System

Abstract

An object of the system according to the embodiment is to reproduce the exchange between the public account and the private account and satisfy the curiosity of the user.SOLUTION: A system according to an embodiment includes a prompt generation unit, a reply generation unit, and a policy setting unit. The prompt generation unit generates a prompt including the public account tweet content and the reproduction policy set by the user. The reply generation unit generates a reply content of the key owner side based on the prompt generated by the prompt generation unit. The policy setting unit allows a user to set a reproduction policy.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult to reproduce interactions between public and private accounts, and cannot satisfy users' curiosity.

[0005] The system according to the embodiment aims to recreate interactions between public and private accounts and satisfy users' curiosity. [Means for solving the problem]

[0006] The system according to the embodiment includes a prompt generation unit, a reply generation unit, and a policy setting unit. The prompt generation unit generates a prompt including the tweet content of the public account and a reproduction policy set by the user. The reply generation unit generates a reply content for the private account based on the prompt generated by the prompt generation unit. The policy setting unit allows the user to set the reproduction policy. [Effects of the Invention]

[0007] The system according to the embodiment can reproduce interactions between public and private accounts, satisfying the user's curiosity. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) An application according to an embodiment of the present invention is targeted at users who are interested in interactions between public and private accounts (locked accounts) on X (formerly Twitter (registered trademark)). This application provides a function to infer and reproduce the content of replies from the locked account using a generation AI. This allows the application to generate replies from the locked account based on the policy set by the user, allowing users to enjoy the results. Costs can be recovered through advertising revenue and sales of usage data.

[0029] An application according to an embodiment includes a generation AI, a prompt generation unit, a reply generation unit, and a policy setting unit. The generation AI uses a specific model, such as GPT-3 or BERT. The prompt generation unit generates a prompt including the tweet content of a public account and a reproduction policy set by the user. For example, if a public account tweets, "It's a nice day today," the prompt generation unit generates a prompt including the tweet content, "It's a nice day today," and a "friendly" policy set by the user. The reply generation unit generates a reply content for the private account based on the prompt generated by the prompt generation unit. For example, the generation AI generates a reply such as, "Yes, I'd like to go for a walk." The policy setting unit allows the user to set a reproduction policy. For example, the user can instruct the reply content to be reproduced in a tone such as "friendly," "sarcastic," or "humorous." This allows the user to enjoy reply content tailored to their preferences. This allows the application according to an embodiment to generate a reply content for the private account based on the policy set by the user.

[0030] The prompt generation unit can generate prompts based on the tweet content of the public account and the user's past tweet history or interests. For example, when the generation AI infers the content of replies from the private account, the prompt generation unit analyzes the user's past tweet history and generates personalized replies based on that content. For example, it extracts themes and keywords that the user frequently tweets about and generates replies related to them. The prompt generation unit also personalizes the replies from the private account by taking the user's interests into account. For example, it analyzes the content of accounts the user follows and tweets they have "liked" and generates replies based on that. The prompt generation unit also combines the user's past tweet history and interests to generate more accurate personalized replies. For example, if a user frequently tweets about a specific event or topic, it generates replies related to that content. This allows for more personalized replies to be generated by generating prompts that take the user's past tweet history and interests into account.

[0031] The reply generation unit can generate a reply for the private account by referring to other users' reactions to the public account's tweet. For example, the reply generation unit uses a generation AI to analyze other users' reactions to the public account's tweet and generate a reply for the private account by referring to those reactions. For example, it recreates a natural flow of conversation by taking into account the reactions other users have shown through "likes" or replies. The reply generation unit also uses a generation AI to generate a reply for the private account by referring to other users' reactions to the public account's tweet. For example, it analyzes how other users feel about the tweet and generates a reply based on those emotions. The reply generation unit also uses a generation AI to collect other users' reactions to the public account's tweet in real time and generate a reply for the private account based on that data. For example, it recreates a more natural flow of conversation by referring to the content of other users' replies and quoted tweets. This allows a more natural flow of conversation to be recreated by referring to other users' reactions.

[0032] The reply generation unit can generate replies that include multimedia content, such as images or videos. For example, when the generation AI generates a reply for a private account, the reply generation unit includes multimedia content such as images and videos. For example, in response to a tweet from a public account, the reply generation unit generates a reply that attaches related images or videos. In addition, to generate a reply that includes multimedia content, the generation AI analyzes the content of the tweet from the public account and selects appropriate images or videos. For example, the reply includes a GIF or short video related to the content of the tweet. In addition, when the generation AI generates a reply for a private account, the reply generation unit uses images and videos uploaded by the user. For example, by instructing the user to include a specific image or video in the reply, a more personalized reply is generated. This allows for the generation of a reply that includes multimedia content, making it possible to provide richer reply content.

[0033] The reply generation unit can be expanded to reproduce interactions on different social media platforms. The reply generation unit is expanded, for example, so that the generation AI can reproduce interactions on different social media platforms. For example, a function for generating replies to Instagram (registered trademark) comments and Facebook (registered trademark) posts is added. The reply generation unit also collects data from different social media platforms, and the generation AI generates replies for private accounts based on that data. For example, it reproduces comments on Instagram (registered trademark) photo posts and replies to Facebook (registered trademark) posts. The reply generation unit also takes into account the characteristics of each platform when the generation AI reproduces interactions on different social media platforms. For example, it generates replies in response to Instagram (registered trademark) posts that emphasize visuals and Facebook (registered trademark) posts that emphasize text. This allows interactions on different social media platforms to be reproduced, thereby enabling support for a wider variety of usage scenarios.

