System

Abstract

An object of a system according to an embodiment is to confirm whether a word or phrase input by a user is natural and to propose an optimal expression.SOLUTION: A system includes a language input part, a context analysis part, and an expression proposal part. The word input unit receives a word or phrase input by a user. The context analyzer analyzes the context of the word or phrase received by the word input unit. The expression proposing section proposes an optimum expression based on the context analyzed by the context analyzing section.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 had the problem that it is difficult to check whether the words and phrases entered by the user are natural, and it takes time to select appropriate expressions.

[0005] The system according to the embodiment aims to check whether the words and phrases entered by the user are natural and to suggest the most appropriate expressions. [Means for solving the problem]

[0006] The system according to the embodiment includes a word input unit, a context analysis unit, and an expression suggestion unit. The word input unit receives words or phrases input by a user. The context analysis unit analyzes the context of the words or phrases received by the word input unit. The expression suggestion unit suggests an optimal expression based on the context analyzed by the context analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can check whether the words and phrases entered by the user are natural and suggest the most appropriate expressions. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The natural expression checking system according to the embodiment of the present invention is a system that analyzes the context of words and phrases entered by a user and proposes the most appropriate expression. As a result, the natural expression checking system can analyze the context of words and phrases entered by a user and propose the most appropriate expression.

[0029] A natural expression verification system according to an embodiment includes a word input unit, a context analysis unit, and an expression suggestion unit. The word input unit receives words and phrases input by a user. For example, the user inputs using a keyboard. The word input unit can also receive voice input. For example, voice input is performed using a microphone. The word input unit can also receive handwritten input. For example, handwritten characters are input using a tablet and a stylus pen. The context analysis unit analyzes the context of the words and phrases received by the word input unit. For example, the generation AI analyzes the context using a text generation AI (e.g., LLM). The generation AI can also analyze the context using a multimodal generation AI. The generation AI can also analyze the context based on surrounding sentences and related topics. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, in addition to text. The generation AI uses a context analysis algorithm to perform a detailed analysis of the context of words and phrases. The expression suggestion unit suggests the optimal expression based on the context analyzed by the context analysis unit. For example, the generation AI suggests the optimal expression based on the analysis results. The generation AI can also refer to the user's past input history and perform analysis to maintain context consistency. The generation AI can also use an emotion estimation function to analyze the user's emotion at the time of input and suggest the most appropriate expression for that emotion. For example, the generation AI can analyze that the user's emotion is curiosity and suggest the optimal expression based on that. As a result, the natural expression confirmation system according to the embodiment can analyze the context of words and phrases entered by the user and suggest the optimal expression.

[0030] The context analysis unit can refer to the user's past input history and perform analysis to maintain contextual consistency. For example, the context analysis unit refers to the user's past input history of "Tell me what he said," and the generation AI suggests "said" to maintain contextual consistency. For example, analysis is performed based on the past input history. The context analysis unit can also refer to the user's past input history of "Tell me what he said," and the generation AI suggests "said" to maintain contextual consistency. For example, analysis is performed based on the past context. The context analysis unit can also refer to the user's past input history of "Tell me what he said," and the generation AI suggests "said" to maintain contextual consistency. For example, analysis is performed based on the user's past intention. This makes it possible to perform analysis to maintain contextual consistency.

[0031] The word input unit can accept at least one input method of voice input or handwriting input. For example, if a user inputs "Tell me what he said" by voice, the generation AI analyzes the voice and suggests that "said" is the most appropriate expression. For example, voice recognition technology is used. Also, if a user inputs "Tell me what he said" by hand, the word input unit analyzes the handwritten characters and suggests that "said" is the most appropriate expression. For example, handwriting recognition technology is used. Also, if a user inputs "Tell me what he said" by voice, the generation AI analyzes the voice and suggests that "said" is the most appropriate expression. For example, improving the accuracy of voice input. This allows words to be accepted using a variety of input methods.

[0032] The context analysis unit performs context analysis specialized for different industries and fields of expertise, optimizing terminology and industry-specific expressions. For example, if the context analysis unit is input as "Tell me what he said" in the medical field, the generative AI will analyze medical terminology and suggest that "said" is the most appropriate expression. For example, it learns medical terminology. Also, if the context analysis unit is input as "Tell me what he said" in the legal field, the generative AI will analyze legal terminology and suggest that "said" is the most appropriate expression. For example, it learns legal terminology. Also, if the context analysis unit is input as "Tell me what he said" in the technical field, the generative AI will analyze technical terminology and suggest that "said" is the most appropriate expression. For example, it learns technical terminology. This enables context analysis specialized for different industries and fields of expertise.

[0033] The generative AI can reflect feedback provided by the user in its learning. For example, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI adds a function that allows the user to provide feedback on the suggestion. For example, the generative AI reflects the feedback in its learning. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI adds a function that allows the user to provide feedback on the suggestion. For example, the generative AI improves the suggestion based on the feedback. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI adds a function that allows the user to provide feedback on the suggestion. For example, the generative AI updates the learning model based on the feedback. This allows the user's feedback to be reflected in the learning.

[0034] The generation AI can analyze the reason why the user selected an expression and reflect it in future suggestions. For example, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI can analyze the reason why the user selected that expression and reflect it in future suggestions. For example, it can learn the reason for the selection. Also, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI can analyze the reason why the user selected that expression and reflect it in future suggestions. For example, it can improve the suggestions based on the reason for the selection. Also, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI can analyze the reason why the user selected that expression and reflect it in future suggestions. For example, it can update the learning model based on the reason for the selection. This allows it to analyze the reason why the user selected an expression and reflect it in future suggestions.

