System

Abstract

An object of a system according to an embodiment is to automatically generate a natural conversational sentence on the basis of a keyword and a setting specified by a user.SOLUTION: A system includes a keyword and setting input unit, an analysis unit, a generation unit, and a provision unit. The keyword and setting input unit receives a keyword and a setting from a user. The analysis unit analyzes the keyword and the setting received by the keyword and setting input unit. The generator generates the conversational sentence on the basis of the keyword analyzed by the analyzer and the setting. The provider provides the user with the conversational sentence generated by the generator.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 technologies have not been able to adequately automatically generate natural conversational sentences based on keywords and settings specified by the user, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically generate natural conversational sentences based on keywords and settings specified by the user. [Means for solving the problem]

[0006] A system according to an embodiment includes a keyword and setting input unit, an analysis unit, a generation unit, and a provision unit. The keyword and setting input unit accepts keywords and settings from a user. The analysis unit analyzes the keywords and settings accepted by the keyword and setting input unit. The generation unit generates a conversation sentence based on the keywords and settings analyzed by the analysis unit. The provision unit provides the conversation sentence generated by the generation unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment can automatically generate natural conversational sentences based on keywords and settings specified by the user. [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) A conversational sentence generation system according to an embodiment of the present invention is a system that automatically generates natural conversational sentences based on keywords and settings specified by a user. As a result, the conversational sentence generation system can automatically generate and provide natural conversational sentences based on keywords and settings specified by a user.

[0029] A conversation sentence generation system according to an embodiment includes a keyword and setting input unit, an analysis unit, a generation unit, and a provision unit. The keyword and setting input unit accepts keywords and settings from a user. For example, the user can input keywords and settings such as "travel," "conversation with friends," and "casual tone." The keyword and setting input unit can support input formats such as text, numeric, and multiple-choice. The analysis unit analyzes the keywords and settings accepted by the keyword and setting input unit. For example, the generation AI analyzes the keywords and settings using natural language processing technology and understands their content. The analysis unit can also analyze the keywords and settings using a machine learning algorithm. The generation unit generates conversation sentences based on the keywords and settings analyzed by the analysis unit. For example, the generation AI generates conversation sentences using a text generation AI (e.g., LLM). The generation AI can also generate conversation sentences using a multimodal generation AI. The generation unit can also generate conversation sentences taking into account the tone and style of the dialogue. The provision unit provides the conversation sentences generated by the generation unit to a user. For example, the providing unit provides the conversation sentence by a method such as a screen display, an audio output, or a notification. The providing unit can also provide the generated conversation sentence in a text format or an audio format. This allows the conversation sentence generation system to automatically generate and provide natural conversation sentences based on keywords and settings specified by the user.

[0030] The keyword and setting input unit can present related suggested keywords to assist the user in entering information. For example, when a user enters "travel," the generation AI can automatically present related keywords such as "tourist attractions," "hotels," and "flights" to allow the user to select from them. Also, when a user enters "business email," the generation AI can suggest related keywords such as "meeting agenda," "project progress report," and "client proposal." Also, when a user enters "conversation with friends," the generation AI can display related keywords such as "recent events," "hobbies," and "next event" to allow the user to select from them. This assists the user in entering information and allows for more efficient keyword and setting entry.

[0031] The keyword and setting input unit can suggest optimal keywords or settings based on past input history or trend data. For example, when a user inputs "travel," the keyword and setting input unit can suggest "popular tourist destinations," "recommended hotels," "discount flight information," etc. based on past input history and current trend data. Also, when a user inputs "business email," optimal keywords such as "meeting agenda," "project progress report," and "client proposal" can be suggested based on past history and trends. Also, when a user inputs "conversation with friends," optimal keywords such as "recent events," "hobbies," and "next plans" can be suggested based on past history and trends. In this way, optimal keywords and settings can be suggested to the user based on past input history and trend data.

[0032] The keyword and setting input unit supports voice input or gesture input, improving user convenience. For example, when a user says "travel" through voice input, the generation AI analyzes the voice and automatically displays related keywords and settings. Also, when a user indicates "business email" through gesture input, the generation AI can analyze the gesture and automatically display related keywords and settings. Also, when a user says "conversation with friends" through voice input, the generation AI can analyze the voice and automatically display related keywords and settings. This allows for support of voice input and gesture input, improving user convenience.

[0033] The keyword and setting input unit enables seamless input between different devices, allowing the user to input from any device. For example, the keyword and setting input unit allows a user to start typing "travel" on a smartphone and continue typing on a PC. The generation AI synchronizes data between devices. Also, if a user starts typing "business email" on a tablet, it can be continued on a smartphone. The generation AI synchronizes data between devices. Also, if a user starts typing "conversation with a friend" on a PC, it can be continued on a tablet. The generation AI synchronizes data between devices. This enables seamless input between different devices, allowing the user to input from any device.

[0034] The analysis unit can also analyze related image and video data to generate richer conversational text. For example, when a user inputs "travel," the generation AI analyzes related image and video data and generates conversational text based on the visual information. Similarly, when a user inputs "business email," the generation AI can analyze related image and video data and generate conversational text based on the visual information. Similarly, when a user inputs "conversation with friends," the generation AI can analyze related image and video data and generate conversational text based on the visual information. This allows for the analysis of related image and video data to generate richer conversational text.

[0035] The analysis unit can perform more personalized analysis by taking into account the user's past input history or behavioral patterns. For example, when the user inputs "travel," the generation AI can generate a conversation that matches the user's preferences by taking into account the user's past input history and behavioral patterns. Also, when the user inputs "business email," the generation AI can generate a conversation that matches the user's preferences by taking into account the user's past input history and behavioral patterns. Also, when the user inputs "conversation with friends," the generation AI can generate a conversation that matches the user's preferences by taking into account the user's past input history and behavioral patterns. This allows for more personalized analysis by taking into account the user's past input history and behavioral patterns.