[0034] The policy setting unit can learn the user's past setting history and propose an optimal policy that matches the user's preferences. In the policy setting unit, for example, the generation AI learns the user's past setting history and proposes a reproduction policy. For example, the optimal policy is proposed based on the tones and themes selected by the user in the past. Furthermore, when the user sets a reproduction policy, the generation AI refers to the past setting history and proposes a policy that matches the user's preferences. For example, the generation AI prioritizes proposing tones and themes that the user frequently selects. Furthermore, the policy setting unit can analyze the user's past setting history and propose a reproduction policy based on that data. For example, if the user prefers a particular theme or tone, the generation AI prioritizes proposing that policy. In this way, by learning the user's past setting history, the optimal policy that matches the user's preferences can be proposed.

[0035] The policy setting unit can cause the generation AI to generate multiple reply candidates based on a policy selected by the user and allow the user to select from them. For example, when the user sets a reproduction policy, the policy setting unit causes the generation AI to generate multiple reply candidates and allow the user to select from them. For example, the policy setting unit generates reply candidates with tones such as friendly, sarcastic, and humorous. The policy setting unit also causes the generation AI to generate multiple reply candidates based on the policy selected by the user and allow the user to select the optimal reply. For example, the policy setting unit presents reply candidates with different tones or themes. The policy setting unit also causes the generation AI to generate multiple reply candidates in real time when the user sets a reproduction policy and allow the user to select from them. For example, the policy setting unit presents different reply content depending on the policy selected by the user. This allows the generation AI to generate multiple reply candidates based on the policy selected by the user and allow the user to select from them, thereby providing a wider variety of reply content.

[0036] The policy setting unit allows the generation AI to generate replies in different tones based on a policy selected by the user. For example, when the user sets a reproduction policy, the policy setting unit causes the generation AI to generate replies in different tones. For example, the generation AI generates replies in a formal tone or a casual tone. The policy setting unit also causes the generation AI to generate replies in different tones based on a policy selected by the user. For example, the generation AI generates replies in a businesslike tone or a friendly tone. The policy setting unit also causes the generation AI to generate replies in different tones in real time when the user sets a reproduction policy. For example, the generation AI generates replies according to formal and casual situations. In this way, by generating replies in different tones, it is possible to provide replies that meet the diverse needs of users.

[0037] The policy setting unit can enable a user to recreate reply content based on a specific theme. For example, when a user sets a recreation policy, the policy setting unit causes the generation AI to generate reply content based on a specific theme. For example, reply content related to sports or entertainment is generated. The policy setting unit also causes the generation AI to generate reply content based on a theme selected by the user. For example, reply content related to a specific movie or music is generated. The policy setting unit also causes the generation AI to generate reply content based on a specific theme in real time when a user sets a recreation policy. For example, replies related to sporting events or entertainment news are generated. This makes it possible to recreate reply content based on a specific theme, thereby providing interactions that match the user's interests.

[0038] The generation AI can analyze a user's interests and prioritize recreating interactions between specific celebrities or friends. For example, the generation AI analyzes a user's interests and prioritizes recreating interactions between specific celebrities or friends. For example, it recreates interactions between celebrities the user follows. The generation AI also analyzes a user's interests and recreates interactions between specific celebrities or friends based on that data. For example, it recreates tweets by celebrities that the user frequently "likes." The generation AI also analyzes a user's interests in real time and prioritizes recreating interactions between specific celebrities or friends based on the results. For example, it recreates interactions related to topics that the user is interested in. In this way, by analyzing a user's interests, it is possible to prioritize recreating interactions between specific celebrities or friends.

[0039] The generation AI can provide related news and trending information when a user re-enacts an interaction based on a specific theme. For example, the generation AI provides related news and trending information when a user re-enacts an interaction based on a specific theme. For example, it displays the latest news related to sports or entertainment. The generation AI also provides related news and trending information based on a theme selected by the user. For example, it displays the latest information related to specific movies or music. The generation AI also provides related news and trending information in real time when a user re-enacts an interaction based on a specific theme. For example, it displays information related to sporting events or entertainment news. This makes it possible to keep a user interested by providing related news and trending information when re-enacting an interaction based on a specific theme.

[0040] The generation AI can be expanded to reproduce interactions on different social media platforms. For example, the generation AI can be expanded to reproduce interactions on different social media platforms. For example, a function to generate replies to Instagram (registered trademark) comments and Facebook (registered trademark) posts can be added. The generation AI also collects data from different social media platforms and generates replies for private accounts based on that data. For example, it reproduces comments on Instagram (registered trademark) photo posts and replies to Facebook (registered trademark) posts. When reproducing interactions on different social media platforms, the generation AI also takes into account the characteristics of each platform. For example, it generates replies in response to Instagram (registered trademark) posts that emphasize visuals and Facebook (registered trademark) posts that emphasize text. This makes it possible to reproduce interactions on different social media platforms, thereby enabling support for a wider variety of usage scenarios.

[0041] The generation AI can enable a user to recreate interactions based on a specific event. The generation AI, for example, enables a user to recreate interactions based on a specific event. For example, interactions related to a sports game or a movie release are generated. The generation AI also recreates interactions based on an event selected by the user. For example, interactions related to a specific sports game or a movie release are generated. The generation AI also generates related interactions in real time as the user recreates an interaction based on a specific event. For example, interactions related to a sports event or a movie release are generated. This makes it possible to provide interactions that match the user's interests by allowing interactions based on a specific event to be recreated.

[0042] Generative AI can learn a user's usage history and suggest optimal usage scenarios. For example, generative AI can learn a user's past usage history and suggest optimal usage scenarios based on that data. For example, it can suggest scenarios based on the functions and themes that the user frequently uses. Generative AI can also analyze a user's usage history and build a system that suggests optimal usage scenarios based on the results. For example, it can suggest scenarios based on tones and themes that the user has selected in the past. Generative AI can also learn a user's usage history in real time and suggest optimal usage scenarios based on that data. For example, it can suggest scenarios based on topics that the user is currently interested in. In this way, it can suggest optimal usage scenarios by learning a user's usage history.

