system

Abstract

The system according to the embodiment aims to automatically suggest corrections and improvements to text entered by a user and provide an optimal expression style. [Solution] The system according to the embodiment comprises an input unit, a suggestion unit, a selection unit, a generation unit, a setting unit, and a modification unit. The input unit is where the user inputs text. The suggestion unit analyzes the text input by the input unit and suggests corrections and improvements. The selection unit selects the corrections and improvements suggested by the suggestion unit. The generation unit generates a completed text that reflects the corrections and improvements selected by the selection unit. The setting unit sets the desired expression style for the user. The modification unit creates expressions based on the expression style set by the setting unit.

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 do not adequately provide systems that automatically suggest corrections and improvements when users input text, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically suggest corrections and improvements to text entered by a user and provide an optimal expression style. [Means for solving the problem]

[0006] The system according to the embodiment comprises an input unit, a suggestion unit, a selection unit, a generation unit, a setting unit, and a modification unit. The input unit is where the user inputs text. The suggestion unit analyzes the text input by the input unit and suggests corrections and improvements. The selection unit selects the corrections and improvements suggested by the suggestion unit. The generation unit generates a completed text that reflects the corrections and improvements selected by the selection unit. The setting unit sets the desired expression style for the user. The modification unit creates expressions based on the expression style set by the setting unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically suggest corrections and improvements to text entered by the user and provide the optimal style of expression. [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 of form 1) The document editing system according to an embodiment of the present invention is a system that automatically edits text entered by a user and suggests corrections and improvements. In this document editing system, the user inputs text, and the AI ​​analyzes the text and suggests corrections and improvements. The user reviews the suggested corrections and improvements and selects the appropriate ones. A final text reflecting the selected corrections and improvements is generated. The user reviews the final text and can make corrections before sending it. In addition, the user can set an ideal expression style and have the AI ​​create appropriate expressions based on that style. The user can change their ideal expression style at any time to broaden the range of self-expression. For example, when the user inputs text, they can input text freely. For example, various types of text can be input, such as the body of an email or part of a report. This information is entered into the input unit. Next, the entered text is sent to the suggestion unit, where the AI ​​analyzes the text. The AI ​​detects grammatical and expression errors and suggests corrections and improvements. For example, grammatical errors and redundant expressions may be pointed out. The user reviews the corrections and improvements suggested by the suggestion unit and selects the appropriate ones in the selection unit. The selected corrections and improvements are sent to the generation unit, where the final text is generated. The generated final text can be reviewed by the user and revised before sending. For example, the user can review the body of the email and make revisions as needed. The user can also set their ideal writing style. Based on the style set in the settings unit, the AI ​​creates appropriate expressions. For example, expressions tailored to the user's preferences, such as formal or casual expressions, are generated. The user can change their ideal writing style at any time. By changing the style in the modification unit, the user can broaden their range of self-expression. For example, they can change from a business email style to a casual message style. This allows the text editing system to automatically edit the text entered by the user, suggest corrections and improvements, and generate the final text.

[0029] A writing correction system according to an embodiment includes an input unit, a suggestion unit, a selection unit, a generation unit, a setting unit, and a change unit. The input unit allows a user to input a sentence. The sentences input by the user include, but are not limited to, business documents, technical documents, and creative writing. The input unit supports various input methods, such as keyboard input, voice input, and handwriting input. The suggestion unit uses AI to analyze the sentences input by the input unit and suggest corrections and improvements. The suggestion unit detects grammatical errors and improvements to expressions using techniques such as grammatical analysis, semantic analysis, and syntax analysis. The suggestion unit, for example, points out grammatical errors and suggests appropriate corrections. The suggestion unit can also point out redundant expressions and suggest concise expressions. The selection unit allows a user to review the corrections and improvements suggested by the suggestion unit and select appropriate corrections and improvements. The selection unit, for example, displays the suggested corrections through a user interface, allowing the user to select them. The selection unit, for example, displays suggested revisions in a list format, allowing the user to click to select one. The selection unit can also use voice input to allow the user to select a suggested revision by voice. The generation unit generates a final sentence that reflects the revisions and improvements selected by the selection unit. The generation unit, for example, applies the selected suggested revisions to the sentence to generate a grammatically correct sentence. After applying the suggested revisions, the generation unit, for example, checks the consistency of the entire sentence and makes additional revisions as necessary. The setting unit sets a desired expression style from the user. The setting unit can set various expression styles, for example, a formal style, a casual style, a professional style, etc. The setting unit, for example, displays options for the expression style through a user interface, allowing the user to select one. The modification unit creates an expression based on the expression style set by the setting unit. The modification unit, for example, selects appropriate vocabulary and writing style based on the set style, and generates a sentence. For example, in the case of a formal style, the modification unit uses polite language and formal expressions. In the case of a casual style, the modification unit uses friendly language and casual expressions.As a result, the writing correction system according to the embodiment can automatically correct writing input by the user, suggest corrections and improvements, and generate the final writing.

[0030] The suggestion unit can detect grammatical and linguistic errors using AI and suggest corrections and improvements. The suggestion unit can detect grammatical errors using, for example, grammatical analysis technology. For example, the suggestion unit detects errors based on grammatical rules such as subject-verb agreement, tense agreement, and article use. The suggestion unit can also detect context-based linguistic errors using semantic analysis technology. For example, the suggestion unit points out the use of words that do not fit the context or expressions with ambiguous meanings. Furthermore, the suggestion unit can also detect structural errors in sentences using syntactic analysis technology. For example, the suggestion unit points out cases where sentence structure is improper or punctuation is improperly used. In this way, the suggestion unit can accurately detect grammatical and linguistic errors and suggest corrections and improvements by using AI. Some or all of the above-described processing in the suggestion unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the proposal unit can input the received text into a generation AI, which can then detect grammatical errors and areas for improvement in expression, and generate revised versions.

[0031] The selection unit allows the user to review the proposed corrections and improvements and select appropriate corrections and improvements. The selection unit, for example, displays the proposed corrections through a user interface and allows the user to select one. For example, the selection unit displays the proposed corrections in a list format and the user clicks to select one. The selection unit also allows the user to select a correction by voice input. For example, the selection unit allows the user to select a correction by voice instruction such as "Select correction proposal 1." The selection unit can also analyze the user's past selection history and propose optimal corrections. For example, the selection unit prioritizes displaying corrections that the user has frequently selected in the past. This allows the selection unit to review the proposed corrections and improvements and select appropriate ones. Some or all of the above-described processing in the selection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the proposed corrections to a generation AI, which then proposes the optimal correction.

[0032] The generation unit can generate a completed sentence that reflects the selected corrections and improvements. The generation unit, for example, applies the selected correction suggestions to the sentence to generate a grammatically correct sentence. For example, after applying the correction suggestions, the generation unit checks the consistency of the entire sentence and makes additional corrections as necessary. The generation unit can also adjust the style and tone of the sentence based on the selected correction suggestions. For example, when applying a formal style correction suggestion, the generation unit unifies the entire sentence in a formal tone. Furthermore, the generation unit can analyze the user's past generation history and suggest an optimal generation method. For example, the generation unit analyzes patterns of sentences generated by the user in the past and automatically generates similar sentences. This allows the generation unit to generate a final sentence that reflects the selected corrections and improvements. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the selected correction suggestions into a generation AI, which then generates a final sentence.

[0033] The setting unit can set a desired expression style for the user. The setting unit can set various expression styles, such as a formal style, a casual style, and a professional style. For example, the setting unit can display expression style options through a user interface and allow the user to select one. The setting unit can also analyze the user's past setting history and suggest an optimal expression style. For example, the setting unit can prioritize and display expression styles that the user has frequently used in the past. Furthermore, the setting unit can suggest an appropriate expression style based on the user's current project or field of interest. For example, the setting unit can prioritize and display expression styles related to the project the user is currently working on. This allows the setting unit to set the user's ideal expression style. Some or all of the above-described processing in the setting unit can be performed using, or without, a generation AI. For example, the setting unit can input a user's input to the generation AI, which can then suggest an optimal expression style.

[0034] The modification unit can create expressions based on the set expression style. For example, the modification unit selects appropriate vocabulary and writing style based on the set style and generates sentences. For example, the modification unit uses polite language and formal expressions in a formal style. For example, the modification unit uses friendly language and casual expressions in a casual style. The modification unit can also analyze the user's past modification history and suggest optimal expressions. For example, the modification unit can prioritize displaying expressions that the user has frequently used in the past. Furthermore, the modification unit can suggest appropriate expressions based on the user's current project or area of ​​interest. For example, the modification unit can prioritize displaying expressions related to the project the user is currently working on. This allows the modification unit to create expressions based on the set style. Some or all of the above-mentioned processing in the modification unit may be performed using, or without, a generation AI. For example, the modification unit can input to the generation AI based on the set style, and the generation AI can generate appropriate expressions.

