system

Abstract

The system according to this embodiment aims to efficiently perform tasks such as proofreading and editing texts, translation, and researching the meanings of the latest languages ​​and slang. [Solution] The system according to the embodiment comprises an editing unit, a translation unit, a research unit, and a linking unit. The editing unit edits and proofreads the text. The translation unit translates the text that has been edited and proofread by the editing unit. The research unit looks up the meanings of the latest words and slang. The linking unit moves to links as needed.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that proofreading, correction, translation of sentences, and investigation of the meanings of the latest languages and buzzwords are performed individually, and it is difficult to perform them efficiently.

[0005] The system according to the embodiment aims to efficiently perform proofreading, correction, translation of sentences, and investigation of the meanings of the latest languages and buzzwords.

Means for Solving the Problems

[0006] The system according to the embodiment includes a proofreading unit, a translation unit, an investigation unit, and a link unit. The proofreading unit performs proofreading and correction of sentences. The translation unit translates the sentences proofread and corrected by the proofreading unit. The investigation unit investigates the meanings of the latest languages and buzzwords. The link unit moves to a link as needed. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently perform tasks such as proofreading and editing text, translation, and researching the meanings of the latest languages ​​and slang. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 x48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, 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 text support system according to an embodiment of the present invention provides functions for editing, proofreading, and translating text in messaging apps and email services when users struggle with writing, make mistakes, or when foreigners have difficulty with translation. The text support system also has a function to display a Wiki when the meaning of the latest language or slang is not understood by tapping it. Furthermore, it also provides a function to move to a link on an email service page as needed. First, when a user enters text in a messaging app or email service, the AI ​​edits and proofreads the text in real time. For example, it corrects typos and grammatical errors and corrects the text to make it appropriate. It can also suggest more appropriate expressions and phrasing depending on the content of the text. This allows users to send text with confidence. Next, when foreigners have difficulty with translation, the AI ​​translates the text in real time. For example, it translates from Japanese to English or from English to Japanese and displays it in a format that is easy for the user to understand. This enables smooth communication across language barriers. Furthermore, if the meaning of the latest language or slang is not understood, the AI ​​automatically displays a Wiki when the user taps the word. For example, it allows users to easily obtain information when looking up the meaning of new slang or technical terms. This ensures that users always stay up-to-date. Finally, it also provides a function to navigate to links to email service pages as needed. For example, if a user wants to investigate specific information in more detail, the AI ​​will suggest the appropriate email service page, and they can be directly accessed by clicking the link. This allows users to efficiently gather information. In this way, the writing assistance system provides functions that enable users of messaging apps and email services to create accurate and appropriate sentences and easily obtain the latest information without struggling with writing.

[0029] The document support system according to this embodiment comprises an editing unit, a translation unit, a research unit, and a linking unit. The editing unit edits and proofreads the text when it is input. For example, the editing unit corrects typographical errors and checks grammar. For example, the editing unit corrects typographical errors using a dictionary. The editing unit can also correct typographical errors based on context. Furthermore, the editing unit checks grammar by applying grammatical rules. For example, the editing unit detects grammatical errors and suggests appropriate corrections. The translation unit translates the text that has been edited and proofread by the editing unit. For example, the translation unit translates from Japanese to English and from English to Japanese. For example, the translation unit uses a neural network-based translation algorithm to perform the translation. The translation unit can also use a rule-based translation algorithm to perform the translation. Furthermore, the translation unit considers the context to improve the accuracy of the translation. The research unit looks up the meanings of the latest words and slang. The research unit, for example, retrieves the meaning of a word tapped by the user from a wiki. The research unit retrieves the meaning of a word by referring to a specific wiki site, for example. The research unit can also retrieve wiki data using an API. Furthermore, the research unit applies an appropriate research method depending on the category of the word the user wants to investigate. The linking unit moves to links as needed. For example, if the user wants to investigate specific information in more detail, the linking unit suggests a page of an appropriate email service and moves directly to it by clicking the link. For example, the linking unit suggests pages related to the information the user wants to investigate. The linking unit can also select the optimal link by referring to the user's past operation history. Furthermore, the linking unit selects the optimal link considering the user's device information. As a result, the text support system according to the embodiment enables text editing and proofreading, translation, research, and link navigation.

[0030] The editing department corrects and proofreads text as it is entered. Specifically, it corrects typos and grammatical errors. For example, the editing department uses dictionaries to correct typos. These dictionaries include not only general word dictionaries but also specialized terminology dictionaries and user-customized dictionaries. This makes it possible to edit texts specific to particular fields or industries. The editing department can also correct typos based on context. For example, it analyzes the flow and meaning of the entire text to detect and correct words or phrases that do not fit the context. Furthermore, the editing department checks grammar by applying grammatical rules. These grammatical rules include not only basic grammatical rules but also style guides and rules based on specific formats. For example, it can perform grammatical checks suitable for business documents and academic papers. The editing department detects grammatical errors and suggests appropriate corrections. The suggested corrections can be reviewed and approved by the user, improving the quality of the final text. In addition, the editing department can use AI to evaluate the naturalness and fluency of the text and suggest areas for improvement. For example, using generative AI, it can suggest more natural expressions and appropriate vocabulary choices. This allows the editing function to go beyond simply correcting typos and grammatical errors, and instead support the overall improvement of the writing quality.

[0031] The translation department translates texts that have been edited and proofread by the editing department. Specifically, it performs translations from Japanese to English and from English to Japanese. The translation department uses neural network-based translation algorithms. Neural network-based translation algorithms learn from large amounts of data to achieve highly accurate translations. For example, a translation algorithm using a Transformer model provides natural translations that take context into account. The translation department can also perform translations using rule-based translation algorithms. Rule-based translation algorithms perform translations based on specific grammatical rules and lexical transformation rules, thus exhibiting high accuracy for specific fields and technical terms. Furthermore, the translation department considers context when translating to improve translation accuracy. For example, it analyzes the surrounding context and the meaning of the entire paragraph to provide an appropriate translation. The translation department can also use AI to evaluate the quality of translations and suggest corrections as needed. For example, it can use generative AI to evaluate the naturalness and fluency of the translation results and suggest areas for improvement. This allows the translation department to provide highly accurate and natural translations and to respond flexibly to user needs.