[0036] The analysis unit can analyze keywords or settings in multiple languages, making it possible to accommodate users of different languages. For example, when a user inputs "travel," the analysis unit allows the generation AI to analyze in multiple languages ​​and generate a conversation that can accommodate users of different languages. Also, when a user inputs "business email," the generation AI can analyze in multiple languages ​​and generate a conversation that can accommodate users of different languages. Also, when a user inputs "conversation with friends," the generation AI can analyze in multiple languages ​​and generate a conversation that can accommodate users of different languages. This multilingual support makes it possible to accommodate users of different languages.

[0037] The analysis unit can cooperate with other applications or services to perform analysis based on a wider range of data. For example, when a user inputs "travel," the generation AI can cooperate with other applications or services to perform analysis based on a wider range of data. Also, when a user inputs "business email," the generation AI can cooperate with other applications or services to perform analysis based on a wider range of data. Also, when a user inputs "conversation with friends," the generation AI can cooperate with other applications or services to perform analysis based on a wider range of data. This allows the analysis to be performed based on a wider range of data by cooperating with other applications or services.

[0038] The generation unit can refer to the user's past conversation history and generate consistent conversational sentences. For example, when the user inputs "travel," the generation AI can refer to the past conversation history and generate consistent conversational sentences. Also, when the user inputs "business email," the generation AI can refer to the past conversation history and generate consistent conversational sentences. Also, when the user inputs "conversation with friends," the generation AI can refer to the past conversation history and generate consistent conversational sentences. In this way, consistent conversational sentences can be generated by referring to the user's past conversation history.

[0039] The generation unit can generate more personalized conversational text by taking into account the user's preferences or interests. For example, when a user inputs "travel," the generation AI generates personalized conversational text by taking into account the user's preferences and interests. For example, conversational text is generated based on places the user has visited in the past or favorite activities. Also, when a user inputs "business email," the generation AI can generate personalized conversational text by taking into account the user's preferences and interests. For example, conversational text is generated based on projects or industries in which the user is interested. Also, when a user inputs "conversations with friends," the generation AI can generate personalized conversational text by taking into account the user's preferences and interests. For example, conversational text is generated based on the user's favorite topics or common hobbies. In this way, more personalized conversational text can be generated by taking into account the user's preferences and interests.

[0040] The generation unit can respond to different scenarios and generate conversational sentences that meet the user's needs. For example, when a user inputs "travel," the generation AI generates conversational sentences that correspond to scenarios such as business, casual, and formal. For example, in a business scenario, it might generate "recommended spots for business trips," and in a casual scenario, it might generate "travel plans with friends." Similarly, when a user inputs "business email," the generation AI can generate conversational sentences that correspond to scenarios such as business, casual, and formal. For example, in a business scenario, it might generate "meeting agenda," and in a formal scenario, it might generate "official report." Similarly, when a user inputs "conversation with friends," the generation AI can generate conversational sentences that correspond to scenarios such as business, casual, and formal. For example, in a casual scenario, it might generate "recent events," and in a formal scenario, it might generate "official invitation." This allows the generation unit to respond to different scenarios and generate conversational sentences that meet the user's needs.

[0041] The generation unit can generate conversational text that can be used globally, taking into account the characteristics of different cultures or regions. For example, when a user inputs "travel," the generation AI generates conversational text that can be used globally, taking into account the characteristics of different cultures and regions. For example, it generates conversational text based on the culture and customs of a specific country or region. Also, when a user inputs "business email," the generation AI can generate conversational text that can be used globally, taking into account the characteristics of different cultures and regions. For example, it generates conversational text based on international business manners and etiquette. Also, when a user inputs "conversation with friends," the generation AI can generate conversational text that can be used globally, taking into account the characteristics of different cultures and regions. For example, it generates conversational text about intercultural exchange or international events. In this way, it is possible to generate conversational text that can be used globally, taking into account the characteristics of different cultures and regions.

[0042] The providing unit can provide an interface that allows the user to customize the generated conversation text according to their preferences. For example, when a user inputs "travel," the providing unit provides an interface that allows the user to customize the conversation text generated by the generation AI. For example, the user can add specific phrases or change the tone. Also, when a user inputs "business email," the providing unit can provide an interface that allows the user to customize the conversation text generated by the generation AI. For example, the user can add specific information or change the format. Also, when a user inputs "conversation with friends," the providing unit can provide an interface that allows the user to customize the conversation text generated by the generation AI. For example, the user can add specific topics or change the style. In this way, an interface that allows the user to customize the generated conversation text according to their preferences can be provided.

[0043] The providing unit can attach images or videos related to the generated conversation text, thereby realizing richer communication. For example, when a user inputs "travel," the providing unit attaches images or videos related to the conversation text generated by the generation AI, thereby realizing richer communication. For example, photos of travel destinations or videos of tourist spots can be attached. Also, when a user inputs "business email," the generating AI can attach images or videos related to the generated conversation text, thereby realizing richer communication. For example, a graph showing project progress or a presentation video can be attached. Also, when a user inputs "conversation with friends," the generating AI can attach images or videos related to the generated conversation text, thereby realizing richer communication. For example, photos of shared memories or videos of events can be attached. In this way, images and videos related to the generated conversation text can be attached, thereby realizing richer communication.

[0044] The providing unit can adapt the generated conversation text to different platforms, allowing the user to use it on any platform. For example, when a user inputs "travel," the providing unit provides the conversation text generated by the generation AI in a way that is compatible with different platforms, such as email, social media, and chat apps. For example, the format is adjusted depending on whether the conversation text is sent by email or posted on a social media platform. Also, when a user inputs "business email," the providing unit can adapt the conversation text generated by the generation AI in a way that is compatible with different platforms, such as email, social media, and chat apps. For example, the format is adjusted depending on whether the conversation text is sent by email or shared on a chat app. Also, when a user inputs "conversation with a friend," the providing unit can adapt the conversation text generated by the generation AI in a way that is compatible with different platforms, such as email, social media, and chat apps. For example, the format is adjusted depending on whether the conversation text is posted on a social media platform or shared on a chat app. In this way, the generated conversation text is compatible with different platforms, allowing the user to use it on any platform.