[0035] The input unit can analyze the user's past input history and suggest an appropriate input method. The input unit, for example, analyzes the user's past input history and suggests the optimal input method. For example, the input unit prioritizes suggesting input methods (such as voice and text) that the user has frequently used in the past. The input unit can also analyze patterns of sentences the user has previously input and automatically complete similar sentences. For example, the input unit predicts and suggests an input method to be used during a specific time period based on the user's past input history. In this way, the optimal input method can be suggested by analyzing the user's past input history. Some or all of the above-described processing in the input unit may be performed using, or without, a generation AI. For example, the input unit can input the user's past input history into a generation AI, which then suggests the optimal input method.

[0036] The input unit can filter the input content based on the user's current projects and areas of interest. For example, the input unit may prioritize displaying keywords related to the project the user is currently working on. For example, the input unit may automatically suggest relevant expressions and phrases based on the user's areas of interest. The input unit can also prioritize displaying information related to a specific theme if the user is interested in that theme. For example, the input unit may filter the input content based on the user's current projects and areas of interest. This allows the input unit to provide highly relevant information by filtering the input content based on the user's current projects and areas of interest. Some or all of the above processing in the input unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the input unit may input data on the user's projects and areas of interest into a generative AI, which can then suggest highly relevant information.

[0037] The input unit can prioritize retrieving highly relevant input content while considering the user's geographical location information. For example, if the user is in a specific region, the input unit will prioritize displaying information related to that region. For example, the input unit will automatically suggest relevant expressions and phrases based on the user's current location. The input unit can also prioritize displaying information related to the user's travel destination if the user is traveling. For example, the input unit will prioritize retrieving highly relevant input content while considering the user's geographical location information. This allows the system to provide highly relevant information based on the user's geographical location information. Some or all of the above processing in the input unit may be performed using, for example, a generative AI, or without a generative AI. For example, the input unit can input the user's geographical location information into a generative AI, which can then suggest highly relevant information.

[0038] The input unit can analyze the user's social media activity at the time of input and acquire relevant input content. The input unit, for example, automatically suggests expressions and phrases frequently used by the user on social media. For example, the input unit can prioritize displaying information related to a topic of interest from the user's social media activity. Furthermore, if the user is participating in a specific event, the input unit can prioritize displaying information related to the event. For example, the input unit can analyze the user's social media activity and acquire relevant input content. This makes it possible to provide relevant information based on the user's social media activity. Some or all of the above-described processing in the input unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the input unit can input the user's social media data to a generation AI, which can then suggest relevant information.

[0039] When making a proposal, the suggestion unit can adjust the level of detail of the proposal based on the importance of the sentence. For example, in the case of an important sentence, the suggestion unit suggests detailed corrections and improvements. For example, the suggestion unit presents detailed correction suggestions for sentences of high importance, such as business documents or official documents. The suggestion unit can also suggest concise corrections and improvements for general sentences. For example, the suggestion unit presents concise correction suggestions for everyday messages or casual sentences. Furthermore, the suggestion unit can also suggest corrections and improvements that focus on the main points for short sentences. For example, the suggestion unit presents concise correction suggestions that focus on the main points for short memos or notices. This allows the suggestion unit to make more appropriate suggestions by adjusting the level of detail of the proposal according to the importance of the sentence. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input sentence importance data into the generation AI, which can then adjust the level of detail of the proposal.

[0040] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the text. For example, in the case of a business document, the suggestion unit prioritizes formal expressions in suggestion. For example, the suggestion unit suggests formal expressions for business documents such as business letters and reports. The suggestion unit can also prioritize friendly expressions in the case of casual messages. For example, the suggestion unit suggests casual expressions for messages to friends and social media posts. Furthermore, in the case of academic papers, the suggestion unit can make suggestions including technical terms and appropriate citations. For example, the suggestion unit makes suggestions including technical terms and appropriate citations for academic papers and research reports. This allows the suggestion unit to make more appropriate suggestions by applying different suggestion algorithms depending on the category of the text. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input text category data into a generation AI, which then applies an appropriate suggestion algorithm.

[0041] When making a proposal, the suggestion unit can determine the priority of the proposal based on the submission date of the document. For example, the suggestion unit prioritizes proposals for documents with an approaching deadline. For example, the suggestion unit prioritizes revision suggestions for reports or projects with an approaching submission deadline. The suggestion unit can also provide detailed suggestions for documents with a distant submission date. For example, the suggestion unit presents detailed revision suggestions for documents with a future submission deadline. Furthermore, the suggestion unit can provide general suggestions for documents with an unknown submission date. For example, the suggestion unit presents general revision suggestions for notes or notebooks with no specific submission deadline. This allows the suggestion unit to prioritize proposals based on the submission date of the document, thereby enabling more appropriate proposals. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input document submission date data into the generation AI, which can then determine the priority of the proposals.

[0042] The suggestion function can adjust the order of suggestions based on the relevance of the text. For example, the suggestion function may prioritize suggesting important revisions. For instance, it may prioritize suggesting revisions for particularly important parts of the text. The suggestion function can also prioritize suggesting improvements that are highly relevant. For example, it may prioritize suggesting improvements that are highly relevant based on the overall flow and context of the text. Furthermore, the suggestion function may prioritize displaying the most relevant suggestions based on user input. For example, it may prioritize displaying suggestions that are highly relevant based on keywords or phrases entered by the user. This allows the suggestion function to make more appropriate suggestions by adjusting the order of suggestions based on the relevance of the text. Some or all of the above processing in the suggestion function may be performed using, for example, a generative AI, or not using a generative AI. For example, the suggestion function can input text relevance data into a generative AI, which can then adjust the order of suggestions.

[0043] When making a selection, the selection unit can analyze the user's past selection history and suggest the optimal selection method. For example, the selection unit automatically displays corrections and improvements that the user frequently selected in the past as candidates. For example, the selection unit displays correction suggestions that the user previously selected in list format, and the user clicks to select. The selection unit can also preferentially suggest a selection method (such as voice or text) that the user has used in the past. For example, if the user previously selected a correction suggestion using voice input, the selection unit preferentially suggests voice input. Furthermore, the selection unit can predict and suggest a selection method to be used in a specific time period based on the user's past selection history. For example, the selection unit analyzes selection methods that the user frequently uses in a specific time period and suggests the optimal selection method for that time period. In this way, the selection unit can suggest the optimal selection method by analyzing the user's past selection history. Some or all of the above-described processing in the selection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the user's past selection history data into a generation AI, which then suggests the optimal selection method.

[0044] When making a selection, the selection unit can filter the selection content based on the user's current project or area of ​​interest. For example, the selection unit can prioritize displaying fixes and improvements related to the project the user is currently working on. For example, the selection unit can automatically suggest related fixes and improvements based on the user's area of ​​interest. Furthermore, if the user is interested in a particular topic, the selection unit can prioritize displaying fixes and improvements related to that topic. For example, the selection unit filters the selection content based on the user's current project or area of ​​interest. By filtering the selection content based on the user's current project or area of ​​interest, highly relevant information can be provided. Some or all of the above-described processing in the selection unit can be performed using, or without, a generation AI. For example, the selection unit can input data on the user's project or area of ​​interest into the generation AI, which can then suggest highly relevant information.

[0045] When making a selection, the selection unit can prioritize obtaining highly relevant selection content by taking into account the user's geographical location information. For example, if the user is in a specific area, the selection unit can prioritize displaying corrections and improvements related to that area. For example, the selection unit can automatically suggest relevant corrections and improvements based on the user's current location. Furthermore, if the user is traveling, the selection unit can prioritize displaying corrections and improvements related to the user's travel destination. For example, the selection unit prioritizes obtaining highly relevant selection content by taking into account the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the selection unit may be performed using, or without, a generation AI. For example, the selection unit can input the user's geographical location information into the generation AI, which can then suggest highly relevant information.

[0046] When making a selection, the selection unit can analyze the user's social media activity and obtain relevant selections. For example, the selection unit can automatically suggest expressions and phrases that the user frequently uses on social media. For example, the selection unit can prioritize displaying corrections and improvements related to a topic of interest based on the user's social media activity. Furthermore, if the user is participating in a specific event, the selection unit can prioritize displaying corrections and improvements related to the event. For example, the selection unit can analyze the user's social media activity and obtain relevant selections. This makes it possible to provide relevant information based on the user's social media activity. Some or all of the above-described processing in the selection unit may be performed using, or without, a generation AI. For example, the selection unit can input the user's social media data into a generation AI, which then suggests relevant information.