[0032] The research department investigates the meanings of the latest words and slang. Specifically, it retrieves the meaning of words tapped by users from wikis. The research department obtains the meaning of words by referring to specific wiki sites. For example, it uses general encyclopedia sites and sites that provide specialized knowledge. The research department can also obtain wiki data using APIs. By using APIs, it can obtain the latest information in real time and provide it to users. Furthermore, the research department applies appropriate research methods depending on the category of the word the user wants to research. For example, it provides more accurate information by referring to information sources that specialize in specific fields, such as technical terms or medical terms. The research department can also use AI to evaluate the reliability and relevance of research results and select the most optimal information. For example, it uses generative AI to integrate data obtained from multiple information sources and provide the most reliable information. In this way, the research department can provide users with the information they need quickly and accurately and support them in writing.

[0033] The Links section navigates to links as needed. Specifically, if the user wants to investigate specific information in more detail, it suggests the appropriate email service page, and clicking the link will take them directly to that page. The Links section suggests pages related to the information the user is looking for. For example, it can refer to websites that provide detailed information on a specific topic, or to related papers and articles. The Links section can also select the most suitable links by referring to the user's past activity history. This enables the provision of information based on the user's interests and preferences. Furthermore, the Links section selects the most suitable links considering the user's device information. For example, it provides the optimal display format and link destination depending on the device being used, such as a smartphone, tablet, or PC. The Links section can also use AI to analyze the user's behavior patterns and interests and suggest the most suitable links. For example, it can use generative AI to select highly relevant links based on the user's past search and browsing history. This allows the Links section to provide users with quick and appropriate information and improve the efficiency of writing.

[0034] The editing unit can correct typographical errors and perform grammatical checks. For example, the editing unit can correct typographical errors using a dictionary. The editing unit can also correct typographical errors based on context. Furthermore, the editing unit performs grammatical checks by applying grammatical rules. For example, the editing unit can detect grammatical errors and suggest appropriate corrections. This enables the correction of typographical errors and grammatical checks. Some or all of the above processes in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can receive text as input and perform editing and proofreading using an AI model that corrects typographical errors and performs grammatical checks.

[0035] The editing unit can suggest appropriate expressions and phrases depending on the content of the text. For example, the editing unit can suggest appropriate expressions and phrases based on the context. For example, the editing unit can also suggest appropriate expressions and phrases by applying a style guide. Furthermore, the editing unit can suggest even more appropriate expressions and phrases depending on the content of the text. This makes it possible to suggest appropriate expressions and phrases. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can take text as input and perform editing and proofreading of the text using an AI model that suggests appropriate expressions and phrases.

[0036] The translation unit can perform translations from Japanese to English and from English to Japanese. The translation unit can use, for example, a neural network-based translation algorithm. It can also use, for example, a rule-based translation algorithm. Furthermore, the translation unit can consider context to improve translation accuracy. This enables translation between Japanese and English. Some or all of the above-described processes in the translation unit may be performed using, for example, AI, or not. For example, the translation unit can take a text as input and translate it using an AI model that performs translations from Japanese to English and from English to Japanese.

[0037] The research unit can obtain the meaning of a word tapped by a user from a wiki. For example, the research unit can obtain the meaning of a word by referring to a specific wiki site. The research unit can also obtain wiki data using an API, for example. Furthermore, the research unit can apply an appropriate research method depending on the category of the word the user wants to investigate. This makes it possible to obtain the meaning of a tapped word from a wiki. Some or all of the above processing in the research unit may be performed using AI, for example, or not using AI. For example, the research unit can investigate the meaning of a word by receiving a word tapped by a user as input and using an AI model that obtains its meaning from a wiki.

[0038] The linking function suggests the appropriate email service page when the user wants to investigate specific information in more detail, and the user can navigate directly to the page by clicking the link. For example, the linking function suggests pages related to the information the user wants to investigate. The linking function can also select the optimal link by referring to the user's past activity history. Furthermore, the linking function can select the optimal link by considering the user's device information. This makes it possible to navigate to the appropriate page to investigate specific information in more detail. Some or all of the above processing in the linking function may be performed using AI, for example, or without AI. For example, the linking function can perform link navigation using an AI model that receives the information the user wants to investigate as input and suggests links to appropriate pages.

[0039] The editing unit can analyze the user's past writing history and select the most suitable editing method. For example, the editing unit can prioritize checking grammar and expressions that the user has frequently made mistakes with in the past and suggest corrections. For example, the editing unit can also analyze expressions and styles that the user has used in the past and provide editing advice based on that. Furthermore, the editing unit can enhance editing on specific themes or topics based on the user's past writing history. This makes it possible to select the most suitable editing method based on past writing history. Some or all of the above processes in the editing unit may be performed using AI, for example, or not. For example, the editing unit can take the user's past writing history as input and use an AI model that selects the most suitable editing method to edit and proofread the text.

[0040] The editing unit can automatically edit technical terms and industry-specific expressions according to the content of the text. For example, in medical documents, the editing unit checks for the accurate use of technical terms and corrects them to appropriate expressions. In legal documents, for example, the editing unit can also check the accuracy of legal expressions and terminology and correct them as necessary. Furthermore, in technical documents, the editing unit can check the accuracy of technical terms and expressions and make appropriate corrections. This makes it possible to edit technical terms and industry-specific expressions. Some or all of the above processing in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can receive text as input and perform editing and proofreading using an AI model that automatically edits technical terms and industry-specific expressions.

[0041] The editing unit can prioritize correcting region-specific expressions by taking into account the user's geographical location during the editing process. For example, if the user is in the United States, the editing unit can prioritize the use of American English expressions. If the user is in the United Kingdom, the editing unit can also prioritize the use of British English expressions. Furthermore, if the user is in Japan, the editing unit can prioritize the use of region-specific Japanese expressions. This makes it possible to correct region-specific expressions based on geographical location information. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can receive the user's geographical location information as input and use an AI model that prioritizes correcting region-specific expressions to edit and proofread the text.

[0042] The editing unit can analyze the user's social media activity during editing and suggest relevant expressions. For example, the editing unit can analyze the social media expressions the user frequently uses and make edits based on that. For example, the editing unit can also suggest appropriate expressions by referring to the expressions of influencers the user follows. Furthermore, the editing unit can analyze the content of the user's social media posts and suggest relevant expressions and phrases. This makes it possible to suggest relevant expressions based on social media activity. Some or all of the above processing in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can receive the user's social media activity data as input and use an AI model that suggests relevant expressions to edit and proofread the text.

[0043] The translation unit can adjust the level of detail of the translation based on the importance of the text during the translation process. For example, the translation unit can provide a detailed and accurate translation for important business documents. For example, it can provide a concise and easy-to-understand translation for casual messages. Furthermore, in academic papers, the translation unit can accurately translate specialized terminology and provide detailed explanations. This makes it possible to adjust the level of detail of the translation based on the importance of the text. Some or all of the above processes in the translation unit may be performed using AI, for example, or not. For example, the translation unit can take text importance data as input and perform translation using an AI model that adjusts the level of detail of the translation based on importance.

