system

Abstract

The system according to this embodiment aims to accurately translate Japanese documents into English, taking into account context and industry-specific terminology. [Solution] The system according to the embodiment comprises a reception unit, a translation unit, an adjustment unit, an editing unit, and a learning unit. The reception unit receives Japanese documents as input. The translation unit analyzes the documents received by the reception unit and translates them into English, taking into account the context and industry-specific terminology. The adjustment unit adjusts the content translated by the translation unit to match the tone and purpose of the document. The editing unit allows the user to modify and edit the translation content adjusted by the adjustment unit. The learning unit learns the content modified by the editing unit and reflects it in subsequent translations.

Description

Technical Field

[0006] , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including 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 prior art, Japanese materials have not been accurately translated into English while fully considering the context and industry-specific terms, leaving room for improvement.

[0005] The system according to the embodiment aims to accurately translate Japanese materials into English while considering the context and industry-specific terms.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a translation unit, a coordination unit, an editing unit, and a learning unit. The reception unit receives Japanese documents as input. The translation unit analyzes the documents received by the reception unit and translates them into English, taking into account the context and industry-specific terminology. The coordination unit adjusts the content translated by the translation unit to match the tone and purpose of the document. The editing unit allows the user to modify and edit the translation content adjusted by the coordination unit. The learning unit learns the content modified by the editing unit and reflects it in subsequent translations. [Effects of the Invention]

[0007] The system according to this embodiment can accurately translate Japanese documents into English, taking into account context and industry-specific terminology. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also 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 translation system according to an embodiment of the present invention is a system in which a generating AI automatically translates documents created in Japanese into English. This translation system goes beyond simple translation, providing translations that accurately capture the context and industry-specific terminology. Furthermore, it adjusts the translation style to match the tone and purpose of the document, handling a wide range of content from formal business documents to casual content. Users can easily modify and edit the translation, and the generating AI also suggests and improves the translation. First, the user inputs a document created in Japanese. Next, the generating AI analyzes the input document and translates it into English, taking into account the context and industry-specific terminology. For example, in the case of a technical document, specialized terms and technical expressions are accurately translated. In the case of a business document, the translation uses appropriate expressions while maintaining a formal tone. The generating AI adjusts the translation style to match the tone and purpose of the document. For example, in the case of casual content, it uses friendly expressions. On the other hand, in the case of a formal business document, it uses formal expressions. As a result, the user can obtain an appropriate translation according to their purpose. Furthermore, the user can easily modify and edit the translation. The generation AI also suggests and improves the translation, allowing users to efficiently obtain high-quality translations. For example, if a user makes corrections to the content translated by the generation AI, the AI ​​learns from those corrections and incorporates them into subsequent translations. This mechanism allows users to easily translate documents created in Japanese into high-quality English. It provides translations that accurately capture context and industry-specific terminology, and adjusts the translation style to match the tone and purpose of the document, making it suitable for a wide range of documents, from formal business documents to casual content. Furthermore, it is easy to correct and edit, and the generation AI also suggests and improves the translation, allowing users to efficiently obtain high-quality translations. As a result, the translation system can efficiently translate Japanese documents into English and provide translations that accurately capture context and industry-specific terminology.

[0029] The translation system according to this embodiment comprises a reception unit, a translation unit, a coordination unit, an editing unit, and a learning unit. The reception unit receives Japanese documents as input. The reception unit has a function to upload, for example, documents created by users in Japanese. The reception unit can also scan paper documents and convert them into digital data. For example, the reception unit reads paper documents using a scanner and saves them as digital data. The reception unit can also receive documents using voice input. For example, the reception unit converts voice data into text data using speech recognition technology. The translation unit analyzes the documents input by the reception unit and translates them into English, taking into account the context and industry-specific terminology. The translation unit translates Japanese documents into English using, for example, a generative AI. The generative AI uses a text generation AI (e.g., LLM) to understand the context and perform an appropriate translation. The translation unit can also accurately translate specialized terms and technical expressions. For example, the translation unit accurately translates specialized terms in technical documents. The coordination unit adjusts the content translated by the translation unit to match the tone and purpose of the document. The adjustment unit adjusts the translation using formal language, for example, in the case of a formal business document. It can also adjust the translation using friendly language for casual content. For example, it adjusts the translation of a casual document, such as everyday conversation, using friendly language. The editing unit allows users to modify and edit the translation adjusted by the adjustment unit. For example, the editing unit allows users to review the translation and make corrections as needed. The editing unit also provides an interface for users to edit the translation. For example, the editing unit provides an intuitive editing tool so that users can easily modify and edit the translation. The learning unit learns from the corrections made by the editing unit and incorporates them into subsequent translations. For example, the learning unit learns from user corrections using machine learning algorithms. Based on the user's corrections, the learning unit can improve the accuracy of subsequent translations. For example, the learning unit saves the user's corrected translations in a database and incorporates them into subsequent translations.As a result, the translation system according to this embodiment can efficiently translate Japanese documents into English and provide translations that accurately capture the context and industry-specific terminology.