[0045] The providing unit can collect user feedback on the generated conversational text and use it to improve the generation algorithm. For example, when a user inputs "travel," the providing unit collects user feedback on the conversational text generated by the generation AI and uses it to improve the generation algorithm. For example, the user evaluates the quality and content of the conversational text. Also, when a user inputs "business email," user feedback on the conversational text generated by the generation AI can be collected and used to improve the generation algorithm. For example, the user evaluates the appropriateness and effectiveness of the conversational text. Also, when a user inputs "conversation with a friend," user feedback on the conversational text generated by the generation AI can be collected and used to improve the generation algorithm. For example, the user evaluates the enjoyment and relatability of the conversational text. In this way, user feedback on the generated conversational text can be collected and used to improve the generation algorithm.

[0046] Furthermore, the conversation generation system develops specialized modules for generating conversations specialized for specific industries or applications. For example, the conversation generation system utilizes generative AI to develop specialized modules for generating conversations specialized for the medical industry. For example, it generates conversations used between doctors and patients. Furthermore, generative AI can be used to develop specialized modules for generating conversations specialized for the education industry. For example, it generates conversations used between teachers and students. Furthermore, generative AI can be used to develop specialized modules for generating conversations specialized for customer support. For example, it generates conversations used between customers and support staff. This makes it possible to develop specialized modules for generating conversations specialized for specific industries or applications.

[0047] Furthermore, the conversation generation system generates educational content using generative AI or supports communication with patients in the medical field. The conversation generation system generates educational content using generative AI, for example. For example, it generates explanatory text and example questions that are easy for students to understand. In addition, generative AI can be used to support communication with patients in the medical field. For example, it generates conversations that explain diagnosis results and treatment plans in a way that is easy for patients to understand. In addition, generative AI can be used to generate content for corporate training. For example, it generates training manuals and scenarios that are easy for employees to learn. This makes it possible to generate educational content using generative AI or support communication with patients in the medical field.

[0048] Furthermore, the conversation generation system will expand the conversation generation service utilizing generative AI to different industries (education, medicine, entertainment, etc.), achieving a wide range of applications. For example, the conversation generation system will expand the conversation generation service utilizing generative AI to the education industry to generate conversations used between teachers and students. For example, it will generate lesson explanations and homework instructions. Also, the conversation generation service utilizing generative AI will be expanded to the medical industry to generate conversations used between doctors and patients. For example, it will generate explanations of diagnosis results and treatment plans. Also, the conversation generation service utilizing generative AI will be expanded to the entertainment industry to generate conversations used between characters and users. For example, it will generate lines and stories for characters in games. This will enable the conversation generation service utilizing generative AI to be expanded to different industries, achieving a wide range of applications.

[0049] Furthermore, the conversational text generation system is used to develop an automatic response system or a customer support chatbot using generative AI. For example, the conversational text generation system uses generative AI to develop an automatic response system. For example, it can automate corporate inquiry responses and generate appropriate answers to customer questions. Generative AI can also be used to develop a customer support chatbot. For example, it can automate customer support on an online shopping site and generate appropriate answers to customer questions. Generative AI can also be used to develop an automatic response system for a reservation system. For example, it can generate appropriate answers to inquiries about restaurant or hotel reservations. This makes it possible to develop an automatic response system or a customer support chatbot using generative AI.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The conversation generation system can also automatically search for related news articles and blog posts based on the user's input and incorporate them into the conversation. For example, if a user inputs "travel," the generation AI will search for the latest travel-related news and blog posts and incorporate their contents into the conversation. Similarly, if a user inputs "business email," the generation AI can search for the latest business-related news and blog posts and incorporate their contents into the conversation. Similarly, if a user inputs "conversations with friends," the generation AI can search for the latest trends and topics and incorporate their contents into the conversation. This allows related news articles and blog posts to be automatically searched for based on the user's input and incorporated into the conversation.

[0052] The conversation generation system can also suggest related music and podcasts based on the user's input. For example, if a user inputs "travel," the generation AI can suggest music and podcasts related to travel. If a user inputs "business email," the generation AI can suggest music and podcasts related to business. If a user inputs "conversation with friends," the generation AI can suggest music and podcasts related to conversations with friends. This allows the system to suggest related music and podcasts based on the user's input.

[0053] The conversation generation system can also suggest related events and activities based on the user's input. For example, if a user inputs "travel," the generation AI can suggest events and activities at the travel destination. If a user inputs "business email," the generation AI can suggest business-related events and seminars. If a user inputs "conversation with friends," the generation AI can suggest events and activities that can be enjoyed with friends. This allows the system to suggest related events and activities based on the user's input.

[0054] The conversation generation system can also suggest related books and movies based on the user's input. For example, if a user inputs "travel," the generation AI can suggest books and movies related to travel. Also, if a user inputs "business email," the generation AI can suggest books and movies related to business. Also, if a user inputs "conversation with friends," the generation AI can suggest books and movies related to conversations with friends. In this way, it is possible to suggest related books and movies based on the user's input.