[0044] The translation unit can apply different translation algorithms depending on the category of the document during translation. For example, the translation unit may use a translation algorithm specialized for technical terminology in technical documents. For example, the translation unit may also use a translation algorithm specialized for legal expressions in legal documents. Furthermore, the translation unit may use a translation algorithm specialized for medical terminology in medical documents. This makes it possible to apply different translation algorithms depending on the category of the document. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can take document category data as input and translate documents using an AI model that applies different translation algorithms depending on the category.

[0045] The translation department can prioritize translations based on the submission date of the document. For example, it can quickly translate and prioritize urgent business documents. For example, it can translate periodic reports to meet their submission deadlines. It can also translate casual messages after other important documents have been completed. This makes it possible to prioritize translations based on the submission date of the document. Some or all of the above processes in the translation department may be performed using AI, for example, or not. For example, the translation department can take document submission date data as input and perform translations using an AI model that determines translation priorities based on the submission date.

[0046] The translation unit can adjust the order of translations based on the relevance of the texts during the translation process. For example, in important business documents, the unit will prioritize translating relevant documents. In academic papers, for example, the unit may prioritize translating relevant research and data. Furthermore, in casual messages, the unit may consider the flow of the conversation when translating. This makes it possible to adjust the order of translations based on the relevance of the texts. Some or all of the above processing in the translation unit may be performed using AI, for example, or not. For example, the translation unit can take text relevance data as input and perform translations using an AI model that adjusts the order of translations based on relevance.

[0047] The research department can optimize the current research by referring to past research data during the research process. For example, the research department can prioritize displaying relevant information based on what the user has researched in the past. For example, the research department can also prioritize displaying frequently researched themes based on the user's past research history. Furthermore, the research department can analyze the user's past research data and provide the most relevant information. This makes it possible to optimize the current research based on past research data. Some or all of the above processes in the research department may be performed using AI, for example, or not. For example, the research department can receive past research data as input and display the research results using an AI model that optimizes the current research.

[0048] The research department can apply different research methods to each category of words during the research process. For example, for technical terms, the research department can refer to specialized databases for its research. For example, for slang, the research department can refer to social media data for its research. Furthermore, for medical terms, the research department can refer to specialized medical databases for its research. This makes it possible to apply different research methods to each category of words. Some or all of the above processing in the research department may be performed using AI, for example, or not. For example, the research department can receive word category data as input and display the research results using an AI model that applies different research methods to each category.

[0049] The research department can analyze changes in the survey based on the timing of word introduction during the survey. For example, the research department can analyze changes in word usage frequency based on past data. The research department can also analyze changes in trends based on the timing of word introduction. Furthermore, the research department can analyze related trends based on the timing of word introduction. This makes it possible to analyze changes in the survey based on the timing of word introduction. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can receive word introduction timing data as input and display the survey results using an AI model that analyzes changes in the survey based on the introduction timing.

[0050] The research department can analyze the survey by referring to relevant market data for the words used during the survey. For example, the research department can analyze the frequency of use and trends based on the relevant market data for the words. The research department can also analyze related products and services based on the relevant market data for the words used. Furthermore, the research department can predict future trends based on the relevant market data for the words used. This makes it possible to analyze the survey by referring to relevant market data for the words used. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can receive relevant market data for words as input and display the survey results using an AI model that analyzes the survey based on the market data.

[0051] The link section can select the most suitable link by referring to the user's past activity history when displaying links. For example, the link section can prioritize displaying pages that the user has frequently accessed in the past as links. The link section can also suggest highly relevant links based on the user's past activity history. Furthermore, the link section can prioritize displaying pages that the user has previously bookmarked as links. This makes it possible to select the most suitable link based on past activity history. Some or all of the above processing in the link section may be performed using AI, for example, or without AI. For example, the link section can receive data on the user's past activity history as input and display links using an AI model that selects the most suitable link.

[0052] The link section can select the most suitable link when displaying links, taking into account the user's device information. For example, if the user is using a smartphone, the link section will prioritize displaying mobile-friendly links. If the user is using a tablet, the link section can also display links optimized for larger screens. Furthermore, if the user is using a desktop, the link section can display links containing detailed information. This makes it possible to select the most suitable link based on device information. Some or all of the above processing in the link section may be performed using AI, for example, or without AI. For example, the link section can receive the user's device information as input and display links using an AI model that selects the most suitable link for the device.

[0053] The link section can select the most suitable link when displaying links, taking into account the user's device information. For example, if the user is using a smartphone, the link section will prioritize displaying mobile-friendly links. If the user is using a tablet, the link section can also display links optimized for larger screens. Furthermore, if the user is using a desktop, the link section can display links containing detailed information. This makes it possible to select the most suitable link based on device information. Some or all of the above processing in the link section may be performed using AI, for example, or without AI. For example, the link section can receive the user's device information as input and display links using an AI model that selects the most suitable link for the device.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The writing support system can further learn the user's writing style and provide individually customized editing and proofreading. For example, it can learn the expressions and phrases the user frequently uses and suggest revisions based on that. It can also revise the writing to be more natural, taking into account the user's preferred style and tone. Furthermore, it can analyze the user's past writing history and provide advice on specific themes and topics. This allows users to create writing that suits their own style.

[0056] A writing assistance system can monitor a user's writing progress in real time and provide feedback at the appropriate time. For example, if a user is typing for a long time, the system can suggest a break. If a user is stuck on a particular section, the system can also provide specific advice on that section. Furthermore, after the user completes the document, it can provide feedback on the overall flow and structure. This allows users to write more efficiently.

[0057] A writing support system can suggest the optimal structure for a document according to the user's writing purpose. For example, in the case of a business document, the system can suggest a logical and clear structure. For casual messages, it can suggest a friendly and approachable structure. Furthermore, for academic papers, it can suggest a rigorous structure and citation methods. This allows users to create documents with an appropriate structure for their purpose.

[0058] A writing support system can analyze a user's writing frequency and patterns and provide reminders for writing at the optimal time. For example, if a user regularly updates their blog, the system can remind them when to update. Similarly, if a user reports on project progress, the system can remind them when to submit the report. Furthermore, if a user keeps a diary, the system can remind them to write in it. This allows users to write more efficiently.