[0030] The reception desk receives input of Japanese documents. For example, the reception desk has a function to upload documents created by users in Japanese. Users can easily upload documents through a dedicated web portal or application. Uploaded documents are processed immediately within the system. The reception desk can also scan paper documents and convert them into digital data. For example, the reception desk uses a scanner to read paper documents and save them as digital data. The scanner performs high-resolution scanning and converts the data into text using OCR (Optical Character Recognition) technology. This digitizes paper documents, making them processable within the system. Furthermore, the reception desk can accept documents using voice input. For example, the reception desk uses speech recognition technology to convert speech data into text data. Users input Japanese voice through a microphone, and the system converts the voice into text in real time. The speech recognition technology removes background noise and corrects the speaker's accent, achieving highly accurate text conversion. This allows users to provide documents to the reception desk in various ways, and the system can process these documents efficiently.

[0031] The translation department analyzes the documents entered by the reception department and translates them into English, taking into account the context and industry-specific terminology. For example, the translation department uses generative AI to translate Japanese documents into English. The generative AI uses text generation AI (e.g., LLM) to understand the context and provide an appropriate translation. Specifically, the generative AI analyzes the input Japanese document, understanding its context and grammatical structure. It then generates appropriate English expressions, providing a natural translation. The generative AI is trained on a large dataset and can handle various contexts and industry-specific terminology. Furthermore, the translation department can accurately translate specialized terminology and technical expressions. For example, the translation department accurately translates specialized terminology in technical documents. The generative AI is trained using datasets specific to particular industries or fields, accurately understanding specialized terminology and technical expressions and providing appropriate translations. In addition, the translation department can combine multiple translation models to improve translation quality. This allows the translation department to provide high-quality, accurate translations that meet user needs.

[0032] The adjustment department adjusts the content translated by the translation department to match the tone and purpose of the document. For example, in the case of a formal business document, the adjustment department adjusts the translation using formal expressions. Specifically, in business documents, it uses honorifics and polite expressions to unify the tone of the entire document. The adjustment department can also adjust the translation using friendly expressions in the case of casual content. For example, for casual documents such as everyday conversations, the adjustment department adjusts the translation using friendly expressions. The adjustment department considers the purpose of the document and the characteristics of the recipient to select the most appropriate expression. Furthermore, the adjustment department unifies terminology and expressions to maintain consistency in the document. For example, if the same term is used in different expressions within the document, the adjustment department unifies them to maintain consistency throughout the document. In this way, the adjustment department ensures that the translated document is delivered in an appropriate tone that suits the purpose, and that the user's intent is accurately conveyed.

[0033] The editorial team allows users to modify and edit translations that have been adjusted by the adjustment team. For example, the editorial team allows users to review translations and make corrections as needed. Users can easily modify and edit translations through a dedicated editing interface. The editing interface is intuitive, allowing users to easily make corrections using drag-and-drop and click operations. The editorial team also provides an interface for users to edit translations. For example, the editorial team provides an intuitive editing tool to enable users to easily modify and edit translations. The editing tool displays the translation in real time, and changes made by the user are reflected immediately. Furthermore, the editorial team provides a function to save user corrections and apply them to future translations. This allows the editorial team to provide an environment where users can freely modify and edit translations, improving the quality of the final translated document.

[0034] The learning unit learns from the revisions made by the editorial unit and incorporates them into subsequent translations. For example, the learning unit uses machine learning algorithms to learn from user revisions. Specifically, the learning unit saves user-revisiond translations to a database and incorporates them into subsequent translations. The machine learning algorithms analyze user revision patterns and trends and predict where similar revisions will be needed in future translations. This allows the learning unit to provide translations tailored to the user's preferences and style. Furthermore, the learning unit continuously improves the translation model based on user feedback. For example, it improves translation accuracy by analyzing user feedback and adjusting the parameters of the translation model. This allows the learning unit to provide highly accurate translations that meet user needs and improve the overall system performance.

