System

Abstract

An object of the system according to the embodiment is to learn a past sentence and generate a natural sentence by imitating its wording, punctuation, and line feed habit.SOLUTION: A system according to an embodiment includes a learning unit, an imitation unit, and a generation unit. The learning unit learns a past sentence. The imitator imitates the wording, punctuation, and line feed habit learned by the learner. The generation unit generates a sentence based on the content imitated by the imitation unit.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 techniques have room for improvement in generating drafts that allow for realistic and natural conversations.

[0005] The system according to the embodiment aims to learn from past sentences and imitate their wording, punctuation, and line break habits to generate natural-sounding sentences. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, an imitation unit, and a generation unit. The learning unit learns past sentences. The imitation unit imitates the wording, punctuation, and line break habits learned by the learning unit. The generation unit generates sentences based on the content imitated by the imitation unit. [Effects of the Invention]

[0007] The system according to the embodiment can learn from past sentences and imitate their wording, punctuation, and line break habits to generate natural-sounding sentences. [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) The text generation system according to the embodiment of the present invention is a system that learns from past texts and generates texts by imitating the language, punctuation, and line break habits of a person. This allows the text generation system to learn from past texts and generate texts by imitating the language, punctuation, and line break habits of a person.

[0029] A text generation system according to an embodiment includes a learning unit, an imitation unit, and a generation unit. The learning unit learns past texts. For example, the learning unit collects and learns a user's past emails, reports, blog posts, and the like. The learning unit also uses machine learning and deep learning to learn the user's vocabulary, punctuation, and line break habits. For example, the learning unit learns the user's frequently used phrases, specific expressions, and sentence rhythms. The imitation unit then imitates the vocabulary, punctuation, and line break habits learned by the learning unit. For example, the imitation unit reproduces the user's frequently used "desumasu" and "de aru" styles, the use of specific punctuation, and the timing of line breaks. The imitation unit can also imitate style and format. The generation unit generates text based on the content imitated by the imitation unit. For example, the generation unit uses natural language generation technology or template-based generation to generate text that reflects the user's vocabulary, punctuation, and line break habits. The generation unit generates sentences with appropriate wording and formatting based on the user's past sentence data. This allows the sentence generation system according to the embodiment to learn from past sentences and generate sentences by imitating the user's wording, punctuation, and line break habits.

[0030] The learning unit can analyze metadata contained in the user's past writings and learn language usage appropriate to the context. For example, the generation AI analyzes the sending date and time and recipient attributes contained in the user's past writings to learn language usage patterns appropriate to the context. For example, it learns the difference between business emails and private emails. The learning unit also analyzes the language usage of the user at specific times of the day or to specific recipients based on the metadata and learns those patterns. For example, the generation AI analyzes metadata and learns language usage and punctuation marks appropriate to the context. This makes it possible to analyze metadata contained in the user's past writings and learn language usage appropriate to the context.

[0031] The learning unit can learn not only the user's writing style but also their opinions and positions on specific topics. For example, the generation AI analyzes the user's past writings to learn their opinions and positions on specific topics. For example, it learns opinions on politics and economics. The learning unit also analyzes keywords and phrases in the text to learn the user's opinions and positions on specific topics in addition to their writing style. For example, the generation AI learns the user's opinions and positions on specific topics based on the user's past writings and generates text based on that information. This makes it possible to learn not only the user's writing style but also their opinions and positions on specific topics.

[0032] The learning unit learns not only the user's past sentences but also audio and video data, and is able to imitate language usage from multimodal information. For example, the generation AI of the learning unit analyzes the user's past audio and video data to learn the user's language usage and punctuation usage. For example, it learns the rhythm and tone of speech from the audio data. The learning unit also analyzes the audio and video data to learn the user's language usage and punctuation usage based on multimodal information. For example, it learns facial expressions and gestures from the video data. The generation AI of the learning unit also learns the user's language usage and punctuation usage based on the audio and video data, and generates sentences based on that information. This allows the system to learn not only the user's past sentences but also audio and video data, and is able to imitate language usage from multimodal information.

[0033] The learning unit compares the writing styles of different users and learns the similarities and differences, allowing it to handle a wider variety of styles. For example, the generation AI compares the writing styles of different users and learns the similarities and differences. For example, it learns the differences between business documents and casual documents. The learning unit also analyzes the writing styles of different users and compares keywords and phrases in the sentences to learn the similarities and differences. For example, the generation AI learns the similarities and differences based on the writing styles of different users and generates sentences based on that information. In this way, it is possible to handle a wider variety of styles by comparing the writing styles of different users and learning the similarities and differences.

[0034] The imitation unit can imitate not only the user's writing style but also the language and format specific to a specific industry or field of expertise. For example, the generation AI learns the language and format specific to a specific industry or field of expertise in addition to the user's writing style. For example, it learns the specific phrases used in legal documents and technical documents. In order to imitate the language and format specific to a specific industry or field of expertise, the generation AI collects and learns text data from that field. For example, it learns specialized terminology in the medical field. In addition, the generation AI imitates the language and format specific to a specific industry or field of expertise in addition to the user's writing style, and generates text based on that information. This allows the generation AI to imitate the language and format specific to a specific industry or field of expertise in addition to the user's writing style.