[0059] A writing support system can suggest the most appropriate citations and references according to the user's writing purpose. For example, in the case of an academic paper, the system can suggest relevant research and data. In the case of a business document, the system can also suggest industry statistics and market analysis. Furthermore, in the case of a casual message, the system can suggest relevant articles and blogs. This allows users to use appropriate citations and references according to their purpose.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The editing section corrects and proofreads the text as you input it. For example, it corrects typos and grammatical errors. It can correct typos using a dictionary and also correct typos based on context. Furthermore, it applies grammatical rules to check grammar, detects grammatical errors, and suggests appropriate corrections. Step 2: The translation department translates the text that has been edited and proofread by the editing department. For example, it translates from Japanese to English and from English to Japanese. Neural network-based translation algorithms and rule-based translation algorithms are used to perform the translation and improve the accuracy of the translation by taking the context into consideration. Step 3: The research team investigates the meanings of the latest words and slang. For example, they might obtain the meaning of a word tapped by the user from a wiki. They can also obtain the meaning of a word by referring to a specific wiki site, or they can retrieve wiki data using an API. They apply the appropriate research method depending on the category of word the user wants to investigate. Step 4: The link section will navigate to the link as needed. For example, if the user wants to investigate specific information in more detail, it will suggest the appropriate email service page and allow the user to go directly there by clicking the link. It will suggest pages related to the information the user wants to investigate and select the most suitable link considering the user's past activity history and device information.

[0062] (Example of form 2) The text support system according to an embodiment of the present invention provides functions for editing, proofreading, and translating text in messaging apps and email services when users struggle with writing, make mistakes, or when foreigners have difficulty with translation. The text support system also has a function to display a Wiki when the meaning of the latest language or slang is not understood by tapping it. Furthermore, it also provides a function to move to a link on an email service page as needed. First, when a user enters text in a messaging app or email service, the AI ​​edits and proofreads the text in real time. For example, it corrects typos and grammatical errors and corrects the text to make it appropriate. It can also suggest more appropriate expressions and phrasing depending on the content of the text. This allows users to send text with confidence. Next, when foreigners have difficulty with translation, the AI ​​translates the text in real time. For example, it translates from Japanese to English or from English to Japanese and displays it in a format that is easy for the user to understand. This enables smooth communication across language barriers. Furthermore, if the meaning of the latest language or slang is not understood, the AI ​​automatically displays a Wiki when the user taps the word. For example, it allows users to easily obtain information when looking up the meaning of new slang or technical terms. This ensures that users always stay up-to-date. Finally, it also provides a function to navigate to links to email service pages as needed. For example, if a user wants to investigate specific information in more detail, the AI ​​will suggest the appropriate email service page, and they can be directly accessed by clicking the link. This allows users to efficiently gather information. In this way, the writing assistance system provides functions that enable users of messaging apps and email services to create accurate and appropriate sentences and easily obtain the latest information without struggling with writing.

[0063] The document support system according to this embodiment comprises an editing unit, a translation unit, a research unit, and a linking unit. The editing unit edits and proofreads the text when it is input. For example, the editing unit corrects typographical errors and checks grammar. For example, the editing unit corrects typographical errors using a dictionary. The editing unit can also correct typographical errors based on context. Furthermore, the editing unit checks grammar by applying grammatical rules. For example, the editing unit detects grammatical errors and suggests appropriate corrections. The translation unit translates the text that has been edited and proofread by the editing unit. For example, the translation unit translates from Japanese to English and from English to Japanese. For example, the translation unit uses a neural network-based translation algorithm to perform the translation. The translation unit can also use a rule-based translation algorithm to perform the translation. Furthermore, the translation unit considers the context to improve the accuracy of the translation. The research unit looks up the meanings of the latest words and slang. The research unit, for example, retrieves the meaning of a word tapped by the user from a wiki. The research unit retrieves the meaning of a word by referring to a specific wiki site, for example. The research unit can also retrieve wiki data using an API. Furthermore, the research unit applies an appropriate research method depending on the category of the word the user wants to investigate. The linking unit moves to links as needed. For example, if the user wants to investigate specific information in more detail, the linking unit suggests a page of an appropriate email service and moves directly to it by clicking the link. For example, the linking unit suggests pages related to the information the user wants to investigate. The linking unit can also select the optimal link by referring to the user's past operation history. Furthermore, the linking unit selects the optimal link considering the user's device information. As a result, the text support system according to the embodiment enables text editing and proofreading, translation, research, and link navigation.

[0064] The editing department corrects and proofreads text as it is entered. Specifically, it corrects typos and grammatical errors. For example, the editing department uses dictionaries to correct typos. These dictionaries include not only general word dictionaries but also specialized terminology dictionaries and user-customized dictionaries. This makes it possible to edit texts specific to particular fields or industries. The editing department can also correct typos based on context. For example, it analyzes the flow and meaning of the entire text to detect and correct words or phrases that do not fit the context. Furthermore, the editing department checks grammar by applying grammatical rules. These grammatical rules include not only basic grammatical rules but also style guides and rules based on specific formats. For example, it can perform grammatical checks suitable for business documents and academic papers. The editing department detects grammatical errors and suggests appropriate corrections. The suggested corrections can be reviewed and approved by the user, improving the quality of the final text. In addition, the editing department can use AI to evaluate the naturalness and fluency of the text and suggest areas for improvement. For example, using generative AI, it can suggest more natural expressions and appropriate vocabulary choices. This allows the editing function to go beyond simply correcting typos and grammatical errors, and instead support the overall improvement of the writing quality.

[0065] The translation department translates texts that have been edited and proofread by the editing department. Specifically, it performs translations from Japanese to English and from English to Japanese. The translation department uses neural network-based translation algorithms. Neural network-based translation algorithms learn from large amounts of data to achieve highly accurate translations. For example, a translation algorithm using a Transformer model provides natural translations that take context into account. The translation department can also perform translations using rule-based translation algorithms. Rule-based translation algorithms perform translations based on specific grammatical rules and lexical transformation rules, thus exhibiting high accuracy for specific fields and technical terms. Furthermore, the translation department considers context when translating to improve translation accuracy. For example, it analyzes the surrounding context and the meaning of the entire paragraph to provide an appropriate translation. The translation department can also use AI to evaluate the quality of translations and suggest corrections as needed. For example, it can use generative AI to evaluate the naturalness and fluency of the translation results and suggest areas for improvement. This allows the translation department to provide highly accurate and natural translations and to respond flexibly to user needs.

[0066] The research department investigates the meanings of the latest words and slang. Specifically, it retrieves the meaning of words tapped by users from wikis. The research department obtains the meaning of words by referring to specific wiki sites. For example, it uses general encyclopedia sites and sites that provide specialized knowledge. The research department can also obtain wiki data using APIs. By using APIs, it can obtain the latest information in real time and provide it to users. Furthermore, the research department applies appropriate research methods depending on the category of the word the user wants to research. For example, it provides more accurate information by referring to information sources that specialize in specific fields, such as technical terms or medical terms. The research department can also use AI to evaluate the reliability and relevance of research results and select the most optimal information. For example, it uses generative AI to integrate data obtained from multiple information sources and provide the most reliable information. In this way, the research department can provide users with the information they need quickly and accurately and support them in writing.