[0035] The generative AI can provide expressions in different styles or tones. For example, if a user inputs "Tell me what he said," the generative AI will suggest "said" in a formal style. For example, it might suggest "Tell me what he said." Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" in a casual style. For example, it might suggest "Tell me what he said." Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" in a different tone. For example, it might suggest "Tell me what he said." This allows the generative AI to provide expressions in different styles or tones.

[0036] The generative AI can customize expressions according to the user's preferences. For example, if a user inputs "Tell me what he said," the generative AI will suggest "said" and add a function that allows the user to customize the expression. For example, the user can choose their preferred expression. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and add a function that allows the user to customize the expression. For example, the user can choose the style and tone. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and add a function that allows the user to customize the expression. For example, the user can choose their preferred words. This makes it possible to customize expressions according to the user's preferences.

[0037] When supporting multiple languages, generative AI can perform analysis that takes into account the cultural background and nuances of each language. For example, when translating the Japanese phrase "Tell me what he said" into French, generative AI will consider the cultural background and suggest "Qu'est-ce qu'il a dit?", taking into account French honorific expressions. Similarly, when translating the English phrase "He told me what he said" into German, generative AI will consider the cultural background and suggest "Er hat mir gesagt, was er gesagt hat," taking into account the grammatical structure of German. Similarly, when translating the Chinese phrase "He ?le ??" into Spanish, generative AI will consider the cultural background and suggest "?Que dijo el?", taking into account the nuances of Spanish. This enables analysis that takes into account the cultural background and nuances of each language.

[0038] When supporting multiple languages, the generative AI can analyze the slang and colloquialisms of each language and suggest appropriate expressions. For example, when translating the English phrase "He told me what he said" into Japanese, the generative AI will take the slang into consideration and suggest "Tell me what he said." For example, it will appropriately convert English slang into Japanese. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit?" into English, the generative AI will take the slang into consideration and suggest "What did he say?" For example, it will appropriately convert French slang into English. Similarly, when translating the Spanish phrase "?Que dijo el?" into German, the generative AI will take the slang into consideration and suggest "Was hat er gesagt?" For example, it will appropriately convert Spanish slang into German. This makes it possible to analyze the slang and colloquialisms of each language and suggest appropriate expressions.

[0039] When supporting multiple languages, the generative AI can analyze regional expressions and dialects of each language and suggest the most appropriate expression. For example, when translating the English phrase "He told me what he said" into Japanese, the generative AI will consider regional expressions and suggest "Tell me what he said." For example, it will take into account Kansai dialect. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit?" into English, the generative AI will consider regional expressions and suggest "What did he say?" For example, it will take into account the differences between American English and British English. Similarly, when translating the Spanish phrase "?Que dijo el?" into German, the generative AI will consider regional expressions and suggest "Was hat er gesagt?" For example, it will take into account German dialects. This allows the generative AI to analyze regional expressions and dialects of each language and suggest the most appropriate expression.

[0040] When supporting multiple languages, the generative AI can add a learning function to improve translation accuracy. For example, when translating the Japanese phrase "Tell me what he said" into English, the generative AI adds a learning function to improve translation accuracy. For example, it learns from past translation data. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit ?" into English, the generative AI adds a learning function to improve translation accuracy. For example, it learns the grammatical structures of French and English. Similarly, when translating the Spanish phrase "?Que dijo el?" into German, the generative AI adds a learning function to improve translation accuracy. For example, it learns the nuances of Spanish and German. This allows the addition of learning functions to improve translation accuracy between different languages.

[0041] The generation AI can learn the user's input history, analyze the user's individual expression style and preferences, and suggest the most appropriate expression. For example, if a user frequently inputs "Tell me what he said," the generation AI will learn that expression style and suggest "said." For example, by analyzing the user's preferences. Also, if a user frequently inputs "Tell me what he said," the generation AI will learn that expression style and suggest "said." For example, by analyzing the user's expression patterns. Also, if a user frequently inputs "Tell me what he said," the generation AI will learn that expression style and suggest "said." For example, by analyzing the user's writing style. This allows the generation AI to suggest the most appropriate expression based on the user's individual expression style and preferences.

[0042] The generative AI can reflect user feedback in real time and improve the accuracy of its suggestions. For example, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI can reflect the user's feedback in real time and improve the accuracy of its suggestions. For example, the feedback can be reflected in learning. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI can reflect the user's feedback in real time and improve the accuracy of its suggestions. For example, the suggestions can be improved based on the feedback. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI can reflect the user's feedback in real time and improve the accuracy of its suggestions. For example, the learning model can be updated based on the feedback. This allows the generative AI to reflect user feedback in real time and improve the accuracy of its suggestions.

[0043] Generative AI can analyze common expression patterns among different users and suggest optimal expressions. For example, generative AI can analyze the input history of multiple users, find common expression patterns, and suggest "said" when the user types "tell me what he said." For example, it learns common patterns. Generative AI can also analyze the input history of multiple users, find common expression patterns, and suggest "said" when the user types "tell me what he said." For example, it learns common intentions. Generative AI can also analyze the input history of multiple users, find common expression patterns, and suggest "said" when the user types "tell me what he said." For example, it learns common contexts. This allows generative AI to analyze common expression patterns among different users and suggest optimal expressions.

[0044] Generative AI can learn data from different industries and specialties and optimize terminology and industry-specific expressions. For example, if a generative AI learns data from the medical field and inputs "Tell me what he said," it will take medical terminology into consideration and suggest "said." For example, it learns medical terminology. Also, if a generative AI learns data from the legal field and inputs "Tell me what he said," it will take legal terminology into consideration and suggest "said." For example, it learns legal terminology. Also, if a generative AI learns data from the technical field and inputs "Tell me what he said," it will take technical terminology into consideration and suggest "said." For example, it learns technical terminology. This makes it possible to learn data from different industries and specialties and optimize terminology and industry-specific expressions.