[0055] The conversation generation system can also suggest related recipes based on the user's input. For example, if a user inputs "travel," the generation AI can suggest recipes for travel destinations. If a user inputs "business email," the generation AI can suggest recipes suitable for business lunches or dinners. If a user inputs "conversation with friends," the generation AI can suggest recipes that can be enjoyed with friends. This allows the system to suggest related recipes based on the user's input.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The keyword and setting input unit accepts keywords and settings from the user. For example, the user can input keywords and settings such as "travel," "conversation with friends," and "casual tone." The keyword and setting input unit can also support input formats such as text, numeric, and multiple-choice options. Step 2: The analysis unit analyzes the keywords and settings received by the keyword and setting input unit. For example, the generation AI uses natural language processing technology to analyze the keywords and settings and understand their content. The analysis unit can also analyze the keywords and settings using machine learning algorithms. Step 3: The generator generates conversational text based on the keywords and settings analyzed by the analyzer. For example, the generator generates conversational text using a text generation AI (e.g., LLM). The generator can also generate conversational text using a multimodal generation AI. The generator can also generate conversational text taking into account the tone and style of the dialogue. Step 4: The providing unit provides the conversation sentence generated by the generating unit to the user. For example, the providing unit provides the conversation sentence by a method such as a screen display, an audio output, or a notification. The providing unit can also provide the generated conversation sentence in a text format or an audio format.

[0058] (Example 2) A conversational sentence generation system according to an embodiment of the present invention is a system that automatically generates natural conversational sentences based on keywords and settings specified by a user. As a result, the conversational sentence generation system can automatically generate and provide natural conversational sentences based on keywords and settings specified by a user.

[0059] A conversation sentence generation system according to an embodiment includes a keyword and setting input unit, an analysis unit, a generation unit, and a provision unit. The keyword and setting input unit accepts keywords and settings from a user. For example, the user can input keywords and settings such as "travel," "conversation with friends," and "casual tone." The keyword and setting input unit can support input formats such as text, numeric, and multiple-choice. The analysis unit analyzes the keywords and settings accepted by the keyword and setting input unit. For example, the generation AI analyzes the keywords and settings using natural language processing technology and understands their content. The analysis unit can also analyze the keywords and settings using a machine learning algorithm. The generation unit generates conversation sentences based on the keywords and settings analyzed by the analysis unit. For example, the generation AI generates conversation sentences using a text generation AI (e.g., LLM). The generation AI can also generate conversation sentences using a multimodal generation AI. The generation unit can also generate conversation sentences taking into account the tone and style of the dialogue. The provision unit provides the conversation sentences generated by the generation unit to a user. For example, the providing unit provides the conversation sentence by a method such as a screen display, an audio output, or a notification. The providing unit can also provide the generated conversation sentence in a text format or an audio format. This allows the conversation sentence generation system to automatically generate and provide natural conversation sentences based on keywords and settings specified by the user.

[0060] The keyword and setting input unit can present related suggested keywords to assist the user in entering information. For example, when a user enters "travel," the generation AI can automatically present related keywords such as "tourist attractions," "hotels," and "flights" to allow the user to select from them. Also, when a user enters "business email," the generation AI can suggest related keywords such as "meeting agenda," "project progress report," and "client proposal." Also, when a user enters "conversation with friends," the generation AI can display related keywords such as "recent events," "hobbies," and "next event" to allow the user to select from them. This assists the user in entering information and allows for more efficient keyword and setting entry.

[0061] The keyword and setting input unit can suggest optimal keywords or settings based on past input history or trend data. For example, when a user inputs "travel," the keyword and setting input unit can suggest "popular tourist destinations," "recommended hotels," "discount flight information," etc. based on past input history and current trend data. Also, when a user inputs "business email," optimal keywords such as "meeting agenda," "project progress report," and "client proposal" can be suggested based on past history and trends. Also, when a user inputs "conversation with friends," optimal keywords such as "recent events," "hobbies," and "next plans" can be suggested based on past history and trends. In this way, optimal keywords and settings can be suggested to the user based on past input history and trend data.

[0062] The keyword and setting input unit can use the emotion estimation function to analyze the user's emotion at the time of input and suggest keywords or settings to elicit positive emotions. For example, when a user inputs "travel," the emotion estimation function analyzes the user's emotion and suggests "relaxing beaches" and "adventurous hiking trails" to elicit positive emotions. When a user inputs "business email," the emotion estimation function can analyze the user's emotion and suggest "sharing success stories" and "positive feedback" to elicit positive emotions. When a user inputs "conversations with friends," the emotion estimation function can analyze the user's emotion and suggest "happy memories" and "next fun plans" to elicit positive emotions. This allows the user's emotion to be analyzed and keywords and settings to elicit positive emotions to be suggested.

[0063] The keyword and setting input unit supports voice input or gesture input, improving user convenience. For example, when a user says "travel" through voice input, the generation AI analyzes the voice and automatically displays related keywords and settings. Also, when a user indicates "business email" through gesture input, the generation AI can analyze the gesture and automatically display related keywords and settings. Also, when a user says "conversation with friends" through voice input, the generation AI can analyze the voice and automatically display related keywords and settings. This allows for support of voice input and gesture input, improving user convenience.

[0064] The keyword and setting input unit enables seamless input between different devices, allowing the user to input from any device. For example, the keyword and setting input unit allows a user to start typing "travel" on a smartphone and continue typing on a PC. The generation AI synchronizes data between devices. Also, if a user starts typing "business email" on a tablet, it can be continued on a smartphone. The generation AI synchronizes data between devices. Also, if a user starts typing "conversation with a friend" on a PC, it can be continued on a tablet. The generation AI synchronizes data between devices. This enables seamless input between different devices, allowing the user to input from any device.

[0065] The keyword and setting input unit uses the emotion estimation function to provide real-time feedback on the user's emotional response to keywords and settings entered by the user, and can adjust the input content. For example, when the user enters "travel," the emotion estimation function analyzes the user's emotion in real time and adjusts the keywords and settings to obtain a positive response. Also, when the user enters "business email," the emotion estimation function can analyze the user's emotion in real time and adjust the keywords and settings to obtain a positive response. Also, when the user enters "conversation with friends," the emotion estimation function can analyze the user's emotion in real time and adjust the keywords and settings to obtain a positive response. In this way, the user's emotional response can be fed back in real time and the input content can be adjusted.