[0067] The Links section navigates to links as needed. Specifically, if the user wants to investigate specific information in more detail, it suggests the appropriate email service page, and clicking the link will take them directly to that page. The Links section suggests pages related to the information the user is looking for. For example, it can refer to websites that provide detailed information on a specific topic, or to related papers and articles. The Links section can also select the most suitable links by referring to the user's past activity history. This enables the provision of information based on the user's interests and preferences. Furthermore, the Links section selects the most suitable links considering the user's device information. For example, it provides the optimal display format and link destination depending on the device being used, such as a smartphone, tablet, or PC. The Links section can also use AI to analyze the user's behavior patterns and interests and suggest the most suitable links. For example, it can use generative AI to select highly relevant links based on the user's past search and browsing history. This allows the Links section to provide users with quick and appropriate information and improve the efficiency of writing.

[0068] The editing unit can correct typographical errors and perform grammatical checks. For example, the editing unit can correct typographical errors using a dictionary. The editing unit can also correct typographical errors based on context. Furthermore, the editing unit performs grammatical checks by applying grammatical rules. For example, the editing unit can detect grammatical errors and suggest appropriate corrections. This enables the correction of typographical errors and grammatical checks. Some or all of the above processes in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can receive text as input and perform editing and proofreading using an AI model that corrects typographical errors and performs grammatical checks.

[0069] The editing unit can suggest appropriate expressions and phrases depending on the content of the text. For example, the editing unit can suggest appropriate expressions and phrases based on the context. For example, the editing unit can also suggest appropriate expressions and phrases by applying a style guide. Furthermore, the editing unit can suggest even more appropriate expressions and phrases depending on the content of the text. This makes it possible to suggest appropriate expressions and phrases. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can take text as input and perform editing and proofreading of the text using an AI model that suggests appropriate expressions and phrases.

[0070] The translation unit can perform translations from Japanese to English and from English to Japanese. The translation unit can use, for example, a neural network-based translation algorithm. It can also use, for example, a rule-based translation algorithm. Furthermore, the translation unit can consider context to improve translation accuracy. This enables translation between Japanese and English. Some or all of the above-described processes in the translation unit may be performed using, for example, AI, or not. For example, the translation unit can take a text as input and translate it using an AI model that performs translations from Japanese to English and from English to Japanese.

[0071] The research unit can obtain the meaning of a word tapped by a user from a wiki. For example, the research unit can obtain the meaning of a word by referring to a specific wiki site. The research unit can also obtain wiki data using an API, for example. Furthermore, the research unit can apply an appropriate research method depending on the category of the word the user wants to investigate. This makes it possible to obtain the meaning of a tapped word from a wiki. Some or all of the above processing in the research unit may be performed using AI, for example, or not using AI. For example, the research unit can investigate the meaning of a word by receiving a word tapped by a user as input and using an AI model that obtains its meaning from a wiki.

[0072] The linking function suggests the appropriate email service page when the user wants to investigate specific information in more detail, and the user can navigate directly to the page by clicking the link. For example, the linking function suggests pages related to the information the user wants to investigate. The linking function can also select the optimal link by referring to the user's past activity history. Furthermore, the linking function can select the optimal link by considering the user's device information. This makes it possible to navigate to the appropriate page to investigate specific information in more detail. Some or all of the above processing in the linking function may be performed using AI, for example, or without AI. For example, the linking function can perform link navigation using an AI model that receives the information the user wants to investigate as input and suggests links to appropriate pages.

[0073] The editing unit can estimate the user's emotions and adjust the timing of editing based on the estimated emotions. For example, if the user is stressed, the editing unit can immediately edit the text using AI and provide rapid feedback. If the user is relaxed, the editing unit can also edit the text at regular intervals, allowing the user to review the text at their own pace. Furthermore, if the user is concentrating, the editing unit can edit the text all at once after it is completed, so as not to interrupt their concentration. This makes it possible to adjust the timing of editing based on 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 processing in the editing unit may be performed using AI or not. For example, the editing unit can receive user emotion data as input and perform editing and proofreading of text using an AI model that adjusts the timing of editing based on emotions.

[0074] The editing unit can analyze the user's past writing history and select the most suitable editing method. For example, the editing unit can prioritize checking grammar and expressions that the user has frequently made mistakes with in the past and suggest corrections. For example, the editing unit can also analyze expressions and styles that the user has used in the past and provide editing advice based on that. Furthermore, the editing unit can enhance editing on specific themes or topics based on the user's past writing history. This makes it possible to select the most suitable editing method based on past writing history. Some or all of the above processes in the editing unit may be performed using AI, for example, or not. For example, the editing unit can take the user's past writing history as input and use an AI model that selects the most suitable editing method to edit and proofread the text.

[0075] The editing unit can automatically edit technical terms and industry-specific expressions according to the content of the text. For example, in medical documents, the editing unit checks for the accurate use of technical terms and corrects them to appropriate expressions. In legal documents, for example, the editing unit can also check the accuracy of legal expressions and terminology and correct them as necessary. Furthermore, in technical documents, the editing unit can check the accuracy of technical terms and expressions and make appropriate corrections. This makes it possible to edit technical terms and industry-specific expressions. Some or all of the above processing in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can receive text as input and perform editing and proofreading using an AI model that automatically edits technical terms and industry-specific expressions.

[0076] The editing unit can estimate the user's emotions and determine editing priorities based on those emotions. For example, if the user is nervous, the editing unit can prioritize editing important parts to provide reassurance. If the user is relaxed, the editing unit can perform overall editing and check details. If the user is in a hurry, the editing unit can prioritize correcting major errors and provide quick feedback. This makes it possible to determine editing priorities based on 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 processing in the editing unit may be performed using AI or not. For example, the editing unit can receive user emotion data as input and perform editing and proofreading of text using an AI model that determines editing priorities based on emotions.

[0077] The editing unit can prioritize correcting region-specific expressions by taking into account the user's geographical location during the editing process. For example, if the user is in the United States, the editing unit can prioritize the use of American English expressions. If the user is in the United Kingdom, the editing unit can also prioritize the use of British English expressions. Furthermore, if the user is in Japan, the editing unit can prioritize the use of region-specific Japanese expressions. This makes it possible to correct region-specific expressions based on geographical location information. Some or all of the above processing in the editing unit may be performed using AI, for example, or without AI. For example, the editing unit can receive the user's geographical location information as input and use an AI model that prioritizes correcting region-specific expressions to edit and proofread the text.