[0035] The imitation unit also reproduces the rhythm and tempo of the user's writing, making it possible to generate more natural-sounding sentences. For example, the generation AI of the imitation unit learns the rhythm and tempo of the user's writing and generates sentences based on that information. For example, it reproduces the rhythm of phrases and expressions frequently used by the user. In addition, to reproduce the rhythm and tempo of the user's writing, the generation AI analyzes past writing data and learns rhythm and tempo patterns. For example, it adjusts the length of the sentences and the position of punctuation marks. In addition, the imitation unit allows the generation AI to generate more natural-sounding sentences based on the rhythm and tempo of the user's writing. This allows the generation AI to reproduce the rhythm and tempo of the user's writing and generate more natural-sounding sentences.

[0036] The imitation unit can also reproduce nuances such as humor and sarcasm contained in the user's writing. For example, the generation AI learns nuances such as humor and sarcasm contained in the user's writing and generates sentences based on that information. For example, it learns specific phrases and expressions. In addition, to reproduce nuances such as humor and sarcasm contained in the user's writing, the generation AI analyzes past writing data and learns patterns of nuance. For example, it learns how to use humorous expressions and sarcasm. In addition, the imitation unit generates more natural-looking sentences based on nuances such as humor and sarcasm contained in the user's writing. This allows the generation AI to reproduce nuances such as humor and sarcasm contained in the user's writing.

[0037] The generation unit learns templates specialized for specific tasks in secretarial work and can efficiently generate sentences. For example, the generation AI of the generation unit learns templates specialized for creating meeting minutes and efficiently generates minutes based on that information. For example, it automatically organizes the agenda, speakers, and content of remarks. In addition, in order to learn templates specialized for specific tasks, the generation AI collects and learns past minutes data. For example, it learns formats according to the progress of the meeting. In addition, the generation unit efficiently generates sentences based on templates specialized for specific tasks. This allows the generation AI to learn templates specialized for specific tasks in secretarial work and efficiently generate sentences.

[0038] The generation unit can refer to data from similar past tasks and select the optimal wording and format when creating documents for secretarial work. For example, the generation unit allows the generation AI to refer to data from similar past tasks and select the optimal wording and format. For example, new minutes are created in an appropriate format based on past meeting minutes. The generation unit also builds a database based on data from similar past tasks so that the generation AI can select the optimal wording and format. For example, it collects and learns data from past reports and emails. The generation unit also allows the generation AI to select the optimal wording and format based on data from similar past tasks and generate documents based on that information. This allows the generation AI to refer to data from similar past tasks and select the optimal wording and format when creating documents for secretarial work.

[0039] The generation unit can be applied not only to secretarial tasks but also to other tasks, enabling use in a wide range of tasks. For example, the generation unit applies the generation AI not only to secretarial tasks but also to creating marketing materials. For example, it can learn from past marketing materials and create new materials in an appropriate format. In addition, the generation unit allows the generation AI to collect and learn various business data in order to be applied to other tasks. For example, it can collect and learn data from sales reports and presentation materials. In addition, the generation unit generates text based on data from different tasks in order to enable the generation AI to be used in a wide range of tasks. This allows the generation AI to be applied not only to secretarial tasks but also to other tasks, enabling use in a wide range of tasks.

[0040] The generation unit can link the generated text with other generation AIs to process multiple tasks simultaneously. For example, the generation unit links text created by a generation AI with other generation AIs to process multiple tasks simultaneously. For example, it can create meeting minutes while simultaneously generating a draft report. In addition, in order to link multiple generation AIs, the generation unit has the generation AI collect and learn data specialized for each task. For example, it links an AI that creates meeting minutes with an AI that creates emails. In addition, the generation unit links text created by a generation AI with other generation AIs to build a system that efficiently processes multiple tasks. This allows the generated text to be linked with other generation AIs to process multiple tasks simultaneously.

[0041] The generation unit selects an appropriate tone and style depending on the content of the email, making it possible to clearly distinguish between business emails and private emails. In the generation unit, for example, the generation AI selects an appropriate tone and style depending on the content of the email. For example, formal language is used in business emails and casual language is used in private emails. In addition, in order to clearly distinguish between business emails and private emails depending on the content of the email, the generation AI collects and learns from past email data. For example, it learns the format and wording of business emails. In addition, the generation unit selects an appropriate tone and style depending on the content of the email, and generates the email based on that information. In this way, it is possible to select an appropriate tone and style depending on the content of the email, making it possible to clearly distinguish between business emails and private emails.

[0042] The generation unit can be applied not only to creating emails, but also to creating social media posts and blog articles, enabling use in a wide range of communication methods. The generation unit, for example, applies the generation AI not only to creating emails, but also to creating social media posts and blog articles. For example, it can learn from past social media posts and blog articles to create new posts and articles in an appropriate format. The generation unit also allows the generation AI to collect and learn various data in order to be applied to other communication methods. For example, it can collect and learn from social media post data and blog article data. The generation unit also generates sentences based on different data in order to enable the generation AI to be used in a wide range of communication methods. This allows the generation AI to be applied not only to creating emails, but also to creating social media posts and blog articles, enabling use in a wide range of communication methods.

[0043] The generation unit can link generated emails with other generation AIs to process multiple communication methods simultaneously. For example, the generation unit links emails created by a generation AI with other generation AIs to process multiple communication methods simultaneously. For example, while creating an email, the generation unit simultaneously generates a draft of a social media post or blog article. In addition, in order to link multiple generation AIs, the generation unit has the generation AI collect and learn data specialized for each communication method. For example, it links an email creation AI with an social media posting AI. In addition, the generation unit links emails created by a generation AI with other generation AIs to build a system that efficiently processes multiple communication methods. This allows generated emails to be linked with other generation AIs to process multiple communication methods simultaneously.