[0045] Generative AI can visually display the reasons and evidence for an expression. For example, if a user inputs "Tell me what he said," the generative AI will suggest "said" and visually display the reasons and evidence. For example, it can display the results of context analysis in a graph. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and visually display the reasons and evidence. For example, it can display the results of sentiment analysis in a chart. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and visually display the reasons and evidence. For example, it can display the analysis results based on past input history in a diagram. This makes it possible to visually display the reasons and evidence for the suggested expression.

[0046] The generation AI can interactively display expression options, allowing the user to easily select. For example, if a user inputs "Tell me what he said," the generation AI can interactively display multiple options including "said," allowing the user to easily select. For example, by using a drop-down menu. Alternatively, if a user inputs "Tell me what he said," the generation AI can interactively display multiple options including "said," allowing the user to easily select. For example, by displaying them in the form of buttons. Alternatively, if a user inputs "Tell me what he said," the generation AI can interactively display multiple options including "said," allowing the user to easily select. For example, by displaying them in the form of a slider. In this way, the expression options can be interactively displayed, allowing the user to easily select.

[0047] The generative AI can provide expressions by voice. For example, when a user inputs "Tell me what he said," the generative AI adds a function to suggest "said" and provide that expression by voice. For example, it uses voice synthesis technology. Also, when a user inputs "Tell me what he said," the generative AI adds a function to suggest "said" and provide that expression by voice. For example, it uses a voice output device. Also, when a user inputs "Tell me what he said," the generative AI adds a function to suggest "said" and provide that expression by voice. For example, it provides voice feedback in real time. This allows the suggested expressions to be provided by voice.

[0048] The generative AI can display expressions as visual notes or mind maps. For example, if a user types "Tell me what he said," the generative AI will suggest "said" and add a function to display that expression as a visual note. For example, it can indicate important points with diagrams or icons. Furthermore, if a user types "Tell me what he said," the generative AI will suggest "said" and add a function to display that expression as a mind map. For example, it can visually organize related keywords and concepts. Furthermore, if a user types "Tell me what he said," the generative AI will suggest "said" and add a function to display that expression as a visual note or mind map. For example, it can visualize a summary sentence with drag and drop. This allows the suggested expression to be displayed as a visual note or mind map.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The natural expression verification system can automatically search for relevant news articles and academic papers based on the user's input and provide them to the user. For example, if a user types, "Tell me what he said," the system can search for relevant news articles and provide links to those articles. If a user types, "Tell me about new technologies," the system can search for relevant academic papers and provide summaries of those papers. Furthermore, if a user types, "I want to know about the latest trends," the system can search for relevant blog articles and social media posts and provide their contents. This allows users to quickly obtain information related to their input.

[0051] The natural expression verification system can automatically search for and provide related images and videos based on the user's input. For example, if a user types, "Tell me what he said," the system can search for related images and videos and provide links to them. If a user types, "Tell me about new technology," the system can search for demonstration videos of related technology and provide links to them. Furthermore, if a user types, "I want to know about the latest trends," the system can search for related fashion and lifestyle images and provide their content. This allows users to quickly obtain visual information related to their input.

[0052] The natural expression verification system can automatically search for and provide related music and podcasts based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for related podcast episodes and provide links to them. Alternatively, if a user inputs "Tell me about new technology," the system can search for podcasts about related technology and provide links to them. Furthermore, if a user inputs "Tell me some relaxing music," the system can search for and provide related music playlists. This allows users to quickly obtain audio content related to their input.

[0053] The natural expression verification system can automatically search for related events and seminars based on the user's input and provide them to the user. For example, if a user inputs "Tell me what he said," the system can search for related events and seminars and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technical seminars and workshops and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion shows and exhibitions and provide their contents. This allows users to quickly obtain event information related to their input.

[0054] The natural expression verification system can automatically search for related books and e-books based on the user's input and provide them to the user. For example, if the user inputs "Tell me what he said," the system can search for related books and provide links to them. If the user inputs "Tell me about new technology," the system can search for related technical books and provide links to them. Furthermore, if the user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle books and provide their contents. This allows the user to quickly obtain book information related to the input content.

[0055] The natural expression verification system can automatically search for and provide relevant online courses and tutorials based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for relevant online courses and provide links to them. Alternatively, if a user inputs "Tell me about new technology," the system can search for relevant technology tutorials and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for relevant online courses on fashion and lifestyle and provide their content. This allows users to quickly obtain learning resources related to their input.

[0056] The natural expression verification system can automatically search for and provide related products and services based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for related products and services and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technology products and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle products and provide their content. This allows users to quickly obtain product information related to their input.

[0057] The natural expression verification system can automatically search for related communities and forums based on the user's input and provide them to the user. For example, if a user inputs "Tell me what he said," the system can search for related online forums and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technology communities and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle communities and provide their content. This allows users to quickly obtain community information related to their input.