[0078] The editing unit can analyze the user's social media activity during editing and suggest relevant expressions. For example, the editing unit can analyze the social media expressions the user frequently uses and make edits based on that. For example, the editing unit can also suggest appropriate expressions by referring to the expressions of influencers the user follows. Furthermore, the editing unit can analyze the content of the user's social media posts and suggest relevant expressions and phrases. This makes it possible to suggest relevant expressions based on social media activity. Some or all of the above processing in the editing unit may be performed using AI, for example, or not using AI. For example, the editing unit can receive the user's social media activity data as input and use an AI model that suggests relevant expressions to edit and proofread the text.

[0079] The translation unit can estimate the user's emotions and adjust the translation's expression based on those emotions. For example, if the user is nervous, the translation unit can provide a concise and clear translation. If the user is relaxed, the translation unit can also provide a detailed and polite translation. Furthermore, if the user is in a hurry, the translation unit can provide a quick and concise translation. This makes it possible to adjust the translation's expression based on 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 processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can receive user emotion data as input and translate text using an AI model that adjusts the translation's expression based on the emotion.

[0080] The translation unit can adjust the level of detail of the translation based on the importance of the text during the translation process. For example, the translation unit can provide a detailed and accurate translation for important business documents. For example, it can provide a concise and easy-to-understand translation for casual messages. Furthermore, in academic papers, the translation unit can accurately translate specialized terminology and provide detailed explanations. This makes it possible to adjust the level of detail of the translation based on the importance of the text. Some or all of the above processes in the translation unit may be performed using AI, for example, or not. For example, the translation unit can take text importance data as input and perform translation using an AI model that adjusts the level of detail of the translation based on importance.

[0081] The translation unit can apply different translation algorithms depending on the category of the document during translation. For example, the translation unit may use a translation algorithm specialized for technical terminology in technical documents. For example, the translation unit may also use a translation algorithm specialized for legal expressions in legal documents. Furthermore, the translation unit may use a translation algorithm specialized for medical terminology in medical documents. This makes it possible to apply different translation algorithms depending on the category of the document. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can take document category data as input and translate documents using an AI model that applies different translation algorithms depending on the category.

[0082] The translation unit can estimate the user's emotions and adjust the length of the translation based on the estimated emotions. For example, if the user is in a hurry, the translation unit can provide a short, concise translation. If the user is relaxed, the translation unit can provide a longer translation that includes detailed explanations. Furthermore, if the user is excited, the translation unit can provide a translation with visually stimulating effects. This makes it possible to adjust the length of the translation based on 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 processing in the translation unit may be performed using AI or not. For example, the translation unit can take user emotion data as input and translate text using an AI model that adjusts the length of the translation based on the emotions.

[0083] The translation department can prioritize translations based on the submission date of the document. For example, it can quickly translate and prioritize urgent business documents. For example, it can translate periodic reports to meet their submission deadlines. It can also translate casual messages after other important documents have been completed. This makes it possible to prioritize translations based on the submission date of the document. Some or all of the above processes in the translation department may be performed using AI, for example, or not. For example, the translation department can take document submission date data as input and perform translations using an AI model that determines translation priorities based on the submission date.

[0084] The translation unit can adjust the order of translations based on the relevance of the texts during the translation process. For example, in important business documents, the unit will prioritize translating relevant documents. In academic papers, for example, the unit may prioritize translating relevant research and data. Furthermore, in casual messages, the unit may consider the flow of the conversation when translating. This makes it possible to adjust the order of translations based on the relevance of the texts. Some or all of the above processing in the translation unit may be performed using AI, for example, or not. For example, the translation unit can take text relevance data as input and perform translations using an AI model that adjusts the order of translations based on relevance.

[0085] The research unit can estimate the user's emotions and adjust the way the survey is displayed based on the estimated emotions. For example, if the user is nervous, the research unit can provide a simple and highly visible display. For example, if the user is relaxed, the research unit can also provide a display that includes detailed information. Furthermore, if the user is in a hurry, the research unit can provide a concise display. This makes it possible to adjust the way the survey is displayed based on 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 processing in the research unit may be performed using AI, for example, or not using AI. For example, the research unit can receive user emotion data as input and display the survey results using an AI model that adjusts the way the survey is displayed based on the emotions.

[0086] The research department can optimize the current research by referring to past research data during the research process. For example, the research department can prioritize displaying relevant information based on what the user has researched in the past. For example, the research department can also prioritize displaying frequently researched themes based on the user's past research history. Furthermore, the research department can analyze the user's past research data and provide the most relevant information. This makes it possible to optimize the current research based on past research data. Some or all of the above processes in the research department may be performed using AI, for example, or not. For example, the research department can receive past research data as input and display the research results using an AI model that optimizes the current research.

[0087] The research department can apply different research methods to each category of words during the research process. For example, for technical terms, the research department can refer to specialized databases for its research. For example, for slang, the research department can refer to social media data for its research. Furthermore, for medical terms, the research department can refer to specialized medical databases for its research. This makes it possible to apply different research methods to each category of words. Some or all of the above processing in the research department may be performed using AI, for example, or not. For example, the research department can receive word category data as input and display the research results using an AI model that applies different research methods to each category.

[0088] The research unit can estimate the user's emotions and adjust the importance of the survey based on those emotions. For example, if the user is stressed, the research unit can prioritize displaying important information. If the user is relaxed, the research unit can also provide detailed information. Furthermore, if the user is in a hurry, the research unit can provide concise information. This makes it possible to adjust the importance of the survey based on 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 processing in the research unit may be performed using AI or not. For example, the research unit can receive user emotion data as input and display the survey results using an AI model that adjusts the importance of the survey based on emotions.

[0089] The research department can analyze changes in the survey based on the timing of word introduction during the survey. For example, the research department can analyze changes in word usage frequency based on past data. The research department can also analyze changes in trends based on the timing of word introduction. Furthermore, the research department can analyze related trends based on the timing of word introduction. This makes it possible to analyze changes in the survey based on the timing of word introduction. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can receive word introduction timing data as input and display the survey results using an AI model that analyzes changes in the survey based on the introduction timing.

[0090] The research department can analyze the survey by referring to relevant market data for the words used during the survey. For example, the research department can analyze the frequency of use and trends based on the relevant market data for the words. The research department can also analyze related products and services based on the relevant market data for the words used. Furthermore, the research department can predict future trends based on the relevant market data for the words used. This makes it possible to analyze the survey by referring to relevant market data for the words used. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can receive relevant market data for words as input and display the survey results using an AI model that analyzes the survey based on the market data.