[0044] The generation unit selects an appropriate tone and style depending on the content of the conversation, making it possible to clearly distinguish between business and casual conversations. For example, the generation AI selects an appropriate tone and style depending on the content of the conversation. For example, formal language is used in business conversations, and relaxed language is used in casual conversations. In addition, the generation unit has the generation AI collect and learn from past conversation data in order to clearly distinguish between business and casual conversations depending on the content of the conversation. For example, it learns the format and phrasing of business conversations. In addition, the generation AI selects an appropriate tone and style depending on the content of the conversation, and generates conversations based on that information. This allows the generation AI to select an appropriate tone and style depending on the content of the conversation, making it possible to clearly distinguish between business and casual conversations.

[0045] When generating a conversation, the generation unit can refer to data on similar past conversations and select the optimal wording and tone. For example, the generation unit allows the generation AI to refer to data on similar past conversations and select the optimal wording and tone. For example, it creates a new conversation in an appropriate format based on past business conversations. The generation unit also builds a database based on data on similar past conversations so that the generation AI can select the optimal wording and tone. For example, it collects and learns from past success stories and failure stories. The generation unit also allows the generation AI to select the optimal wording and tone based on data on similar past conversations and generate a conversation based on that information. This allows the generation AI to refer to data on similar past conversations and select the optimal wording and tone when generating a conversation.

[0046] The generation unit can be applied not only to conversation generation but also to voice assistants and navigation systems, enabling use in a wide range of interaction methods. The generation unit, for example, applies the generation AI not only to conversation generation but also to voice assistants and navigation systems. For example, it learns from past voice data and creates new voice responses in an appropriate format. The generation unit also collects and learns various data so that the generation AI can be applied to other interaction methods. For example, it collects and learns from response data for voice assistants and guidance data for navigation systems. The generation unit also generates conversations based on different data so that the generation AI can be used in a wide range of interaction methods. This allows the generation AI to be applied not only to conversation generation but also to voice assistants and navigation systems, enabling use in a wide range of interaction methods.

[0047] The generation unit can link the generated conversation with other generation AIs to simultaneously process multiple interaction means. For example, the generation unit links the conversation generated by the generation AI with other generation AIs to simultaneously process multiple interaction means. For example, while generating a conversation, the generation unit simultaneously generates responses for a voice assistant or guidance for a navigation system. In addition, in order to link multiple generation AIs, the generation unit has the generation AI collect and learn data specialized for each interaction means. For example, the generation unit links a conversation generation AI with a voice assistant AI. In addition, the generation unit links the conversation generated by the generation AI with other generation AIs to build a system that efficiently processes multiple interaction means. This allows the generated conversation to be linked with other generation AIs to simultaneously process multiple interaction means.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The acquisition unit can collect and learn not only the user's past writings but also posts from websites and social media that the user frequently visits. For example, it can collect posts from news sites and forums that the user frequently reads and learn their language and style. The acquisition unit can also collect posts from social media accounts that the user follows and generate sentences based on the user's interests. Furthermore, the acquisition unit can collect posts from online communities in which the user participates and learn the language and style unique to those communities. This makes it possible to generate sentences that reflect the user's entire online activity.

[0050] When providing the generated text to the user, the providing unit can provide it in an optimal format by taking into account the user's past feedback. For example, the generated text can be customized based on the user's past preferred formats and styles. The providing unit can also collect user feedback in real time and modify the text based on that feedback. Furthermore, the providing unit can select an optimal display format when the user views the text on a specific device or platform. For example, the providing unit can provide short paragraphs suitable for viewing on a smartphone or detailed descriptions suitable for viewing on a desktop. This enables flexible text provision according to the user's preferences and devices.

[0051] The acquisition unit can learn by collecting data not only from the user's past writing but also from applications and tools the user frequently uses. For example, it can collect data from the user's frequently used messaging app or project management tool to learn their vocabulary and style. The acquisition unit can also collect data from documents and presentations created by the user to gain a deeper understanding of the user's writing style. Furthermore, the acquisition unit can also collect data from recordings of online meetings and webinars the user participates in to learn the content and style of their speech. This makes it possible to generate writing that reflects the user's diverse activities.

[0052] When providing the generated text to the user, the providing unit can provide it at the optimal timing, taking into account the user's past behavioral history. For example, if the user has tended to view text during a specific time period in the past, the providing unit can provide the text according to that time period. The providing unit can also customize the method of providing the text based on the user's behavioral history. For example, if the user prefers notifications by email, the generated text is sent by email, and if the user prefers in-app notifications, the notification is sent within the app. Furthermore, the providing unit can set priorities for the text based on the user's behavioral history and provide important information preferentially. This enables flexible text provision according to the user's behavioral history.

[0053] The acquisition unit can collect and learn data not only from the user's past writing but also from the digital content and media the user frequently uses. For example, it can collect transcripts of videos and podcasts the user frequently watches and learn their vocabulary and style. The acquisition unit can also collect data from newsletters and e-books the user subscribes to to generate writing based on the user's interests. Furthermore, the acquisition unit can also collect data from materials from online courses and webinars the user participates in to learn their content and style. This enables the generation of writing that reflects the user's diverse digital content.