[0043] The generation AI can suggest related content when a user re-enacts an interaction based on a specific theme. For example, the generation AI suggests related content when a user re-enacts an interaction based on a specific theme. For example, it displays articles and videos related to sports or entertainment. The generation AI also suggests related content based on a theme selected by the user. For example, it displays content related to specific movies or music. The generation AI also suggests related content in real time when a user re-enacts an interaction based on a specific theme. For example, it displays content related to sporting events or entertainment news. This makes it possible to keep the user interested by suggesting related content when re-enacting an interaction based on a specific theme.

[0044] The generation AI can be expanded to reproduce interactions on different social media platforms. For example, the generation AI can be expanded to reproduce interactions on different social media platforms. For example, a function to generate replies to Instagram (registered trademark) comments and Facebook (registered trademark) posts can be added. The generation AI also collects data from different social media platforms and generates replies for private accounts based on that data. For example, it reproduces comments on Instagram (registered trademark) photo posts and replies to Facebook (registered trademark) posts. When reproducing interactions on different social media platforms, the generation AI also takes into account the characteristics of each platform. For example, it generates replies in response to Instagram (registered trademark) posts that emphasize visuals and Facebook (registered trademark) posts that emphasize text. This makes it possible to reproduce interactions on different social media platforms, thereby enabling support for a wider variety of usage scenarios.

[0045] The generation AI can enable a user to recreate interactions based on a specific event. The generation AI, for example, enables a user to recreate interactions based on a specific event. For example, interactions related to a sports game or a movie release are generated. The generation AI also recreates interactions based on an event selected by the user. For example, interactions related to a specific sports game or a movie release are generated. The generation AI also generates related interactions in real time as the user recreates an interaction based on a specific event. For example, interactions related to a sports event or a movie release are generated. This makes it possible to provide interactions that match the user's interests by allowing interactions based on a specific event to be recreated.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] Based on a user's past tweet history and interests, a reply related to a specific theme can be generated. For example, if a user is interested in sports, the prompt generation unit generates a reply related to sports. Specifically, if a user tweets, "I'm going to see a game today," the prompt generation unit generates a reply such as, "Which team are you rooting for?" If a user is interested in entertainment, the prompt generation unit generates a reply related to entertainment. For example, if a user tweets, "I saw a new movie," the prompt generation unit generates a reply such as, "What did you think of the movie?" Furthermore, if a user is interested in a particular event, a reply related to that event can also be generated. For example, if a user tweets, "I'm going to a concert," the prompt generation unit generates a reply such as, "Which artist's concert?" This makes it possible to provide a more personalized reply based on the user's interests.

[0048] By referencing other users' reactions to tweets from public accounts, the reply generator can generate a wider variety of replies. For example, the reply generator can recreate a natural conversation flow by referring to other users' reactions through "likes" and replies. Specifically, if a public account tweets, "I started a new project today," the reply generator can generate a reply such as, "What kind of project is it?" based on other users' reactions. The reply generator can also analyze the emotions expressed by other users in response to a tweet and generate replies based on those emotions. For example, if another user responds positively with, "That's amazing!", the reply generator can generate a reply such as, "That's really amazing!". Furthermore, the reply generator can collect the content of other users' replies and quoted tweets in real time and generate replies for private accounts based on that data. For example, if another user sends a message of encouragement saying, "Good luck," the reply generator can generate a reply such as, "Thank you, I'll do my best!". By referring to other users' reactions, the reply generator can recreate a more natural conversation flow.

[0049] It is possible to generate replies that include multimedia content, such as images or videos. For example, in response to a tweet from a public account, a reply can be generated that includes related images or videos. Specifically, if a public account tweets, "I started a new project today," the reply generation unit can generate a reply that includes images or videos related to the project. The generation AI can also analyze the content of the public account's tweet and select appropriate images or videos. For example, GIFs or short videos related to the tweet content can be included in the reply. Furthermore, images and videos uploaded by the user can be used. For example, a user can specify that a specific image or video be included in the reply, allowing for the generation of more personalized replies. This allows for the generation of replies that include multimedia content, thereby providing richer reply content.

[0050] The system can be expanded to reproduce interactions across different social media platforms. For example, a function for generating replies to Instagram® comments and Facebook® posts can be added. Specifically, it can reproduce comments on Instagram® photo posts and replies to Facebook® posts. The generation AI can also collect data from different social media platforms and generate replies for private accounts based on that data. For example, it can generate replies for Instagram® posts that emphasize visuals and Facebook® posts that emphasize text. Furthermore, it can generate more natural replies by taking into account the characteristics of each platform. For example, it can generate replies that emphasize visuals for Instagram® posts and replies that emphasize text for Facebook® posts. This allows the system to reproduce interactions across different social media platforms, enabling it to accommodate a wider variety of usage scenarios.

[0051] The system can learn the user's past setting history and propose the optimal policy that matches the user's preferences. For example, the system can propose the optimal policy based on the tones and themes selected by the user in the past. Specifically, it can prioritize suggestions for tones and themes that the user frequently selects. The generation AI can also analyze the user's past setting history and propose a reproduction policy based on that data. For example, if the user prefers a particular theme or tone, it can prioritize suggestions for that policy. Furthermore, when the user sets a reproduction policy, the generation AI can refer to the user's past setting history and propose a policy that matches the user's preferences. For example, it can propose the optimal policy based on the tones and themes selected by the user in the past. In this way, by learning the user's past setting history, it is possible to propose the optimal policy that matches the user's preferences.