[0091] The link section can estimate the user's emotions and adjust how links are displayed based on those emotions. For example, if the user is tense, the link section can provide a simple and highly visible link display method. If the user is relaxed, the link section can also provide a link display method that includes detailed information. Furthermore, if the user is in a hurry, the link section can provide a concise link display method. This makes it possible to adjust how links are displayed based on 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 processing described above in the link section may be performed using AI, for example, or not using AI. For example, the link section can display links using an AI model that receives user emotion data as input and adjusts how links are displayed based on the emotion.

[0092] The link section can select the most suitable link by referring to the user's past activity history when displaying links. For example, the link section can prioritize displaying pages that the user has frequently accessed in the past as links. The link section can also suggest highly relevant links based on the user's past activity history. Furthermore, the link section can prioritize displaying pages that the user has previously bookmarked as links. This makes it possible to select the most suitable link based on past activity history. Some or all of the above processing in the link section may be performed using AI, for example, or without AI. For example, the link section can receive data on the user's past activity history as input and display links using an AI model that selects the most suitable link.

[0093] The link section can select the most suitable link when displaying links, taking into account the user's device information. For example, if the user is using a smartphone, the link section will prioritize displaying mobile-friendly links. If the user is using a tablet, the link section can also display links optimized for larger screens. Furthermore, if the user is using a desktop, the link section can display links containing detailed information. This makes it possible to select the most suitable link based on device information. Some or all of the above processing in the link section may be performed using AI, for example, or without AI. For example, the link section can receive the user's device information as input and display links using an AI model that selects the most suitable link for the device.

[0094] The link unit can estimate the user's emotions and adjust the link's operation procedure based on the estimated user emotions. For example, if the user is nervous, the link unit can provide a simple and intuitive operation procedure. If the user is relaxed, the link unit can also provide a detailed operation procedure. Furthermore, if the user is in a hurry, the link unit can provide a procedure that allows for quick operation. This makes it possible to adjust the link's operation procedure based on 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 processing in the link unit may be performed using AI, for example, or without AI. For example, the link unit can receive user emotion data as input and provide the link's operation procedure using an AI model that adjusts the link's operation procedure based on the emotions.

[0095] The link section can select the most suitable link when displaying links, taking into account the user's device information. For example, if the user is using a smartphone, the link section will prioritize displaying mobile-friendly links. If the user is using a tablet, the link section can also display links optimized for larger screens. Furthermore, if the user is using a desktop, the link section can display links containing detailed information. This makes it possible to select the most suitable link based on device information. Some or all of the above processing in the link section may be performed using AI, for example, or without AI. For example, the link section can receive the user's device information as input and display links using an AI model that selects the most suitable link for the device.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] The writing support system can further learn the user's writing style and provide individually customized editing and proofreading. For example, it can learn the expressions and phrases the user frequently uses and suggest revisions based on that. It can also revise the writing to be more natural, taking into account the user's preferred style and tone. Furthermore, it can analyze the user's past writing history and provide advice on specific themes and topics. This allows users to create writing that suits their own style.

[0098] A text support system can estimate a user's emotions and adjust the tone of the text based on those emotions. For example, if the user is angry, the system will suggest a calmer, gentler tone. If the user is sad, it can suggest an encouraging or comforting tone. Furthermore, if the user is happy, it can suggest expressions that emphasize that emotion. This allows the system to create text with an appropriate tone that matches the user's emotions.

[0099] A writing assistance system can monitor a user's writing progress in real time and provide feedback at the appropriate time. For example, if a user is typing for a long time, the system can suggest a break. If a user is stuck on a particular section, the system can also provide specific advice on that section. Furthermore, after the user completes the document, it can provide feedback on the overall flow and structure. This allows users to write more efficiently.

[0100] A text support system can estimate a user's emotions and adjust the content of the text based on those emotions. For example, if the user is nervous, the system will suggest concise and clear content. If the user is relaxed, it can suggest detailed and polite content. Furthermore, if the user is in a hurry, it can suggest content that gets straight to the point. This allows for the creation of text with content appropriate to the user's emotions.

[0101] A writing support system can suggest the optimal structure for a document according to the user's writing purpose. For example, in the case of a business document, the system can suggest a logical and clear structure. For casual messages, it can suggest a friendly and approachable structure. Furthermore, for academic papers, it can suggest a rigorous structure and citation methods. This allows users to create documents with an appropriate structure for their purpose.

[0102] A text support system can estimate a user's emotions and adjust the length of the text based on those emotions. For example, if the user is in a hurry, the system will suggest a short, concise text. If the user is relaxed, it can suggest a longer text with more detailed explanations. Furthermore, if the user is excited, it can suggest text with visually stimulating effects. This allows for the creation of texts of appropriate length according to the user's emotions.

[0103] A writing support system can analyze a user's writing frequency and patterns and provide reminders for writing at the optimal time. For example, if a user regularly updates their blog, the system can remind them when to update. Similarly, if a user reports on project progress, the system can remind them when to submit the report. Furthermore, if a user keeps a diary, the system can remind them to write in it. This allows users to write more efficiently.

[0104] A text support system can estimate a user's emotions and adjust the writing style based on those emotions. For example, if the user is nervous, the system will suggest concise and clear language. If the user is relaxed, it can suggest detailed and polite language. Furthermore, if the user is in a hurry, it can suggest quick and concise language. This allows for the creation of text with appropriate language tailored to the user's emotions.

[0105] A writing support system can suggest the most appropriate citations and references according to the user's writing purpose. For example, in the case of an academic paper, the system can suggest relevant research and data. In the case of a business document, the system can also suggest industry statistics and market analysis. Furthermore, in the case of a casual message, the system can suggest relevant articles and blogs. This allows users to use appropriate citations and references according to their purpose.

[0106] The writing support system can estimate the user's emotions and prioritize the text based on those emotions. For example, if the user is stressed, it can prioritize editing important parts to provide reassurance. If the user is relaxed, it can perform overall editing and check details. Furthermore, if the user is in a hurry, it can prioritize correcting major errors and provide quick feedback. This allows the text to be edited with appropriate priorities according to the user's emotions.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The editing section corrects and proofreads the text as you input it. For example, it corrects typos and grammatical errors. It can correct typos using a dictionary and also correct typos based on context. Furthermore, it applies grammatical rules to check grammar, detects grammatical errors, and suggests appropriate corrections. Step 2: The translation department translates the text that has been edited and proofread by the editing department. For example, it translates from Japanese to English and from English to Japanese. Neural network-based translation algorithms and rule-based translation algorithms are used to perform the translation and improve the accuracy of the translation by taking the context into consideration. Step 3: The research team investigates the meanings of the latest words and slang. For example, they might obtain the meaning of a word tapped by the user from a wiki. They can also obtain the meaning of a word by referring to a specific wiki site, or they can retrieve wiki data using an API. They apply the appropriate research method depending on the category of word the user wants to investigate. Step 4: The link section will navigate to the link as needed. For example, if the user wants to investigate specific information in more detail, it will suggest the appropriate email service page and allow the user to go directly there by clicking the link. It will suggest pages related to the information the user wants to investigate and select the most suitable link considering the user's past activity history and device information.