[0054] When providing the generated text to the user, the providing unit can provide it in a format optimized for the user's device or platform. For example, the providing unit can provide short paragraphs suitable for viewing on a smartphone or detailed explanations suitable for viewing on a desktop. The providing unit can also customize the format of the text to suit a specific application or tool used by the user. For example, the providing unit can provide the text in a task list format suitable for a project management tool used by the user or in a chat format suitable for a messaging app. The providing unit can also adjust the way the text is displayed depending on the user's device or platform. For example, the providing unit can provide a design that supports dark mode or a text-to-speech function. This enables flexible text provision that is optimized for the user's device or platform.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The learning unit studies past sentences. For example, the learning unit collects and studies the user's past emails, reports, blog posts, etc. The learning unit also uses machine learning and deep learning to learn the user's vocabulary, punctuation, and line break habits. Specifically, it learns the user's frequently used phrases, specific expressions, and sentence rhythms. Step 2: The mimicking unit imitates the vocabulary, punctuation, and line break habits learned by the learning unit. For example, the mimicking unit reproduces the user's frequently used "desumasu" and "dearu" styles, the use of specific punctuation, and the timing of line breaks. It can also imitate style and formatting. Step 3: The generator generates sentences based on the content imitated by the imitator. For example, the generator uses natural language generation technology or template-based generation to generate sentences that reflect the user's vocabulary, punctuation, and line break habits. The generator also generates sentences with appropriate vocabulary and formatting based on the user's past writing data.

[0057] (Example 2) The text generation system according to the embodiment of the present invention is a system that learns from past texts and generates texts by imitating the language, punctuation, and line break habits of a person. This allows the text generation system to learn from past texts and generate texts by imitating the language, punctuation, and line break habits of a person.

[0058] A text generation system according to an embodiment includes a learning unit, an imitation unit, and a generation unit. The learning unit learns past texts. For example, the learning unit collects and learns a user's past emails, reports, blog posts, and the like. The learning unit also uses machine learning and deep learning to learn the user's vocabulary, punctuation, and line break habits. For example, the learning unit learns the user's frequently used phrases, specific expressions, and sentence rhythms. The imitation unit then imitates the vocabulary, punctuation, and line break habits learned by the learning unit. For example, the imitation unit reproduces the user's frequently used "desumasu" and "de aru" styles, the use of specific punctuation, and the timing of line breaks. The imitation unit can also imitate style and format. The generation unit generates text based on the content imitated by the imitation unit. For example, the generation unit uses natural language generation technology or template-based generation to generate text that reflects the user's vocabulary, punctuation, and line break habits. The generation unit generates sentences with appropriate wording and formatting based on the user's past sentence data. This allows the sentence generation system according to the embodiment to learn from past sentences and generate sentences by imitating the user's wording, punctuation, and line break habits.

[0059] The learning unit can estimate the user's emotional state and learn how to change language in response to changes in emotion. For example, the learning unit has the generation AI analyze the user's past sentences and perform emotion analysis. For example, it learns the differences in language and punctuation used when the user is happy and sad. In addition, to estimate the user's emotional state, the learning unit analyzes emotional expressions and specific keywords in sentences and learns language patterns that correspond to changes in emotion. For example, using the emotion estimation function, it learns changes in language in response to the user's emotional state in real time, and the generation AI generates sentences that reflect those changes. This allows it to learn how to change language in response to the user's emotional state.

[0060] The learning unit can analyze metadata contained in the user's past writings and learn language usage appropriate to the context. For example, the generation AI analyzes the sending date and time and recipient attributes contained in the user's past writings to learn language usage patterns appropriate to the context. For example, it learns the difference between business emails and private emails. The learning unit also analyzes the language usage of the user at specific times of the day or to specific recipients based on the metadata and learns those patterns. For example, the generation AI analyzes metadata and learns language usage and punctuation marks appropriate to the context. This makes it possible to analyze metadata contained in the user's past writings and learn language usage appropriate to the context.

[0061] The learning unit can learn not only the user's writing style but also their opinions and positions on specific topics. For example, the generation AI analyzes the user's past writings to learn their opinions and positions on specific topics. For example, it learns opinions on politics and economics. The learning unit also analyzes keywords and phrases in the text to learn the user's opinions and positions on specific topics in addition to their writing style. For example, the generation AI learns the user's opinions and positions on specific topics based on the user's past writings and generates text based on that information. This makes it possible to learn not only the user's writing style but also their opinions and positions on specific topics.

[0062] The learning unit learns not only the user's past sentences but also audio and video data, and is able to imitate language usage from multimodal information. For example, the generation AI of the learning unit analyzes the user's past audio and video data to learn the user's language usage and punctuation usage. For example, it learns the rhythm and tone of speech from the audio data. The learning unit also analyzes the audio and video data to learn the user's language usage and punctuation usage based on multimodal information. For example, it learns facial expressions and gestures from the video data. The generation AI of the learning unit also learns the user's language usage and punctuation usage based on the audio and video data, and generates sentences based on that information. This allows the system to learn not only the user's past sentences but also audio and video data, and is able to imitate language usage from multimodal information.

[0063] The learning unit compares the writing styles of different users and learns the similarities and differences, allowing it to handle a wider variety of styles. For example, the generation AI compares the writing styles of different users and learns the similarities and differences. For example, it learns the differences between business documents and casual documents. The learning unit also analyzes the writing styles of different users and compares keywords and phrases in the sentences to learn the similarities and differences. For example, the generation AI learns the similarities and differences based on the writing styles of different users and generates sentences based on that information. In this way, it is possible to handle a wider variety of styles by comparing the writing styles of different users and learning the similarities and differences.