[0052] Based on the policy selected by the user, the generation AI can generate multiple reply candidates and allow the user to choose from them. For example, reply candidates can be generated in tones such as friendly, sarcastic, and humorous. Specifically, if the user selects a "friendly" policy, the reply generation unit can generate a reply candidate such as "What a great day today!". If the user selects a "sarcastic" policy, the reply generation unit can generate a reply candidate such as "I don't think it's really a great day, though." Furthermore, if the user selects a "humorous" policy, the reply generation unit can generate a reply candidate such as "Today is a great day, but what about tomorrow?" This allows the system to provide a wider variety of reply content by generating multiple reply candidates based on the policy selected by the user and allowing the user to choose from them.

[0053] It is possible to enable a user to reproduce replies based on a specific theme. For example, a user can generate replies related to sports or entertainment. Specifically, if a user tweets, "I'm going to see a game today," the policy setting unit can set the "sports" theme, and the reply generation unit can generate a reply such as, "Which team are you rooting for?". If a user tweets, "I saw a new movie," the policy setting unit can set the "entertainment" theme, and the reply generation unit can generate a reply such as, "How was the movie?". Furthermore, if a user is interested in a specific event, a reply related to the event can be generated. For example, if a user tweets, "I'm going to a concert," the policy setting unit can set the "event" theme, and the reply generation unit can generate a reply such as, "Which artist's concert?". This makes it possible to reproduce replies based on a specific theme, thereby providing interactions that match the user's interests.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The prompt generator generates a prompt that includes the tweet content of the public account and the reproduction policy set by the user. For example, if a public account tweets "It's a nice day today," the prompt generator generates a prompt that includes the tweet content "It's a nice day today" and the "friendly" policy set by the user. Step 2: The reply generator generates a reply from the account based on the prompt generated by the prompt generator. For example, the AI ​​might generate a reply such as, "Yes, I'd like to go for a walk." Step 3: The policy setting unit allows the user to set a reproduction policy. For example, the user can instruct the reply content to be reproduced in a "friendly," "sarcastic," "humorous," or other tone.

[0056] (Example 2) An application according to an embodiment of the present invention is targeted at users who are interested in interactions between public and private accounts (locked accounts) on X (formerly Twitter (registered trademark)). This application provides a function to infer and reproduce the content of replies from the locked account using a generation AI. This allows the application to generate replies from the locked account based on the policy set by the user, allowing users to enjoy the results. Costs can be recovered through advertising revenue and sales of usage data.

[0057] An application according to an embodiment includes a generation AI, a prompt generation unit, a reply generation unit, and a policy setting unit. The generation AI uses a specific model, such as GPT-3 or BERT. The prompt generation unit generates a prompt including the tweet content of a public account and a reproduction policy set by the user. For example, if a public account tweets, "It's a nice day today," the prompt generation unit generates a prompt including the tweet content, "It's a nice day today," and a "friendly" policy set by the user. The reply generation unit generates a reply content for the private account based on the prompt generated by the prompt generation unit. For example, the generation AI generates a reply such as, "Yes, I'd like to go for a walk." The policy setting unit allows the user to set a reproduction policy. For example, the user can instruct the reply content to be reproduced in a tone such as "friendly," "sarcastic," or "humorous." This allows the user to enjoy reply content tailored to their preferences. This allows the application according to an embodiment to generate a reply content for the private account based on the policy set by the user.

[0058] The prompt generation unit can generate prompts based on the tweet content of the public account and the user's past tweet history or interests. For example, when the generation AI infers the content of replies from the private account, the prompt generation unit analyzes the user's past tweet history and generates personalized replies based on that content. For example, it extracts themes and keywords that the user frequently tweets about and generates replies related to them. The prompt generation unit also personalizes the replies from the private account by taking the user's interests into account. For example, it analyzes the content of accounts the user follows and tweets they have "liked" and generates replies based on that. The prompt generation unit also combines the user's past tweet history and interests to generate more accurate personalized replies. For example, if a user frequently tweets about a specific event or topic, it generates replies related to that content. This allows for more personalized replies to be generated by generating prompts that take the user's past tweet history and interests into account.

[0059] The reply generation unit can generate a reply for the private account by referring to other users' reactions to the public account's tweet. For example, the reply generation unit uses a generation AI to analyze other users' reactions to the public account's tweet and generate a reply for the private account by referring to those reactions. For example, it recreates a natural flow of conversation by taking into account the reactions other users have shown through "likes" or replies. The reply generation unit also uses a generation AI to generate a reply for the private account by referring to other users' reactions to the public account's tweet. For example, it analyzes how other users feel about the tweet and generates a reply based on those emotions. The reply generation unit also uses a generation AI to collect other users' reactions to the public account's tweet in real time and generate a reply for the private account based on that data. For example, it recreates a more natural flow of conversation by referring to the content of other users' replies and quoted tweets. This allows a more natural flow of conversation to be recreated by referring to other users' reactions.

[0060] The reply generation unit can use the emotion estimation function to estimate the emotion of the private account in response to the public account's tweet and generate a reply based on that emotion. For example, the reply generation unit uses a generation AI to estimate the emotion of the public account's tweet and generate a reply based on that emotion. For example, if the public account's tweet expresses a positive emotion, the private account's reply will also be positive. The reply generation unit also uses the emotion estimation function to estimate the emotion of the private account in response to the public account's tweet and generate a reply based on that emotion. For example, if the public account's tweet expresses a negative emotion, the private account's reply will also be appropriate. The reply generation unit also uses the generation AI to estimate the emotion of the public account in response to the tweet in real time and generate a reply based on that emotion. For example, if the public account's tweet expresses surprise or joy, the private account's reply will also reflect that emotion. In this way, by using the emotion estimation function, reply content can be generated that is more based on emotion.