[0047] During generation, the generation unit can analyze the user's past sentence generation history and suggest an optimal generation method. The generation unit, for example, analyzes patterns of sentences generated by the user in the past and automatically generates similar sentences. For example, the generation unit can suggest sentences based on a specific style from the user's past generation history. The generation unit can also analyze the user's past generation history and suggest the most efficient generation method. For example, the generation unit can prioritize suggesting generation methods that the user has frequently used in the past. This allows the generation unit to suggest the optimal generation method by analyzing the user's past sentence generation history. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the user's past generation history data into the generation AI, which can then suggest the optimal generation method.

[0048] The generation unit can filter the generated content based on the user's current project or area of ​​interest at the time of generation. For example, the generation unit can prioritize generating sentences related to the project the user is currently working on. For example, the generation unit can automatically generate related expressions and phrases based on the user's area of ​​interest. Furthermore, if the user is interested in a specific topic, the generation unit can prioritize generating information related to that topic. For example, the generation unit filters the generated content based on the user's current project or area of ​​interest. This makes it possible to provide highly relevant information by filtering the generated content based on the user's current project or area of ​​interest. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can input data on the user's project or area of ​​interest into the generation AI, which can then suggest highly relevant information.

[0049] During generation, the generation unit can prioritize acquiring highly relevant generated content by taking into account the user's geographical location information. For example, if the user is in a specific area, the generation unit prioritizes generating information related to that area. For example, the generation unit automatically generates related expressions and phrases based on the user's current location. Furthermore, if the user is traveling, the generation unit can also prioritize generating information related to the travel destination. For example, the generation unit prioritizes acquiring highly relevant generated content by taking into account the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's geographical location information to the generation AI, which can then suggest highly relevant information.

[0050] The generation unit can analyze the user's social media activity and obtain related generated content at the time of generation. For example, the generation unit automatically generates expressions and phrases that the user frequently uses on social media. For example, the generation unit can prioritize generating information related to topics of interest from the user's social media activity. Furthermore, if the user is participating in a specific event, the generation unit can prioritize generating information related to the event. For example, the generation unit can analyze the user's social media activity and obtain related generated content. This makes it possible to provide relevant information based on the user's social media activity. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the user's social media data into the generation AI, which can then suggest related information.

[0051] The settings unit can analyze the user's past settings history during the setup process and propose the optimal settings method. For example, the settings unit can prioritize suggesting settings methods that the user has frequently used in the past. For example, the settings unit can automatically suggest similar settings based on the user's past settings. The settings unit can also predict and suggest settings methods to be used during specific time periods based on the user's past settings history. For example, the settings unit can analyze settings methods that the user frequently uses during specific time periods and propose the optimal settings method for those times. In this way, the settings unit can propose the optimal settings method by analyzing the user's past settings history. Some or all of the above processing in the settings unit may be performed using, for example, a generative AI, or without a generative AI. For example, the settings unit can input the user's past settings history data into a generative AI, which can then propose the optimal settings method.

[0052] The settings unit can filter settings based on the user's current projects and areas of interest during the setup process. For example, the settings unit can prioritize suggesting settings related to the project the user is currently working on. For example, the settings unit can automatically suggest relevant setting options based on the user's areas of interest. The settings unit can also prioritize suggesting settings related to a specific theme if the user is interested in that theme. For example, the settings unit can filter settings based on the user's current projects and areas of interest. This allows the settings unit to provide highly relevant information by filtering settings based on the user's current projects and areas of interest. Some or all of the above processing in the settings unit may be performed using, for example, a generative AI, or not. For example, the settings unit can input data on the user's projects and areas of interest into a generative AI, which can then suggest highly relevant information.

[0053] During setup, the setting unit can prioritize acquiring highly relevant setting content by taking into account the user's geographical location information. For example, if the user is in a specific area, the setting unit prioritizes suggesting settings related to that area. For example, the setting unit automatically suggests related setting options based on the user's current location. Furthermore, if the user is traveling, the setting unit can prioritize suggesting settings related to the user's travel destination. For example, the setting unit prioritizes acquiring highly relevant setting content by taking into account the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the setting unit may be performed using, or without, a generation AI. For example, the setting unit can input the user's geographical location information into the generation AI, which then suggests highly relevant information.

[0054] During setup, the setting unit can analyze the user's social media activity and obtain relevant setting content. For example, the setting unit automatically suggests setting options frequently used by the user on social media. For example, the setting unit may prioritize suggesting settings related to topics of interest to the user based on the user's social media activity. Furthermore, if the user is participating in a specific event, the setting unit may prioritize suggesting settings related to the event. For example, the setting unit may analyze the user's social media activity and obtain relevant setting content. This allows relevant information to be provided based on the user's social media activity. Some or all of the above-described processing in the setting unit may be performed using, or without, a generation AI. For example, the setting unit may input the user's social media data into a generation AI, which may then suggest relevant information.

[0055] When making a change, the change unit can analyze the user's past change history and suggest the optimal change method. For example, the change unit prioritizes suggesting change methods that the user has frequently used in the past. For example, the change unit automatically suggests similar changes based on styles that the user has previously set. The change unit can also predict and suggest a change method to be used during a specific time period from the user's past change history. For example, the change unit analyzes change methods that the user frequently uses during a specific time period and suggests the optimal change method for that time period. In this way, the change unit can suggest the optimal change method by analyzing the user's past change history. Some or all of the above-mentioned processing in the change unit may be performed using, or without, a generation AI. For example, the change unit can input the user's past change history data into the generation AI, which then suggests the optimal change method.

[0056] When making a change, the change unit can filter the change content based on the user's current project or area of ​​interest. For example, the change unit can prioritize suggesting changes related to the project the user is currently working on. For example, the change unit can automatically suggest related change options based on the user's area of ​​interest. Also, if the user is interested in a particular topic, the change unit can prioritize suggesting changes related to that topic. For example, the change unit filters the change content based on the user's current project or area of ​​interest. This makes it possible to provide highly relevant information by filtering the change content based on the user's current project or area of ​​interest. Some or all of the above-described processing in the change unit can be performed using, or without, a generation AI. For example, the change unit can input data on the user's project or area of ​​interest into the generation AI, which can then suggest highly relevant information.

[0057] The change function can prioritize retrieving highly relevant changes when changes are made, taking into account the user's geographical location. For example, if the user is in a specific region, the change function will prioritize suggesting changes related to that region. For example, the change function will automatically suggest relevant change options based on the user's current location. The change function can also prioritize suggesting changes related to the user's travel destination if the user is traveling. For example, the change function will prioritize retrieving highly relevant changes, taking into account the user's geographical location. This allows the system to provide highly relevant information based on the user's geographical location. Some or all of the above processing in the change function may be performed using, for example, a generative AI, or without a generative AI. For example, the change function can input the user's geographical location into a generative AI, which can then suggest highly relevant information.

[0058] The change function can analyze the user's social media activity and retrieve relevant changes when changes are made. For example, the change function can automatically suggest change options that the user frequently uses on social media. For example, the change function can prioritize suggesting changes related to topics of interest based on the user's social media activity. The change function can also prioritize suggesting changes related to events if the user is participating in a particular event. For example, the change function can analyze the user's social media activity and retrieve relevant changes. This allows the function to provide relevant information based on the user's social media activity. Some or all of the above processing in the change function may be performed using, for example, generative AI, or not using generative AI. For example, the change function can input the user's social media data into a generative AI, which can then suggest relevant information.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The suggestion function can analyze the user's past selection history and provide optimal suggestions. For example, it can prioritize suggesting revisions that the user has frequently selected in the past. Furthermore, if the user prefers a particular writing style, it can provide suggestions based on that style. Additionally, if the user tends to input a specific type of text at a particular time of day, it can provide suggestions appropriate for that time slot. This allows for optimal suggestions based on the user's past selection history.

[0061] The input section can prioritize retrieving highly relevant input content by considering the user's geographical location. For example, if the user is in a specific region, information related to that region can be displayed preferentially. Similarly, if the user is traveling, information related to their travel destination can be displayed preferentially. Furthermore, if the user is participating in a specific event, information related to that event can be displayed preferentially. This allows the system to provide highly relevant information based on the user's geographical location.

[0062] The input unit can analyze the user's social media activity and retrieve relevant input content. For example, it can automatically suggest expressions and phrases that the user frequently uses on social media. Furthermore, if the user is interested in a particular theme, it can prioritize displaying information related to that theme. Additionally, if the user is participating in a specific event, it can prioritize displaying information related to that event. This allows the system to provide relevant information based on the user's social media activity.

[0063] The proposal department can adjust the level of detail in its proposals based on the importance of the document. For example, for important documents, it can propose detailed revisions and improvements. For general documents, it can propose concise revisions and improvements. Furthermore, for short documents, it can propose revisions and improvements that capture the main points. This allows for appropriate proposals tailored to the importance of each document.

