system

Abstract

The system according to this embodiment aims to enable users to interact with movie and anime characters in real time. [Solution] The system according to the embodiment comprises a reception unit, a learning unit, a dialogue generation unit, a dialogue unit, and an evolution unit. The reception unit allows the user to select a character with whom they wish to interact. The learning unit learns the personality and background of the character selected by the reception unit. The dialogue generation unit generates a dialogue based on the information learned by the learning unit. The dialogue unit performs the dialogue generated by the dialogue generation unit in real time. The evolution unit learns the user's reactions to the dialogue performed by the dialogue unit and evolves the dialogue.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that a user cannot interact with movie or anime characters in real time, and there are limitations in the interaction with the characters.

[0005] The system according to the embodiment aims to enable a user to interact with movie or anime characters in real time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a learning unit, a dialogue generation unit, a dialogue unit, and an evolution unit. The reception unit allows the user to select a character with whom they wish to interact. The learning unit learns the personality and background of the character selected by the reception unit. The dialogue generation unit generates a dialogue based on the information learned by the learning unit. The dialogue unit performs the dialogue generated by the dialogue generation unit in real time. The evolution unit learns the user's reactions to the dialogue performed by the dialogue unit and evolves the dialogue. [Effects of the Invention]

[0007] The system according to this embodiment can enable users to interact with movie and anime characters in real time. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The dialogue platform according to an embodiment of the present invention is a system that allows users to interact with movie and anime characters in real time. In this system, the user selects a character they wish to interact with, and the AI ​​learns the character's personality and background and generates a dialogue based on that. Users can enjoy free conversation with their favorite characters, and the system can also be used as content for fan activities and fan clubs. For example, the user selects a character they wish to interact with. In this case, the user can choose their favorite character from among movie and anime characters. For example, a wide range of characters are available, such as popular anime characters and movie heroes. Next, the AI ​​learns the personality and background of the selected character. The AI ​​collects information about the character's personality and background and generates a dialogue based on that. For example, it learns the character's tone of voice, way of speaking, past episodes, etc., and reflects this in the dialogue with the user. The generated dialogue takes place in real time. The AI ​​instantly generates a response to the message entered by the user, and the dialogue progresses as if the character were speaking. This allows the user to enjoy a natural conversation with the character. Furthermore, the AI ​​learns the user's reactions and evolves the dialogue. It learns how the user reacted and evolves the next dialogue to be more natural and engaging based on that. This allows users to have a more personalized experience. The platform can also be used for content related to fan activities and fan clubs. Users can deepen their emotional connection with their favorite characters through interaction. For example, they can share special episodes with characters or receive messages from them. This mechanism is expected to increase user engagement, improve repeat visit rates, and acquire new users. For example, the average interaction time is expected to increase by 30%, and the user repeat visit rate is expected to increase by 40%. In addition, the uniqueness of the platform is expected to increase the number of new users by 20%.In this way, platforms that allow users to interact with movie and anime characters in real time offer users a new form of entertainment experience and drive innovation in the entertainment industry. These interaction platforms can provide users with an experience where they can interact with movie and anime characters in real time, and personalize the user experience.

[0029] The dialogue platform according to this embodiment comprises a reception unit, a learning unit, a dialogue generation unit, a dialogue unit, and an evolution unit. The reception unit allows the user to select a character they wish to interact with. The reception unit can, for example, allow the user to choose a character from among characters in movies or anime. For example, the reception unit provides a wide range of characters, such as popular anime characters or movie heroes. The learning unit learns the personality and background of the character selected by the reception unit. The learning unit collects information about the character's personality and background and generates a dialogue based on it. For example, the learning unit learns the character's tone of voice, manner of speaking, past episodes, etc., and reflects this in the dialogue with the user. The dialogue generation unit generates a dialogue based on the information learned by the learning unit. For example, the dialogue generation unit generates a dialogue based on the character's personality and background. For example, the dialogue generation unit generates a dialogue that reflects the character's tone of voice, manner of speaking, past episodes, etc. The dialogue unit performs the dialogue generated by the dialogue generation unit in real time. For example, the dialogue unit generates an immediate response to a message entered by the user. For example, the dialogue unit generates responses to user-inputted messages as if a character were speaking. The evolution unit learns the user's reactions to the dialogue conducted by the dialogue unit and evolves the dialogue. For example, the evolution unit learns how the user reacted and evolves the next dialogue based on that to make it more natural and engaging. For example, the evolution unit learns the user's reactions and adjusts the content and expression of the dialogue. In this way, the dialogue platform according to the embodiment can provide a user with an experience of interacting with movie or anime characters in real time and personalize the user's experience.

[0030] The reception desk allows users to select the character they wish to interact with. For example, users can choose their favorite character from a selection of characters from movies or anime. Specifically, the reception desk displays a list of characters through the user interface, allowing users to make visual selections. The character list includes images, names, and brief descriptions, which users use to guide their selection. Furthermore, the reception desk learns the user's past selection history and preferences, and recommends suitable characters. For instance, it analyzes the genre and personality of characters the user has previously selected and recommends similar characters. This makes it easy for users to find characters that suit their preferences, improving their satisfaction with the interaction experience. The reception desk also collects feedback on character selections and regularly updates the character lineup, ensuring users can always enjoy interacting with new characters. This allows the reception desk to meet diverse user needs and increase the frequency of use of the interaction platform.

[0031] The learning unit learns the personality and background of the character selected by the reception unit. For example, the learning unit collects information about the character's personality and background and generates dialogue based on it. Specifically, the learning unit extracts information from the character's official setting materials and related media content to gain a detailed understanding of the character's personality and background. For example, it learns the character's tone of voice and way of speaking, past episodes, specific phrases, and behavioral patterns. Furthermore, the learning unit uses natural language processing technology to build rules to maintain consistency in the character's statements and actions. This allows the learning unit to generate realistic dialogue as if the character were actually real. In addition, the learning unit analyzes the user's dialogue history and continuously improves the model for generating responses based on the character's personality and background. For example, it learns how the user reacted to a particular character and adjusts the character's responses accordingly. This allows the learning unit to provide dialogue that meets the user's expectations and improve the quality of the dialogue experience.

[0032] The dialogue generation unit generates dialogues based on information learned by the learning unit. For example, the dialogue generation unit generates dialogues based on the character's personality and background. Specifically, the dialogue generation unit generates appropriate responses to user input based on the character information provided by the learning unit. For example, if a user asks a character a question, the dialogue generation unit generates a natural and consistent response based on the character's personality and background. The dialogue generation unit uses generation AI to faithfully reproduce the character's tone of voice and speaking style. For example, if a character frequently uses certain phrases or expressions, these are reflected in the dialogue. The dialogue generation unit also analyzes the user's input and generates responses that take the appropriate context into account. For example, if a user asks a question related to a past episode, it provides a detailed response based on that episode. This allows the dialogue generation unit to make conversations with users more realistic and engaging. Furthermore, the dialogue generation unit has a function to evaluate the quality of the generated dialogues and make corrections or improvements as needed. This allows the dialogue generation unit to consistently provide high-quality dialogues and increase user satisfaction.