[0035] The translation department can accurately translate technical terms and expressions in technical documents. For example, the translation department accurately translates technical terms in technical documents. For example, the translation department accurately translates technical terms in patent documents. The translation department can also accurately translate technical expressions in technical specifications. For example, the translation department accurately translates the technical content described in technical specifications into English. The translation department can also accurately translate technical terms and expressions in technical reports. For example, the translation department accurately translates the technical content described in technical reports into English. This enables the accurate translation of technical terms and expressions in technical documents. Technical documents include, but are not limited to, patent documents, technical specifications, and technical reports. Technical terms and expressions include, but are not limited to, terms in a specific technical field.

[0036] The translation department can translate business documents using appropriate language while maintaining a formal tone. For example, in business documents, the translation department can translate contracts using formal language. The translation department can also translate reports using appropriate language while maintaining a formal tone. For example, in business reports, the translation department can translate formal language. The translation department can also translate official statements using appropriate language while maintaining a formal tone. For example, the translation department can translate the content of official statements into English using formal language. This allows for translation of business documents using appropriate language while maintaining a formal tone. Business documents include, but are not limited to, contracts, reports, and official statements. A formal tone includes, but is not limited to, the use of honorifics and formal language.

[0037] The translation tool can translate casual content using friendly language. For example, the translation tool translates casual content using friendly language. For example, the translation tool translates everyday conversation using friendly language. The translation tool can also translate informal emails using friendly language. For example, the translation tool translates emails between friends using friendly language. The translation tool can also translate casual blog posts using friendly language. For example, the translation tool translates the content of a casual blog post into English using friendly language. This allows for the use of friendly language in translations of casual content. Casual content includes, but is not limited to, everyday conversation, informal emails, and casual blog posts. Friendly language includes, but is not limited to, friendly language and simple expressions.

[0038] The Coordination Department can translate formal business documents using formal language. For example, the Coordination Department translates formal business documents using formal language. For example, the Coordination Department translates official statements using formal language. The Coordination Department can also translate corporate reports using formal language. For example, the Coordination Department translates corporate annual reports using formal language. The Coordination Department can also translate formal business letters using formal language. For example, the Coordination Department translates the contents of a formal business letter into English using formal language. This allows for the use of formal language in the translation of formal business documents. Formal business documents include, but are not limited to, official statements, corporate reports, and formal business letters. Formal language includes, but is not limited to, the use of honorifics and formal expressions.

[0039] The editorial team allows users to modify and edit translations. For example, the editorial team can allow users to review translations and make corrections as needed. The editorial team also provides an interface for users to edit translations. For example, the editorial team provides intuitive editing tools to allow users to easily modify and edit translations. For example, the editorial team provides tools for grammatical corrections and changes in expression. Furthermore, the editorial team can enable users to edit translations in real time. For example, the editorial team provides an interface that allows users to modify translations in real time and have the results reflected immediately. This enables users to modify and edit translations. Modifications and edits include, but are not limited to, grammatical corrections and changes in expression.

[0040] The learning unit can learn from user corrections and incorporate them into subsequent translations. For example, the learning unit can learn from user corrections using machine learning algorithms. Based on user corrections, the learning unit can improve the accuracy of subsequent translations. For example, the learning unit can save user-corrected translations to a database and incorporate them into subsequent translations. The learning unit can also analyze user corrections and optimize the translation algorithm. For example, the learning unit can adjust the parameters of the translation algorithm based on user corrections. This allows the learning unit to learn from user corrections and incorporate them into subsequent translations. Learning includes, but is not limited to, the use of machine learning algorithms and methods for incorporating feedback.

[0041] The reception desk can analyze a user's past document submission history and select the optimal submission method. For example, the reception desk can automatically recognize the format of documents that a user has frequently submitted in the past and prompt them to submit in the same format. The reception desk can also prioritize suggesting submission methods (online, offline, etc.) that the user has used in the past. For example, the reception desk can suggest online submission based on the user's past online submission history. The reception desk can also analyze a user's past submission history to suggest a submission time at a specific time. For example, the reception desk can suggest submitting at a specific time based on the user's past submission history at a specific time. This allows the reception desk to analyze a user's past document submission history and select the optimal submission method. Some or all of the above processes in the reception desk may be performed using AI, for example, or not. Optimal submission methods include, but are not limited to, online submission and in-person submission.