[0064] At the time of selection, the selection unit can filter the selection based on the user's current project or area of ​​interest. For example, fixes and improvements related to the project the user is currently working on can be displayed preferentially. Also, if the user is interested in a particular theme, fixes and improvements related to that theme can be displayed preferentially. Furthermore, if the user is participating in a particular event, fixes and improvements related to that event can be displayed preferentially. This allows the user to receive information that is highly relevant based on the user's current project or area of ​​interest.

[0065] During generation, the generation unit can analyze the user's past sentence generation history and suggest the optimal generation method. For example, it can analyze patterns of sentences the user has generated in the past and automatically generate similar sentences. It can also suggest sentences based on a specific style from the user's past generation history. Furthermore, it can preferentially suggest generation methods that the user has frequently used in the past. This makes it possible to suggest the optimal generation method based on the user's past sentence generation history.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The input unit allows the user to input text. The text input by the user can be business documents, technical documents, creative documents, etc. The input unit supports various input methods, such as keyboard input, voice input, and handwriting input. Step 2: The suggestion unit uses AI to analyze the sentences entered by the input unit and propose corrections and improvements. The suggestion unit uses techniques such as grammatical analysis, semantic analysis, and syntax analysis to detect grammatical errors and improvements to expressions. For example, it points out grammatical errors and suggests appropriate corrections. It can also point out redundant expressions and propose concise expressions. Step 3: The selection unit allows the user to review the corrections and improvements suggested by the suggestion unit and select appropriate corrections and improvements. The selection unit displays the suggested corrections through a user interface and allows the user to select one. For example, the selection unit may display the corrections in a list format, and the user may click to select one. Alternatively, the user may select a correction by voice using voice input. Step 4: The generation unit generates the final text that reflects the revisions and improvements selected by the selection unit. The generation unit applies the selected revisions to the text and generates a grammatically correct text. For example, after applying the revisions, it checks the overall consistency of the text and makes additional revisions as needed. Step 5: The setting unit sets the user's desired expression style. The setting unit can set various expression styles, such as formal style, casual style, and professional style. The user interface displays options for the expression style, allowing the user to select one. Step 6: The modification unit creates expressions based on the expression style set by the setting unit. The modification unit selects appropriate vocabulary and writing style based on the set style and generates sentences. For example, in the case of a formal style, polite language and formal expressions are used. In the case of a casual style, friendly language and casual expressions are used.

[0068] (Example 2) The document editing system according to an embodiment of the present invention is a system that automatically edits text entered by a user and suggests corrections and improvements. In this document editing system, the user inputs text, and the AI ​​analyzes the text and suggests corrections and improvements. The user reviews the suggested corrections and improvements and selects the appropriate ones. A final text reflecting the selected corrections and improvements is generated. The user reviews the final text and can make corrections before sending it. In addition, the user can set an ideal expression style and have the AI ​​create appropriate expressions based on that style. The user can change their ideal expression style at any time to broaden the range of self-expression. For example, when the user inputs text, they can input text freely. For example, various types of text can be input, such as the body of an email or part of a report. This information is entered into the input unit. Next, the entered text is sent to the suggestion unit, where the AI ​​analyzes the text. The AI ​​detects grammatical and expression errors and suggests corrections and improvements. For example, grammatical errors and redundant expressions may be pointed out. The user reviews the corrections and improvements suggested by the suggestion unit and selects the appropriate ones in the selection unit. The selected corrections and improvements are sent to the generation unit, where the final text is generated. The generated final text can be reviewed by the user and revised before sending. For example, the user can review the body of the email and make revisions as needed. The user can also set their ideal writing style. Based on the style set in the settings unit, the AI ​​creates appropriate expressions. For example, expressions tailored to the user's preferences, such as formal or casual expressions, are generated. The user can change their ideal writing style at any time. By changing the style in the modification unit, the user can broaden their range of self-expression. For example, they can change from a business email style to a casual message style. This allows the text editing system to automatically edit the text entered by the user, suggest corrections and improvements, and generate the final text.

[0069] A writing correction system according to an embodiment includes an input unit, a suggestion unit, a selection unit, a generation unit, a setting unit, and a change unit. The input unit allows a user to input a sentence. The sentences input by the user include, but are not limited to, business documents, technical documents, and creative writing. The input unit supports various input methods, such as keyboard input, voice input, and handwriting input. The suggestion unit uses AI to analyze the sentences input by the input unit and suggest corrections and improvements. The suggestion unit detects grammatical errors and improvements to expressions using techniques such as grammatical analysis, semantic analysis, and syntax analysis. The suggestion unit, for example, points out grammatical errors and suggests appropriate corrections. The suggestion unit can also point out redundant expressions and suggest concise expressions. The selection unit allows a user to review the corrections and improvements suggested by the suggestion unit and select appropriate corrections and improvements. The selection unit, for example, displays the suggested corrections through a user interface, allowing the user to select them. The selection unit, for example, displays suggested revisions in a list format, allowing the user to click to select one. The selection unit can also use voice input to allow the user to select a suggested revision by voice. The generation unit generates a final sentence that reflects the revisions and improvements selected by the selection unit. The generation unit, for example, applies the selected suggested revisions to the sentence to generate a grammatically correct sentence. After applying the suggested revisions, the generation unit, for example, checks the consistency of the entire sentence and makes additional revisions as necessary. The setting unit sets a desired expression style from the user. The setting unit can set various expression styles, for example, a formal style, a casual style, a professional style, etc. The setting unit, for example, displays options for the expression style through a user interface, allowing the user to select one. The modification unit creates an expression based on the expression style set by the setting unit. The modification unit, for example, selects appropriate vocabulary and writing style based on the set style, and generates a sentence. For example, in the case of a formal style, the modification unit uses polite language and formal expressions. In the case of a casual style, the modification unit uses friendly language and casual expressions.As a result, the writing correction system according to the embodiment can automatically correct writing input by the user, suggest corrections and improvements, and generate the final writing.

[0070] The suggestion unit can detect grammatical and linguistic errors using AI and suggest corrections and improvements. The suggestion unit can detect grammatical errors using, for example, grammatical analysis technology. For example, the suggestion unit detects errors based on grammatical rules such as subject-verb agreement, tense agreement, and article use. The suggestion unit can also detect context-based linguistic errors using semantic analysis technology. For example, the suggestion unit points out the use of words that do not fit the context or expressions with ambiguous meanings. Furthermore, the suggestion unit can also detect structural errors in sentences using syntactic analysis technology. For example, the suggestion unit points out cases where sentence structure is improper or punctuation is improperly used. In this way, the suggestion unit can accurately detect grammatical and linguistic errors and suggest corrections and improvements by using AI. Some or all of the above-described processing in the suggestion unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the proposal unit can input the received text into a generation AI, which can then detect grammatical errors and areas for improvement in expression, and generate revised versions.

[0071] The selection unit allows the user to review the proposed corrections and improvements and select appropriate corrections and improvements. The selection unit, for example, displays the proposed corrections through a user interface and allows the user to select one. For example, the selection unit displays the proposed corrections in a list format and the user clicks to select one. The selection unit also allows the user to select a correction by voice input. For example, the selection unit allows the user to select a correction by voice instruction such as "Select correction proposal 1." The selection unit can also analyze the user's past selection history and propose optimal corrections. For example, the selection unit prioritizes displaying corrections that the user has frequently selected in the past. This allows the selection unit to review the proposed corrections and improvements and select appropriate ones. Some or all of the above-described processing in the selection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the proposed corrections to a generation AI, which then proposes the optimal correction.

[0072] The generation unit can generate a completed sentence that reflects the selected corrections and improvements. The generation unit, for example, applies the selected correction suggestions to the sentence to generate a grammatically correct sentence. For example, after applying the correction suggestions, the generation unit checks the consistency of the entire sentence and makes additional corrections as necessary. The generation unit can also adjust the style and tone of the sentence based on the selected correction suggestions. For example, when applying a formal style correction suggestion, the generation unit unifies the entire sentence in a formal tone. Furthermore, the generation unit can analyze the user's past generation history and suggest an optimal generation method. For example, the generation unit analyzes patterns of sentences generated by the user in the past and automatically generates similar sentences. This allows the generation unit to generate a final sentence that reflects the selected corrections and improvements. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the selected correction suggestions into a generation AI, which then generates a final sentence.

[0073] The setting unit can set a desired expression style for the user. The setting unit can set various expression styles, such as a formal style, a casual style, and a professional style. For example, the setting unit can display expression style options through a user interface and allow the user to select one. The setting unit can also analyze the user's past setting history and suggest an optimal expression style. For example, the setting unit can prioritize and display expression styles that the user has frequently used in the past. Furthermore, the setting unit can suggest an appropriate expression style based on the user's current project or field of interest. For example, the setting unit can prioritize and display expression styles related to the project the user is currently working on. This allows the setting unit to set the user's ideal expression style. Some or all of the above-described processing in the setting unit can be performed using, or without, a generation AI. For example, the setting unit can input a user's input to the generation AI, which can then suggest an optimal expression style.