[0066] The analysis unit can also analyze related image and video data to generate richer conversational text. For example, when a user inputs "travel," the generation AI analyzes related image and video data and generates conversational text based on the visual information. Similarly, when a user inputs "business email," the generation AI can analyze related image and video data and generate conversational text based on the visual information. Similarly, when a user inputs "conversation with friends," the generation AI can analyze related image and video data and generate conversational text based on the visual information. This allows for the analysis of related image and video data to generate richer conversational text.

[0067] The analysis unit can perform more personalized analysis by taking into account the user's past input history or behavioral patterns. For example, when the user inputs "travel," the generation AI can generate a conversation that matches the user's preferences by taking into account the user's past input history and behavioral patterns. Also, when the user inputs "business email," the generation AI can generate a conversation that matches the user's preferences by taking into account the user's past input history and behavioral patterns. Also, when the user inputs "conversation with friends," the generation AI can generate a conversation that matches the user's preferences by taking into account the user's past input history and behavioral patterns. This allows for more personalized analysis by taking into account the user's past input history and behavioral patterns.

[0068] The analysis unit can use the emotion estimation function to consider the user's emotions when analyzing keywords or settings, and provide analysis results that correspond to the emotions. For example, when a user inputs "travel," the emotion estimation function can analyze the user's emotions and provide analysis results that elicit positive emotions. Also, when a user inputs "business email," the emotion estimation function can analyze the user's emotions and provide analysis results that elicit positive emotions. Also, when a user inputs "conversation with friends," the emotion estimation function can analyze the user's emotions and provide analysis results that elicit positive emotions. In this way, the analysis unit can consider the user's emotions and provide analysis results that correspond to the emotions.

[0069] The analysis unit can analyze keywords or settings in multiple languages, making it possible to accommodate users of different languages. For example, when a user inputs "travel," the analysis unit allows the generation AI to analyze in multiple languages ​​and generate a conversation that can accommodate users of different languages. Also, when a user inputs "business email," the generation AI can analyze in multiple languages ​​and generate a conversation that can accommodate users of different languages. Also, when a user inputs "conversation with friends," the generation AI can analyze in multiple languages ​​and generate a conversation that can accommodate users of different languages. This multilingual support makes it possible to accommodate users of different languages.

[0070] The analysis unit can cooperate with other applications or services to perform analysis based on a wider range of data. For example, when a user inputs "travel," the generation AI can cooperate with other applications or services to perform analysis based on a wider range of data. Also, when a user inputs "business email," the generation AI can cooperate with other applications or services to perform analysis based on a wider range of data. Also, when a user inputs "conversation with friends," the generation AI can cooperate with other applications or services to perform analysis based on a wider range of data. This allows the analysis to be performed based on a wider range of data by cooperating with other applications or services.

[0071] The analysis unit can use the emotion estimation function to collect the user's emotional reactions to the analysis results and improve the accuracy of the analysis algorithm. For example, when the user inputs "travel," the emotion estimation function collects the user's emotional reactions to the analysis results and improves the accuracy of the analysis algorithm. Also, when the user inputs "business email," the emotion estimation function collects the user's emotional reactions to the analysis results and improves the accuracy of the analysis algorithm. Also, when the user inputs "conversation with friends," the emotion estimation function collects the user's emotional reactions to the analysis results and improves the accuracy of the analysis algorithm. In this way, the user's emotional reactions to the analysis results can be collected and the accuracy of the analysis algorithm can be improved.

[0072] The generation unit can refer to the user's past conversation history and generate consistent conversational sentences. For example, when the user inputs "travel," the generation AI can refer to the past conversation history and generate consistent conversational sentences. Also, when the user inputs "business email," the generation AI can refer to the past conversation history and generate consistent conversational sentences. Also, when the user inputs "conversation with friends," the generation AI can refer to the past conversation history and generate consistent conversational sentences. In this way, consistent conversational sentences can be generated by referring to the user's past conversation history.

[0073] The generation unit can generate more personalized conversational text by taking into account the user's preferences or interests. For example, when a user inputs "travel," the generation AI generates personalized conversational text by taking into account the user's preferences and interests. For example, conversational text is generated based on places the user has visited in the past or favorite activities. Also, when a user inputs "business email," the generation AI can generate personalized conversational text by taking into account the user's preferences and interests. For example, conversational text is generated based on projects or industries in which the user is interested. Also, when a user inputs "conversations with friends," the generation AI can generate personalized conversational text by taking into account the user's preferences and interests. For example, conversational text is generated based on the user's favorite topics or common hobbies. In this way, more personalized conversational text can be generated by taking into account the user's preferences and interests.

[0074] The generation unit can use the emotion estimation function to generate conversational text in a tone or style that matches the user's emotion. For example, when a user inputs "travel," the emotion estimation function analyzes the user's emotion and generates conversational text in a tone and style that elicits positive emotion. For example, a conversational text sharing memories of a fun trip is generated. Also, when a user inputs "business email," the emotion estimation function can analyze the user's emotion and generate conversational text in a tone and style that elicits positive emotion. For example, a conversational text reporting on the progress of a positive project is generated. Also, when a user inputs "conversation with friends," the emotion estimation function can analyze the user's emotion and generate conversational text in a tone and style that elicits positive emotion. For example, a conversational text discussing a fun event or next plans is generated. In this way, conversational text in a tone and style that matches the user's emotion can be generated.

[0075] The generation unit can respond to different scenarios and generate conversational sentences that meet the user's needs. For example, when a user inputs "travel," the generation AI generates conversational sentences that correspond to scenarios such as business, casual, and formal. For example, in a business scenario, it might generate "recommended spots for business trips," and in a casual scenario, it might generate "travel plans with friends." Similarly, when a user inputs "business email," the generation AI can generate conversational sentences that correspond to scenarios such as business, casual, and formal. For example, in a business scenario, it might generate "meeting agenda," and in a formal scenario, it might generate "official report." Similarly, when a user inputs "conversation with friends," the generation AI can generate conversational sentences that correspond to scenarios such as business, casual, and formal. For example, in a casual scenario, it might generate "recent events," and in a formal scenario, it might generate "official invitation." This allows the generation unit to respond to different scenarios and generate conversational sentences that meet the user's needs.