[0042] The reception system can filter materials upon receipt based on the user's current projects and areas of interest. For example, it can prioritize receiving materials related to the user's current projects. It can also automatically filter highly relevant materials based on the user's areas of interest. For example, it can prioritize receiving materials related to areas the user has shown interest in. Furthermore, it can prioritize receiving materials related to areas the user has shown interest in in the past. For example, it can prioritize receiving materials related to areas the user has shown interest in in the past. This allows for filtering materials based on the user's current projects and areas of interest. Some or all of the above processing in the reception system may be performed using AI, for example, or not. Filtering includes, but is not limited to, the type of project and the method of identifying areas of interest.

[0043] The reception desk can prioritize receiving highly relevant materials by considering the user's geographical location when receiving materials. For example, if the user is in a specific region, the reception desk will prioritize receiving materials related to that region. The reception desk can also prioritize receiving materials related to locations close to the user's current location. For example, the reception desk will prioritize receiving materials related to locations close to the user's current location. Furthermore, if the user is traveling, the reception desk can prioritize receiving materials related to their travel destination. For example, the reception desk will detect that the user is traveling and prioritize receiving materials related to their travel destination. This allows the reception desk to prioritize receiving highly relevant materials by considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. Geographical location information includes, but is not limited to, GPS data and IP addresses. Highly relevant materials include, but are not limited to, the user's areas of interest and past browsing history.

[0044] The reception desk can analyze a user's social media activity when receiving materials and accept relevant materials. For example, the reception desk can prioritize accepting relevant materials based on information shared by the user on social media. The reception desk can also analyze a user's social media activity history and accept highly relevant materials. For example, the reception desk can prioritize accepting relevant materials based on information shared by the user on social media. The reception desk can also prioritize accepting materials related to accounts that the user follows on social media. For example, the reception desk can prioritize accepting materials related to accounts that the user follows. This allows the reception desk to analyze a user's social media activity and accept relevant materials. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. Social media activity includes, but is not limited to, analysis of posts and followers.

[0045] The translation department can adjust the level of detail of the translation based on the importance of the material. For example, the translation department will provide a detailed translation for important material. Alternatively, the translation department can provide a standard translation for general material. For example, the translation department will provide a standard translation for general material. Alternatively, the translation department can provide a concise translation for simple material. For example, the translation department will provide a concise translation for simple material. This allows the level of detail of the translation to be adjusted based on the importance of the material. Some or all of the above processing in the translation department may be performed using, for example, generative AI, or not using generative AI. The importance of the material includes, but is not limited to, urgency and impact. The level of detail of the translation includes, but is not limited to, detailed explanations and concise summaries.

[0046] The translation unit can apply different translation algorithms depending on the category of the document during translation. For example, in the case of technical documents, the translation unit can apply a translation algorithm specialized in technical terminology. Similarly, in the case of business documents, the translation unit can apply a translation algorithm specialized in formal expressions. For example, the translation unit can apply a translation algorithm specialized in formal expressions to business documents. Similarly, in the case of casual documents, the translation unit can apply a translation algorithm specialized in friendly expressions. For example, the translation unit can apply a translation algorithm specialized in friendly expressions to casual documents. This allows for the application of 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, for example, generative AI, or not using generative AI. The categories of documents include, for example, technical documents, business documents, and casual documents, but are not limited to these examples. The translation algorithms include, for example, neural networks and rule-based translation, but are not limited to these examples.

[0047] The translation department can determine translation priorities based on the submission date of the materials. For example, it may prioritize urgent materials. For regular materials, it may prioritize them according to a standard order of priority. For example, it may prioritize regular materials according to a standard order of priority. It may also postpone the translation of materials with longer deadlines. For example, it may postpone the translation of materials with longer deadlines. This allows the translation department to determine translation priorities based on the submission date of the materials. Some or all of the above processing in the translation department may be performed using, for example, generative AI, or not. The submission date of the materials includes, but is not limited to, the submission date and time. Priorities include, but are not limited to, urgency and importance.

[0048] The translation unit can adjust the order of translations based on the relevance of the materials during the translation process. For example, the unit may prioritize translating materials that are highly relevant to other materials. Alternatively, the unit may translate materials in the normal order if they are independent. For example, the unit may detect that a material is independent and translate it in the normal order. Furthermore, the unit may postpone translating materials that are less relevant. For example, the unit may detect that a material is less relevant and postpone translating it. This allows the translation order to be adjusted based on the relevance of the materials. Some or all of the above processing in the translation unit may be performed using, for example, generative AI, or without generative AI. Relevance of materials includes, but is not limited to, similarity of content or matching of themes. The order of translation includes, but is not limited to, priority or relevance.

