answer based on the estimated user's emotion. The answer generation unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the answer generation unit adjusts the length of the answer. For example, if the user is excited, the answer is short and to the point. If the user is relaxed, the answer is longer. This allows the length of the answer to be adjusted based on the user's emotion. The emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit inputs the user's emotion data into the generation AI, and the generation AI can adjust the length of the answer.

[0128] The answer generation unit can determine the priority of answers based on the time of question submission when generating answers. For example, the most recent question is given priority in answering. Important questions are given priority in answering. This makes it possible to determine the priority of answers based on the time of question submission. Some or all of the above-mentioned processing in the answer generation unit may be performed using AI, or may be performed without using AI. For example, the answer generation unit can input the time of question submission to the generation AI, and the generation AI can determine the priority of answers.

[0129] The entertainment unit can estimate the user's emotion and adjust the entertainment provision method based on the estimated user's emotion. The entertainment unit estimates the emotion from, for example, the user's facial expression, voice, text input, etc. For example, using an emotion engine or a generation AI, the emotion is estimated from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the entertainment unit adjusts the entertainment provision method. For example, if the user is excited, an energetic game is provided. If the user is relaxed, a calm game is provided. This makes it possible to adjust the entertainment provision method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the entertainment unit may be performed using an AI, or may be performed without using an AI. For example, the entertainment unit can input the user's emotion data to the generation AI, and the generation AI can adjust the entertainment provision method.

[0130] When providing entertainment, the entertainment unit can select the optimal providing method by referring to the user's past entertainment history. For example, the providing method is selected based on the genre of games or types of jokes that the user has enjoyed in the past, and the length of entertainment. In this way, the optimal providing method can be selected based on the user's past entertainment history. Some or all of the above-mentioned processing in the entertainment unit may be performed using AI, or may be performed without using AI. For example, the entertainment unit can input the user's past entertainment history to a generation AI, which can select the optimal providing method.

[0131] The entertainment unit can estimate the user's emotion and determine the priority of entertainment based on the estimated user's emotion. The entertainment unit estimates emotion from, for example, the user's facial expression, voice, text input, and the like. For example, an emotion engine or a generation AI is used to estimate emotion from the user's facial expression, voice tone, and text content. Based on the estimated emotion, the entertainment unit determines the priority of entertainment. For example, if the user is excited, energetic games are preferentially provided. If the user is relaxed, calm games are preferentially provided. This allows the priority of entertainment to be determined based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the entertainment unit may be performed using AI, or may be performed without using AI. For example, the entertainment unit inputs the user's emotion data into the generation AI, and the generation AI can determine the priority of entertainment.

[0132] When providing entertainment, the entertainment unit can select the optimal providing method in consideration of the geographical location information of the user. The entertainment unit provides entertainment, for example, based on the geographical location information of the user. For example, when the user is in a specific area, entertainment related to the area is provided. When the user is traveling, entertainment related to the travel destination is provided. In this way, optimal entertainment can be provided based on the geographical location information of the user. Some or all of the above-mentioned processing in the entertainment unit may be performed using AI, or may be performed without using AI. For example, the entertainment unit inputs the geographical location information of the user to a generation AI, which can provide optimal entertainment.

[0133] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0134] The reception unit can analyze the user's past dialogue history and recommend the most suitable character. For example, the genre and personality of a character with whom the user has previously interacted, and the series of a movie or television program are analyzed, and a character of the same genre, personality, and series is recommended. This makes it possible to recommend the most suitable character based on the user's past dialogue history. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's past dialogue history to a generation AI, and the generation AI can recommend the most suitable character.

[0135] The interview information generation unit can estimate the user's emotion and adjust the generation method of the interview content based on the estimated user's emotion. For example, if the user is excited, an energetic question is generated. If the user is relaxed, a gentle question is generated. This allows the generation method of the interview content to be adjusted based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the interview information generation unit may be performed using an AI, or may be performed without using an AI. For example, the interview information generation unit can input the user's emotion data to the generation AI, and the generation AI can adjust the generation method of the interview content.

[0136] The answer generation unit can estimate the user's emotion and adjust the way of expressing the answer based on the estimated emotion of the user. For example, if the user is excited, the answer is given in an energetic way of expression. If the user is relaxed, the answer is given in a calm way of expression. This allows the way of expressing the answer to be adjusted based on the emotion of the user. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the answer generation unit may be performed using an AI, or may be performed without using an AI. For example, the answer generation unit can input the user's emotion data to the generation AI, and the generation AI can adjust the way of expressing the answer.