[0076] The generation unit can generate conversational text that can be used globally, taking into account the characteristics of different cultures or regions. For example, when a user inputs "travel," the generation AI generates conversational text that can be used globally, taking into account the characteristics of different cultures and regions. For example, it generates conversational text based on the culture and customs of a specific country or region. Also, when a user inputs "business email," the generation AI can generate conversational text that can be used globally, taking into account the characteristics of different cultures and regions. For example, it generates conversational text based on international business manners and etiquette. Also, when a user inputs "conversation with friends," the generation AI can generate conversational text that can be used globally, taking into account the characteristics of different cultures and regions. For example, it generates conversational text about intercultural exchange or international events. In this way, it is possible to generate conversational text that can be used globally, taking into account the characteristics of different cultures and regions.

[0077] The generation unit can monitor the user's emotional response to the conversational text generated using the emotion estimation function in real time and adjust the generation algorithm. For example, when the user inputs "travel," the generation unit can monitor the user's emotional response to the conversational text generated by the emotion estimation function in real time and adjust the generation algorithm. For example, the generation unit can modify the conversational text to obtain a positive response. Also, when the user inputs "business email," the generation unit can monitor the user's emotional response to the conversational text generated by the emotion estimation function in real time and adjust the generation algorithm. For example, the generation unit can modify the conversational text to obtain a positive response. Also, when the user inputs "conversation with friends," the generation unit can monitor the user's emotional response to the conversational text generated by the emotion estimation function in real time and adjust the generation algorithm. For example, the generation unit can modify the conversational text to obtain a happy response. In this way, the generation algorithm can be adjusted by monitoring the user's emotional response to the generated conversational text in real time.

[0078] The providing unit can provide an interface that allows the user to customize the generated conversation text according to their preferences. For example, when a user inputs "travel," the providing unit provides an interface that allows the user to customize the conversation text generated by the generation AI. For example, the user can add specific phrases or change the tone. Also, when a user inputs "business email," the providing unit can provide an interface that allows the user to customize the conversation text generated by the generation AI. For example, the user can add specific information or change the format. Also, when a user inputs "conversation with friends," the providing unit can provide an interface that allows the user to customize the conversation text generated by the generation AI. For example, the user can add specific topics or change the style. In this way, an interface that allows the user to customize the generated conversation text according to their preferences can be provided.

[0079] The providing unit can attach images or videos related to the generated conversation text, thereby realizing richer communication. For example, when a user inputs "travel," the providing unit attaches images or videos related to the conversation text generated by the generation AI, thereby realizing richer communication. For example, photos of travel destinations or videos of tourist spots can be attached. Also, when a user inputs "business email," the generating AI can attach images or videos related to the generated conversation text, thereby realizing richer communication. For example, a graph showing project progress or a presentation video can be attached. Also, when a user inputs "conversation with friends," the generating AI can attach images or videos related to the generated conversation text, thereby realizing richer communication. For example, photos of shared memories or videos of events can be attached. In this way, images and videos related to the generated conversation text can be attached, thereby realizing richer communication.

[0080] The providing unit can use the emotion estimation function to analyze the emotion the user felt when receiving the conversational text and reflect it in the generation of the next conversational text. For example, when the user inputs "travel," the emotion estimation function analyzes the emotion the user felt when receiving the conversational text and reflects it in the generation of the next conversational text. For example, the providing unit adjusts the next conversational text to obtain a positive response. Also, when the user inputs "business email," the emotion estimation function analyzes the emotion the user felt when receiving the conversational text and reflects it in the generation of the next conversational text. For example, the next conversational text is adjusted to obtain a positive response. Also, when the user inputs "conversation with a friend," the emotion estimation function analyzes the emotion the user felt when receiving the conversational text and reflects it in the generation of the next conversational text. For example, the next conversational text is adjusted to obtain a happy response. In this way, the emotion the user felt when receiving the conversational text can be analyzed and reflected in the generation of the next conversational text.

[0081] The providing unit can adapt the generated conversation text to different platforms, allowing the user to use it on any platform. For example, when a user inputs "travel," the providing unit provides the conversation text generated by the generation AI in a way that is compatible with different platforms, such as email, social media, and chat apps. For example, the format is adjusted depending on whether the conversation text is sent by email or posted on a social media platform. Also, when a user inputs "business email," the providing unit can adapt the conversation text generated by the generation AI in a way that is compatible with different platforms, such as email, social media, and chat apps. For example, the format is adjusted depending on whether the conversation text is sent by email or shared on a chat app. Also, when a user inputs "conversation with a friend," the providing unit can adapt the conversation text generated by the generation AI in a way that is compatible with different platforms, such as email, social media, and chat apps. For example, the format is adjusted depending on whether the conversation text is posted on a social media platform or shared on a chat app. In this way, the generated conversation text is compatible with different platforms, allowing the user to use it on any platform.

[0082] The providing unit can collect user feedback on the generated conversational text and use it to improve the generation algorithm. For example, when a user inputs "travel," the providing unit collects user feedback on the conversational text generated by the generation AI and uses it to improve the generation algorithm. For example, the user evaluates the quality and content of the conversational text. Also, when a user inputs "business email," user feedback on the conversational text generated by the generation AI can be collected and used to improve the generation algorithm. For example, the user evaluates the appropriateness and effectiveness of the conversational text. Also, when a user inputs "conversation with a friend," user feedback on the conversational text generated by the generation AI can be collected and used to improve the generation algorithm. For example, the user evaluates the enjoyment and relatability of the conversational text. In this way, user feedback on the generated conversational text can be collected and used to improve the generation algorithm.