[0061] The reply generation unit can generate replies that include multimedia content, such as images or videos. For example, when the generation AI generates a reply for a private account, the reply generation unit includes multimedia content such as images and videos. For example, in response to a tweet from a public account, the reply generation unit generates a reply that attaches related images or videos. In addition, to generate a reply that includes multimedia content, the generation AI analyzes the content of the tweet from the public account and selects appropriate images or videos. For example, the reply includes a GIF or short video related to the content of the tweet. In addition, when the generation AI generates a reply for a private account, the reply generation unit uses images and videos uploaded by the user. For example, by instructing the user to include a specific image or video in the reply, a more personalized reply is generated. This allows for the generation of a reply that includes multimedia content, making it possible to provide richer reply content.

[0062] The reply generation unit can be expanded to reproduce interactions on different social media platforms. The reply generation unit is expanded, for example, so that the generation AI can reproduce interactions on different social media platforms. For example, a function for generating replies to Instagram (registered trademark) comments and Facebook (registered trademark) posts is added. The reply generation unit also collects data from different social media platforms, and the generation AI generates replies for private accounts based on that data. For example, it reproduces comments on Instagram (registered trademark) photo posts and replies to Facebook (registered trademark) posts. The reply generation unit also takes into account the characteristics of each platform when the generation AI reproduces interactions on different social media platforms. For example, it generates replies in response to Instagram (registered trademark) posts that emphasize visuals and Facebook (registered trademark) posts that emphasize text. This allows interactions on different social media platforms to be reproduced, thereby enabling support for a wider variety of usage scenarios.

[0063] The policy setting unit can learn the user's past setting history and propose an optimal policy that matches the user's preferences. In the policy setting unit, for example, the generation AI learns the user's past setting history and proposes a reproduction policy. For example, the optimal policy is proposed based on the tones and themes selected by the user in the past. Furthermore, when the user sets a reproduction policy, the generation AI refers to the past setting history and proposes a policy that matches the user's preferences. For example, the generation AI prioritizes proposing tones and themes that the user frequently selects. Furthermore, the policy setting unit can analyze the user's past setting history and propose a reproduction policy based on that data. For example, if the user prefers a particular theme or tone, the generation AI prioritizes proposing that policy. In this way, by learning the user's past setting history, the optimal policy that matches the user's preferences can be proposed.

[0064] The policy setting unit can cause the generation AI to generate multiple reply candidates based on a policy selected by the user and allow the user to select from them. For example, when the user sets a reproduction policy, the policy setting unit causes the generation AI to generate multiple reply candidates and allow the user to select from them. For example, the policy setting unit generates reply candidates with tones such as friendly, sarcastic, and humorous. The policy setting unit also causes the generation AI to generate multiple reply candidates based on the policy selected by the user and allow the user to select the optimal reply. For example, the policy setting unit presents reply candidates with different tones or themes. The policy setting unit also causes the generation AI to generate multiple reply candidates in real time when the user sets a reproduction policy and allow the user to select from them. For example, the policy setting unit presents different reply content depending on the policy selected by the user. This allows the generation AI to generate multiple reply candidates based on the policy selected by the user and allow the user to select from them, thereby providing a wider variety of reply content.

[0065] The policy setting unit can use the emotion estimation function to enable the user to set a policy for recreating reply content with a specific emotion. For example, the policy setting unit uses the emotion estimation function to enable the user to set a policy for recreating reply content with a specific emotion. For example, the policy setting unit sets a policy for recreating reply content with a positive emotion. The policy setting unit also enables the generation AI to estimate the user's emotion and set a policy for recreating reply content based on the emotion. For example, the policy setting unit sets a policy for recreating reply content with a negative emotion. The policy setting unit also uses the emotion estimation function to enable the user to set a policy in real time for recreating reply content with a specific emotion. For example, the policy setting unit sets a policy for recreating reply content with a surprise or joy. In this way, the emotion estimation function enables the user to set a policy for recreating reply content with a specific emotion.

[0066] The policy setting unit allows the generation AI to generate replies in different tones based on a policy selected by the user. For example, when the user sets a reproduction policy, the policy setting unit causes the generation AI to generate replies in different tones. For example, the generation AI generates replies in a formal tone or a casual tone. The policy setting unit also causes the generation AI to generate replies in different tones based on a policy selected by the user. For example, the generation AI generates replies in a businesslike tone or a friendly tone. The policy setting unit also causes the generation AI to generate replies in different tones in real time when the user sets a reproduction policy. For example, the generation AI generates replies according to formal and casual situations. In this way, by generating replies in different tones, it is possible to provide replies that meet the diverse needs of users.

[0067] The policy setting unit can enable a user to recreate reply content based on a specific theme. For example, when a user sets a recreation policy, the policy setting unit causes the generation AI to generate reply content based on a specific theme. For example, reply content related to sports or entertainment is generated. The policy setting unit also causes the generation AI to generate reply content based on a theme selected by the user. For example, reply content related to a specific movie or music is generated. The policy setting unit also causes the generation AI to generate reply content based on a specific theme in real time when a user sets a recreation policy. For example, replies related to sporting events or entertainment news are generated. This makes it possible to recreate reply content based on a specific theme, thereby providing interactions that match the user's interests.

[0068] The policy setting unit can use the emotion estimation function to enable the user to set a policy for recreating reply content with a specific emotion. For example, the policy setting unit uses the emotion estimation function to enable the user to set a policy for recreating reply content with a specific emotion. For example, the policy setting unit sets a policy for recreating reply content with a positive emotion. The policy setting unit also enables the generation AI to estimate the user's emotion and set a policy for recreating reply content based on the emotion. For example, the policy setting unit sets a policy for recreating reply content with a negative emotion. The policy setting unit also uses the emotion estimation function to enable the user to set a policy in real time for recreating reply content with a specific emotion. For example, the policy setting unit sets a policy for recreating reply content with a surprise or joy. In this way, the emotion estimation function enables the user to set a policy for recreating reply content with a specific emotion.