[0049] The adjustment unit can select the optimal adjustment method by referring to the document's past adjustment history during the adjustment process. For example, the adjustment unit can select the optimal adjustment method by referring to how similar documents have been adjusted in the past. The adjustment unit can also select the most effective adjustment method from the document's past adjustment history. For example, the adjustment unit can analyze the document's past adjustment history and propose the optimal adjustment method. This allows the adjustment unit to select the optimal adjustment method by referring to the document's past adjustment history. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without AI. Past adjustment history includes, but is not limited to, database referencing and history analysis. Optimal adjustment methods include, but are not limited to, user feedback and past success stories.

[0050] The adjustment unit can apply different adjustment methods depending on the category of the document during the adjustment process. For example, in the case of a technical document, the adjustment unit can apply an adjustment method specialized in technical terminology. Similarly, in the case of a business document, the adjustment unit can apply an adjustment method specialized in formal expression. For example, the adjustment unit can apply an adjustment method specialized in formal expression to a business document. Furthermore, in the case of a casual document, the adjustment unit can apply an adjustment method specialized in approachable expression. For example, the adjustment unit can apply an adjustment method specialized in approachable expression to a casual document. This allows for the application of different adjustment methods depending on the category of the document. Some or all of the above processing in the adjustment unit may be performed using, for example, AI, or not using AI. The categories of documents include, but are not limited to, technical documents, business documents, and casual documents. The adjustment methods include, but are not limited to, changes in writing style and revisions to expressions.

[0051] The coordination unit can change the order of coordination based on the submission timing of the documents. For example, the coordination unit will prioritize urgent documents. For regular documents, the coordination unit can also coordinate them in a standard order. For example, the coordination unit will coordinate regular documents in a standard order. The coordination unit can also postpone the coordination of documents with long deadlines. For example, the coordination unit will postpone the coordination of documents with long deadlines. This allows the order of coordination to be changed based on the submission timing of the documents. Some or all of the above processing in the coordination unit may be performed using AI, for example, or not using AI. The submission timing of documents includes, but is not limited to, the submission date and time. The order of coordination includes, but is not limited to, priority and relevance.

[0052] The adjustment unit can change its adjustment method based on the relevance of the materials during the adjustment process. For example, the adjustment unit may prioritize adjustments to materials that are highly relevant to other materials. It can also adjust materials in the usual way if they are independent. For example, the adjustment unit may detect that the materials are independent and adjust them in the usual way. Furthermore, the adjustment unit may postpone adjustments to materials that are less relevant. For example, the adjustment unit may detect that the materials are less relevant and postpone adjustments. This allows the adjustment method to be changed based on the relevance of the materials. Some or all of the above-described processes in the adjustment unit may be performed using AI, for example, or without AI. Relevance of materials includes, but is not limited to, similarity of content or matching of themes. Adjustment methods include, but are not limited to, changes in writing style or revisions of expression.

[0053] The editorial department can select the optimal editing method by referring to the document's past editing history during the editing process. For example, the editorial department can select the optimal editing method by referring to how similar documents have been edited in the past. Alternatively, the editorial department can select the most effective editing method from the document's past editing history. For example, the editorial department can analyze the document's past editing history and propose the optimal editing method. This allows the editorial department to select the optimal editing method by referring to the document's past editing history. Some or all of the above processes performed by the editorial department may be carried out using AI, for example, or not. Past editing history includes, but is not limited to, database referencing and history analysis. Optimal editing methods include, but are not limited to, user feedback and past success stories.

[0054] The editorial department may apply different editing techniques depending on the category of the material during editing. For example, in the case of technical documents, the editorial department may apply editing techniques specialized in technical terminology. Similarly, in the case of business documents, the editorial department may apply editing techniques specialized in formal expression. For example, the editorial department may apply editing techniques specialized in formal expression to business documents. Similarly, in the case of casual documents, the editorial department may apply editing techniques specialized in approachable expression. For example, the editorial department may apply editing techniques specialized in approachable expression to casual documents. This allows for the application of different editing techniques depending on the category of the material. Some or all of the above processing by the editorial department may be performed using AI, for example, or not using AI. The categories of materials include, but are not limited to, technical documents, business documents, and casual documents. The editing techniques include, but are not limited to, grammatical corrections and changes in expression.