[0058] The natural expression verification system can automatically search for and provide related applications and tools based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for related applications and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technology tools and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle applications and provide their content. This allows users to quickly obtain application information related to their input.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The word input unit receives words or phrases entered by the user. For example, the user inputs using a keyboard. The word input unit can also receive voice input. For example, voice input is performed using a microphone. The word input unit can also receive handwritten input. For example, handwritten characters are input using a tablet and a stylus pen. Step 2: The context analysis unit analyzes the context of the words and phrases received by the word input unit. For example, the generation AI analyzes the context using a text generation AI (e.g., LLM). The generation AI can also analyze the context using a multimodal generation AI. The generation AI can also analyze the context based on the surrounding sentences and related topics. For example, the text generation AI has learned from large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses a context analysis algorithm to perform a detailed analysis of the context of words and phrases. Step 3: The expression suggestion unit suggests the optimal expression based on the context analyzed by the context analysis unit. For example, the generation AI suggests the optimal expression based on the analysis results. The generation AI can also refer to the user's past input history and perform analysis to maintain context consistency. The generation AI can also use an emotion estimation function to analyze the user's emotions at the time of input and suggest the most appropriate expression for that emotion. For example, the generation AI can analyze that the user's emotion is curiosity and suggest the optimal expression based on that.

[0061] (Example 2) The natural expression checking system according to the embodiment of the present invention is a system that analyzes the context of words and phrases entered by a user and proposes the most appropriate expression. As a result, the natural expression checking system can analyze the context of words and phrases entered by a user and propose the most appropriate expression.

[0062] A natural expression verification system according to an embodiment includes a word input unit, a context analysis unit, and an expression suggestion unit. The word input unit receives words and phrases input by a user. For example, the user inputs using a keyboard. The word input unit can also receive voice input. For example, voice input is performed using a microphone. The word input unit can also receive handwritten input. For example, handwritten characters are input using a tablet and a stylus pen. The context analysis unit analyzes the context of the words and phrases received by the word input unit. For example, the generation AI analyzes the context using a text generation AI (e.g., LLM). The generation AI can also analyze the context using a multimodal generation AI. The generation AI can also analyze the context based on surrounding sentences and related topics. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, in addition to text. The generation AI uses a context analysis algorithm to perform a detailed analysis of the context of words and phrases. The expression suggestion unit suggests the optimal expression based on the context analyzed by the context analysis unit. For example, the generation AI suggests the optimal expression based on the analysis results. The generation AI can also refer to the user's past input history and perform analysis to maintain context consistency. The generation AI can also use an emotion estimation function to analyze the user's emotion at the time of input and suggest the most appropriate expression for that emotion. For example, the generation AI can analyze that the user's emotion is curiosity and suggest the optimal expression based on that. As a result, the natural expression confirmation system according to the embodiment can analyze the context of words and phrases entered by the user and suggest the optimal expression.

[0063] The context analysis unit can refer to the user's past input history and perform analysis to maintain contextual consistency. For example, the context analysis unit refers to the user's past input history of "Tell me what he said," and the generation AI suggests "said" to maintain contextual consistency. For example, analysis is performed based on the past input history. The context analysis unit can also refer to the user's past input history of "Tell me what he said," and the generation AI suggests "said" to maintain contextual consistency. For example, analysis is performed based on the past context. The context analysis unit can also refer to the user's past input history of "Tell me what he said," and the generation AI suggests "said" to maintain contextual consistency. For example, analysis is performed based on the user's past intention. This makes it possible to perform analysis to maintain contextual consistency.

[0064] The context analysis unit uses the emotion estimation function to analyze the emotion a user is expressing when inputting a message and suggests the most appropriate expression for that emotion. For example, the context analysis unit analyzes the emotion when a user inputs "Tell me what he said," and the generation AI suggests that "said" is the most appropriate expression. For example, it analyzes that the user's emotion is curiosity. The context analysis unit also analyzes the emotion when a user inputs "Tell me what he said," and the generation AI suggests that "said" is the most appropriate expression. For example, it analyzes that the user's emotion is interest. The context analysis unit also analyzes the emotion when a user inputs "Tell me what he said," and the generation AI suggests that "said" is the most appropriate expression. For example, it analyzes that the user's emotion is doubt. This makes it possible to suggest the most appropriate expression based on the user's emotion.

[0065] The word input unit can accept at least one input method of voice input or handwriting input. For example, if a user inputs "Tell me what he said" by voice, the generation AI analyzes the voice and suggests that "said" is the most appropriate expression. For example, voice recognition technology is used. Also, if a user inputs "Tell me what he said" by hand, the word input unit analyzes the handwritten characters and suggests that "said" is the most appropriate expression. For example, handwriting recognition technology is used. Also, if a user inputs "Tell me what he said" by voice, the generation AI analyzes the voice and suggests that "said" is the most appropriate expression. For example, improving the accuracy of voice input. This allows words to be accepted using a variety of input methods.

[0066] The context analysis unit performs context analysis specialized for different industries and fields of expertise, optimizing terminology and industry-specific expressions. For example, if the context analysis unit is input as "Tell me what he said" in the medical field, the generative AI will analyze medical terminology and suggest that "said" is the most appropriate expression. For example, it learns medical terminology. Also, if the context analysis unit is input as "Tell me what he said" in the legal field, the generative AI will analyze legal terminology and suggest that "said" is the most appropriate expression. For example, it learns legal terminology. Also, if the context analysis unit is input as "Tell me what he said" in the technical field, the generative AI will analyze technical terminology and suggest that "said" is the most appropriate expression. For example, it learns technical terminology. This enables context analysis specialized for different industries and fields of expertise.

[0067] The context analysis unit uses the emotion estimation function to analyze other users' emotional reactions to words and phrases entered by the user and suggest the most appropriate expression. For example, if a user enters "Tell me what he said," the context analysis unit allows the generation AI to analyze other users' emotional reactions and suggest that "said" is the most appropriate expression. For example, it selects an expression with a high number of positive reactions. Also, if a user enters "Tell me what he said," the context analysis unit allows the generation AI to analyze other users' emotional reactions and suggest that "said" is the most appropriate expression. For example, it selects an expression with a low number of negative reactions. Also, if a user enters "Tell me what he said," the context analysis unit allows the generation AI to analyze other users' emotional reactions and suggest that "said" is the most appropriate expression. For example, it selects an expression with a high emotion score. This allows the generation AI to suggest the most appropriate expression based on the emotional reactions of other users.