[0069] The generation AI can analyze a user's interests and prioritize recreating interactions between specific celebrities or friends. For example, the generation AI analyzes a user's interests and prioritizes recreating interactions between specific celebrities or friends. For example, it recreates interactions between celebrities the user follows. The generation AI also analyzes a user's interests and recreates interactions between specific celebrities or friends based on that data. For example, it recreates tweets by celebrities that the user frequently "likes." The generation AI also analyzes a user's interests in real time and prioritizes recreating interactions between specific celebrities or friends based on the results. For example, it recreates interactions related to topics that the user is interested in. In this way, by analyzing a user's interests, it is possible to prioritize recreating interactions between specific celebrities or friends.

[0070] The generation AI can provide related news and trending information when a user re-enacts an interaction based on a specific theme. For example, the generation AI provides related news and trending information when a user re-enacts an interaction based on a specific theme. For example, it displays the latest news related to sports or entertainment. The generation AI also provides related news and trending information based on a theme selected by the user. For example, it displays the latest information related to specific movies or music. The generation AI also provides related news and trending information in real time when a user re-enacts an interaction based on a specific theme. For example, it displays information related to sporting events or entertainment news. This makes it possible to keep a user interested by providing related news and trending information when re-enacting an interaction based on a specific theme.

[0071] The generation AI can use the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, the generation AI uses the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, it recreates interactions in which the user has a positive emotion. The generation AI also estimates the user's emotion and recreates interactions based on that emotion. For example, it recreates interactions in which the user has a negative emotion. The generation AI also uses the emotion estimation function to recreate interactions in which the user has a specific emotion in real time. For example, it recreates interactions in which the user shows surprise or joy. In this way, by using the emotion estimation function, it is possible to prioritize recreating interactions in which the user has a specific emotion.

[0072] The generation AI can be expanded to reproduce interactions on different social media platforms. For example, the generation AI can be expanded to reproduce interactions on different social media platforms. For example, a function to generate replies to Instagram (registered trademark) comments and Facebook (registered trademark) posts can be added. The generation AI also collects data from different social media platforms and generates replies for private accounts based on that data. For example, it reproduces comments on Instagram (registered trademark) photo posts and replies to Facebook (registered trademark) posts. When reproducing interactions on different social media platforms, the generation AI also takes into account the characteristics of each platform. For example, it generates replies in response to Instagram (registered trademark) posts that emphasize visuals and Facebook (registered trademark) posts that emphasize text. This makes it possible to reproduce interactions on different social media platforms, thereby enabling support for a wider variety of usage scenarios.

[0073] The generation AI can enable a user to recreate interactions based on a specific event. The generation AI, for example, enables a user to recreate interactions based on a specific event. For example, interactions related to a sports game or a movie release are generated. The generation AI also recreates interactions based on an event selected by the user. For example, interactions related to a specific sports game or a movie release are generated. The generation AI also generates related interactions in real time as the user recreates an interaction based on a specific event. For example, interactions related to a sports event or a movie release are generated. This makes it possible to provide interactions that match the user's interests by allowing interactions based on a specific event to be recreated.

[0074] The generation AI can use the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, the generation AI uses the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, it recreates interactions in which the user has a positive emotion. The generation AI also estimates the user's emotion and recreates interactions based on that emotion. For example, it recreates interactions in which the user has a negative emotion. The generation AI also uses the emotion estimation function to recreate interactions in which the user has a specific emotion in real time. For example, it recreates interactions in which the user shows surprise or joy. In this way, by using the emotion estimation function, it is possible to prioritize recreating interactions in which the user has a specific emotion.

[0075] Generative AI can learn a user's usage history and suggest optimal usage scenarios. For example, generative AI can learn a user's past usage history and suggest optimal usage scenarios based on that data. For example, it can suggest scenarios based on the functions and themes that the user frequently uses. Generative AI can also analyze a user's usage history and build a system that suggests optimal usage scenarios based on the results. For example, it can suggest scenarios based on tones and themes that the user has selected in the past. Generative AI can also learn a user's usage history in real time and suggest optimal usage scenarios based on that data. For example, it can suggest scenarios based on topics that the user is currently interested in. In this way, it can suggest optimal usage scenarios by learning a user's usage history.

[0076] The generation AI can suggest related content when a user re-enacts an interaction based on a specific theme. For example, the generation AI suggests related content when a user re-enacts an interaction based on a specific theme. For example, it displays articles and videos related to sports or entertainment. The generation AI also suggests related content based on a theme selected by the user. For example, it displays content related to specific movies or music. The generation AI also suggests related content in real time when a user re-enacts an interaction based on a specific theme. For example, it displays content related to sporting events or entertainment news. This makes it possible to keep the user interested by suggesting related content when re-enacting an interaction based on a specific theme.

[0077] The generation AI can use the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, the generation AI uses the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, it recreates interactions in which the user has a positive emotion. The generation AI also estimates the user's emotion and recreates interactions based on that emotion. For example, it recreates interactions in which the user has a negative emotion. The generation AI also uses the emotion estimation function to recreate interactions in which the user has a specific emotion in real time. For example, it recreates interactions in which the user shows surprise or joy. In this way, by using the emotion estimation function, it is possible to prioritize recreating interactions in which the user has a specific emotion.