[0055] The editorial department may change the editing order based on the submission date of the materials. For example, the editorial department may prioritize editing urgent materials. For regular materials, the editorial department may also edit them in a standard order. For example, the editorial department may edit regular materials in a standard order. The editorial department may also postpone editing materials with long deadlines. For example, the editorial department may postpone editing materials with long deadlines. This allows the editing order to be changed based on the submission date of the materials. Some or all of the above processes by the editorial department may be performed using AI, for example, or not. The submission date of the materials includes, but is not limited to, the submission date and time. The editing order includes, but is not limited to, priority and relevance.

[0056] The editorial department may change its editing method based on the relevance of the materials during the editing process. For example, the editorial department may prioritize editing materials that are highly relevant to other materials. Alternatively, the editorial department may edit materials in the usual way if they are independent. For example, the editorial department may detect that a material is independent and edit it in the usual way. Furthermore, the editorial department may postpone editing materials that are less relevant. For example, the editorial department may detect that a material is less relevant and postpone editing it. This allows the editorial department to change its editing method based on the relevance of the materials. Some or all of the above processes performed by the editorial department may be carried out using AI, for example, or not. Relevance of materials includes, but is not limited to, similarity of content or matching of themes. Editing methods include, but are not limited to, changes in writing style or revisions of expression.

[0057] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal learning algorithm. The learning unit can also extract effective learning patterns from past learning data and optimize the algorithm. For example, the learning unit can adjust the parameters of the learning algorithm based on past learning data. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. Past learning data includes, but is not limited to, database lookups and historical analysis. Learning algorithms include, but are not limited to, neural networks and rule-based learning.

[0058] The learning unit can apply different learning methods depending on the category of the material during learning. For example, in the case of technical documents, the learning unit can apply a learning method specialized in technical terminology. Similarly, in the case of business documents, the learning unit can apply a learning method specialized in formal expressions. For example, the learning unit can apply a learning method specialized in formal expressions to business documents. Furthermore, in the case of casual documents, the learning unit can apply a learning method specialized in friendly expressions. For example, the learning unit can apply a learning method specialized in friendly expressions to casual documents. This allows for the application of different learning methods depending on the category of the material. Some or all of the processing described above in the learning unit may be performed using AI, for example, or without AI. The categories of materials include, but are not limited to, technical documents, business documents, and casual documents. The learning methods include, but are not limited to, neural networks and rule-based learning.

[0059] The learning unit can weight the training data based on the submission timing of the materials during training. For example, the learning unit can set a higher weight for urgent materials. The learning unit can also train with a standard weight for regular materials. For example, the learning unit can train with a standard weight for regular materials. The learning unit can also set a lower weight for materials with longer deadlines. For example, the learning unit can set a lower weight for materials with longer deadlines. This allows the learning unit to weight the training data based on the submission timing of the materials. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. The submission timing of the materials includes, but is not limited to, the submission date and submission time. The weighting of the training data includes, but is not limited to, high weighting, standard weighting, and low weighting.

[0060] The learning unit can select training data based on the relevance of the materials during training. For example, the learning unit will prioritize selecting materials as training data if they are highly relevant to other materials. The learning unit can also select materials as training data in the usual way if they are independent. For example, the learning unit will detect that the materials are independent and select them as training data in the usual way. The learning unit can also postpone selecting materials as training data if they are not highly relevant. For example, the learning unit will detect that the materials are not highly relevant and postpone selecting them as training data. This allows for the selection of training data based on the relevance of the materials. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. The relevance of materials includes, but is not limited to, similarity of content or matching of themes. The training data includes, but is not limited to, highly relevant data, normal data, or unrelevant data.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The translation system can further analyze the user's past translation history and suggest the optimal translation style. For example, it can learn the expressions and styles the user has preferred to use in the past and translate based on that. Furthermore, if the user requests translations specific to a particular industry or field, the system can prioritize the use of terminology and expressions relevant to that field. This allows for more personalized translations based on the user's past translation history.

[0063] The translation system can also take the user's geographical location into consideration when performing translations. For example, if the user is in a specific region, it will prioritize the use of terminology and expressions related to that region. Furthermore, if the user is traveling, it can provide translations that include information related to their travel destination. This allows for more relevant translations based on the user's geographical location.