[0074] The modification unit can create expressions based on the set expression style. For example, the modification unit selects appropriate vocabulary and writing style based on the set style and generates sentences. For example, the modification unit uses polite language and formal expressions in a formal style. For example, the modification unit uses friendly language and casual expressions in a casual style. The modification unit can also analyze the user's past modification history and suggest optimal expressions. For example, the modification unit can prioritize displaying expressions that the user has frequently used in the past. Furthermore, the modification unit can suggest appropriate expressions based on the user's current project or area of ​​interest. For example, the modification unit can prioritize displaying expressions related to the project the user is currently working on. This allows the modification unit to create expressions based on the set style. Some or all of the above-mentioned processing in the modification unit may be performed using, or without, a generation AI. For example, the modification unit can input to the generation AI based on the set style, and the generation AI can generate appropriate expressions.

[0075] The input unit can analyze the user's emotions and dynamically change the design of the input interface based on the analyzed emotions. For example, the input unit can capture the user's facial expressions with a camera and analyze the emotions using an emotion estimation algorithm. For example, the input unit can calculate an emotion score based on changes in facial expressions and change the design of the input interface. The input unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the input unit can analyze the tone and speed of the voice, calculate an emotion score, and change the design of the input interface. Furthermore, the input unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and analyze the emotions using an emotion estimation algorithm. For example, the input unit can calculate an emotion score based on fluctuations in heart rate and change the design of the input interface. This makes the user's input work easier by dynamically changing the design of the input interface according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the input unit may input user emotion data to the generation AI, and the generation AI may dynamically change the design of the input interface.

[0076] The input unit can analyze the user's past input history and suggest an appropriate input method. The input unit, for example, analyzes the user's past input history and suggests the optimal input method. For example, the input unit prioritizes suggesting input methods (such as voice and text) that the user has frequently used in the past. The input unit can also analyze patterns of sentences the user has previously input and automatically complete similar sentences. For example, the input unit predicts and suggests an input method to be used during a specific time period based on the user's past input history. In this way, the optimal input method can be suggested by analyzing the user's past input history. Some or all of the above-described processing in the input unit may be performed using, or without, a generation AI. For example, the input unit can input the user's past input history into a generation AI, which then suggests the optimal input method.

[0077] The input unit can filter the input content based on the user's current projects and areas of interest. For example, the input unit may prioritize displaying keywords related to the project the user is currently working on. For example, the input unit may automatically suggest relevant expressions and phrases based on the user's areas of interest. The input unit can also prioritize displaying information related to a specific theme if the user is interested in that theme. For example, the input unit may filter the input content based on the user's current projects and areas of interest. This allows the input unit to provide highly relevant information by filtering the input content based on the user's current projects and areas of interest. Some or all of the above processing in the input unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the input unit may input data on the user's projects and areas of interest into a generative AI, which can then suggest highly relevant information.

[0078] The input unit can analyze the user's emotions and prioritize inputs based on the analyzed user emotions. For example, the input unit captures the user's facial expressions with a camera and analyzes the emotions using an emotion estimation algorithm. For example, the input unit calculates an emotion score based on changes in facial expressions and prioritizes the inputs. The input unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the input unit analyzes the tone and speed of the voice, calculates an emotion score, and prioritizes the inputs. Furthermore, the input unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and analyze the emotions using an emotion estimation algorithm. For example, the input unit calculates an emotion score based on heart rate fluctuations and prioritizes the inputs. This allows important input items to be processed quickly by prioritizing the inputs according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the input unit may input user emotion data to the generation AI, and the generation AI may determine the priority of the input.

[0079] The input unit can prioritize retrieving highly relevant input content while considering the user's geographical location information. For example, if the user is in a specific region, the input unit will prioritize displaying information related to that region. For example, the input unit will automatically suggest relevant expressions and phrases based on the user's current location. The input unit can also prioritize displaying information related to the user's travel destination if the user is traveling. For example, the input unit will prioritize retrieving highly relevant input content while considering the user's geographical location information. This allows the system to provide highly relevant information based on the user's geographical location information. Some or all of the above processing in the input unit may be performed using, for example, a generative AI, or without a generative AI. For example, the input unit can input the user's geographical location information into a generative AI, which can then suggest highly relevant information.

[0080] The input unit can analyze the user's social media activity at the time of input and acquire relevant input content. The input unit, for example, automatically suggests expressions and phrases frequently used by the user on social media. For example, the input unit can prioritize displaying information related to a topic of interest from the user's social media activity. Furthermore, if the user is participating in a specific event, the input unit can prioritize displaying information related to the event. For example, the input unit can analyze the user's social media activity and acquire relevant input content. This makes it possible to provide relevant information based on the user's social media activity. Some or all of the above-described processing in the input unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the input unit can input the user's social media data to a generation AI, which can then suggest relevant information.

[0081] The suggestion unit can estimate the user's emotions and adjust the way the suggestions are presented based on the estimated user emotions. For example, the suggestion unit captures the user's facial expressions with a camera and analyzes the emotions using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on changes in facial expressions and adjusts the way the suggestions are presented. The suggestion unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the way the suggestions are presented. Furthermore, the suggestion unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and analyze the emotions using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on heart rate fluctuations and adjusts the way the suggestions are presented. This allows the suggestion unit to adjust the way the suggestions are presented based on the user's emotions, thereby making it possible to provide more appropriate suggestions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the proposal section may be performed using, for example, a generative AI, or without using a generative AI. For example, the proposal section can input user emotion data into a generative AI, which can then adjust the way the proposal is expressed.

[0082] When making a proposal, the suggestion unit can adjust the level of detail of the proposal based on the importance of the sentence. For example, in the case of an important sentence, the suggestion unit suggests detailed corrections and improvements. For example, the suggestion unit presents detailed correction suggestions for sentences of high importance, such as business documents or official documents. The suggestion unit can also suggest concise corrections and improvements for general sentences. For example, the suggestion unit presents concise correction suggestions for everyday messages or casual sentences. Furthermore, the suggestion unit can also suggest corrections and improvements that focus on the main points for short sentences. For example, the suggestion unit presents concise correction suggestions that focus on the main points for short memos or notices. This allows the suggestion unit to make more appropriate suggestions by adjusting the level of detail of the proposal according to the importance of the sentence. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input sentence importance data into the generation AI, which can then adjust the level of detail of the proposal.

[0083] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the text. For example, in the case of a business document, the suggestion unit prioritizes formal expressions in suggestion. For example, the suggestion unit suggests formal expressions for business documents such as business letters and reports. The suggestion unit can also prioritize friendly expressions in the case of casual messages. For example, the suggestion unit suggests casual expressions for messages to friends and social media posts. Furthermore, in the case of academic papers, the suggestion unit can make suggestions including technical terms and appropriate citations. For example, the suggestion unit makes suggestions including technical terms and appropriate citations for academic papers and research reports. This allows the suggestion unit to make more appropriate suggestions by applying different suggestion algorithms depending on the category of the text. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input text category data into a generation AI, which then applies an appropriate suggestion algorithm.

[0084] The suggestion unit can estimate the user's emotion and adjust the length of the suggestion based on the estimated user emotion. For example, the suggestion unit captures the user's facial expression with a camera and analyzes the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on changes in facial expression and adjusts the length of the suggestion. The suggestion unit can also record the user's voice and analyze the emotion using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the suggestion. Furthermore, the suggestion unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and analyze the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on heart rate fluctuations and adjusts the length of the suggestion. This allows for more appropriate suggestions to be made by adjusting the length of the suggestion based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the proposal section may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal section can input user emotion data into the generative AI, which can then adjust the length of the proposal.

[0085] When making a proposal, the suggestion unit can determine the priority of the proposal based on the submission date of the document. For example, the suggestion unit prioritizes proposals for documents with an approaching deadline. For example, the suggestion unit prioritizes revision suggestions for reports or projects with an approaching submission deadline. The suggestion unit can also provide detailed suggestions for documents with a distant submission date. For example, the suggestion unit presents detailed revision suggestions for documents with a future submission deadline. Furthermore, the suggestion unit can provide general suggestions for documents with an unknown submission date. For example, the suggestion unit presents general revision suggestions for notes or notebooks with no specific submission deadline. This allows the suggestion unit to prioritize proposals based on the submission date of the document, thereby enabling more appropriate proposals. Some or all of the above-described processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can input document submission date data into the generation AI, which can then determine the priority of the proposals.