[0033] The dialogue unit performs dialogues generated by the dialogue generation unit in real time. For example, the dialogue unit instantly generates responses to messages entered by the user. Specifically, the dialogue unit receives user input and quickly generates and displays responses to it. The dialogue unit uses algorithms to analyze the messages entered by the user and select appropriate responses. For example, if a user asks a question to a character, the dialogue unit generates the optimal response to that question and displays it as if the character were speaking. The dialogue unit also has the ability to adjust the speed and timing of responses to ensure smooth dialogue with the user. For example, by generating responses with appropriate pauses in response to messages entered by the user, it achieves a natural flow of dialogue. Furthermore, the dialogue unit can flexibly change the topic of the dialogue according to the user's input. For example, if a user suggests a new topic, it generates responses related to that topic and continues the dialogue. This allows the dialogue unit to make dialogues with users more interactive and engaging. In addition, the dialogue unit has the ability to collect user feedback and continuously improve the quality of the dialogue. This allows the dialogue unit to provide high-quality dialogues that meet user needs and improve the user experience of the dialogue platform.

[0034] The evolution unit learns from user responses to conversations conducted by the dialogue unit and evolves the dialogue accordingly. For example, the evolution unit learns how users responded and uses that information to make subsequent conversations more natural and engaging. Specifically, the evolution unit collects user responses and uses them as data to adjust the content and expression of the dialogue. For example, if a user responds favorably to a particular character's response, it strengthens that character's response pattern. Conversely, if a user responds negatively, it modifies that response pattern. The evolution unit uses machine learning algorithms to analyze user response data and continuously improve the quality of the dialogue. For example, it clusters user response data to identify the optimal response pattern for different user groups. This allows the evolution unit to provide personalized dialogues for each user. The evolution unit also saves the history of conversations and references past conversations to achieve more consistent dialogue. For example, it remembers what users have said in the past and generates responses based on that. This allows the evolution unit to make conversations with users deeper and more continuous. Furthermore, the evolution unit can optimize settings by referencing user feedback when adding new characters or dialogue scenarios. This allows the evolution unit to accelerate the evolution of the dialogue platform and continuously provide users with new experiences.

[0035] The dialogue generation unit can generate dialogue based on the character's personality and background. For example, the dialogue generation unit collects information about the character's personality and background and generates dialogue based on that information. For example, the dialogue generation unit learns the character's tone of voice, manner of speaking, past episodes, etc., and reflects this in the dialogue with the user. For example, the dialogue generation unit can adjust the tone and content of the dialogue based on the character's personality. As a result, more natural conversations become possible by generating dialogue based on the character's personality and background.

[0036] The evolutionary unit can learn from user responses and evolve subsequent conversations to make them more natural and engaging. For example, it can learn how users responded and adjust the next conversation accordingly. For example, it can analyze user responses and improve the content and expression of the conversation. For example, it can adjust the tone and content of the conversation based on user responses. In this way, the quality of the conversation can be improved by learning from user responses.

[0037] The dialogue unit can instantly generate responses to messages entered by the user. For example, the dialogue unit can generate responses to user-entered messages as if a character were speaking. For example, the dialogue unit can generate responses to user-entered messages in real time. The dialogue unit can instantly generate responses to user-entered messages. This enables real-time dialogue by instantly generating responses to user-entered messages.

[0038] The reception desk allows users to choose their favorite character from among movie and anime characters. For example, the reception desk can offer a wide range of characters, including popular anime characters and movie heroes. The reception desk allows users to choose the character they want to interact with. This allows users to choose their favorite character from among movie and anime characters.

[0039] The dialogue generation unit can learn the character's tone of voice, speaking style, past episodes, etc., and reflect them in the dialogue with the user. For example, the dialogue generation unit can learn the character's tone of voice, speaking style, past episodes, etc., and generate dialogue based on that. For example, the dialogue generation unit can learn the character's tone of voice and speaking style, etc., and reflect them in the dialogue with the user. For example, the dialogue generation unit can learn the character's past episodes and generate dialogue based on that. This makes it possible to have more realistic dialogues by learning the character's tone of voice, speaking style, past episodes, etc.

[0040] The reception desk can analyze the user's past character selection history and recommend the most suitable character. For example, the reception desk can prioritize displaying characters that the user has frequently selected in the past. For example, if the reception desk knows that the user prefers characters of a particular genre, it can recommend characters from that genre. For example, based on the personalities of characters the user has selected in the past, the reception desk can recommend characters with similar personalities. In this way, by analyzing the user's past character selection history, the reception desk can recommend the most suitable character.

[0041] The reception system can filter characters based on the user's current interests and preferences when they select a character. For example, it can display characters relevant to movies or anime the user has recently watched. For example, it can prioritize displaying characters the user has mentioned on social media. For example, it can filter characters based on keywords the user has recently searched for. This allows the system to provide more appropriate characters by filtering them based on the user's current interests and preferences.

[0042] The reception desk can prioritize presenting highly relevant characters by considering the user's geographical location when selecting a character. For example, if the user is in a specific region, the reception desk can display characters related to that region. For example, if the user is traveling, the reception desk can display characters related to their travel destination. For example, if the user is participating in a specific event, the reception desk can display characters related to that event. In this way, by considering the user's geographical location, it is possible to provide highly relevant characters.

[0043] The reception desk can analyze the user's social media activity when selecting a character and recommend relevant characters. For example, the reception desk can prioritize displaying characters that the user follows on social media. For example, the reception desk can display characters that the user has liked on social media. For example, the reception desk can display characters that the user has shared on social media. In this way, by analyzing the user's social media activity, it is possible to provide relevant characters.

[0044] The learning unit can adjust the level of detail in its learning based on key episodes and characteristics of the character. For example, it can focus on learning representative episodes of the character. For example, it can learn in detail important events that shape the character's personality. For example, it can learn the character's characteristic catchphrases and behavioral patterns. By adjusting the level of detail in learning based on key episodes and characteristics of the character, the accuracy of the learning is improved.

[0045] The learning unit can apply different learning algorithms depending on the character category during training. For example, it can apply a combat scene learning algorithm to action characters, a humor learning algorithm to comedy characters, and an emotional expression learning algorithm to drama characters. By applying different learning algorithms depending on the character category, the accuracy of the learning process is improved.

[0046] The learning unit can adjust the learning priority based on when the characters were introduced. For example, the learning unit can prioritize learning the most recent characters. For example, the learning unit can prioritize learning popular characters. For example, the learning unit can adjust the learning priority based on user requests. This improves the accuracy of learning by adjusting the learning priority based on when the characters were introduced.

[0047] The learning unit can improve the accuracy of its learning by referring to related works of the character during the learning process. For example, the learning unit can learn by referring to other works in which the character appears. For example, the learning unit can learn by referring to spin-off works of the character. For example, the learning unit can learn by referring to related merchandise and media of the character. In this way, the accuracy of learning is improved by referring to related works of the character.