[0068] The generative AI can reflect feedback provided by the user in its learning. For example, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI adds a function that allows the user to provide feedback on the suggestion. For example, the generative AI reflects the feedback in its learning. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI adds a function that allows the user to provide feedback on the suggestion. For example, the generative AI improves the suggestion based on the feedback. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI adds a function that allows the user to provide feedback on the suggestion. For example, the generative AI updates the learning model based on the feedback. This allows the user's feedback to be reflected in the learning.

[0069] The generation AI can analyze the reason why the user selected an expression and reflect it in future suggestions. For example, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI can analyze the reason why the user selected that expression and reflect it in future suggestions. For example, it can learn the reason for the selection. Also, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI can analyze the reason why the user selected that expression and reflect it in future suggestions. For example, it can improve the suggestions based on the reason for the selection. Also, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI can analyze the reason why the user selected that expression and reflect it in future suggestions. For example, it can update the learning model based on the reason for the selection. This allows it to analyze the reason why the user selected an expression and reflect it in future suggestions.

[0070] The generation AI can analyze the impact on the user's emotions and select the optimal expression. For example, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI analyzes the impact of the suggestion on the user's emotions and selects the optimal expression. For example, it selects based on the emotion score. Also, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI analyzes the impact of the suggestion on the user's emotions and selects the optimal expression. For example, it selects an expression that has a positive impact. Also, if a user inputs "Tell me what he said" and the generation AI suggests "said," the generation AI analyzes the impact of the suggestion on the user's emotions and selects the optimal expression. For example, it selects an expression that avoids a negative impact. This makes it possible to select the optimal expression based on the user's emotions.

[0071] The generative AI can provide expressions in different styles or tones. For example, if a user inputs "Tell me what he said," the generative AI will suggest "said" in a formal style. For example, it might suggest "Tell me what he said." Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" in a casual style. For example, it might suggest "Tell me what he said." Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" in a different tone. For example, it might suggest "Tell me what he said." This allows the generative AI to provide expressions in different styles or tones.

[0072] The generative AI can customize expressions according to the user's preferences. For example, if a user inputs "Tell me what he said," the generative AI will suggest "said" and add a function that allows the user to customize the expression. For example, the user can choose their preferred expression. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and add a function that allows the user to customize the expression. For example, the user can choose the style and tone. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and add a function that allows the user to customize the expression. For example, the user can choose their preferred words. This makes it possible to customize expressions according to the user's preferences.

[0073] The generation AI can collect the emotional reactions of other users and suggest the most appropriate expression based on that data. For example, if a user inputs "Tell me what he said," the generation AI will suggest "said" and collect the emotional reactions of other users to suggest the most appropriate expression. For example, it will select an expression with a high number of positive reactions. Also, if a user inputs "Tell me what he said," the generation AI will suggest "said" and collect the emotional reactions of other users to suggest the most appropriate expression. For example, it will select an expression with a low number of negative reactions. Also, if a user inputs "Tell me what he said," the generation AI will suggest "said" and collect the emotional reactions of other users to suggest the most appropriate expression. For example, it will select an expression with a high emotional score. This makes it possible to suggest the most appropriate expression based on the emotional reactions of other users.

[0074] When supporting multiple languages, generative AI can perform analysis that takes into account the cultural background and nuances of each language. For example, when translating the Japanese phrase "Tell me what he said" into French, generative AI will consider the cultural background and suggest "Qu'est-ce qu'il a dit?", taking into account French honorific expressions. Similarly, when translating the English phrase "He told me what he said" into German, generative AI will consider the cultural background and suggest "Er hat mir gesagt, was er gesagt hat," taking into account the grammatical structure of German. Similarly, when translating the Chinese phrase "He ?le ??" into Spanish, generative AI will consider the cultural background and suggest "?Que dijo el?", taking into account the nuances of Spanish. This enables analysis that takes into account the cultural background and nuances of each language.

[0075] When supporting multiple languages, the generative AI can analyze the slang and colloquialisms of each language and suggest appropriate expressions. For example, when translating the English phrase "He told me what he said" into Japanese, the generative AI will take the slang into consideration and suggest "Tell me what he said." For example, it will appropriately convert English slang into Japanese. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit?" into English, the generative AI will take the slang into consideration and suggest "What did he say?" For example, it will appropriately convert French slang into English. Similarly, when translating the Spanish phrase "?Que dijo el?" into German, the generative AI will take the slang into consideration and suggest "Was hat er gesagt?" For example, it will appropriately convert Spanish slang into German. This makes it possible to analyze the slang and colloquialisms of each language and suggest appropriate expressions.

[0076] When supporting multiple languages, the generative AI can use its emotion estimation function to analyze differences in emotions between different languages ​​and suggest the most appropriate expression. For example, when translating the Japanese phrase "Tell me what he said" into English, the generative AI analyzes the difference in emotions and suggests "What did he say?", appropriately converting Japanese emotions into English. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit ?" into German, the generative AI analyzes the difference in emotions and suggests "Was hat er gesagt?", appropriately converting French emotions into German. Similarly, when translating the Spanish phrase "?Que dijo el?" into Chinese, the generative AI analyzes the difference in emotions and suggests "He ?le ??", appropriately converting Spanish emotions into Chinese. This makes it possible to analyze differences in emotions between different languages ​​and suggest the most appropriate expression.