[0086] The suggestion function can adjust the order of suggestions based on the relevance of the text. For example, the suggestion function may prioritize suggesting important revisions. For instance, it may prioritize suggesting revisions for particularly important parts of the text. The suggestion function can also prioritize suggesting improvements that are highly relevant. For example, it may prioritize suggesting improvements that are highly relevant based on the overall flow and context of the text. Furthermore, the suggestion function may prioritize displaying the most relevant suggestions based on user input. For example, it may prioritize displaying suggestions that are highly relevant based on keywords or phrases entered by the user. This allows the suggestion function to make more appropriate suggestions by adjusting the order of suggestions based on the relevance of the text. Some or all of the above processing in the suggestion function may be performed using, for example, a generative AI, or not using a generative AI. For example, the suggestion function can input text relevance data into a generative AI, which can then adjust the order of suggestions.

[0087] The selection unit can estimate the user's emotions and dynamically change the design of the selection interface based on the estimated emotions. For example, the selection unit can capture the user's facial expressions with a camera and analyze the emotions using an emotion estimation algorithm. For example, the selection unit can calculate an emotion score based on changes in facial expressions and change the design of the selection interface. The selection unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the selection unit can analyze the tone and speed of the voice, calculate an emotion score, and change the design of the selection interface. Furthermore, the selection unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and analyze the emotions using an emotion estimation algorithm. For example, the selection unit can calculate an emotion score based on fluctuations in heart rate and change the design of the selection interface. This makes the user's selection process easier by dynamically changing the design of the selection interface according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the selection unit may input user emotion data into the generation AI, which may then dynamically change the design of the selection interface.

[0088] When making a selection, the selection unit can analyze the user's past selection history and suggest the optimal selection method. For example, the selection unit automatically displays corrections and improvements that the user frequently selected in the past as candidates. For example, the selection unit displays correction suggestions that the user previously selected in list format, and the user clicks to select. The selection unit can also preferentially suggest a selection method (such as voice or text) that the user has used in the past. For example, if the user previously selected a correction suggestion using voice input, the selection unit preferentially suggests voice input. Furthermore, the selection unit can predict and suggest a selection method to be used in a specific time period based on the user's past selection history. For example, the selection unit analyzes selection methods that the user frequently uses in a specific time period and suggests the optimal selection method for that time period. In this way, the selection unit can suggest the optimal selection method by analyzing the user's past selection history. Some or all of the above-described processing in the selection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the user's past selection history data into a generation AI, which then suggests the optimal selection method.

[0089] When making a selection, the selection unit can filter the selection content based on the user's current project or area of ​​interest. For example, the selection unit can prioritize displaying fixes and improvements related to the project the user is currently working on. For example, the selection unit can automatically suggest related fixes and improvements based on the user's area of ​​interest. Furthermore, if the user is interested in a particular topic, the selection unit can prioritize displaying fixes and improvements related to that topic. For example, the selection unit filters the selection content based on the user's current project or area of ​​interest. By filtering the selection content based on the user's current project or area of ​​interest, highly relevant information can be provided. Some or all of the above-described processing in the selection unit can be performed using, or without, a generation AI. For example, the selection unit can input data on the user's project or area of ​​interest into the generation AI, which can then suggest highly relevant information.

[0090] The selection unit can estimate the user's emotions and determine the priority of selections based on the estimated emotions. For example, the selection unit can capture the user's facial expressions with a camera and analyze the emotions using an emotion estimation algorithm. For example, the selection unit can calculate an emotion score based on changes in facial expressions and determine the priority of selections. The selection unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the selection unit can analyze the tone and speed of the voice, calculate an emotion score, and determine the priority of selections. Furthermore, the selection unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and analyze the emotions using an emotion estimation algorithm. For example, the selection unit can calculate an emotion score based on fluctuations in heart rate and determine the priority of selections. This allows for the rapid processing of important selection items by determining the priority of selections according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the selection unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the selection unit may input user emotion data into the generation AI, and the generation AI may determine the priority of selection.

[0091] When making a selection, the selection unit can prioritize obtaining highly relevant selection content by taking into account the user's geographical location information. For example, if the user is in a specific area, the selection unit can prioritize displaying corrections and improvements related to that area. For example, the selection unit can automatically suggest relevant corrections and improvements based on the user's current location. Furthermore, if the user is traveling, the selection unit can prioritize displaying corrections and improvements related to the user's travel destination. For example, the selection unit prioritizes obtaining highly relevant selection content by taking into account the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the selection unit may be performed using, or without, a generation AI. For example, the selection unit can input the user's geographical location information into the generation AI, which can then suggest highly relevant information.

[0092] When making a selection, the selection unit can analyze the user's social media activity and obtain relevant selections. For example, the selection unit can automatically suggest expressions and phrases that the user frequently uses on social media. For example, the selection unit can prioritize displaying corrections and improvements related to a topic of interest based on the user's social media activity. Furthermore, if the user is participating in a specific event, the selection unit can prioritize displaying corrections and improvements related to the event. For example, the selection unit can analyze the user's social media activity and obtain relevant selections. This makes it possible to provide relevant information based on the user's social media activity. Some or all of the above-described processing in the selection unit may be performed using, or without, a generation AI. For example, the selection unit can input the user's social media data into a generation AI, which then suggests relevant information.

[0093] The generation unit can estimate the user's emotions and adjust the tone of the generated text based on the estimated emotions. For example, the generation unit can capture the user's facial expressions with a camera and analyze the emotions using an emotion estimation algorithm. For example, the generation unit can calculate an emotion score based on changes in facial expressions and adjust the tone of the generated text. The generation unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the generation unit can analyze the tone and speed of the voice, calculate an emotion score, and adjust the tone of the generated text. Furthermore, the generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and analyze the emotions using an emotion estimation algorithm. For example, the generation unit can calculate an emotion score based on fluctuations in heart rate and adjust the tone of the generated text. By adjusting the tone of the generated text according to the user's emotions, more appropriate text can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input user emotion data into the generation AI, and the generation AI may adjust the tone of the generated sentence.

[0094] During generation, the generation unit can analyze the user's past sentence generation history and suggest an optimal generation method. The generation unit, for example, analyzes patterns of sentences generated by the user in the past and automatically generates similar sentences. For example, the generation unit can suggest sentences based on a specific style from the user's past generation history. The generation unit can also analyze the user's past generation history and suggest the most efficient generation method. For example, the generation unit can prioritize suggesting generation methods that the user has frequently used in the past. This allows the generation unit to suggest the optimal generation method by analyzing the user's past sentence generation history. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the user's past generation history data into the generation AI, which can then suggest the optimal generation method.

[0095] The generation unit can filter the generated content based on the user's current project or area of ​​interest at the time of generation. For example, the generation unit can prioritize generating sentences related to the project the user is currently working on. For example, the generation unit can automatically generate related expressions and phrases based on the user's area of ​​interest. Furthermore, if the user is interested in a specific topic, the generation unit can prioritize generating information related to that topic. For example, the generation unit filters the generated content based on the user's current project or area of ​​interest. This makes it possible to provide highly relevant information by filtering the generated content based on the user's current project or area of ​​interest. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can input data on the user's project or area of ​​interest into the generation AI, which can then suggest highly relevant information.

[0096] The generation unit can estimate the user's emotions and determine the priority of generated text based on the estimated emotions. For example, the generation unit can capture the user's facial expressions with a camera and analyze the emotions using an emotion estimation algorithm. For example, the generation unit can calculate an emotion score based on changes in facial expressions and determine the priority of generated text. The generation unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the generation unit can analyze the tone and speed of the voice, calculate an emotion score, and determine the priority of generated text. Furthermore, the generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and analyze the emotions using an emotion estimation algorithm. For example, the generation unit can calculate an emotion score based on fluctuations in heart rate and determine the priority of generated text. This allows for the rapid provision of important information by determining the priority of generated text according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit may input user emotion data into the generation AI, and the generation AI may determine the priority of the sentences to be generated.

[0097] During generation, the generation unit can prioritize acquiring highly relevant generated content by taking into account the user's geographical location information. For example, if the user is in a specific area, the generation unit prioritizes generating information related to that area. For example, the generation unit automatically generates related expressions and phrases based on the user's current location. Furthermore, if the user is traveling, the generation unit can also prioritize generating information related to the travel destination. For example, the generation unit prioritizes acquiring highly relevant generated content by taking into account the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's geographical location information to the generation AI, which can then suggest highly relevant information.

[0098] The generation unit can analyze the user's social media activity and obtain related generated content at the time of generation. For example, the generation unit automatically generates expressions and phrases that the user frequently uses on social media. For example, the generation unit can prioritize generating information related to topics of interest from the user's social media activity. Furthermore, if the user is participating in a specific event, the generation unit can prioritize generating information related to the event. For example, the generation unit can analyze the user's social media activity and obtain related generated content. This makes it possible to provide relevant information based on the user's social media activity. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the user's social media data into the generation AI, which can then suggest related information.