[0137] The entertainment unit can estimate the user's emotion and adjust the entertainment provision method based on the estimated user's emotion. For example, if the user is excited, an energetic game is provided. If the user is relaxed, a calm game is provided. This allows the entertainment provision method to be adjusted based on the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the entertainment unit may be performed using an AI, or may be performed without using an AI. For example, the entertainment unit can input the user's emotion data to the generation AI, and the generation AI can adjust the entertainment provision method.

[0138] The providing unit can estimate the user's emotion and adjust the content providing method based on the estimated user's emotion. For example, if the user is excited, the content is provided with energetic music. If the user is relaxed, the content is provided with calm music. This allows the content providing method to be adjusted based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the user's emotion data to the generation AI, and the generation AI can adjust the content providing method.

[0139] The reception unit can filter characters based on the user's current interests and concerns. For example, the characters are filtered based on the genre of movies the user has recently watched, the theme of books the user has read, and the contents of events the user has attended. This allows the characters to be filtered based on the user's current interests and concerns. A part or all of the above-mentioned processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's current interests and concerns to the generation AI, which can then filter out the most suitable characters.

[0140] The acquisition unit can analyze the user's past dialogue history and select the optimal acquisition method. For example, the acquisition unit preferentially acquires information on characters with whom the user has previously interacted. The acquisition unit preferentially acquires information on characters in which the user has previously shown interest. This allows the optimal acquisition method to be selected based on the user's past dialogue history. A part or all of the above-mentioned processing in the acquisition unit may be performed using AI, or may be performed without using AI. For example, the acquisition unit can input the user's past dialogue history to a generation AI, which can select the optimal acquisition method.

[0141] The dialogue unit can apply different dialogue algorithms depending on the character category during dialogue. For example, a dialogue algorithm related to action is applied to a dialogue with a character in an action movie, and a dialogue algorithm related to humor is applied to a dialogue with a character in a comedy movie. This makes it possible to apply an optimal dialogue algorithm depending on the character category. Some or all of the above-mentioned processing in the dialogue unit may be performed using AI or may be performed without using AI. For example, the dialogue unit can input the character category to a generation AI, which can then apply an optimal dialogue algorithm.

[0142] The content expansion unit can analyze the character's past episodes and select the optimal expansion method when expanding the content. For example, the content expansion unit analyzes the character's past events, behavior patterns, and relationships, and generates new episodes based on the results. This allows the character's past episodes to be analyzed and the optimal expansion method to be selected. Some or all of the above-mentioned processing in the content expansion unit may be performed using AI, or may be performed without using AI. For example, the content expansion unit can input the character's past episodes to a generation AI, and the generation AI can select the optimal expansion method.

[0143] When providing content, the providing unit can select the optimal providing method by referring to the user's past viewing history. For example, the providing method is selected based on the genre, length, and viewing time period of the content viewed by the user in the past. This makes it possible to select the optimal providing method based on the user's past viewing history. A part or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the user's past viewing history to the generating AI, which can select the optimal providing method.

[0144] The process flow of the second embodiment will be briefly described below.

[0145] Step 1: The reception unit receives the character selected by the user. For example, the user can select the character they like by clicking, tapping, or by voice input. Step 2: The acquisition unit acquires information about the character selected by the reception unit, such as the character's lines, personality, background information, and the like. Step 3: The dialogue unit conducts a dialogue between the character and the user based on the information acquired by the acquisition unit. For example, the dialogue unit uses a generation AI to generate a response based on the character's lines and personality. Step 4: The content expansion unit generates video content including new episodes for the character based on the dialogue results from the dialogue unit. For example, a generation AI is used to generate new episodes that include the character's background and predictions for the future. Step 5: The providing unit provides the video content generated by the content extension unit to the user. For example, the providing unit delivers the generated video content to the user's device.

[0146] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0148] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0149] For example, the reception unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the dialogue unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the content extension unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the provision unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0150] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0151] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0152] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0153] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0154] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0157] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0158] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0160] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0162] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0164] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0165] For example, the reception unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the dialogue unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the content expansion unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the provision unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0166] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0167] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0168] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0169] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0170] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0171] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0172] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0173] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0174] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0175] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0176] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0177] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0178] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0179] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0180] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0181] For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the dialogue unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the content expansion unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the provision unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0182] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0183] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0184] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0185] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0186] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0187] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0188] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0189] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0190] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0191] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0192] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0193] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0194] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0195] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0196] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0197] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0198] For example, the reception unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the dialogue unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the content extension unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the provision unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0199] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0200] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0201] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0202] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0203] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0204] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0205] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0206] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0207] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0208] In addition, 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 upon request from the data processing device 12.