[0109] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0110] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0111] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0112] Each of the multiple elements described above, including the editing unit, translation unit, research unit, and linking unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the editing unit is implemented by the control unit 46A of the smart device 14 and corrects typographical errors and grammatical mistakes in the text entered by the user. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and translates the text. The research unit is implemented by the control unit 46A of the smart device 14 and retrieves the meaning of a word tapped by the user from the Wiki. The linking unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides a link to a page related to the information the user wants to look up. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0116] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0117] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0119] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0120] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0121] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0122] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0123] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0124] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0125] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0127] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the editing unit, translation unit, research unit, and linking unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the editing unit is implemented by the control unit 46A of the smart glasses 214 and corrects typographical errors and grammatical mistakes in the text entered by the user. The translation unit is implemented by the identification processing unit 290 of the data processing unit 12 and translates the text. The research unit is implemented by the control unit 46A of the smart glasses 214 and retrieves the meaning of a word tapped by the user from the Wiki. The linking unit is implemented by the identification processing unit 290 of the data processing unit 12 and provides a link to a page related to the information the user wants to look up. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the editing unit, translation unit, research unit, and linking unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the editing unit is implemented by the control unit 46A of the headset terminal 314 and corrects typographical errors and grammatical mistakes in the text entered by the user. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and translates the text. The research unit is implemented by the control unit 46A of the headset terminal 314 and retrieves the meaning of a word tapped by the user from the Wiki. The linking unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides a link to a page related to the information the user wants to look up. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] As shown in Figure 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.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0153] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0158] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0159] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0160] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0161] Each of the multiple elements described above, including the editing unit, translation unit, research unit, and linking unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the editing unit is implemented by the control unit 46A of the robot 414 and corrects typographical errors and grammatical mistakes in the text entered by the user. The translation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and translates the text. The research unit is implemented by, for example, the control unit 46A of the robot 414 and retrieves the meaning of a word tapped by the user from the Wiki. The linking unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides a link to a page related to the information the user wants to look up. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0162] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0164] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0165] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0166] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0170] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0171] 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.

[0172] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0173] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0174] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0175] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0177] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0178] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0179] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0180] (Note 1) When typing text, The editing department is responsible for proofreading and correcting texts, A translation unit translates the text that has been edited and proofread by the aforementioned editing unit, A research department that investigates the meanings of the latest words and slang, It includes a link section that moves to the link as needed. A system characterized by the following features. (Note 2) The aforementioned editing unit is, Correct typos and grammatical errors. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned editing unit is, We will suggest appropriate expressions and phrases depending on the content of the text. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned translation department, We provide translation services from Japanese to English and from English to Japanese. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned investigation department, The meaning of the word the user tapped is retrieved from the Wiki. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned link section is If you want to look up specific information in more detail, we will suggest the appropriate email service page, and you can go there directly by clicking the link. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned editing unit is, The system estimates the user's emotions and adjusts the timing of editing based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned editing unit is, The system analyzes the user's past writing history and selects the most suitable editing method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned editing unit is, The system automatically corrects technical terms and industry-specific expressions based on the content of the text. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned editing unit is, The system estimates the user's emotions and determines the priority of editing based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned editing unit is, During editing, the system prioritizes correcting region-specific expressions by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned editing unit is, During the editing process, we analyze the user's social media activity and suggest relevant expressions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned translation department, It estimates the user's emotions and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned translation department, During translation, adjust the level of detail based on the importance of the text. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned translation department, During translation, different translation algorithms are applied depending on the category of the text. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned translation department, It estimates the user's sentiment and adjusts the translation length based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned translation department, During the translation process, translation priorities are determined based on the submission date of the documents. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned translation department, During translation, the order of translations is adjusted based on the relevance of the sentences. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned investigation department, We estimate the user's sentiment and adjust how the survey is displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned investigation department, During the survey, we refer to past survey data to optimize the current survey. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned investigation department, During the survey, different research methods will be applied to each category of words. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned investigation department, We estimate user sentiment and adjust the importance of the survey based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned investigation department, During the survey, we analyze changes in the survey based on when the words were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned investigation department, During the research, we analyze the research by referring to market data related to the term. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned link section is It estimates the user's sentiment and adjusts how links are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned link section is When displaying links, the system selects the most suitable link by referring to the user's past activity history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned link section is When displaying links, the system selects the most suitable link by considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned link section is It estimates the user's emotions and adjusts the link operation procedure based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned link section is When displaying links, the system selects the most suitable link by considering the user's device information. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. When typing text, The editing department is responsible for proofreading and correcting texts, A translation unit translates the text that has been edited and proofread by the aforementioned editing unit, A research department that investigates the meanings of the latest words and slang, It includes a link section that moves to the link as needed. A system characterized by the following features.

2. The aforementioned editing unit is, Correct typos and grammatical errors. The system according to feature 1.

3. The aforementioned editing unit is, We will suggest appropriate expressions and phrases depending on the content of the text. The system according to feature 1.

4. The aforementioned translation department, We provide translation services from Japanese to English and from English to Japanese. The system according to feature 1.

5. The aforementioned investigation department, The meaning of the word the user tapped is retrieved from the Wiki. The system according to feature 1.

6. The aforementioned link section is If you want to look up specific information in more detail, we will suggest the appropriate email service page, and you can go there directly by clicking the link. The system according to feature 1.

7. The aforementioned editing unit is, The system estimates the user's emotions and adjusts the timing of editing based on those emotions. The system according to feature 1.

8. The aforementioned editing unit is, The system analyzes the user's past writing history and selects the most suitable editing method. The system according to feature 1.

9. The aforementioned editing unit is, The system automatically corrects technical terms and industry-specific expressions based on the content of the text. The system according to feature 1.

10. The aforementioned editing unit is, The system estimates the user's emotions and determines the priority of editing based on those estimated emotions. The system according to feature 1.

Images