[0048] The dialogue generation unit can adjust the level of detail in the dialogue based on important episodes and characteristics of the characters during the dialogue generation process. For example, the dialogue generation unit can reflect representative episodes of the characters in the dialogue. For example, the dialogue generation unit can reflect important events that shape the characters' personalities in the dialogue. For example, the dialogue generation unit can reflect characteristic catchphrases and behavioral patterns of the characters in the dialogue. By adjusting the level of detail in the dialogue based on important episodes and characteristics of the characters, the accuracy of the dialogue is improved.

[0049] The dialogue generation unit can apply different dialogue algorithms depending on the character category during dialogue generation. For example, it can apply a combat scene dialogue algorithm to an action character. For example, it can apply a humorous dialogue algorithm to a comedy character. For example, it can apply an emotional expression dialogue algorithm to a drama character. By applying different dialogue algorithms depending on the character category, the accuracy of the dialogue is improved.

[0050] The dialogue generation unit can determine the priority of dialogues based on the timing of the characters' appearances during dialogue generation. For example, the dialogue generation unit can prioritize the generation of dialogues for the most recent character. For example, the dialogue generation unit can prioritize the generation of dialogues for popular characters. For example, the dialogue generation unit can adjust the priority of dialogues based on user requests. This improves the accuracy of dialogues by determining the priority of dialogues based on the timing of the characters' appearances.

[0051] The dialogue generation unit can improve the accuracy of the dialogue by referencing related works of the characters during dialogue generation. For example, the dialogue generation unit can generate dialogue by referencing other works in which the characters appear. For example, the dialogue generation unit can generate dialogue by referencing spin-off works of the characters. For example, the dialogue generation unit can generate dialogue by referencing related merchandise and media of the characters. In this way, referencing related works of the characters improves the accuracy of the dialogue.

[0052] The dialogue unit can provide the most appropriate dialogue by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can provide relevant dialogue based on what the user has said in the past. For example, the dialogue unit can prioritize providing topics that the user has shown interest in in the past. For example, the dialogue unit can select the topic of greatest interest from the user's past dialogue history and proceed with the conversation. In this way, the dialogue unit can provide the most appropriate dialogue by referring to the user's past dialogue history.

[0053] The dialogue unit can customize the conversation content based on the user's current interests and preferences. For example, it can customize the conversation content based on movies or anime the user has recently watched. For example, it can reflect topics the user has mentioned on social media in the conversation. For example, it can customize the conversation content based on keywords the user has recently searched for. This allows for more relevant conversations by customizing the content based on the user's current interests and preferences.

[0054] The dialogue unit can provide optimal conversations by considering the user's geographical location during the interaction. For example, if the user is in a specific region, the dialogue unit can provide topics related to that region. For example, if the user is traveling, the dialogue unit can provide topics related to the travel destination. For example, if the user is participating in a specific event, the dialogue unit can provide topics related to that event. In this way, by considering the user's geographical location, the dialogue unit can provide optimal conversations.

[0055] The dialogue unit can analyze the user's social media activity during a conversation and customize the conversation content. For example, the dialogue unit can reflect topics the user follows on social media in the conversation. For example, the dialogue unit can reflect topics the user has liked on social media in the conversation. For example, the dialogue unit can reflect topics the user has shared on social media in the conversation. In this way, the conversation content can be customized by analyzing the user's social media activity.

[0056] The evolution unit can analyze the user's past responses during evolution to select the optimal evolution method. For example, the evolution unit can prioritize evolving dialogue patterns in which the user has shown a favorable response in the past. For example, the evolution unit can prioritize evolving topics in which the user has shown interest in the past. For example, the evolution unit can analyze the user's past responses and select the topics of greatest interest to evolve. In this way, by analyzing the user's past responses, the optimal evolution method can be selected.

[0057] The evolutionary component can evolve the conversation based on the user's current interests and preferences. For example, it can evolve the conversation based on movies or anime the user has recently watched. For example, it can reflect topics the user has mentioned on social media in the conversation. For example, it can evolve the conversation based on keywords the user has recently searched for. This allows for more relevant conversations by evolving the conversation based on the user's current interests and preferences.

[0058] The evolution unit can select the optimal evolution method by considering the user's geographical location during the evolution process. For example, if the user is in a specific region, the evolution unit can evolve topics related to that region. For example, if the user is traveling, the evolution unit can evolve topics related to the travel destination. For example, if the user is participating in a specific event, the evolution unit can evolve topics related to that event. In this way, the optimal evolution method can be selected by considering the user's geographical location.

[0059] The evolution unit can evolve the dialogue content by analyzing the user's social media activity during the evolution process. For example, the evolution unit can reflect topics that the user follows on social media in the dialogue. For example, the evolution unit can reflect topics that the user has liked on social media in the dialogue. For example, the evolution unit can reflect topics that the user has shared on social media in the dialogue. In this way, the dialogue content can be evolved by analyzing the user's social media activity.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The reception desk can provide information on related merchandise and events based on the character selected by the user. For example, if a user selects a specific character, it can display the latest merchandise information related to that character. It can also provide information on events related to the character selected by the user. Furthermore, it can provide information on fan clubs related to the character selected by the user. This allows users not only to enjoy interacting with the characters but also to obtain related information.

[0062] The learning unit can analyze the user's conversation history and learn the conversation style the user prefers. For example, if the user likes humor, the learning unit can instruct the conversation generation unit to generate humorous conversations based on that information. Similarly, if the user prefers touching stories, the learning unit can instruct the conversation generation unit to generate touching conversations based on that information. Furthermore, if the user shows interest in a particular topic, it can instruct the unit to generate conversations related to that topic. This ensures that conversations are tailored to the user's preferences.

[0063] The dialogue generation unit can dynamically change the topic of the conversation based on the user's input. For example, if the user starts talking about a specific movie, the dialogue generation unit can shift the conversation to a topic related to that movie. Also, if the user starts talking about a specific character, it can provide episodes and background information related to that character. Furthermore, if the user expresses a specific emotion, it can generate a conversation that corresponds to that emotion. In this way, a conversation tailored to the user's interests and concerns is provided.

[0064] The evolutionary component can optimize the way a conversation progresses based on the user's conversation history. For example, if a user has previously preferred a particular conversation pattern, that pattern can be prioritized. Also, if a user shows interest in a particular topic, conversations related to that topic can be prioritized. Furthermore, if a user expresses a particular emotion, the conversation can evolve to reflect that emotion. This ensures that conversations are tailored to the user's preferences and interests.