[0077] When supporting multiple languages, the generative AI can analyze regional expressions and dialects of each language and suggest the most appropriate expression. For example, when translating the English phrase "He told me what he said" into Japanese, the generative AI will consider regional expressions and suggest "Tell me what he said." For example, it will take into account Kansai dialect. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit?" into English, the generative AI will consider regional expressions and suggest "What did he say?" For example, it will take into account the differences between American English and British English. Similarly, when translating the Spanish phrase "?Que dijo el?" into German, the generative AI will consider regional expressions and suggest "Was hat er gesagt?" For example, it will take into account German dialects. This allows the generative AI to analyze regional expressions and dialects of each language and suggest the most appropriate expression.

[0078] When supporting multiple languages, the generative AI can add a learning function to improve translation accuracy. For example, when translating the Japanese phrase "Tell me what he said" into English, the generative AI adds a learning function to improve translation accuracy. For example, it learns from past translation data. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit ?" into English, the generative AI adds a learning function to improve translation accuracy. For example, it learns the grammatical structures of French and English. Similarly, when translating the Spanish phrase "?Que dijo el?" into German, the generative AI adds a learning function to improve translation accuracy. For example, it learns the nuances of Spanish and German. This allows the addition of learning functions to improve translation accuracy between different languages.

[0079] When supporting multiple languages, the generative AI can use its emotion estimation function to compare emotional responses across different languages ​​and suggest the most appropriate expression. For example, when translating the Japanese phrase "Tell me what he said" into English, the generative AI compares emotional responses and suggests "What did he say?" For example, it compares the emotional responses between Japanese and English. Similarly, when translating the French phrase "Qu'est-ce qu'il a dit ?" into German, the generative AI compares the emotional responses and suggests "Was hat er gesagt?" For example, it compares the emotional responses between French and German. Similarly, when translating the Spanish phrase "?Que dijo el?" into Chinese, the generative AI compares the emotional responses and suggests "He ?le ??" For example, it compares the emotional responses between Spanish and Chinese. This makes it possible to compare emotional responses across different languages ​​and suggest the most appropriate expression.

[0080] The generation AI can learn the user's input history, analyze the user's individual expression style and preferences, and suggest the most appropriate expression. For example, if a user frequently inputs "Tell me what he said," the generation AI will learn that expression style and suggest "said." For example, by analyzing the user's preferences. Also, if a user frequently inputs "Tell me what he said," the generation AI will learn that expression style and suggest "said." For example, by analyzing the user's expression patterns. Also, if a user frequently inputs "Tell me what he said," the generation AI will learn that expression style and suggest "said." For example, by analyzing the user's writing style. This allows the generation AI to suggest the most appropriate expression based on the user's individual expression style and preferences.

[0081] The generative AI can reflect user feedback in real time and improve the accuracy of its suggestions. For example, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI can reflect the user's feedback in real time and improve the accuracy of its suggestions. For example, the feedback can be reflected in learning. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI can reflect the user's feedback in real time and improve the accuracy of its suggestions. For example, the suggestions can be improved based on the feedback. Also, if a user inputs "Tell me what he said" and the generative AI suggests "said," the generative AI can reflect the user's feedback in real time and improve the accuracy of its suggestions. For example, the learning model can be updated based on the feedback. This allows the generative AI to reflect user feedback in real time and improve the accuracy of its suggestions.

[0082] Generative AI can analyze common expression patterns among different users and suggest optimal expressions. For example, generative AI can analyze the input history of multiple users, find common expression patterns, and suggest "said" when the user types "tell me what he said." For example, it learns common patterns. Generative AI can also analyze the input history of multiple users, find common expression patterns, and suggest "said" when the user types "tell me what he said." For example, it learns common intentions. Generative AI can also analyze the input history of multiple users, find common expression patterns, and suggest "said" when the user types "tell me what he said." For example, it learns common contexts. This allows generative AI to analyze common expression patterns among different users and suggest optimal expressions.

[0083] Generative AI can learn data from different industries and specialties and optimize terminology and industry-specific expressions. For example, if a generative AI learns data from the medical field and inputs "Tell me what he said," it will take medical terminology into consideration and suggest "said." For example, it learns medical terminology. Also, if a generative AI learns data from the legal field and inputs "Tell me what he said," it will take legal terminology into consideration and suggest "said." For example, it learns legal terminology. Also, if a generative AI learns data from the technical field and inputs "Tell me what he said," it will take technical terminology into consideration and suggest "said." For example, it learns technical terminology. This makes it possible to learn data from different industries and specialties and optimize terminology and industry-specific expressions.

[0084] Using its emotion estimation function, the generation AI can learn the user's emotional history and suggest the optimal expression based on that emotion. For example, the generation AI learns the emotional history when the user inputs "Tell me what he said," and the generation AI suggests "said" based on that emotion. For example, it learns that the user's emotion is curiosity. The generation AI also learns the emotional history when the user inputs "Tell me what he said," and the generation AI suggests "said" based on that emotion. For example, it learns that the user's emotion is interest. The generation AI also learns the emotional history when the user inputs "Tell me what he said," and the generation AI suggests "said" based on that emotion. For example, it learns that the user's emotion is doubt. This allows the generation AI to learn the user's emotional history and suggest the optimal expression based on that emotion.

[0085] Generative AI can visually display the reasons and evidence for an expression. For example, if a user inputs "Tell me what he said," the generative AI will suggest "said" and visually display the reasons and evidence. For example, it can display the results of context analysis in a graph. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and visually display the reasons and evidence. For example, it can display the results of sentiment analysis in a chart. Also, if a user inputs "Tell me what he said," the generative AI will suggest "said" and visually display the reasons and evidence. For example, it can display the analysis results based on past input history in a diagram. This makes it possible to visually display the reasons and evidence for the suggested expression.