[0078] The generation AI can be expanded to reproduce interactions on different social media platforms. For example, the generation AI can be expanded to reproduce interactions on different social media platforms. For example, a function to generate replies to Instagram (registered trademark) comments and Facebook (registered trademark) posts can be added. The generation AI also collects data from different social media platforms and generates replies for private accounts based on that data. For example, it reproduces comments on Instagram (registered trademark) photo posts and replies to Facebook (registered trademark) posts. When reproducing interactions on different social media platforms, the generation AI also takes into account the characteristics of each platform. For example, it generates replies in response to Instagram (registered trademark) posts that emphasize visuals and Facebook (registered trademark) posts that emphasize text. This makes it possible to reproduce interactions on different social media platforms, thereby enabling support for a wider variety of usage scenarios.

[0079] The generation AI can enable a user to recreate interactions based on a specific event. The generation AI, for example, enables a user to recreate interactions based on a specific event. For example, interactions related to a sports game or a movie release are generated. The generation AI also recreates interactions based on an event selected by the user. For example, interactions related to a specific sports game or a movie release are generated. The generation AI also generates related interactions in real time as the user recreates an interaction based on a specific event. For example, interactions related to a sports event or a movie release are generated. This makes it possible to provide interactions that match the user's interests by allowing interactions based on a specific event to be recreated.

[0080] The generation AI can use the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, the generation AI uses the emotion estimation function to prioritize recreating interactions in which the user has a specific emotion. For example, it recreates interactions in which the user has a positive emotion. The generation AI also estimates the user's emotion and recreates interactions based on that emotion. For example, it recreates interactions in which the user has a negative emotion. The generation AI also uses the emotion estimation function to recreate interactions in which the user has a specific emotion in real time. For example, it recreates interactions in which the user shows surprise or joy. In this way, by using the emotion estimation function, it is possible to prioritize recreating interactions in which the user has a specific emotion.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The system can estimate a user's emotions and generate a reply based on those emotions. For example, if a user has positive emotions toward a tweet from a public account, the reply generator generates a reply that reflects those emotions. Specifically, if the user feels "Today is a great day," the reply generator generates a reply such as "What a great day!". Furthermore, if the user has negative emotions, the reply generator generates a reply that reflects those emotions. For example, if the user feels "I'm tired today," the reply generator generates a reply such as "Thank you for your hard work. Please get plenty of rest." Furthermore, if the user expresses surprise or joy, the system can also generate a reply that reflects those emotions. For example, if the user feels "Great news!", the reply generator generates a reply such as "I'm so surprised!". This allows the system to provide a more natural reply based on the user's emotions.

[0083] Based on a user's past tweet history and interests, a reply related to a specific theme can be generated. For example, if a user is interested in sports, the prompt generation unit generates a reply related to sports. Specifically, if a user tweets, "I'm going to see a game today," the prompt generation unit generates a reply such as, "Which team are you rooting for?" If a user is interested in entertainment, the prompt generation unit generates a reply related to entertainment. For example, if a user tweets, "I saw a new movie," the prompt generation unit generates a reply such as, "What did you think of the movie?" Furthermore, if a user is interested in a particular event, a reply related to that event can also be generated. For example, if a user tweets, "I'm going to a concert," the prompt generation unit generates a reply such as, "Which artist's concert?" This makes it possible to provide a more personalized reply based on the user's interests.

[0084] By referencing other users' reactions to tweets from public accounts, the reply generator can generate a wider variety of replies. For example, the reply generator can recreate a natural conversation flow by referring to other users' reactions through "likes" and replies. Specifically, if a public account tweets, "I started a new project today," the reply generator can generate a reply such as, "What kind of project is it?" based on other users' reactions. The reply generator can also analyze the emotions expressed by other users in response to a tweet and generate replies based on those emotions. For example, if another user responds positively with, "That's amazing!", the reply generator can generate a reply such as, "That's really amazing!". Furthermore, the reply generator can collect the content of other users' replies and quoted tweets in real time and generate replies for private accounts based on that data. For example, if another user sends a message of encouragement saying, "Good luck," the reply generator can generate a reply such as, "Thank you, I'll do my best!". By referring to other users' reactions, the reply generator can recreate a more natural conversation flow.

[0085] The emotion estimation function can estimate the emotion of a private account in response to a public account's tweet and generate a reply based on that emotion. For example, if a public account's tweet expresses a positive emotion, the reply generator generates a reply that reflects that emotion. Specifically, if a public account tweets, "Today is a great day," the reply generator generates a reply such as, "What a wonderful day!". Furthermore, if a public account tweets, "I'm tired today," the reply generator can generate a reply that reflects that emotion. For example, if a public account tweets, "I'm tired today," the reply generator generates a reply such as, "Thank you for your hard work. Please get plenty of rest." Furthermore, if a public account tweets, "What surprise or joy," the reply generator can also generate a reply that reflects that emotion. For example, if a public account tweets, "Great news!", the reply generator generates a reply such as, "That's really surprising!". This allows the emotion estimation function to generate replies that are more emotionally relevant.

[0086] It is possible to generate replies that include multimedia content, such as images or videos. For example, in response to a tweet from a public account, a reply can be generated that includes related images or videos. Specifically, if a public account tweets, "I started a new project today," the reply generation unit can generate a reply that includes images or videos related to the project. The generation AI can also analyze the content of the public account's tweet and select appropriate images or videos. For example, GIFs or short videos related to the tweet content can be included in the reply. Furthermore, images and videos uploaded by the user can be used. For example, a user can specify that a specific image or video be included in the reply, allowing for the generation of more personalized replies. This allows for the generation of replies that include multimedia content, thereby providing richer reply content.