[0065] The dialogue unit can dynamically change the tone and style of the conversation based on the user's input. For example, if the user is speaking in a relaxed tone, the dialogue unit can generate a response that matches that tone. If the user is excited, it can generate a response that matches that excitement. Furthermore, if the user is speaking emotionally, it can generate a response that reflects that emotion. This provides a conversation that is tailored to the user's tone and style.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The reception desk allows the user to select the character they wish to interact with. For example, they can choose their favorite character from movies or anime. The reception desk offers a wide range of characters, including popular anime characters and movie heroes. Step 2: The learning unit learns the personality and background of the character selected by the reception unit. For example, it collects information about the character's personality and background and generates dialogue based on it. The learning unit learns the character's tone of voice, speaking style, past episodes, etc., and reflects this in the dialogue with the user. Step 3: The dialogue generation unit generates dialogue based on the information learned by the learning unit. For example, it generates dialogue based on the character's personality and background. The dialogue generation unit generates dialogue that reflects the character's tone of voice, manner of speaking, past episodes, etc. Step 4: The dialogue unit performs the dialogue generated by the dialogue generation unit in real time. For example, it instantly generates a response to a message entered by the user. The dialogue unit generates a response to the message entered by the user as if a character were speaking. Step 5: The evolution unit learns from the user's responses to the dialogue conducted by the dialogue unit and evolves the dialogue. For example, it learns how the user responded and uses that to evolve the next dialogue to make it more natural and engaging. The evolution unit learns from the user's responses and adjusts the content and expression of the dialogue.

[0068] (Example of form 2) The dialogue platform according to an embodiment of the present invention is a system that allows users to interact with movie and anime characters in real time. In this system, the user selects a character they wish to interact with, and the AI ​​learns the character's personality and background and generates a dialogue based on that. Users can enjoy free conversation with their favorite characters, and the system can also be used as content for fan activities and fan clubs. For example, the user selects a character they wish to interact with. In this case, the user can choose their favorite character from among movie and anime characters. For example, a wide range of characters are available, such as popular anime characters and movie heroes. Next, the AI ​​learns the personality and background of the selected character. The AI ​​collects information about the character's personality and background and generates a dialogue based on that. For example, it learns the character's tone of voice, way of speaking, past episodes, etc., and reflects this in the dialogue with the user. The generated dialogue takes place in real time. The AI ​​instantly generates a response to the message entered by the user, and the dialogue progresses as if the character were speaking. This allows the user to enjoy a natural conversation with the character. Furthermore, the AI ​​learns the user's reactions and evolves the dialogue. It learns how the user reacted and evolves the next dialogue to be more natural and engaging based on that. This allows users to have a more personalized experience. The platform can also be used for content related to fan activities and fan clubs. Users can deepen their emotional connection with their favorite characters through interaction. For example, they can share special episodes with characters or receive messages from them. This mechanism is expected to increase user engagement, improve repeat visit rates, and acquire new users. For example, the average interaction time is expected to increase by 30%, and the user repeat visit rate is expected to increase by 40%. In addition, the uniqueness of the platform is expected to increase the number of new users by 20%.In this way, platforms that allow users to interact with movie and anime characters in real time offer users a new form of entertainment experience and drive innovation in the entertainment industry. These interaction platforms can provide users with an experience where they can interact with movie and anime characters in real time, and personalize the user experience.

[0069] The dialogue platform according to this embodiment comprises a reception unit, a learning unit, a dialogue generation unit, a dialogue unit, and an evolution unit. The reception unit allows the user to select a character they wish to interact with. The reception unit can, for example, allow the user to choose a character from among characters in movies or anime. For example, the reception unit provides a wide range of characters, such as popular anime characters or movie heroes. The learning unit learns the personality and background of the character selected by the reception unit. The learning unit collects information about the character's personality and background and generates a dialogue based on it. For example, the learning unit learns the character's tone of voice, manner of speaking, past episodes, etc., and reflects this in the dialogue with the user. The dialogue generation unit generates a dialogue based on the information learned by the learning unit. For example, the dialogue generation unit generates a dialogue based on the character's personality and background. For example, the dialogue generation unit generates a dialogue that reflects the character's tone of voice, manner of speaking, past episodes, etc. The dialogue unit performs the dialogue generated by the dialogue generation unit in real time. For example, the dialogue unit generates an immediate response to a message entered by the user. For example, the dialogue unit generates responses to user-inputted messages as if a character were speaking. The evolution unit learns the user's reactions to the dialogue conducted by the dialogue unit and evolves the dialogue. For example, the evolution unit learns how the user reacted and evolves the next dialogue based on that to make it more natural and engaging. For example, the evolution unit learns the user's reactions and adjusts the content and expression of the dialogue. In this way, the dialogue platform according to the embodiment can provide a user with an experience of interacting with movie or anime characters in real time and personalize the user's experience.

[0070] The reception desk allows users to select the character they wish to interact with. For example, users can choose their favorite character from a selection of characters from movies or anime. Specifically, the reception desk displays a list of characters through the user interface, allowing users to make visual selections. The character list includes images, names, and brief descriptions, which users use to guide their selection. Furthermore, the reception desk learns the user's past selection history and preferences, and recommends suitable characters. For instance, it analyzes the genre and personality of characters the user has previously selected and recommends similar characters. This makes it easy for users to find characters that suit their preferences, improving their satisfaction with the interaction experience. The reception desk also collects feedback on character selections and regularly updates the character lineup, ensuring users can always enjoy interacting with new characters. This allows the reception desk to meet diverse user needs and increase the frequency of use of the interaction platform.

[0071] The learning unit learns the personality and background of the character selected by the reception unit. For example, the learning unit collects information about the character's personality and background and generates dialogue based on it. Specifically, the learning unit extracts information from the character's official setting materials and related media content to gain a detailed understanding of the character's personality and background. For example, it learns the character's tone of voice and way of speaking, past episodes, specific phrases, and behavioral patterns. Furthermore, the learning unit uses natural language processing technology to build rules to maintain consistency in the character's statements and actions. This allows the learning unit to generate realistic dialogue as if the character were actually real. In addition, the learning unit analyzes the user's dialogue history and continuously improves the model for generating responses based on the character's personality and background. For example, it learns how the user reacted to a particular character and adjusts the character's responses accordingly. This allows the learning unit to provide dialogue that meets the user's expectations and improve the quality of the dialogue experience.

[0072] The dialogue generation unit generates dialogues based on information learned by the learning unit. For example, the dialogue generation unit generates dialogues based on the character's personality and background. Specifically, the dialogue generation unit generates appropriate responses to user input based on the character information provided by the learning unit. For example, if a user asks a character a question, the dialogue generation unit generates a natural and consistent response based on the character's personality and background. The dialogue generation unit uses generation AI to faithfully reproduce the character's tone of voice and speaking style. For example, if a character frequently uses certain phrases or expressions, these are reflected in the dialogue. The dialogue generation unit also analyzes the user's input and generates responses that take the appropriate context into account. For example, if a user asks a question related to a past episode, it provides a detailed response based on that episode. This allows the dialogue generation unit to make conversations with users more realistic and engaging. Furthermore, the dialogue generation unit has a function to evaluate the quality of the generated dialogues and make corrections or improvements as needed. This allows the dialogue generation unit to consistently provide high-quality dialogues and increase user satisfaction.