[0083] The providing unit can use the emotion estimation function to monitor the user's emotions in real time when providing a conversation sentence, and provide the conversation sentence at an appropriate timing. For example, when the user inputs "travel," the emotion estimation function monitors the user's emotions in real time and provides the conversation sentence at an appropriate timing. For example, a topic about travel is provided when the user is relaxed. Also, when the user inputs "business email," the emotion estimation function can monitor the user's emotions in real time and provide the conversation sentence at an appropriate timing. For example, the content of the business email is provided when the user is concentrating. Also, when the user inputs "conversation with friends," the emotion estimation function can monitor the user's emotions in real time and provide the conversation sentence at an appropriate timing. For example, a topic about conversation with friends is provided when the user is relaxed. In this way, the user's emotions can be monitored in real time when providing a conversation sentence, and the conversation sentence can be provided at an appropriate timing.

[0084] Furthermore, the conversation generation system develops specialized modules for generating conversations specialized for specific industries or applications. For example, the conversation generation system utilizes generative AI to develop specialized modules for generating conversations specialized for the medical industry. For example, it generates conversations used between doctors and patients. Furthermore, generative AI can be used to develop specialized modules for generating conversations specialized for the education industry. For example, it generates conversations used between teachers and students. Furthermore, generative AI can be used to develop specialized modules for generating conversations specialized for customer support. For example, it generates conversations used between customers and support staff. This makes it possible to develop specialized modules for generating conversations specialized for specific industries or applications.

[0085] Furthermore, the conversation generation system generates educational content using generative AI or supports communication with patients in the medical field. The conversation generation system generates educational content using generative AI, for example. For example, it generates explanatory text and example questions that are easy for students to understand. In addition, generative AI can be used to support communication with patients in the medical field. For example, it generates conversations that explain diagnosis results and treatment plans in a way that is easy for patients to understand. In addition, generative AI can be used to generate content for corporate training. For example, it generates training manuals and scenarios that are easy for employees to learn. This makes it possible to generate educational content using generative AI or support communication with patients in the medical field.

[0086] Furthermore, the conversation generation system uses an emotion estimation function to generate conversation that takes into account the user's emotions in specific application examples. For example, the conversation generation system uses a generative AI to utilize the emotion estimation function when generating educational content to generate conversation that takes into account the student's emotions. For example, it generates explanatory text in a positive tone to make it easier for students to interest. The generative AI can also be used to utilize the emotion estimation function when supporting communication with patients in the medical field to generate conversation that takes into account the patient's emotions. For example, it can generate explanatory text in a gentle tone to make the patient feel at ease. The generative AI can also be used to utilize the emotion estimation function when responding to customer support calls to generate conversation that takes into account the customer's emotions. For example, it can generate responses in a polite tone to make the customer satisfied. In this way, conversation that takes into account the user's emotions can be generated in specific application examples.

[0087] Furthermore, the conversation generation system will expand the conversation generation service utilizing generative AI to different industries (education, medicine, entertainment, etc.), achieving a wide range of applications. For example, the conversation generation system will expand the conversation generation service utilizing generative AI to the education industry to generate conversations used between teachers and students. For example, it will generate lesson explanations and homework instructions. Also, the conversation generation service utilizing generative AI will be expanded to the medical industry to generate conversations used between doctors and patients. For example, it will generate explanations of diagnosis results and treatment plans. Also, the conversation generation service utilizing generative AI will be expanded to the entertainment industry to generate conversations used between characters and users. For example, it will generate lines and stories for characters in games. This will enable the conversation generation service utilizing generative AI to be expanded to different industries, achieving a wide range of applications.

[0088] Furthermore, the conversational text generation system is used to develop an automatic response system or a customer support chatbot using generative AI. For example, the conversational text generation system uses generative AI to develop an automatic response system. For example, it can automate corporate inquiry responses and generate appropriate answers to customer questions. Generative AI can also be used to develop a customer support chatbot. For example, it can automate customer support on an online shopping site and generate appropriate answers to customer questions. Generative AI can also be used to develop an automatic response system for a reservation system. For example, it can generate appropriate answers to inquiries about restaurant or hotel reservations. This makes it possible to develop an automatic response system or a customer support chatbot using generative AI.

[0089] Furthermore, the conversation generation system uses the emotion estimation function to analyze the emotional reactions of users in application examples and utilizes the results to improve services. For example, the conversation generation system utilizes the emotion estimation function when generating educational content using generative AI, analyzing students' emotional reactions and utilizing the results to improve services. For example, providing content that is likely to interest students. Also, when using generative AI to support communication with patients in the medical field, the emotion estimation function can be utilized to analyze patients' emotional reactions and utilize the results to improve services. For example, providing explanations that put patients at ease. Also, when using generative AI to provide customer support, the emotion estimation function can be utilized to analyze customers' emotional reactions and utilize the results to improve services. For example, providing a response that satisfies customers. This allows the analysis of users' emotional reactions in application examples to be utilized to improve services.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The conversation generation system can also automatically search for related news articles and blog posts based on the user's input and incorporate them into the conversation. For example, if a user inputs "travel," the generation AI will search for the latest travel-related news and blog posts and incorporate their contents into the conversation. Similarly, if a user inputs "business email," the generation AI can search for the latest business-related news and blog posts and incorporate their contents into the conversation. Similarly, if a user inputs "conversations with friends," the generation AI can search for the latest trends and topics and incorporate their contents into the conversation. This allows related news articles and blog posts to be automatically searched for based on the user's input and incorporated into the conversation.

[0092] The conversation generation system can also suggest related music and podcasts based on the user's input. For example, if a user inputs "travel," the generation AI can suggest music and podcasts related to travel. If a user inputs "business email," the generation AI can suggest music and podcasts related to business. If a user inputs "conversation with friends," the generation AI can suggest music and podcasts related to conversations with friends. This allows the system to suggest related music and podcasts based on the user's input.