[0064] The learning unit can use the emotion estimation function to learn and adapt changes in writing style according to the user's emotional state in real time. The learning unit, for example, uses the emotion estimation function to learn changes in writing style according to the user's emotional state in real time. For example, the learning unit adjusts the tone and style of the writing based on the emotion score. The learning unit also learns changes in writing style according to the user's emotional state based on the emotion estimation data, and generates sentences based on that information. For example, it learns the difference between positive and negative emotions. The learning unit also uses the emotion estimation function to build a system that learns and adapts changes in writing style according to the user's emotional state in real time. This makes it possible to use the emotion estimation function to learn and adapt changes in writing style according to the user's emotional state in real time.

[0065] The mimicry unit can estimate the user's emotional state and reproduce the use of punctuation and line breaks according to the emotion. For example, the generation AI of the mimicry unit estimates the user's emotional state and reproduces the use of punctuation and line breaks according to the emotion. For example, it uses more punctuation when the user is emotional and less when the user is calm. The mimicry unit also uses the emotion estimation function to adjust the use of punctuation and line breaks according to the user's emotional state in real time. For example, it changes the timing of line breaks according to changes in emotion. The mimicry unit also learns how to use punctuation and line breaks according to the user's emotional state based on the emotion estimation data, and generates sentences based on that information. This makes it possible to reproduce the use of punctuation and line breaks according to the user's emotional state.

[0066] The imitation unit can imitate not only the user's writing style but also the language and format specific to a specific industry or field of expertise. For example, the generation AI learns the language and format specific to a specific industry or field of expertise in addition to the user's writing style. For example, it learns the specific phrases used in legal documents and technical documents. In order to imitate the language and format specific to a specific industry or field of expertise, the generation AI collects and learns text data from that field. For example, it learns specialized terminology in the medical field. In addition, the generation AI imitates the language and format specific to a specific industry or field of expertise in addition to the user's writing style, and generates text based on that information. This allows the generation AI to imitate the language and format specific to a specific industry or field of expertise in addition to the user's writing style.

[0067] The imitation unit also reproduces the rhythm and tempo of the user's writing, making it possible to generate more natural-sounding sentences. For example, the generation AI of the imitation unit learns the rhythm and tempo of the user's writing and generates sentences based on that information. For example, it reproduces the rhythm of phrases and expressions frequently used by the user. In addition, to reproduce the rhythm and tempo of the user's writing, the generation AI analyzes past writing data and learns rhythm and tempo patterns. For example, it adjusts the length of the sentences and the position of punctuation marks. In addition, the imitation unit allows the generation AI to generate more natural-sounding sentences based on the rhythm and tempo of the user's writing. This allows the generation AI to reproduce the rhythm and tempo of the user's writing and generate more natural-sounding sentences.

[0068] The imitation unit can also reproduce nuances such as humor and sarcasm contained in the user's writing. For example, the generation AI learns nuances such as humor and sarcasm contained in the user's writing and generates sentences based on that information. For example, it learns specific phrases and expressions. In addition, to reproduce nuances such as humor and sarcasm contained in the user's writing, the generation AI analyzes past writing data and learns patterns of nuance. For example, it learns how to use humorous expressions and sarcasm. In addition, the imitation unit generates more natural-looking sentences based on nuances such as humor and sarcasm contained in the user's writing. This allows the generation AI to reproduce nuances such as humor and sarcasm contained in the user's writing.

[0069] The mimicry unit can use the emotion estimation function to adjust the use of punctuation and line breaks in real time according to the user's emotional state. For example, the mimicry unit uses the emotion estimation function to adjust the use of punctuation and line breaks in real time according to the user's emotional state. For example, it uses more punctuation when the user is emotionally excited and fewer punctuation when the user is calm. The mimicry unit also uses the emotion estimation data to learn how to use punctuation and line breaks according to the user's emotional state, and generates sentences based on that information. For example, it uses fewer punctuation when the user is emotionally positive and more punctuation when the user is emotionally negative. The mimicry unit also uses the emotion estimation function to build a system that adjusts the use of punctuation and line breaks in real time according to the user's emotional state. This makes it possible to use the emotion estimation function to adjust the use of punctuation and line breaks in real time according to the user's emotional state.

[0070] The generation unit, when creating text for secretarial work, can estimate the user's emotional state and reflect language that corresponds to the emotion. For example, the generation unit uses a generation AI to estimate the user's emotional state and reflect language that corresponds to the emotion. For example, when the user is feeling stressed, more polite and calm language is used. The generation unit also uses an emotion estimation function to adjust language in real time according to the user's emotional state. For example, when the user is happy, more cheerful and positive language is used. The generation unit also uses a generation AI to learn language that corresponds to the user's emotional state based on the emotion estimation data, and generates text based on that information. This makes it possible to estimate the user's emotional state and reflect language that corresponds to the emotion when creating text for secretarial work.

[0071] The generation unit learns templates specialized for specific tasks in secretarial work and can efficiently generate sentences. For example, the generation AI of the generation unit learns templates specialized for creating meeting minutes and efficiently generates minutes based on that information. For example, it automatically organizes the agenda, speakers, and content of remarks. In addition, in order to learn templates specialized for specific tasks, the generation AI collects and learns past minutes data. For example, it learns formats according to the progress of the meeting. In addition, the generation unit efficiently generates sentences based on templates specialized for specific tasks. This allows the generation AI to learn templates specialized for specific tasks in secretarial work and efficiently generate sentences.

[0072] The generation unit can refer to data from similar past tasks and select the optimal wording and format when creating documents for secretarial work. For example, the generation unit allows the generation AI to refer to data from similar past tasks and select the optimal wording and format. For example, new minutes are created in an appropriate format based on past meeting minutes. The generation unit also builds a database based on data from similar past tasks so that the generation AI can select the optimal wording and format. For example, it collects and learns data from past reports and emails. The generation unit also allows the generation AI to select the optimal wording and format based on data from similar past tasks and generate documents based on that information. This allows the generation AI to refer to data from similar past tasks and select the optimal wording and format when creating documents for secretarial work.