[0073] The dialogue unit performs dialogues generated by the dialogue generation unit in real time. For example, the dialogue unit instantly generates responses to messages entered by the user. Specifically, the dialogue unit receives user input and quickly generates and displays responses to it. The dialogue unit uses algorithms to analyze the messages entered by the user and select appropriate responses. For example, if a user asks a question to a character, the dialogue unit generates the optimal response to that question and displays it as if the character were speaking. The dialogue unit also has the ability to adjust the speed and timing of responses to ensure smooth dialogue with the user. For example, by generating responses with appropriate pauses in response to messages entered by the user, it achieves a natural flow of dialogue. Furthermore, the dialogue unit can flexibly change the topic of the dialogue according to the user's input. For example, if a user suggests a new topic, it generates responses related to that topic and continues the dialogue. This allows the dialogue unit to make dialogues with users more interactive and engaging. In addition, the dialogue unit has the ability to collect user feedback and continuously improve the quality of the dialogue. This allows the dialogue unit to provide high-quality dialogues that meet user needs and improve the user experience of the dialogue platform.

[0074] The evolution unit learns from user responses to conversations conducted by the dialogue unit and evolves the dialogue accordingly. For example, the evolution unit learns how users responded and uses that information to make subsequent conversations more natural and engaging. Specifically, the evolution unit collects user responses and uses them as data to adjust the content and expression of the dialogue. For example, if a user responds favorably to a particular character's response, it strengthens that character's response pattern. Conversely, if a user responds negatively, it modifies that response pattern. The evolution unit uses machine learning algorithms to analyze user response data and continuously improve the quality of the dialogue. For example, it clusters user response data to identify the optimal response pattern for different user groups. This allows the evolution unit to provide personalized dialogues for each user. The evolution unit also saves the history of conversations and references past conversations to achieve more consistent dialogue. For example, it remembers what users have said in the past and generates responses based on that. This allows the evolution unit to make conversations with users deeper and more continuous. Furthermore, the evolution unit can optimize settings by referencing user feedback when adding new characters or dialogue scenarios. This allows the evolution unit to accelerate the evolution of the dialogue platform and continuously provide users with new experiences.

[0075] The dialogue generation unit can generate dialogue based on the character's personality and background. For example, the dialogue generation unit collects information about the character's personality and background and generates dialogue based on that information. For example, the dialogue generation unit learns the character's tone of voice, manner of speaking, past episodes, etc., and reflects this in the dialogue with the user. For example, the dialogue generation unit can adjust the tone and content of the dialogue based on the character's personality. As a result, more natural conversations become possible by generating dialogue based on the character's personality and background.

[0076] The evolutionary unit can learn from user responses and evolve subsequent conversations to make them more natural and engaging. For example, it can learn how users responded and adjust the next conversation accordingly. For example, it can analyze user responses and improve the content and expression of the conversation. For example, it can adjust the tone and content of the conversation based on user responses. In this way, the quality of the conversation can be improved by learning from user responses.

[0077] The dialogue unit can instantly generate responses to messages entered by the user. For example, the dialogue unit can generate responses to user-entered messages as if a character were speaking. For example, the dialogue unit can generate responses to user-entered messages in real time. The dialogue unit can instantly generate responses to user-entered messages. This enables real-time dialogue by instantly generating responses to user-entered messages.

[0078] The reception desk allows users to choose their favorite character from among movie and anime characters. For example, the reception desk can offer a wide range of characters, including popular anime characters and movie heroes. The reception desk allows users to choose the character they want to interact with. This allows users to choose their favorite character from among movie and anime characters.

[0079] The dialogue generation unit can learn the character's tone of voice, speaking style, past episodes, etc., and reflect them in the dialogue with the user. For example, the dialogue generation unit can learn the character's tone of voice, speaking style, past episodes, etc., and generate dialogue based on that. For example, the dialogue generation unit can learn the character's tone of voice and speaking style, etc., and reflect them in the dialogue with the user. For example, the dialogue generation unit can learn the character's past episodes and generate dialogue based on that. This makes it possible to have more realistic dialogues by learning the character's tone of voice, speaking style, past episodes, etc.

[0080] The reception desk can estimate the user's emotions and present character options based on those emotions. For example, if the user is sad, the reception desk can prioritize presenting a cheering character. For example, if the user is happy, the reception desk can prioritize presenting a humorous character. For example, if the user is stressed, the reception desk can prioritize presenting a relaxing character. This allows for a more personalized experience by presenting character options based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] The reception desk can analyze the user's past character selection history and recommend the most suitable character. For example, the reception desk can prioritize displaying characters that the user has frequently selected in the past. For example, if the reception desk knows that the user prefers characters of a particular genre, it can recommend characters from that genre. For example, based on the personalities of characters the user has selected in the past, the reception desk can recommend characters with similar personalities. In this way, by analyzing the user's past character selection history, the reception desk can recommend the most suitable character.

[0082] The reception system can filter characters based on the user's current interests and preferences when they select a character. For example, it can display characters relevant to movies or anime the user has recently watched. For example, it can prioritize displaying characters the user has mentioned on social media. For example, it can filter characters based on keywords the user has recently searched for. This allows the system to provide more appropriate characters by filtering them based on the user's current interests and preferences.

[0083] The reception desk can estimate the user's emotions and adjust the order in which characters are selected based on those emotions. For example, if the user is tired, the reception desk can display relaxing characters first. For example, if the user is excited, the reception desk can display action-oriented characters first. For example, if the user is depressed, the reception desk can display encouraging characters first. This allows for a more personalized experience by adjusting the order in which characters are selected based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The reception desk can prioritize presenting highly relevant characters by considering the user's geographical location when selecting a character. For example, if the user is in a specific region, the reception desk can display characters related to that region. For example, if the user is traveling, the reception desk can display characters related to their travel destination. For example, if the user is participating in a specific event, the reception desk can display characters related to that event. In this way, by considering the user's geographical location, it is possible to provide highly relevant characters.

[0085] The reception desk can analyze the user's social media activity when selecting a character and recommend relevant characters. For example, the reception desk can prioritize displaying characters that the user follows on social media. For example, the reception desk can display characters that the user has liked on social media. For example, the reception desk can display characters that the user has shared on social media. In this way, by analyzing the user's social media activity, it is possible to provide relevant characters.

[0086] The learning unit can estimate the user's emotions and adjust how it learns the character's personality and background based on the estimated user emotions. For example, if the user is relaxed, the learning unit can learn detailed background information. For example, if the user is in a hurry, the learning unit can focus on learning important personality traits. For example, if the user is excited, the learning unit can learn episode highlights. This allows for more appropriate learning by adjusting the learning method based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The learning unit can adjust the level of detail in its learning based on key episodes and characteristics of the character. For example, it can focus on learning representative episodes of the character. For example, it can learn in detail important events that shape the character's personality. For example, it can learn the character's characteristic catchphrases and behavioral patterns. By adjusting the level of detail in learning based on key episodes and characteristics of the character, the accuracy of the learning is improved.