[0086] The generation AI can interactively display expression options, allowing the user to easily select. For example, if a user inputs "Tell me what he said," the generation AI can interactively display multiple options including "said," allowing the user to easily select. For example, by using a drop-down menu. Alternatively, if a user inputs "Tell me what he said," the generation AI can interactively display multiple options including "said," allowing the user to easily select. For example, by displaying them in the form of buttons. Alternatively, if a user inputs "Tell me what he said," the generation AI can interactively display multiple options including "said," allowing the user to easily select. For example, by displaying them in the form of a slider. In this way, the expression options can be interactively displayed, allowing the user to easily select.

[0087] The emotion estimation function allows the user interface to dynamically change according to the user's emotions. For example, when a user inputs "Tell me what he said," the emotion estimation function analyzes the user's emotions, and the generation AI dynamically changes the interface according to that emotion. For example, if the emotion is positive, the color tone is changed to brighter. The emotion estimation function also analyzes the user's emotions when a user inputs "Tell me what he said," and the generation AI dynamically changes the interface according to that emotion. For example, if the emotion is negative, the color tone is changed to more subdued. The emotion estimation function also analyzes the user's emotions when a user inputs "Tell me what he said," and the generation AI dynamically changes the interface according to that emotion. For example, the layout of the interface is adjusted according to changes in emotion. This allows the user interface to dynamically change according to the user's emotions.

[0088] The generative AI can provide expressions by voice. For example, when a user inputs "Tell me what he said," the generative AI adds a function to suggest "said" and provide that expression by voice. For example, it uses voice synthesis technology. Also, when a user inputs "Tell me what he said," the generative AI adds a function to suggest "said" and provide that expression by voice. For example, it uses a voice output device. Also, when a user inputs "Tell me what he said," the generative AI adds a function to suggest "said" and provide that expression by voice. For example, it provides voice feedback in real time. This allows the suggested expressions to be provided by voice.

[0089] The generative AI can display expressions as visual notes or mind maps. For example, if a user types "Tell me what he said," the generative AI will suggest "said" and add a function to display that expression as a visual note. For example, it can indicate important points with diagrams or icons. Furthermore, if a user types "Tell me what he said," the generative AI will suggest "said" and add a function to display that expression as a mind map. For example, it can visually organize related keywords and concepts. Furthermore, if a user types "Tell me what he said," the generative AI will suggest "said" and add a function to display that expression as a visual note or mind map. For example, it can visualize a summary sentence with drag and drop. This allows the suggested expression to be displayed as a visual note or mind map.

[0090] The emotion estimation function allows the user interface to be customized based on the user's emotions. For example, the emotion estimation function analyzes the emotion expressed when the user inputs "Tell me what he said," and the generation AI customizes the interface based on that emotion. For example, if the emotion is positive, the color tone is changed to brighter. The emotion estimation function also analyzes the emotion expressed when the user inputs "Tell me what he said," and the generation AI customizes the interface based on that emotion. For example, if the emotion is negative, the color tone is changed to more subdued. The emotion estimation function also analyzes the emotion expressed when the user inputs "Tell me what he said," and the generation AI customizes the interface based on that emotion. For example, the layout of the interface is adjusted according to changes in emotion. This allows the user interface to be customized based on the user's emotions.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The natural expression verification system can automatically search for relevant news articles and academic papers based on the user's input and provide them to the user. For example, if a user types, "Tell me what he said," the system can search for relevant news articles and provide links to those articles. If a user types, "Tell me about new technologies," the system can search for relevant academic papers and provide summaries of those papers. Furthermore, if a user types, "I want to know about the latest trends," the system can search for relevant blog articles and social media posts and provide their contents. This allows users to quickly obtain information related to their input.

[0093] The natural expression verification system can automatically search for and provide related images and videos based on the user's input. For example, if a user types, "Tell me what he said," the system can search for related images and videos and provide links to them. If a user types, "Tell me about new technology," the system can search for demonstration videos of related technology and provide links to them. Furthermore, if a user types, "I want to know about the latest trends," the system can search for related fashion and lifestyle images and provide their content. This allows users to quickly obtain visual information related to their input.

[0094] The natural expression verification system can automatically search for and provide related music and podcasts based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for related podcast episodes and provide links to them. Alternatively, if a user inputs "Tell me about new technology," the system can search for podcasts about related technology and provide links to them. Furthermore, if a user inputs "Tell me some relaxing music," the system can search for and provide related music playlists. This allows users to quickly obtain audio content related to their input.

[0095] The natural expression verification system can automatically search for related events and seminars based on the user's input and provide them to the user. For example, if a user inputs "Tell me what he said," the system can search for related events and seminars and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technical seminars and workshops and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion shows and exhibitions and provide their contents. This allows users to quickly obtain event information related to their input.

[0096] The natural expression verification system can automatically search for related books and e-books based on the user's input and provide them to the user. For example, if the user inputs "Tell me what he said," the system can search for related books and provide links to them. If the user inputs "Tell me about new technology," the system can search for related technical books and provide links to them. Furthermore, if the user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle books and provide their contents. This allows the user to quickly obtain book information related to the input content.

[0097] The natural expression verification system can automatically search for and provide relevant online courses and tutorials based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for relevant online courses and provide links to them. Alternatively, if a user inputs "Tell me about new technology," the system can search for relevant technology tutorials and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for relevant online courses on fashion and lifestyle and provide their content. This allows users to quickly obtain learning resources related to their input.