[0073] The generation unit can be applied not only to secretarial tasks but also to other tasks, enabling use in a wide range of tasks. For example, the generation unit applies the generation AI not only to secretarial tasks but also to creating marketing materials. For example, it can learn from past marketing materials and create new materials in an appropriate format. In addition, the generation unit allows the generation AI to collect and learn various business data in order to be applied to other tasks. For example, it can collect and learn data from sales reports and presentation materials. In addition, the generation unit generates text based on data from different tasks in order to enable the generation AI to be used in a wide range of tasks. This allows the generation AI to be applied not only to secretarial tasks but also to other tasks, enabling use in a wide range of tasks.

[0074] The generation unit can link the generated text with other generation AIs to process multiple tasks simultaneously. For example, the generation unit links text created by a generation AI with other generation AIs to process multiple tasks simultaneously. For example, it can create meeting minutes while simultaneously generating a draft report. In addition, in order to link multiple generation AIs, the generation unit has the generation AI collect and learn data specialized for each task. For example, it links an AI that creates meeting minutes with an AI that creates emails. In addition, the generation unit links text created by a generation AI with other generation AIs to build a system that efficiently processes multiple tasks. This allows the generated text to be linked with other generation AIs to process multiple tasks simultaneously.

[0075] The generation unit uses the emotion estimation function to create sentences according to the user's emotional state, thereby providing more personalized secretarial services. The generation unit, for example, uses the emotion estimation function to create sentences according to the user's emotional state. For example, when the user is feeling stressed, more polite and calm sentences are generated. The generation unit also provides personalized secretarial services by having the generation AI generate sentences according to the user's emotional state based on the emotion estimation data. For example, when the user is happy, it generates bright and positive sentences. The generation unit also uses the emotion estimation function to build a system that creates sentences according to the user's emotional state in real time. This makes it possible to use the emotion estimation function to create sentences according to the user's emotional state, thereby providing more personalized secretarial services.

[0076] When creating an email, the generation unit can estimate the user's emotional state and reflect language and formatting that corresponds to the emotion. For example, the generation unit uses a generation AI to estimate the user's emotional state and reflect language and formatting that corresponds to the emotion. For example, when the user is feeling stressed, more polite and calm language is used. The generation unit also uses an emotion estimation function to adjust language and formatting in real time according to the user's emotional state. For example, when the user is happy, more cheerful and positive language is used. The generation unit also uses an emotion estimation AI to learn language and formatting that corresponds to the user's emotional state based on the emotion estimation data, and generates emails based on that information. This makes it possible to estimate the user's emotional state and reflect language and formatting that corresponds to the emotion when creating an email.

[0077] The generation unit selects an appropriate tone and style depending on the content of the email, making it possible to clearly distinguish between business emails and private emails. In the generation unit, for example, the generation AI selects an appropriate tone and style depending on the content of the email. For example, formal language is used in business emails and casual language is used in private emails. In addition, in order to clearly distinguish between business emails and private emails depending on the content of the email, the generation AI collects and learns from past email data. For example, it learns the format and wording of business emails. In addition, the generation unit selects an appropriate tone and style depending on the content of the email, and generates the email based on that information. In this way, it is possible to select an appropriate tone and style depending on the content of the email, making it possible to clearly distinguish between business emails and private emails.

[0078] The generation unit can be applied not only to creating emails, but also to creating social media posts and blog articles, enabling use in a wide range of communication methods. The generation unit, for example, applies the generation AI not only to creating emails, but also to creating social media posts and blog articles. For example, it can learn from past social media posts and blog articles to create new posts and articles in an appropriate format. The generation unit also allows the generation AI to collect and learn various data in order to be applied to other communication methods. For example, it can collect and learn from social media post data and blog article data. The generation unit also generates sentences based on different data in order to enable the generation AI to be used in a wide range of communication methods. This allows the generation AI to be applied not only to creating emails, but also to creating social media posts and blog articles, enabling use in a wide range of communication methods.

[0079] The generation unit can link generated emails with other generation AIs to process multiple communication methods simultaneously. For example, the generation unit links emails created by a generation AI with other generation AIs to process multiple communication methods simultaneously. For example, while creating an email, the generation unit simultaneously generates a draft of a social media post or blog article. In addition, in order to link multiple generation AIs, the generation unit has the generation AI collect and learn data specialized for each communication method. For example, it links an email creation AI with an social media posting AI. In addition, the generation unit links emails created by a generation AI with other generation AIs to build a system that efficiently processes multiple communication methods. This allows generated emails to be linked with other generation AIs to process multiple communication methods simultaneously.

[0080] The generation unit uses the emotion estimation function to create emails according to the user's emotional state, thereby enabling more personalized communication. The generation unit, for example, uses the emotion estimation function to create emails according to the user's emotional state. For example, when the user is feeling stressed, a more polite and calm email is generated. The generation unit also provides personalized communication by having the generation AI generate emails according to the user's emotional state based on the emotion estimation data. For example, when the user is happy, a bright and positive email is generated. The generation unit also uses the emotion estimation function to build a system that creates emails according to the user's emotional state in real time. This makes it possible to use the emotion estimation function to create emails according to the user's emotional state, thereby enabling more personalized communication.