[0093] The conversation generation system can also suggest related events and activities based on the user's input. For example, if a user inputs "travel," the generation AI can suggest events and activities at the travel destination. If a user inputs "business email," the generation AI can suggest business-related events and seminars. If a user inputs "conversation with friends," the generation AI can suggest events and activities that can be enjoyed with friends. This allows the system to suggest related events and activities based on the user's input.

[0094] The conversation generation system can also suggest related books and movies based on the user's input. For example, if a user inputs "travel," the generation AI can suggest books and movies related to travel. Also, if a user inputs "business email," the generation AI can suggest books and movies related to business. Also, if a user inputs "conversation with friends," the generation AI can suggest books and movies related to conversations with friends. In this way, it is possible to suggest related books and movies based on the user's input.

[0095] The conversation generation system can also suggest related recipes based on the user's input. For example, if a user inputs "travel," the generation AI can suggest recipes for travel destinations. If a user inputs "business email," the generation AI can suggest recipes suitable for business lunches or dinners. If a user inputs "conversation with friends," the generation AI can suggest recipes that can be enjoyed with friends. This allows the system to suggest related recipes based on the user's input.

[0096] The conversation sentence generation system can further estimate the user's emotions and provide relaxing environmental sounds and music based on the estimated emotions. For example, when a user inputs "travel," the emotion estimation function analyzes the user's emotions and provides relaxing environmental sounds and music. When a user inputs "business email," the emotion estimation function analyzes the user's emotions and provides music that enhances concentration. When a user inputs "conversation with friends," the emotion estimation function analyzes the user's emotions and provides music that creates a fun atmosphere. In this way, the user's emotions can be estimated and relaxing environmental sounds and music can be provided.

[0097] The conversation sentence generation system can further estimate the user's emotions and suggest relaxing aromas and scents based on the estimated emotions. For example, if a user inputs "travel," the emotion estimation function analyzes the user's emotions and suggests relaxing aromas and scents. If a user inputs "business email," the emotion estimation function can analyze the user's emotions and suggest aromas and scents that will improve concentration. If a user inputs "conversation with friends," the emotion estimation function can analyze the user's emotions and suggest aromas and scents that will create a pleasant atmosphere. In this way, the user's emotions can be estimated and relaxing aromas and scents can be suggested.

[0098] The conversation sentence generation system can further estimate the user's emotions and suggest relaxing exercises and stretches based on the estimated emotions. For example, if a user inputs "travel," the emotion estimation function analyzes the user's emotions and suggests relaxing exercises and stretches. If a user inputs "business email," the emotion estimation function can analyze the user's emotions and suggest exercises and stretches that will improve concentration. If a user inputs "conversation with friends," the emotion estimation function can analyze the user's emotions and suggest exercises and stretches that will create a fun atmosphere. In this way, the user's emotions can be estimated and relaxing exercises and stretches can be suggested.

[0099] The conversation sentence generation system can further estimate the user's emotions and provide a guide to meditation or mindfulness that will help them relax based on the estimated emotions. For example, if a user inputs "travel," the emotion estimation function analyzes the user's emotions and provides a guide to meditation or mindfulness that will help them relax. Alternatively, if a user inputs "business email," the emotion estimation function can analyze the user's emotions and provide a guide to meditation or mindfulness that will help them concentrate. Alternatively, if a user inputs "conversation with friends," the emotion estimation function can analyze the user's emotions and provide a guide to meditation or mindfulness that will create a fun atmosphere. In this way, the user's emotions can be estimated and a guide to meditation or mindfulness that will help them relax can be provided.

[0100] The conversation sentence generation system can further infer the user's emotions and suggest relaxing arts and crafts activities based on the inferred emotions. For example, if a user inputs "travel," the emotion inference function analyzes the user's emotions and suggests relaxing arts and crafts activities. Alternatively, if a user inputs "business email," the emotion inference function can analyze the user's emotions and suggest arts and crafts activities that improve concentration. Alternatively, if a user inputs "conversation with friends," the emotion inference function can analyze the user's emotions and suggest arts and crafts activities that create a fun atmosphere. In this way, the user's emotions can be inferred and relaxing arts and crafts activities can be suggested.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The keyword and setting input unit accepts keywords and settings from the user. For example, the user can input keywords and settings such as "travel," "conversation with friends," and "casual tone." The keyword and setting input unit can also support input formats such as text, numeric, and multiple-choice options. Step 2: The analysis unit analyzes the keywords and settings received by the keyword and setting input unit. For example, the generation AI uses natural language processing technology to analyze the keywords and settings and understand their content. The analysis unit can also analyze the keywords and settings using machine learning algorithms. Step 3: The generator generates conversational text based on the keywords and settings analyzed by the analyzer. For example, the generator generates conversational text using a text generation AI (e.g., LLM). The generator can also generate conversational text using a multimodal generation AI. The generator can also generate conversational text taking into account the tone and style of the dialogue. Step 4: The providing unit provides the conversation sentence generated by the generating unit to the user. For example, the providing unit provides the conversation sentence by a method such as a screen display, an audio output, or a notification. The providing unit can also provide the generated conversation sentence in a text format or an audio format.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 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.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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 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.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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]

[0170] 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 keyword and setting input unit that accepts keywords and settings from a user; an analysis unit that analyzes the keywords and settings received by the keyword and setting input unit; a generation unit that generates conversation sentences based on the keywords and settings analyzed by the analysis unit; a providing unit that provides the conversation sentence generated by the generating unit to a user. A system characterized by:

2. The keyword and setting input unit Provide related suggested keywords to assist the user in typing 2. The system of claim 1.

3. The keyword and setting input unit Suggests optimal keywords or settings based on past input history or trend data 2. The system of claim 1.

4. The keyword and setting input unit Analyzes user sentiment as they type and suggests keywords or settings to elicit positive emotions 2. The system of claim 1.

5. The keyword and setting input unit Supports voice input or gesture input for improved user convenience 2. The system of claim 1.

Images