[0209] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0210] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0211] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0212] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0213] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0214] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0215] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0216] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0217] (Appendix 1) A reception unit that receives a selection of a character for video content; an acquisition unit that acquires information on the character selected by the acceptance unit; A dialogue unit that conducts a dialogue between the character and a user based on the information acquired by the acquisition unit; a content extension unit that generates video content including additional episodes of the character based on a dialogue result by the dialogue unit; a providing unit that provides the video content generated by the content extension unit to the user. A system characterized by: (Appendix 2) an interview information generating unit for generating information of a simulated interview of the character; The providing unit provides information of the simulated interview to the user. 2. The system of claim 1, (Appendix 3) an answer generation unit that generates an answer from the character's point of view to a question about the video content; The providing unit provides the answer generated by the answer generating unit to the user. 2. The system of claim 1, (Appendix 4) An entertainment section is provided to provide games to be played with characters and jokes from the characters. 2. The system of claim 1, (Appendix 5) The content extension unit is Generate video content including new episodes about the character's background and future 2. The system of claim 1, (Appendix 6) The content extension unit is Generate the video content using video generation AI 2. The system of claim 1, (Appendix 7) The interview information generation unit includes: Generate interview content based on questions entered by the user 3. The system of claim 2, (Appendix 8) The content extension unit is Generating video content including new episodes based on the geographic information of the user. 2. The system of claim 1, (Appendix 9) The dialogue unit includes: Changing the topic of the conversation based on specific keywords specified by the user 2. The system of claim 1, (Appendix 10) The reception unit is accepting a change to a setting or a background of the character from the user during a dialogue with the user in the dialogue unit; The content extension unit is The video content is generated based on the change in the setting or the background accepted by the accepting unit. 2. The system of claim 1, (Appendix 11) The reception unit is Estimate the user's emotions and present character options based on the estimated user's emotions. 2. The system of claim 1, (Appendix 12) The reception unit is Analyze the user's past selection history and recommend the most suitable character 2. The system of claim 1, (Appendix 13) The reception unit is Filter character selection based on the user's current interests 2. The system of claim 1, (Appendix 14) The reception unit is Estimate the user's emotions and adjust the character selection order based on the estimated user's emotions. 2. The system of claim 1, (Appendix 15) The reception unit is When selecting a character, the app takes into account the user's geographic location information and prioritizes the most relevant characters. 2. The system of claim 1, (Appendix 16) The reception unit is When selecting a character, the system analyzes the user's social media activity and recommends related characters. 2. The system of claim 1, (Appendix 17) The acquisition unit is To estimate a user's emotion and adjust the timing of acquiring character information based on the estimated user's emotion. 2. The system of claim 1, (Appendix 18) The acquisition unit is Analyze the user's past interaction history and select the optimal acquisition method 2. The system of claim 1, (Appendix 19) The acquisition unit is When retrieving character information, filter it based on the user's current interests 2. The system of claim 1, (Appendix 20) The acquisition unit is A user's emotion is estimated, and a priority order of character information to be acquired is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 21) The acquisition unit is When acquiring character information, the system prioritizes acquiring information that is more relevant to the user based on the user's geographic location. 2. The system of claim 1, (Appendix 22) The acquisition unit is When character information is acquired, the user's social media activity is analyzed to acquire related information. 2. The system of claim 1, (Appendix 23) The dialogue unit includes: Estimate the user's emotions and adjust the way the dialogue is expressed based on the estimated user's emotions. 2. The system of claim 1, (Appendix 24) The dialogue unit includes: During dialogue, adjust the level of detail of the dialogue based on the importance of the character 2. The system of claim 1, (Appendix 25) The dialogue unit includes: During dialogue, apply different dialogue algorithms depending on the character category 2. The system of claim 1, (Appendix 26) The dialogue unit includes: Estimate the user's emotions and adjust the length of the dialogue based on the estimated user emotions. 2. The system of claim 1, (Appendix 27) The dialogue unit includes: During dialogue, prioritize dialogue based on when the character appears 2. The system of claim 1, (Appendix 28) The dialogue unit includes: During dialogue, adjust the order of dialogue based on character relevance 2. The system of claim 1, (Appendix 29) The content extension unit is Estimate the user's emotions and adjust the method of generating new episodes based on the estimated user emotions. 