[0081] When generating a conversation, the generation unit can estimate the user's emotional state and reflect language and tone that corresponds to the emotion. For example, the generation unit uses a generation AI to estimate the user's emotional state and reflect language and tone that corresponds to the emotion. For example, when the user is feeling stressed, more polite and calm language is used. The generation unit also uses an emotion estimation function to adjust language and tone in real time according to the user's emotional state. For example, when the user is happy, more cheerful and positive language is used. The generation unit also uses a generation AI to learn language and tone that corresponds to the user's emotional state based on the emotion estimation data, and generates conversation based on that information. This makes it possible to estimate the user's emotional state and reflect language and tone that corresponds to the emotion when generating a conversation.

[0082] The generation unit selects an appropriate tone and style depending on the content of the conversation, making it possible to clearly distinguish between business and casual conversations. For example, the generation AI selects an appropriate tone and style depending on the content of the conversation. For example, formal language is used in business conversations, and relaxed language is used in casual conversations. In addition, the generation unit has the generation AI collect and learn from past conversation data in order to clearly distinguish between business and casual conversations depending on the content of the conversation. For example, it learns the format and phrasing of business conversations. In addition, the generation AI selects an appropriate tone and style depending on the content of the conversation, and generates conversations based on that information. This allows the generation AI to select an appropriate tone and style depending on the content of the conversation, making it possible to clearly distinguish between business and casual conversations.

[0083] When generating a conversation, the generation unit can refer to data on similar past conversations and select the optimal wording and tone. For example, the generation unit allows the generation AI to refer to data on similar past conversations and select the optimal wording and tone. For example, it creates a new conversation in an appropriate format based on past business conversations. The generation unit also builds a database based on data on similar past conversations so that the generation AI can select the optimal wording and tone. For example, it collects and learns from past success stories and failure stories. The generation unit also allows the generation AI to select the optimal wording and tone based on data on similar past conversations and generate a conversation based on that information. This allows the generation AI to refer to data on similar past conversations and select the optimal wording and tone when generating a conversation.

[0084] The generation unit can be applied not only to conversation generation but also to voice assistants and navigation systems, enabling use in a wide range of interaction methods. The generation unit, for example, applies the generation AI not only to conversation generation but also to voice assistants and navigation systems. For example, it learns from past voice data and creates new voice responses in an appropriate format. The generation unit also collects and learns various data so that the generation AI can be applied to other interaction methods. For example, it collects and learns from response data for voice assistants and guidance data for navigation systems. The generation unit also generates conversations based on different data so that the generation AI can be used in a wide range of interaction methods. This allows the generation AI to be applied not only to conversation generation but also to voice assistants and navigation systems, enabling use in a wide range of interaction methods.

[0085] The generation unit can link the generated conversation with other generation AIs to simultaneously process multiple interaction means. For example, the generation unit links the conversation generated by the generation AI with other generation AIs to simultaneously process multiple interaction means. For example, while generating a conversation, the generation unit simultaneously generates responses for a voice assistant or guidance for a navigation system. In addition, in order to link multiple generation AIs, the generation unit has the generation AI collect and learn data specialized for each interaction means. For example, the generation unit links a conversation generation AI with a voice assistant AI. In addition, the generation unit links the conversation generated by the generation AI with other generation AIs to build a system that efficiently processes multiple interaction means. This allows the generated conversation to be linked with other generation AIs to simultaneously process multiple interaction means.

[0086] The generation unit uses the emotion estimation function to generate conversations according to the user's emotional state, thereby providing more personalized interactions. The generation unit, for example, uses the emotion estimation function to generate conversations according to the user's emotional state. For example, when the user is feeling stressed, a more polite and calm conversation is generated. The generation unit also provides personalized interactions by generating conversations according to the user's emotional state based on the emotion estimation data using a generation AI. For example, when the user is happy, a bright and positive conversation is generated. The generation unit also uses the emotion estimation function to build a system that generates conversations according to the user's emotional state in real time. This makes it possible to use the emotion estimation function to generate conversations according to the user's emotional state, thereby providing more personalized interactions.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The acquisition unit can collect and learn not only the user's past writings but also posts from websites and social media that the user frequently visits. For example, it can collect posts from news sites and forums that the user frequently reads and learn their language and style. The acquisition unit can also collect posts from social media accounts that the user follows and generate sentences based on the user's interests. Furthermore, the acquisition unit can collect posts from online communities in which the user participates and learn the language and style unique to those communities. This makes it possible to generate sentences that reflect the user's entire online activity.

[0089] The determination unit can estimate the user's emotional state and adjust the tone and style of the sentences based on the estimated emotion. For example, if the user is feeling stressed, the determination unit can generate sentences with a calmer tone. On the other hand, if the user is happy, the determination unit can generate sentences with a brighter, more positive tone. Furthermore, the determination unit can adjust the length and complexity of the sentences according to the user's emotional state. For example, if the user is tired, the determination unit can generate short, concise sentences, and if the user is relaxed, the determination unit can generate sentences with detailed, rich expressions. This enables personalized sentence generation according to the user's emotional state.

[0090] When providing the generated text to the user, the providing unit can provide it in an optimal format by taking into account the user's past feedback. For example, the generated text can be customized based on the user's past preferred formats and styles. The providing unit can also collect user feedback in real time and modify the text based on that feedback. Furthermore, the providing unit can select an optimal display format when the user views the text on a specific device or platform. For example, the providing unit can provide short paragraphs suitable for viewing on a smartphone or detailed descriptions suitable for viewing on a desktop. This enables flexible text provision according to the user's preferences and devices.