[0087] The system can be expanded to reproduce interactions across different social media platforms. For example, a function for generating replies to Instagram® comments and Facebook® posts can be added. Specifically, it can reproduce comments on Instagram® photo posts and replies to Facebook® posts. The generation AI can also collect data from different social media platforms and generate replies for private accounts based on that data. For example, it can generate replies for Instagram® posts that emphasize visuals and Facebook® posts that emphasize text. Furthermore, it can generate more natural replies by taking into account the characteristics of each platform. For example, it can generate replies that emphasize visuals for Instagram® posts and replies that emphasize text for Facebook® posts. This allows the system to reproduce interactions across different social media platforms, enabling it to accommodate a wider variety of usage scenarios.

[0088] The system can learn the user's past setting history and propose the optimal policy that matches the user's preferences. For example, the system can propose the optimal policy based on the tones and themes selected by the user in the past. Specifically, it can prioritize suggestions for tones and themes that the user frequently selects. The generation AI can also analyze the user's past setting history and propose a reproduction policy based on that data. For example, if the user prefers a particular theme or tone, it can prioritize suggestions for that policy. Furthermore, when the user sets a reproduction policy, the generation AI can refer to the user's past setting history and propose a policy that matches the user's preferences. For example, it can propose the optimal policy based on the tones and themes selected by the user in the past. In this way, by learning the user's past setting history, it is possible to propose the optimal policy that matches the user's preferences.

[0089] Based on the policy selected by the user, the generation AI can generate multiple reply candidates and allow the user to choose from them. For example, reply candidates can be generated in tones such as friendly, sarcastic, and humorous. Specifically, if the user selects a "friendly" policy, the reply generation unit can generate a reply candidate such as "What a great day today!". If the user selects a "sarcastic" policy, the reply generation unit can generate a reply candidate such as "I don't think it's really a great day, though." Furthermore, if the user selects a "humorous" policy, the reply generation unit can generate a reply candidate such as "Today is a great day, but what about tomorrow?" This allows the system to provide a wider variety of reply content by generating multiple reply candidates based on the policy selected by the user and allowing the user to choose from them.

[0090] The emotion estimation function can be used to enable a user to set a policy for reproducing reply content that reflects a specific emotion. For example, a policy for reproducing reply content that reflects a positive emotion can be set. Specifically, if a user feels, "Today is a great day," the policy setting unit sets a "positive" policy, and the reply generation unit generates a reply such as, "What a great day!". A policy for reproducing reply content that reflects a negative emotion can also be set. For example, if a user feels, "Today is tired," the policy setting unit sets a "negative" policy, and the reply generation unit generates a reply such as, "Thank you for your hard work. Please get plenty of rest." Furthermore, a policy for reproducing reply content that reflects surprise or joy can also be set. For example, if a user feels, "That's great news!", the policy setting unit sets a "surprise" or "joy" policy, and the reply generation unit generates a reply such as, "That's really surprising!". In this way, the emotion estimation function can be used to enable a user to set a policy for reproducing reply content that reflects a specific emotion.

[0091] It is possible to enable a user to reproduce replies based on a specific theme. For example, a user can generate replies related to sports or entertainment. Specifically, if a user tweets, "I'm going to see a game today," the policy setting unit can set the "sports" theme, and the reply generation unit can generate a reply such as, "Which team are you rooting for?". If a user tweets, "I saw a new movie," the policy setting unit can set the "entertainment" theme, and the reply generation unit can generate a reply such as, "How was the movie?". Furthermore, if a user is interested in a specific event, a reply related to the event can be generated. For example, if a user tweets, "I'm going to a concert," the policy setting unit can set the "event" theme, and the reply generation unit can generate a reply such as, "Which artist's concert?". This makes it possible to reproduce replies based on a specific theme, thereby providing interactions that match the user's interests.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The prompt generator generates a prompt that includes the tweet content of the public account and the reproduction policy set by the user. For example, if a public account tweets "It's a nice day today," the prompt generator generates a prompt that includes the tweet content "It's a nice day today" and the "friendly" policy set by the user. Step 2: The reply generator generates a reply from the account based on the prompt generated by the prompt generator. For example, the AI ​​might generate a reply such as, "Yes, I'd like to go for a walk." Step 3: The policy setting unit allows the user to set a reproduction policy. For example, the user can instruct the reply content to be reproduced in a "friendly," "sarcastic," "humorous," or other tone.

[0094] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0095] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0096] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 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.

[0099] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0100] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0101] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0103] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0104] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0105] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0106] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0107] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0108] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0111] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0112] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0113] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0114] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0115] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0116] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0117] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0118] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0119] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0120] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0121] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0122] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0123] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0124] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0127] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0128] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0130] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0135] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0136] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0138] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0143] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0144] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0145] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0146] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0147] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0148] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0149] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0150] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0151] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0152] 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.

[0153] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0154] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0155] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0156] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0157] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0158] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0159] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0160] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0161] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. Equipped with generative AI, a prompt generation unit that generates a prompt including the tweet content of the public account and a reproduction policy set by the user; a reply generation unit that generates a reply content for the private account based on the prompt generated by the prompt generation unit; a policy setting unit in which a user sets a reproduction policy; A system characterized by:

2. The prompt generation unit Generate prompts based on the tweet content of the public account and the user's past tweet history or interests.

2. The system of claim 1.

3. The reply generation unit The reply content of the private account is generated by referring to the reaction of the other user to the tweet of the public account.

2. The system of claim 1.

4. The reply generation unit The emotion of the private account regarding the tweet from the public account is estimated, and the reply content is generated based on the emotion.

2. The system of claim 1.

5. The reply generation unit Generate replies with multimedia content, including images or videos 2. The system of claim 1.

6. The reply generation unit It can be expanded to reproduce the interactions on different social media platforms.

2. The system of claim 1.

Images