[0064] The translation system can further analyze the user's social media activity and provide relevant translations. For example, it can prioritize the use of relevant terminology and expressions based on information the user has shared on social media. It can also provide translations that include information related to the accounts the user follows. This allows for more relevant translations based on the user's social media activity.

[0065] The translation system can further perform translations based on the user's current projects and areas of interest. For example, it can prioritize the use of terminology and expressions related to the user's current projects. It can also provide translations that include highly relevant information based on the user's areas of interest. This allows for the provision of more relevant translations based on the user's current projects and areas of interest.

[0066] The translation system can further analyze the user's past document submission history and select the most suitable translation method. For example, it can automatically recognize the format of documents the user has frequently submitted in the past and prompt translation in the same format. It can also prioritize suggesting the submission method the user has used in the past (online, offline, etc.). This allows for the provision of more efficient translation methods based on the user's past document submission history.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The reception desk inputs Japanese documents. For example, it has a function to upload documents created by users in Japanese, and it can also scan paper documents and convert them into digital data. It can also accept documents using voice input, and uses speech recognition technology to convert the voice data into text data. Step 2: The translation department analyzes the documents submitted by the reception department and translates them into English, taking into account the context and industry-specific terminology. For example, it uses generative AI to translate Japanese documents into English, accurately translating specialized terms and technical expressions. Step 3: The adjustment team adjusts the content translated by the translation team to match the tone and purpose of the document. For example, they adjust the translation to use formal language for formal business documents and friendly language for casual content. Step 4: The editorial team allows users to modify and edit the translations that have been adjusted by the adjustment team. For example, they provide an intuitive editing tool so that users can review the translations and make corrections as needed. Step 5: The learning unit learns from the revisions made by the editorial unit and incorporates them into future translations. For example, it uses machine learning algorithms to learn from user revisions and improve the accuracy of future translations.

[0069] (Example of form 2) The translation system according to an embodiment of the present invention is a system in which a generating AI automatically translates documents created in Japanese into English. This translation system goes beyond simple translation, providing translations that accurately capture the context and industry-specific terminology. Furthermore, it adjusts the translation style to match the tone and purpose of the document, handling a wide range of content from formal business documents to casual content. Users can easily modify and edit the translation, and the generating AI also suggests and improves the translation. First, the user inputs a document created in Japanese. Next, the generating AI analyzes the input document and translates it into English, taking into account the context and industry-specific terminology. For example, in the case of a technical document, specialized terms and technical expressions are accurately translated. In the case of a business document, the translation uses appropriate expressions while maintaining a formal tone. The generating AI adjusts the translation style to match the tone and purpose of the document. For example, in the case of casual content, it uses friendly expressions. On the other hand, in the case of a formal business document, it uses formal expressions. As a result, the user can obtain an appropriate translation according to their purpose. Furthermore, the user can easily modify and edit the translation. The generation AI also suggests and improves the translation, allowing users to efficiently obtain high-quality translations. For example, if a user makes corrections to the content translated by the generation AI, the AI ​​learns from those corrections and incorporates them into subsequent translations. This mechanism allows users to easily translate documents created in Japanese into high-quality English. It provides translations that accurately capture context and industry-specific terminology, and adjusts the translation style to match the tone and purpose of the document, making it suitable for a wide range of documents, from formal business documents to casual content. Furthermore, it is easy to correct and edit, and the generation AI also suggests and improves the translation, allowing users to efficiently obtain high-quality translations. As a result, the translation system can efficiently translate Japanese documents into English and provide translations that accurately capture context and industry-specific terminology.