[0088] The learning unit can apply different learning algorithms depending on the character category during training. For example, it can apply a combat scene learning algorithm to action characters, a humor learning algorithm to comedy characters, and an emotional expression learning algorithm to drama characters. By applying different learning algorithms depending on the character category, the accuracy of the learning process is improved.

[0089] The learning unit can estimate the user's emotions and determine learning priorities based on those estimated emotions. For example, if the user is sad, the learning unit might prioritize learning about encouraging characters. For example, if the user is happy, the learning unit might prioritize learning about humorous characters. For example, if the user is stressed, the learning unit might prioritize learning about relaxing characters. This allows for more appropriate learning by determining learning priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The learning unit can adjust the learning priority based on when the characters were introduced. For example, the learning unit can prioritize learning the most recent characters. For example, the learning unit can prioritize learning popular characters. For example, the learning unit can adjust the learning priority based on user requests. This improves the accuracy of learning by adjusting the learning priority based on when the characters were introduced.

[0091] The learning unit can improve the accuracy of its learning by referring to related works of the character during the learning process. For example, the learning unit can learn by referring to other works in which the character appears. For example, the learning unit can learn by referring to spin-off works of the character. For example, the learning unit can learn by referring to related merchandise and media of the character. In this way, the accuracy of learning is improved by referring to related works of the character.

[0092] The dialogue generation unit can estimate the user's emotions and adjust the way the dialogue is expressed based on the estimated emotions. For example, if the user is sad, the dialogue generation unit can generate a gentle tone of voice. For example, if the user is happy, the dialogue generation unit can generate a cheerful tone of voice. For example, if the user is stressed, the dialogue generation unit can generate a calm tone of voice. In this way, by adjusting the way the dialogue is expressed based on the user's emotions, a more appropriate dialogue is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0093] The dialogue generation unit can adjust the level of detail in the dialogue based on important episodes and characteristics of the characters during the dialogue generation process. For example, the dialogue generation unit can reflect representative episodes of the characters in the dialogue. For example, the dialogue generation unit can reflect important events that shape the characters' personalities in the dialogue. For example, the dialogue generation unit can reflect characteristic catchphrases and behavioral patterns of the characters in the dialogue. By adjusting the level of detail in the dialogue based on important episodes and characteristics of the characters, the accuracy of the dialogue is improved.

[0094] The dialogue generation unit can apply different dialogue algorithms depending on the character category during dialogue generation. For example, it can apply a combat scene dialogue algorithm to an action character. For example, it can apply a humorous dialogue algorithm to a comedy character. For example, it can apply an emotional expression dialogue algorithm to a drama character. By applying different dialogue algorithms depending on the character category, the accuracy of the dialogue is improved.

[0095] The dialogue generation unit can estimate the user's emotions and adjust the length of the dialogue based on the estimated emotions. For example, if the user is in a hurry, the dialogue generation unit can generate a short, to-the-point dialogue. For example, if the user is relaxed, the dialogue generation unit can generate a longer dialogue that includes detailed explanations. For example, if the user is excited, the dialogue generation unit can generate a dialogue with visually stimulating effects. By adjusting the length of the dialogue based on the user's emotions, a more appropriate dialogue is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The dialogue generation unit can determine the priority of dialogues based on the timing of the characters' appearances during dialogue generation. For example, the dialogue generation unit can prioritize the generation of dialogues for the most recent character. For example, the dialogue generation unit can prioritize the generation of dialogues for popular characters. For example, the dialogue generation unit can adjust the priority of dialogues based on user requests. This improves the accuracy of dialogues by determining the priority of dialogues based on the timing of the characters' appearances.

[0097] The dialogue generation unit can improve the accuracy of the dialogue by referencing related works of the characters during dialogue generation. For example, the dialogue generation unit can generate dialogue by referencing other works in which the characters appear. For example, the dialogue generation unit can generate dialogue by referencing spin-off works of the characters. For example, the dialogue generation unit can generate dialogue by referencing related merchandise and media of the characters. In this way, referencing related works of the characters improves the accuracy of the dialogue.

[0098] The dialogue unit can estimate the user's emotions and adjust the way the dialogue proceeds based on the estimated emotions. For example, if the user is sad, the dialogue unit will proceed in a gentle tone. For example, if the user is happy, the dialogue unit can proceed in a cheerful tone. For example, if the user is stressed, the dialogue unit can proceed in a calm tone. In this way, a more appropriate dialogue is conducted by adjusting the way the dialogue proceeds based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The dialogue unit can provide the most appropriate dialogue by referring to the user's past dialogue history during a conversation. For example, the dialogue unit can provide relevant dialogue based on what the user has said in the past. For example, the dialogue unit can prioritize providing topics that the user has shown interest in in the past. For example, the dialogue unit can select the topic of greatest interest from the user's past dialogue history and proceed with the conversation. In this way, the dialogue unit can provide the most appropriate dialogue by referring to the user's past dialogue history.

[0100] The dialogue unit can customize the conversation content based on the user's current interests and preferences. For example, it can customize the conversation content based on movies or anime the user has recently watched. For example, it can reflect topics the user has mentioned on social media in the conversation. For example, it can customize the conversation content based on keywords the user has recently searched for. This allows for more relevant conversations by customizing the content based on the user's current interests and preferences.

[0101] The dialogue unit can estimate the user's emotions and determine the priority of the dialogue based on the estimated emotions. For example, if the user is sad, the dialogue unit can prioritize providing encouraging dialogue. For example, if the user is happy, the dialogue unit can prioritize providing humorous dialogue. For example, if the user is stressed, the dialogue unit can prioritize providing relaxing dialogue. In this way, more appropriate dialogue is provided by determining the priority of dialogue based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The dialogue unit can provide optimal conversations by considering the user's geographical location during the interaction. For example, if the user is in a specific region, the dialogue unit can provide topics related to that region. For example, if the user is traveling, the dialogue unit can provide topics related to the travel destination. For example, if the user is participating in a specific event, the dialogue unit can provide topics related to that event. In this way, by considering the user's geographical location, the dialogue unit can provide optimal conversations.

[0103] The dialogue unit can analyze the user's social media activity during a conversation and customize the conversation content. For example, the dialogue unit can reflect topics the user follows on social media in the conversation. For example, the dialogue unit can reflect topics the user has liked on social media in the conversation. For example, the dialogue unit can reflect topics the user has shared on social media in the conversation. In this way, the conversation content can be customized by analyzing the user's social media activity.