2. The system of claim 1, (Appendix 30) The content extension unit is When expanding content, we analyze the characters' past episodes to select the most appropriate expansion method. 2. The system of claim 1, (Appendix 31) The content extension unit is Customize episodes based on the character's current settings during content expansion 2. The system of claim 1, (Appendix 32) The content extension unit is Estimate user emotions and prioritize new episodes based on the estimated user emotions. 2. The system of claim 1, (Appendix 33) The content extension unit is When expanding content, generate optimal episodes by considering the user's geographic location information 2. The system of claim 1, (Appendix 34) The content extension unit is When expanding content, suggest episodes by analyzing users' social media activity 2. The system of claim 1, (Appendix 35) The providing unit is To estimate a user's emotion and adjust a content delivery method based on the estimated user's emotion. 2. The system of claim 1, (Appendix 36) The providing unit is When providing content, the optimal delivery method is selected by referring to the user's past viewing history. 2. The system of claim 1, (Appendix 37) The providing unit is To estimate a user's emotion and adjust the order of providing contents based on the estimated user's emotion. 2. The system of claim 1, (Appendix 38) The providing unit is When providing content, the optimal delivery method is selected taking into account the user's device information. 2. The system of claim 1, (Appendix 39) The interview information generation unit includes: Inferring user emotions and adjusting the interview content generation method based on the estimated user emotions 3. The system of claim 2, (Appendix 40) The interview information generation unit includes: When generating interview information, the system generates optimal interview content by referring to the user's past question history. 3. The system of claim 2, (Appendix 41) The interview information generation unit includes: Estimate user emotions and prioritize interview content based on the estimated user emotions 3. The system of claim 2, (Appendix 42) The interview information generation unit includes: When generating interview information, the optimal interview content is generated by taking into account the user's geographic location information. 3. The system of claim 2, (Appendix 43) The answer generation unit: Infer user sentiment and adjust answer expression based on the inferred sentiment 4. The system of claim 3. (Appendix 44) The answer generation unit: When generating answers, adjust the detail of the answer based on the importance of the question 4. The system of claim 3. (Appendix 45) The answer generation unit: Infer user sentiment and adjust the length of answers based on the estimated user sentiment 4. The system of claim 3. (Appendix 46) The answer generation unit: When generating answers, prioritize answers based on when the question was submitted 4. The system of claim 3. (Appendix 47) The entertainment department: To estimate a user's emotion and adjust a method of providing entertainment based on the estimated user's emotion 5. The system of claim 4. (Appendix 48) The entertainment department: When providing entertainment, the optimal method of providing the entertainment is selected by referring to the user's past entertainment history. 5. The system of claim 4. (Appendix 49) The entertainment department: Estimating user emotions and prioritizing entertainment based on the estimated user emotions 5. The system of claim 4. (Appendix 50) The entertainment department: When providing entertainment, the optimal delivery method is selected taking into account the user's geographic location information. 5. The system of claim 4. [Explanation of symbols]

[0218] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives a selection of a character for video content; an acquisition unit that acquires information on the character selected by the acceptance unit; A dialogue unit that conducts a dialogue between the character and a user based on the information acquired by the acquisition unit; a content extension unit that generates video content including additional episodes of the character based on a dialogue result by the dialogue unit; a providing unit that provides the video content generated by the content extension unit to the user. A system characterized by:

2. an interview information generating unit for generating information of a simulated interview of the character; The providing unit provides information of the simulated interview to the user.

2. The system of claim 1 .

3. an answer generation unit that generates an answer from the character's point of view to a question about the video content; The providing unit provides the answer generated by the answer generating unit to the user.

2. The system of claim 1 .

4. An entertainment section is provided for providing games to be played with the characters and jokes from the characters.

2. The system of claim 1 .

5. The content extension unit is Generate video content including new episodes about the character's background and future 2. The system of claim 1 .

6. The content extension unit is Generate the video content using video generation AI 2. The system of claim 1 .

7. The interview information generation unit includes: Generate interview content based on questions entered by the user 3. The system of claim 2.

8. The content extension unit is Generating video content including new episodes based on the geographic information of the user.

2. The system of claim 1 .

Images