[0099] The settings unit can estimate the user's emotions and dynamically change the design of the settings interface based on the estimated emotions. For example, the settings unit can capture the user's facial expressions with a camera and analyze the emotions using an emotion estimation algorithm. For example, the settings unit can calculate an emotion score based on changes in facial expressions and change the design of the settings interface. The settings unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the settings unit can analyze the tone and speed of the voice, calculate an emotion score, and change the design of the settings interface. Furthermore, the settings unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and analyze the emotions using an emotion estimation algorithm. For example, the settings unit can calculate an emotion score based on fluctuations in heart rate and change the design of the settings interface. This makes the user's setting process easier by dynamically changing the design of the settings interface according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the setting unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the setting unit may input user emotion data into the generation AI, which may then dynamically change the design of the setting interface.

[0100] The settings unit can analyze the user's past settings history during the setup process and propose the optimal settings method. For example, the settings unit can prioritize suggesting settings methods that the user has frequently used in the past. For example, the settings unit can automatically suggest similar settings based on the user's past settings. The settings unit can also predict and suggest settings methods to be used during specific time periods based on the user's past settings history. For example, the settings unit can analyze settings methods that the user frequently uses during specific time periods and propose the optimal settings method for those times. In this way, the settings unit can propose the optimal settings method by analyzing the user's past settings history. Some or all of the above processing in the settings unit may be performed using, for example, a generative AI, or without a generative AI. For example, the settings unit can input the user's past settings history data into a generative AI, which can then propose the optimal settings method.

[0101] The settings unit can filter settings based on the user's current projects and areas of interest during the setup process. For example, the settings unit can prioritize suggesting settings related to the project the user is currently working on. For example, the settings unit can automatically suggest relevant setting options based on the user's areas of interest. The settings unit can also prioritize suggesting settings related to a specific theme if the user is interested in that theme. For example, the settings unit can filter settings based on the user's current projects and areas of interest. This allows the settings unit to provide highly relevant information by filtering settings based on the user's current projects and areas of interest. Some or all of the above processing in the settings unit may be performed using, for example, a generative AI, or not. For example, the settings unit can input data on the user's projects and areas of interest into a generative AI, which can then suggest highly relevant information.

[0102] The setting unit can estimate the user's emotions and prioritize settings based on the estimated user emotions. For example, the setting unit captures the user's facial expressions with a camera and analyzes the emotions using an emotion estimation algorithm. For example, the setting unit calculates an emotion score based on changes in facial expressions and prioritizes settings. The setting unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the setting unit analyzes the tone and speed of the voice, calculates an emotion score, and prioritizes settings. Furthermore, the setting unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and analyze the emotions using an emotion estimation algorithm. For example, the setting unit calculates an emotion score based on heart rate fluctuations and prioritizes settings. This allows important setting items to be processed quickly by prioritizing settings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the setting unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the setting unit may input user emotion data into the generation AI, and the generation AI may determine the priority of settings.

[0103] During setup, the setting unit can prioritize acquiring highly relevant setting content by taking into account the user's geographical location information. For example, if the user is in a specific area, the setting unit prioritizes suggesting settings related to that area. For example, the setting unit automatically suggests related setting options based on the user's current location. Furthermore, if the user is traveling, the setting unit can prioritize suggesting settings related to the user's travel destination. For example, the setting unit prioritizes acquiring highly relevant setting content by taking into account the user's geographical location information. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the setting unit may be performed using, or without, a generation AI. For example, the setting unit can input the user's geographical location information into the generation AI, which then suggests highly relevant information.

[0104] During setup, the setting unit can analyze the user's social media activity and obtain relevant setting content. For example, the setting unit automatically suggests setting options frequently used by the user on social media. For example, the setting unit may prioritize suggesting settings related to topics of interest to the user based on the user's social media activity. Furthermore, if the user is participating in a specific event, the setting unit may prioritize suggesting settings related to the event. For example, the setting unit may analyze the user's social media activity and obtain relevant setting content. This allows relevant information to be provided based on the user's social media activity. Some or all of the above-described processing in the setting unit may be performed using, or without, a generation AI. For example, the setting unit may input the user's social media data into a generation AI, which may then suggest relevant information.

[0105] The modification unit can estimate the user's emotions and dynamically change the design of the modification interface based on the estimated emotions. For example, the modification unit can capture the user's facial expressions with a camera and analyze the emotions using an emotion estimation algorithm. For example, the modification unit can calculate an emotion score based on changes in facial expressions and change the design of the modification interface. The modification unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the modification unit can analyze the tone and speed of the voice, calculate an emotion score, and change the design of the modification interface. Furthermore, the modification unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and analyze the emotions using an emotion estimation algorithm. For example, the modification unit can calculate an emotion score based on fluctuations in heart rate and change the design of the modification interface. This makes it easier for the user to perform modification tasks by dynamically changing the design of the modification interface according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the modification section may be performed using, for example, a generative AI, or without a generative AI. For example, the modification section can input user emotion data into a generative AI, which can then dynamically change the design of the modification interface.

[0106] When making a change, the change unit can analyze the user's past change history and suggest the optimal change method. For example, the change unit prioritizes suggesting change methods that the user has frequently used in the past. For example, the change unit automatically suggests similar changes based on styles that the user has previously set. The change unit can also predict and suggest a change method to be used during a specific time period from the user's past change history. For example, the change unit analyzes change methods that the user frequently uses during a specific time period and suggests the optimal change method for that time period. In this way, the change unit can suggest the optimal change method by analyzing the user's past change history. Some or all of the above-mentioned processing in the change unit may be performed using, or without, a generation AI. For example, the change unit can input the user's past change history data into the generation AI, which then suggests the optimal change method.

[0107] When making a change, the change unit can filter the change content based on the user's current project or area of ​​interest. For example, the change unit can prioritize suggesting changes related to the project the user is currently working on. For example, the change unit can automatically suggest related change options based on the user's area of ​​interest. Also, if the user is interested in a particular topic, the change unit can prioritize suggesting changes related to that topic. For example, the change unit filters the change content based on the user's current project or area of ​​interest. This makes it possible to provide highly relevant information by filtering the change content based on the user's current project or area of ​​interest. Some or all of the above-described processing in the change unit can be performed using, or without, a generation AI. For example, the change unit can input data on the user's project or area of ​​interest into the generation AI, which can then suggest highly relevant information.

[0108] The modification unit can estimate the user's emotions and determine the priority of changes based on the estimated user emotions. For example, the modification unit captures the user's facial expressions with a camera and analyzes the emotions using an emotion estimation algorithm. For example, the modification unit calculates an emotion score based on changes in facial expressions and determines the priority of changes. The modification unit can also record the user's voice and analyze the emotions using voice analysis technology. For example, the modification unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of changes. Furthermore, the modification unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and analyze the emotions using an emotion estimation algorithm. For example, the modification unit calculates an emotion score based on heart rate fluctuations and determines the priority of changes. This allows important changes to be processed quickly by determining the priority of changes according to the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the modification unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the modification unit may input user emotion data into the generation AI, and the generation AI may determine the priority of the modifications.

[0109] The change function can prioritize retrieving highly relevant changes when changes are made, taking into account the user's geographical location. For example, if the user is in a specific region, the change function will prioritize suggesting changes related to that region. For example, the change function will automatically suggest relevant change options based on the user's current location. The change function can also prioritize suggesting changes related to the user's travel destination if the user is traveling. For example, the change function will prioritize retrieving highly relevant changes, taking into account the user's geographical location. This allows the system to provide highly relevant information based on the user's geographical location. Some or all of the above processing in the change function may be performed using, for example, a generative AI, or without a generative AI. For example, the change function can input the user's geographical location into a generative AI, which can then suggest highly relevant information.