[0104] The evolutionary unit can estimate the user's emotions and adjust the way the dialogue evolves based on the estimated emotions. For example, if the user is sad, the evolutionary unit can evolve the dialogue to be more encouraging. For example, if the user is happy, the evolutionary unit can evolve the dialogue to be more humorous. For example, if the user is stressed, the evolutionary unit can evolve the dialogue to be more relaxing. In this way, by adjusting the way the dialogue evolves based on the user's emotions, a more appropriate dialogue is evolved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The evolution unit can analyze the user's past responses during evolution to select the optimal evolution method. For example, the evolution unit can prioritize evolving dialogue patterns in which the user has shown a favorable response in the past. For example, the evolution unit can prioritize evolving topics in which the user has shown interest in the past. For example, the evolution unit can analyze the user's past responses and select the topics of greatest interest to evolve. In this way, by analyzing the user's past responses, the optimal evolution method can be selected.

[0106] The evolutionary component can evolve the conversation based on the user's current interests and preferences. For example, it can evolve the conversation based on movies or anime the user has recently watched. For example, it can reflect topics the user has mentioned on social media in the conversation. For example, it can evolve the conversation based on keywords the user has recently searched for. This allows for more relevant conversations by evolving the conversation based on the user's current interests and preferences.

[0107] The evolutionary unit can estimate the user's emotions and determine the priority of dialogue evolution based on the estimated emotions. For example, if the user is sad, the evolutionary unit will prioritize evolving the dialogue to encourage them. For example, if the user is happy, the evolutionary unit can prioritize evolving the dialogue to be humorous. For example, if the user is stressed, the evolutionary unit can prioritize evolving the dialogue to be relaxing. In this way, by determining the priority of dialogue evolution based on the user's emotions, more appropriate dialogue is provided. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The evolution unit can select the optimal evolution method by considering the user's geographical location during the evolution process. For example, if the user is in a specific region, the evolution unit can evolve topics related to that region. For example, if the user is traveling, the evolution unit can evolve topics related to the travel destination. For example, if the user is participating in a specific event, the evolution unit can evolve topics related to that event. In this way, the optimal evolution method can be selected by considering the user's geographical location.

[0109] The evolution unit can evolve the dialogue content by analyzing the user's social media activity during the evolution process. For example, the evolution unit can reflect topics that the user follows on social media in the dialogue. For example, the evolution unit can reflect topics that the user has liked on social media in the dialogue. For example, the evolution unit can reflect topics that the user has shared on social media in the dialogue. In this way, the dialogue content can be evolved by analyzing the user's social media activity.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The reception desk can provide information on related merchandise and events based on the character selected by the user. For example, if a user selects a specific character, it can display the latest merchandise information related to that character. It can also provide information on events related to the character selected by the user. Furthermore, it can provide information on fan clubs related to the character selected by the user. This allows users not only to enjoy interacting with the characters but also to obtain related information.

[0112] The learning unit can analyze the user's conversation history and learn the conversation style the user prefers. For example, if the user likes humor, the learning unit can instruct the conversation generation unit to generate humorous conversations based on that information. Similarly, if the user prefers touching stories, the learning unit can instruct the conversation generation unit to generate touching conversations based on that information. Furthermore, if the user shows interest in a particular topic, it can instruct the unit to generate conversations related to that topic. This ensures that conversations are tailored to the user's preferences.

[0113] The dialogue generation unit can dynamically change the topic of the conversation based on the user's input. For example, if the user starts talking about a specific movie, the dialogue generation unit can shift the conversation to a topic related to that movie. Also, if the user starts talking about a specific character, it can provide episodes and background information related to that character. Furthermore, if the user expresses a specific emotion, it can generate a conversation that corresponds to that emotion. In this way, a conversation tailored to the user's interests and concerns is provided.

[0114] The evolutionary component can optimize the way a conversation progresses based on the user's conversation history. For example, if a user has previously preferred a particular conversation pattern, that pattern can be prioritized. Also, if a user shows interest in a particular topic, conversations related to that topic can be prioritized. Furthermore, if a user expresses a particular emotion, the conversation can evolve to reflect that emotion. This ensures that conversations are tailored to the user's preferences and interests.

[0115] The dialogue unit can dynamically change the tone and style of the conversation based on the user's input. For example, if the user is speaking in a relaxed tone, the dialogue unit can generate a response that matches that tone. If the user is excited, it can generate a response that matches that excitement. Furthermore, if the user is speaking emotionally, it can generate a response that reflects that emotion. This provides a conversation that is tailored to the user's tone and style.

[0116] The reception desk can estimate the user's emotions and present character options based on those estimates. For example, if the user is sad, it can prioritize presenting a cheering character. If the user is having fun, it can prioritize presenting a humorous character. Furthermore, if the user is stressed, it can prioritize presenting a relaxing character. By presenting character options based on the user's emotions, a more personalized experience can be provided.

[0117] The learning unit can estimate the user's emotions and adjust how it learns the character's personality and background based on those emotions. For example, if the user is relaxed, it can learn detailed background information. If the user is in a hurry, it can focus on learning important personality traits. Furthermore, if the user is excited, it can learn episode highlights. By adjusting the learning method based on the user's emotions, more appropriate learning becomes possible.

[0118] The dialogue generation unit can estimate the user's emotions and adjust the way the dialogue is expressed based on those emotions. For example, if the user is sad, the dialogue can be generated in a gentle tone. If the user is happy, the dialogue can be generated in a cheerful tone. Furthermore, if the user is stressed, the dialogue can be generated in a calm tone. By adjusting the way the dialogue is expressed based on the user's emotions, a more appropriate dialogue can be generated.

[0119] The dialogue unit can estimate the user's emotions and adjust the way the dialogue proceeds based on those emotions. For example, if the user is sad, the dialogue can proceed in a gentle tone. If the user is happy, the dialogue can proceed in a cheerful tone. Furthermore, if the user is stressed, the dialogue can proceed in a calm tone. In this way, by adjusting the way the dialogue proceeds based on the user's emotions, a more appropriate dialogue can be conducted.