[0098] The natural expression verification system can automatically search for and provide related products and services based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for related products and services and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technology products and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle products and provide their content. This allows users to quickly obtain product information related to their input.

[0099] The natural expression verification system can automatically search for related communities and forums based on the user's input and provide them to the user. For example, if a user inputs "Tell me what he said," the system can search for related online forums and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technology communities and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle communities and provide their content. This allows users to quickly obtain community information related to their input.

[0100] The natural expression verification system can automatically search for and provide related applications and tools based on the user's input. For example, if a user inputs "Tell me what he said," the system can search for related applications and provide links to them. If a user inputs "Tell me about new technology," the system can search for related technology tools and provide links to them. Furthermore, if a user inputs "I want to know about the latest trends," the system can search for related fashion and lifestyle applications and provide their content. This allows users to quickly obtain application information related to their input.

[0101] The natural expression confirmation system can estimate the relevant emotion based on the user's input and suggest the most appropriate expression based on that emotion. For example, if a user inputs "Tell me what he said," the system can estimate the user's emotion and suggest "said" based on that emotion. Also, if a user inputs "Tell me about new technology," the system can estimate the user's emotion and suggest "explain" based on that emotion. Furthermore, if a user inputs "I want to know about the latest trends," the system can estimate the user's emotion and suggest "introduce" based on that emotion. In this way, the system can suggest the most appropriate expression based on the user's emotion.

[0102] The natural expression confirmation system can infer relevant emotions based on the user's input and provide appropriate feedback based on the emotions. For example, if a user inputs "Tell me what he said," the system can infer the user's emotions and provide feedback such as "That's interesting" based on the emotions. If a user inputs "Tell me about new technology," the system can infer the user's emotions and provide feedback such as "That technology is very innovative" based on the emotions. Furthermore, if a user inputs "I want to know about the latest trends," the system can infer the user's emotions and provide feedback such as "That trend is very popular" based on the emotions. This makes it possible to provide appropriate feedback based on the user's emotions.

[0103] The natural expression confirmation system can infer relevant emotions based on the user's input and suggest appropriate actions based on those emotions. For example, if a user inputs "Tell me what he said," the system can infer the user's emotions and suggest "Check details" based on those emotions. Also, if a user inputs "Tell me about new technology," the system can infer the user's emotions and suggest "Try demo" based on those emotions. Furthermore, if a user inputs "I want to know about the latest trends," the system can infer the user's emotions and suggest "Follow" based on those emotions. This makes it possible to suggest appropriate actions based on the user's emotions.

[0104] The natural expression verification system can infer relevant emotions based on the user's input and provide appropriate resources based on those emotions. For example, if a user inputs "Tell me what he said," the system can infer the user's emotions and provide "related articles" based on those emotions. Also, if a user inputs "Tell me about new technologies," the system can infer the user's emotions and provide "technical documents" based on those emotions. Furthermore, if a user inputs "I want to know about the latest trends," the system can infer the user's emotions and provide "trend reports" based on those emotions. This makes it possible to provide appropriate resources based on the user's emotions.

[0105] The natural expression confirmation system can infer relevant emotions based on the user's input and provide appropriate support based on those emotions. For example, if a user inputs "Tell me what he said," the system can infer the user's emotions and suggest "Contact the support team" based on those emotions. Also, if a user inputs "Tell me about new technologies," the system can infer the user's emotions and suggest "Get technical support" based on those emotions. Furthermore, if a user inputs "I want to know about the latest trends," the system can infer the user's emotions and suggest "Consult an expert" based on those emotions. This makes it possible to provide appropriate support based on the user's emotions.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The word input unit receives words or phrases entered by the user. For example, the user inputs using a keyboard. The word input unit can also receive voice input. For example, voice input is performed using a microphone. The word input unit can also receive handwritten input. For example, handwritten characters are input using a tablet and a stylus pen. Step 2: The context analysis unit analyzes the context of the words and phrases received by the word input unit. For example, the generation AI analyzes the context using a text generation AI (e.g., LLM). The generation AI can also analyze the context using a multimodal generation AI. The generation AI can also analyze the context based on the surrounding sentences and related topics. For example, the text generation AI has learned from large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI uses a context analysis algorithm to perform a detailed analysis of the context of words and phrases. Step 3: The expression suggestion unit suggests the optimal expression based on the context analyzed by the context analysis unit. For example, the generation AI suggests the optimal expression based on the analysis results. The generation AI can also refer to the user's past input history and perform analysis to maintain context consistency. The generation AI can also use an emotion estimation function to analyze the user's emotions at the time of input and suggest the most appropriate expression for that emotion. For example, the generation AI can analyze that the user's emotion is curiosity and suggest the optimal expression based on that.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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."

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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]

[0175] 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 word input section for receiving user-entered words or phrases; a context analysis unit that analyzes the context of the words or phrases received by the word input unit; an expression suggestion unit that suggests an optimal expression based on the context analyzed by the context analysis unit; A system characterized by:

2. The context analysis unit Refer to the user's past input history and analyze it to maintain contextual consistency 2. The system of claim 1.

3. The context analysis unit Analyze the user's emotions when they input and suggest expressions that best fit those emotions.

2. The system of claim 1.

4. The word input unit Accept at least one of the following input methods: voice input or handwriting input 2. The system of claim 1.

5. The context analysis unit Conduct contextual analysis specific to the different industries and specialties to optimize terminology and industry-specific expressions 2. The system of claim 1.

6. The context analysis unit Analyzing other users' emotional responses to words or phrases entered by the user and suggesting optimal expressions 2. The system of claim 1.

7. The generating AI is Incorporating the feedback provided by the user into the learning.

2. The system of claim 1.

Images