[0110] The change function can analyze the user's social media activity and retrieve relevant changes when changes are made. For example, the change function can automatically suggest change options that the user frequently uses on social media. For example, the change function can prioritize suggesting changes related to topics of interest based on the user's social media activity. The change function can also prioritize suggesting changes related to events if the user is participating in a particular event. For example, the change function can analyze the user's social media activity and retrieve relevant changes. This allows the function to provide relevant information based on the user's social media activity. Some or all of the above processing in the change function may be performed using, for example, generative AI, or not using generative AI. For example, the change function can input the user's social media data into a generative AI, which can then suggest relevant information. === Hard Collateral 1-1 === Each of the multiple elements, including the input unit, suggestion unit, selection unit, generation unit, setting unit, and change unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the input unit inputs a user's sentence using the keyboard or microphone of the smart device 14. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and AI analyzes the input sentence and suggests corrections and improvements. The selection unit is realized by the control unit 46A of the smart device 14, and the user selects the suggested corrections and improvements. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a final sentence that reflects the selected corrections and improvements. The setting unit is realized by the control unit 46A of the smart device 14, and sets the expression style desired by the user. The change unit is realized by the specific processing unit 290 of the data processing device 12, and creates an expression based on the set style. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned input unit, suggestion unit, selection unit, generation unit, setting unit, and change unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the input unit inputs a user's sentence using a microphone or camera of the smart glasses 214. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and AI analyzes the input sentence and suggests corrections and improvements. The selection unit is realized by the control unit 46A of the smart glasses 214, and the user selects the suggested corrections and improvements. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a final sentence that reflects the selected corrections and improvements. The setting unit is realized by the control unit 46A of the smart glasses 214, and sets the user's desired expression style. The change unit is realized by the specific processing unit 290 of the data processing device 12, and creates an expression based on the set style. === Hard Collateral 1-3 === Each of the multiple elements described above, including the input unit, suggestion unit, selection unit, generation unit, setting unit, and modification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the input unit inputs the user's text using the microphone and camera of the headset terminal 314. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, where the AI ​​analyzes the input text and suggests corrections and improvements. The selection unit is implemented by the control unit 46A of the headset terminal 314, where the user selects the suggested corrections and improvements. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where it generates the final text reflecting the selected corrections and improvements. The setting unit is implemented by the control unit 46A of the headset terminal 314, where the user sets the desired expression style. The modification unit is implemented by the specific processing unit 290 of the data processing unit 12, where it creates an expression based on the set style. === Hard Collateral 1-4 === Each of the multiple elements described above, including the input unit, suggestion unit, selection unit, generation unit, setting unit, and modification unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the input unit inputs the user's text using the microphone and camera of the robot 414. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, where the AI ​​analyzes the input text and suggests corrections and improvements. The selection unit is implemented by the control unit 46A of the robot 414, where the user selects the suggested corrections and improvements. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where it generates a final text that reflects the selected corrections and improvements. The setting unit is implemented by the control unit 46A of the robot 414, where the user sets the desired expression style. The modification unit is implemented by the specific processing unit 290 of the data processing unit 12, where it creates an expression based on the set style.

[0111] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0112] The suggestion function can estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, if the user is stressed, the suggestion function can present suggestions in a gentle tone. If the user is excited, the suggestion function can present concise and direct suggestions. Furthermore, if the user is relaxed, the suggestion function can present suggestions that include detailed explanations. This allows for the provision of appropriate suggestions tailored to the user's emotions.

[0113] The suggestion function can analyze the user's past selection history and provide optimal suggestions. For example, it can prioritize suggesting revisions that the user has frequently selected in the past. Furthermore, if the user prefers a particular writing style, it can provide suggestions based on that style. Additionally, if the user tends to input a specific type of text at a particular time of day, it can provide suggestions appropriate for that time slot. This allows for optimal suggestions based on the user's past selection history.

[0114] The selection section can estimate the user's emotions and dynamically change the design of the selection interface based on those emotions. For example, if the user is tired, the selection interface can be changed to a simple and easy-to-understand design. If the user is focused, the design can be changed to one that displays detailed information. Furthermore, if the user is relaxed, the design can be changed to a colorful and fun design. This allows for the provision of an optimal selection interface tailored to the user's emotions.

[0115] The generation unit can estimate the user's emotions and adjust the tone of the generated text based on those emotions. For example, if the user is angry, the generation unit can generate text in a calm and composed tone. If the user is sad, the generation unit can generate text in an encouraging tone. Furthermore, if the user is happy, the generation unit can generate text in a bright and positive tone. This allows for the generation of text with an appropriate tone that matches the user's emotions.

[0116] The setting unit can estimate the user's emotions and dynamically change the design of the setting interface based on the estimated user's emotions. For example, if the user is feeling stressed, the setting interface can be changed to a simple and intuitive design. If the user is feeling relaxed, the design can be changed to one that displays detailed setting options. Furthermore, if the user is concentrating, the design can be changed to a customizable design. This makes it possible to provide an optimal setting interface according to the user's emotions.

[0117] The input section can prioritize retrieving highly relevant input content by considering the user's geographical location. For example, if the user is in a specific region, information related to that region can be displayed preferentially. Similarly, if the user is traveling, information related to their travel destination can be displayed preferentially. Furthermore, if the user is participating in a specific event, information related to that event can be displayed preferentially. This allows the system to provide highly relevant information based on the user's geographical location.

[0118] The input unit can analyze the user's social media activity and retrieve relevant input content. For example, it can automatically suggest expressions and phrases that the user frequently uses on social media. Furthermore, if the user is interested in a particular theme, it can prioritize displaying information related to that theme. Additionally, if the user is participating in a specific event, it can prioritize displaying information related to that event. This allows the system to provide relevant information based on the user's social media activity.

[0119] The proposal department can adjust the level of detail in its proposals based on the importance of the document. For example, for important documents, it can propose detailed revisions and improvements. For general documents, it can propose concise revisions and improvements. Furthermore, for short documents, it can propose revisions and improvements that capture the main points. This allows for appropriate proposals tailored to the importance of each document.

[0120] At the time of selection, the selection unit can filter the selection based on the user's current project or area of ​​interest. For example, fixes and improvements related to the project the user is currently working on can be displayed preferentially. Also, if the user is interested in a particular theme, fixes and improvements related to that theme can be displayed preferentially. Furthermore, if the user is participating in a particular event, fixes and improvements related to that event can be displayed preferentially. This allows the user to receive information that is highly relevant based on the user's current project or area of ​​interest.

[0121] During generation, the generation unit can analyze the user's past sentence generation history and suggest the optimal generation method. For example, it can analyze patterns of sentences the user has generated in the past and automatically generate similar sentences. It can also suggest sentences based on a specific style from the user's past generation history. Furthermore, it can preferentially suggest generation methods that the user has frequently used in the past. This makes it possible to suggest the optimal generation method based on the user's past sentence generation history.

[0122] The processing flow of the second embodiment will be briefly explained below.

[0123] Step 1: The input unit allows the user to input text. The text input by the user can be business documents, technical documents, creative documents, etc. The input unit supports various input methods, such as keyboard input, voice input, and handwriting input. Step 2: The suggestion unit uses AI to analyze the sentences entered by the input unit and propose corrections and improvements. The suggestion unit uses techniques such as grammatical analysis, semantic analysis, and syntax analysis to detect grammatical errors and improvements to expressions. For example, it points out grammatical errors and suggests appropriate corrections. It can also point out redundant expressions and propose concise expressions. Step 3: The selection unit allows the user to review the corrections and improvements suggested by the suggestion unit and select appropriate corrections and improvements. The selection unit displays the suggested corrections through a user interface and allows the user to select one. For example, the selection unit may display the corrections in a list format, and the user may click to select one. Alternatively, the user may select a correction by voice using voice input. Step 4: The generation unit generates the final text that reflects the revisions and improvements selected by the selection unit. The generation unit applies the selected revisions to the text and generates a grammatically correct text. For example, after applying the revisions, it checks the overall consistency of the text and makes additional revisions as needed. Step 5: The setting unit sets the user's desired expression style. The setting unit can set various expression styles, such as formal style, casual style, and professional style. The user interface displays options for the expression style, allowing the user to select one. Step 6: The modification unit creates expressions based on the expression style set by the setting unit. The modification unit selects appropriate vocabulary and writing style based on the set style and generates sentences. For example, in the case of a formal style, polite language and formal expressions are used. In the case of a casual style, friendly language and casual expressions are used.

[0124] 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.

[0125] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0126] 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.

[0127] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0128] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

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

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

[0138] In the 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.

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

[0140] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0142] 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.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0145] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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 identification processing unit 290 using these models.

[0155] 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.

[0156] 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.

[0157] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0158] 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.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0172] 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.

[0173] 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.

[0174] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0175] 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.

[0176] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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."

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] [Explanation of symbols]

[0196] 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. an input unit for a user to input text; a suggestion unit that analyzes the text input by the input unit and suggests corrections and improvements; a selection unit for selecting the modifications and improvements suggested by the suggestion unit; a generation unit that generates a completed sentence that reflects the corrections and improvements selected by the selection unit; a setting unit for setting a desired expression style by a user; a modification unit that creates an expression based on the expression style set by the setting unit; Equipped with A system characterized by:

2. The proposal unit AI detects grammatical and phrasal errors and suggests corrections and improvements The system of claim 1 .

3. The selection unit The user reviews the proposed fixes and improvements and selects the appropriate fixes and improvements. The system of claim 1 .

4. The generation unit Generate a finished sentence that reflects the selected corrections and improvements The system of claim 1 .

5. The setting unit Set the desired presentation style The system of claim 1 .

6. The change unit Create expressions based on the set expression style The system of claim 1 .

7. The input unit Analyzes user emotions and dynamically changes the design of the input interface based on the analyzed user emotions. The system of claim 1 .

8. The input unit Analyzes the user's past input history and suggests appropriate input methods The system of claim 1 .

Images