[0120] The evolution unit can estimate the user's emotions and adjust the way the dialogue evolves based on those emotions. For example, if the user is sad, the dialogue can evolve to be more encouraging. If the user is happy, the dialogue can evolve to be more humorous. Furthermore, if the user is stressed, the dialogue can evolve to be more relaxing. In this way, by adjusting the way the dialogue evolves based on the user's emotions, a more appropriate dialogue is developed.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The reception desk allows the user to select the character they wish to interact with. For example, they can choose their favorite character from movies or anime. The reception desk offers a wide range of characters, including popular anime characters and movie heroes. Step 2: The learning unit learns the personality and background of the character selected by the reception unit. For example, it collects information about the character's personality and background and generates dialogue based on it. The learning unit learns the character's tone of voice, speaking style, past episodes, etc., and reflects this in the dialogue with the user. Step 3: The dialogue generation unit generates dialogue based on the information learned by the learning unit. For example, it generates dialogue based on the character's personality and background. The dialogue generation unit generates dialogue that reflects the character's tone of voice, manner of speaking, past episodes, etc. Step 4: The dialogue unit performs the dialogue generated by the dialogue generation unit in real time. For example, it instantly generates a response to a message entered by the user. The dialogue unit generates a response to the message entered by the user as if a character were speaking. Step 5: The evolution unit learns from the user's responses to the dialogue conducted by the dialogue unit and evolves the dialogue. For example, it learns how the user responded and uses that to evolve the next dialogue to make it more natural and engaging. The evolution unit learns from the user's responses and adjusts the content and expression of the dialogue.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the reception unit, learning unit, dialogue generation unit, dialogue unit, and evolution unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14, where the user selects the character they wish to interact with. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, where it learns the personality and background of the selected character. The dialogue generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where it generates a dialogue based on the learned information. The dialogue unit is implemented by the control unit 46A of the smart device 14, where it performs the generated dialogue in real time. The evolution unit is implemented by the specific processing unit 290 of the data processing unit 12, where it learns the user's responses and evolves the dialogue. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the reception unit, learning unit, dialogue generation unit, dialogue unit, and evolution unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214, where the user selects the character they wish to interact with. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, where it learns the personality and background of the selected character. The dialogue generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where it generates a dialogue based on the learned information. The dialogue unit is implemented by the control unit 46A of the smart glasses 214, where it performs the generated dialogue in real time. The evolution unit is implemented by the specific processing unit 290 of the data processing unit 12, where it learns the user's responses and evolves the dialogue. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the reception unit, learning unit, dialogue generation unit, dialogue unit, and evolution unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314, where the user selects the character they wish to interact with. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, where it learns the personality and background of the selected character. The dialogue generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where it generates a dialogue based on the learned information. The dialogue unit is implemented by the control unit 46A of the headset terminal 314, where it performs the generated dialogue in real time. The evolution unit is implemented by the specific processing unit 290 of the data processing unit 12, where it learns the user's responses and evolves the dialogue. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the reception unit, learning unit, dialogue generation unit, dialogue unit, and evolution unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414, which allows the user to select a character to interact with. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns the personality and background of the selected character. The dialogue generation unit is implemented by the specific processing unit 290 of the data processing unit 12, which generates a dialogue based on the learned information. The dialogue unit is implemented by the control unit 46A of the robot 414, which performs the generated dialogue in real time. The evolution unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns the user's responses and evolves the dialogue. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A reception desk where the user selects the character they want to interact with, A learning unit that learns the personality and background of the character selected by the reception unit, A dialogue generation unit generates a dialogue based on the information learned by the learning unit, A dialogue unit that performs the dialogue generated by the dialogue generation unit in real time, The system includes an evolution unit that learns the user's responses to the dialogue conducted by the dialogue unit and evolves the dialogue accordingly. A system characterized by the following features. (Note 2) The dialogue generation unit, Generate dialogue based on the character's personality and background. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned evolutionary section is Learn from user responses and evolve the next conversation to be more natural and engaging. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned dialogue unit, Generates an instant response to a message entered by the user. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is You can choose your favorite character from movies and anime characters. The system described in Appendix 1, characterized by the features described herein. (Note 6) The dialogue generation unit, The system learns the character's tone of voice, speaking style, and past episodes, and reflects this in interactions with the user. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the user's emotions and presents character choices based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system analyzes the user's past character selection history and recommends the most suitable character. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When selecting a character, filtering is performed based on the user's current interests and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and adjusts the character selection order based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When selecting a character, the system prioritizes displaying characters that are highly relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When selecting a character, the system analyzes the user's social media activity and recommends relevant characters. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, It estimates the user's emotions and adjusts how the character's personality and background are learned based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, During learning, the level of detail in the learning process is adjusted based on important episodes and characteristics of the character. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned learning unit, During training, different learning algorithms are applied depending on the character category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, It estimates the user's emotions and determines learning priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned learning unit, During learning, the learning priorities are adjusted based on when the characters appear. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning unit, During learning, refer to related works of the characters to improve the accuracy of the learning process. The system described in Appendix 1, characterized by the features described herein. (Note 19) The dialogue generation unit, It estimates the user's emotions and adjusts the way the dialogue is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The dialogue generation unit, When generating dialogue, adjust the level of detail based on important episodes and characteristics of the characters. The system described in Appendix 1, characterized by the features described herein. (Note 21) The dialogue generation unit, When generating dialogue, different dialogue algorithms are applied depending on the character's category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The dialogue generation unit, It estimates the user's emotions and adjusts the length of the conversation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The dialogue generation unit, When generating dialogue, the priority of the dialogue is determined based on when the characters appear. The system described in Appendix 1, characterized by the features described herein. (Note 24) The dialogue generation unit, When generating dialogue, the system references related works of the characters to improve the accuracy of the dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way the conversation progresses based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned dialogue unit, During conversations, the system provides the most appropriate dialogue by referring to the user's past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned dialogue unit, During conversations, the content of the conversation is customized based on the user's current interests and concerns. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned dialogue unit, It estimates the user's emotions and determines the priority of the conversation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned dialogue unit, During conversations, the system takes the user's geographical location into consideration to provide the most appropriate dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned dialogue unit, During conversations, the system analyzes the user's social media activity to customize the conversation content. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned evolutionary section is It estimates the user's emotions and adjusts how the dialogue evolves based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned evolutionary section is During evolution, the system analyzes past user responses to select the optimal evolution method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned evolutionary section is During evolution, the dialogue content evolves based on the user's current interests and concerns. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned evolutionary section is It estimates the user's emotions and determines the priority of dialogue evolution based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned evolutionary section is During evolution, the optimal evolution method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned evolutionary section is During evolution, the content of the dialogue is evolved by analyzing the user's social media activity. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk where the user selects the character they want to interact with, A learning unit that learns the personality and background of the character selected by the reception unit, A dialogue generation unit generates a dialogue based on the information learned by the learning unit, A dialogue unit that performs the dialogue generated by the dialogue generation unit in real time, The system includes an evolution unit that learns the user's responses to the dialogue conducted by the dialogue unit and evolves the dialogue accordingly. A system characterized by the following features.

2. The dialogue generation unit, Generate dialogue based on the character's personality and background. The system according to feature 1.

3. The aforementioned evolutionary section is Learn from user responses and evolve the next conversation to be more natural and engaging. The system according to feature 1.

4. The aforementioned dialogue unit, Generates an instant response to a message entered by the user. The system according to feature 1.

5. The aforementioned reception unit is You can choose your favorite character from movies and anime characters. The system according to feature 1.

6. The dialogue generation unit, The system learns the character's tone of voice, speaking style, and past episodes, and reflects this in interactions with the user. The system according to feature 1.

7. The aforementioned reception unit is It estimates the user's emotions and presents character choices based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is The system analyzes the user's past character selection history and recommends the most suitable character. The system according to feature 1.

9. The aforementioned reception unit is When selecting a character, filtering is performed based on the user's current interests and preferences. The system according to feature 1.

10. The aforementioned reception unit is It estimates the user's emotions and adjusts the character selection order based on the estimated emotions. The system according to feature 1.

Images