[0091] The generation unit can estimate the user's emotional state and select the content and theme of the text based on the estimated emotion. For example, if the user is sad, the generation unit can generate text containing encouraging and comforting content. Also, if the user is excited, the generation unit can generate text containing content that shares that excitement. Furthermore, the generation unit can adjust the pace and rhythm of the text according to the user's emotional state. For example, if the user is relaxed, the generation unit can generate text at a leisurely pace, and if the user is in a hurry, the generation unit can generate text at a pace that quickly conveys information. This makes it possible to select content and themes according to the user's emotional state.

[0092] The acquisition unit can learn by collecting data not only from the user's past writing but also from applications and tools the user frequently uses. For example, it can collect data from the user's frequently used messaging app or project management tool to learn their vocabulary and style. The acquisition unit can also collect data from documents and presentations created by the user to gain a deeper understanding of the user's writing style. Furthermore, the acquisition unit can also collect data from recordings of online meetings and webinars the user participates in to learn the content and style of their speech. This makes it possible to generate writing that reflects the user's diverse activities.

[0093] The determination unit can estimate the user's emotional state and adjust the structure and layout of the sentence based on the estimated emotion. For example, if the user is nervous, the determination unit can generate sentences with a concise and easy-to-understand structure. On the other hand, if the user is relaxed, the determination unit can generate sentences with detailed and rich expressions. Furthermore, the determination unit can also adjust the visual elements of the sentence according to the user's emotional state. For example, if the user is tired, the determination unit can provide a visually simple and easy-to-read layout, and if the user is excited, the determination unit can provide a visually attractive and interactive layout. This enables flexible adjustment of the sentence structure and layout according to the user's emotional state.

[0094] When providing the generated text to the user, the providing unit can provide it at the optimal timing, taking into account the user's past behavioral history. For example, if the user has tended to view text during a specific time period in the past, the providing unit can provide the text according to that time period. The providing unit can also customize the method of providing the text based on the user's behavioral history. For example, if the user prefers notifications by email, the generated text is sent by email, and if the user prefers in-app notifications, the notification is sent within the app. Furthermore, the providing unit can set priorities for the text based on the user's behavioral history and provide important information preferentially. This enables flexible text provision according to the user's behavioral history.

[0095] The generation unit can estimate the user's emotional state and adjust the visual elements of the text based on the estimated emotion. For example, if the user is feeling stressed, the generation unit can generate text with a visually simple and calm design. On the other hand, if the user is happy, the generation unit can generate text with a visually bright and positive design. Furthermore, the generation unit can also adjust the selection of images and graphics included in the text according to the user's emotional state. For example, if the user is relaxed, the generation unit can use images with a relaxed atmosphere, and if the user is excited, the generation unit can use images with an energetic atmosphere. This makes it possible to adjust the visual elements according to the user's emotional state.

[0096] The acquisition unit can collect and learn data not only from the user's past writing but also from the digital content and media the user frequently uses. For example, it can collect transcripts of videos and podcasts the user frequently watches and learn their vocabulary and style. The acquisition unit can also collect data from newsletters and e-books the user subscribes to to generate writing based on the user's interests. Furthermore, the acquisition unit can also collect data from materials from online courses and webinars the user participates in to learn their content and style. This enables the generation of writing that reflects the user's diverse digital content.

[0097] When providing the generated text to the user, the providing unit can provide it in a format optimized for the user's device or platform. For example, the providing unit can provide short paragraphs suitable for viewing on a smartphone or detailed explanations suitable for viewing on a desktop. The providing unit can also customize the format of the text to suit a specific application or tool used by the user. For example, the providing unit can provide the text in a task list format suitable for a project management tool used by the user or in a chat format suitable for a messaging app. The providing unit can also adjust the way the text is displayed depending on the user's device or platform. For example, the providing unit can provide a design that supports dark mode or a text-to-speech function. This enables flexible text provision that is optimized for the user's device or platform.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The learning unit studies past sentences. For example, the learning unit collects and studies the user's past emails, reports, blog posts, etc. The learning unit also uses machine learning and deep learning to learn the user's vocabulary, punctuation, and line break habits. Specifically, it learns the user's frequently used phrases, specific expressions, and sentence rhythms. Step 2: The mimicking unit imitates the vocabulary, punctuation, and line break habits learned by the learning unit. For example, the mimicking unit reproduces the user's frequently used "desumasu" and "dearu" styles, the use of specific punctuation, and the timing of line breaks. It can also imitate style and formatting. Step 3: The generator generates sentences based on the content imitated by the imitator. For example, the generator uses natural language generation technology or template-based generation to generate sentences that reflect the user's vocabulary, punctuation, and line break habits. The generator also generates sentences with appropriate vocabulary and formatting based on the user's past writing data.

[0100] 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.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0102] 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.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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."

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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, to avoid confusion and 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.

[0166] 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]

[0167] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A learning section that studies past texts, an imitation unit that imitates the vocabulary, punctuation, and line break habits learned by the learning unit; a generation unit that generates a sentence based on the content imitated by the imitation unit. A system characterized by:

2. The learning unit Estimate the user's emotional state and learn how to change language in response to changes in emotion 2. The system of claim 1.

3. The learning unit Analyzes metadata contained in users' past writings and learns context-specific language usage 2. The system of claim 1.

4. The learning unit Learn not only your writing style but also your opinions and positions on specific topics 2. The system of claim 1.

5. The learning unit It learns not only from the user's past writing but also from audio and video data, and imitates language usage from multimodal information.

2. The system of claim 1.

Images