[0070] The translation system according to this embodiment comprises a reception unit, a translation unit, a coordination unit, an editing unit, and a learning unit. The reception unit receives Japanese documents as input. The reception unit has a function to upload, for example, documents created by users in Japanese. The reception unit can also scan paper documents and convert them into digital data. For example, the reception unit reads paper documents using a scanner and saves them as digital data. The reception unit can also receive documents using voice input. For example, the reception unit converts voice data into text data using speech recognition technology. The translation unit analyzes the documents input by the reception unit and translates them into English, taking into account the context and industry-specific terminology. The translation unit translates Japanese documents into English using, for example, a generative AI. The generative AI uses a text generation AI (e.g., LLM) to understand the context and perform an appropriate translation. The translation unit can also accurately translate specialized terms and technical expressions. For example, the translation unit accurately translates specialized terms in technical documents. The coordination unit adjusts the content translated by the translation unit to match the tone and purpose of the document. The adjustment unit adjusts the translation using formal language, for example, in the case of a formal business document. It can also adjust the translation using friendly language for casual content. For example, it adjusts the translation of a casual document, such as everyday conversation, using friendly language. The editing unit allows users to modify and edit the translation adjusted by the adjustment unit. For example, the editing unit allows users to review the translation and make corrections as needed. The editing unit also provides an interface for users to edit the translation. For example, the editing unit provides an intuitive editing tool so that users can easily modify and edit the translation. The learning unit learns from the corrections made by the editing unit and incorporates them into subsequent translations. For example, the learning unit learns from user corrections using machine learning algorithms. Based on the user's corrections, the learning unit can improve the accuracy of subsequent translations. For example, the learning unit saves the user's corrected translations in a database and incorporates them into subsequent translations.As a result, the translation system according to this embodiment can efficiently translate Japanese documents into English and provide translations that accurately capture the context and industry-specific terminology.

[0071] The reception desk receives input of Japanese documents. For example, the reception desk has a function to upload documents created by users in Japanese. Users can easily upload documents through a dedicated web portal or application. Uploaded documents are processed immediately within the system. The reception desk can also scan paper documents and convert them into digital data. For example, the reception desk uses a scanner to read paper documents and save them as digital data. The scanner performs high-resolution scanning and converts the data into text using OCR (Optical Character Recognition) technology. This digitizes paper documents, making them processable within the system. Furthermore, the reception desk can accept documents using voice input. For example, the reception desk uses speech recognition technology to convert speech data into text data. Users input Japanese voice through a microphone, and the system converts the voice into text in real time. The speech recognition technology removes background noise and corrects the speaker's accent, achieving highly accurate text conversion. This allows users to provide documents to the reception desk in various ways, and the system can process these documents efficiently.

[0072] The translation department analyzes the documents entered by the reception department and translates them into English, taking into account the context and industry-specific terminology. For example, the translation department uses generative AI to translate Japanese documents into English. The generative AI uses text generation AI (e.g., LLM) to understand the context and provide an appropriate translation. Specifically, the generative AI analyzes the input Japanese document, understanding its context and grammatical structure. It then generates appropriate English expressions, providing a natural translation. The generative AI is trained on a large dataset and can handle various contexts and industry-specific terminology. Furthermore, the translation department can accurately translate specialized terminology and technical expressions. For example, the translation department accurately translates specialized terminology in technical documents. The generative AI is trained using datasets specific to particular industries or fields, accurately understanding specialized terminology and technical expressions and providing appropriate translations. In addition, the translation department can combine multiple translation models to improve translation quality. This allows the translation department to provide high-quality, accurate translations that meet user needs.

[0073] The adjustment department adjusts the content translated by the translation department to match the tone and purpose of the document. For example, in the case of a formal business document, the adjustment department adjusts the translation using formal expressions. Specifically, in business documents, it uses honorifics and polite expressions to unify the tone of the entire document. The adjustment department can also adjust the translation using friendly expressions in the case of casual content. For example, for casual documents such as everyday conversations, the adjustment department adjusts the translation using friendly expressions. The adjustment department considers the purpose of the document and the characteristics of the recipient to select the most appropriate expression. Furthermore, the adjustment department unifies terminology and expressions to maintain consistency in the document. For example, if the same term is used in different expressions within the document, the adjustment department unifies them to maintain consistency throughout the document. In this way, the adjustment department ensures that the translated document is delivered in an appropriate tone that suits the purpose, and that the user's intent is accurately conveyed.

[0074] The editorial team allows users to modify and edit translations that have been adjusted by the adjustment team. For example, the editorial team allows users to review translations and make corrections as needed. Users can easily modify and edit translations through a dedicated editing interface. The editing interface is intuitive, allowing users to easily make corrections using drag-and-drop and click operations. The editorial team also provides an interface for users to edit translations. For example, the editorial team provides an intuitive editing tool to enable users to easily modify and edit translations. The editing tool displays the translation in real time, and changes made by the user are reflected immediately. Furthermore, the editorial team provides a function to save user corrections and apply them to future translations. This allows the editorial team to provide an environment where users can freely modify and edit translations, improving the quality of the final translated document.

[0075] The learning unit learns from the revisions made by the editorial unit and incorporates them into subsequent translations. For example, the learning unit uses machine learning algorithms to learn from user revisions. Specifically, the learning unit saves user-revisiond translations to a database and incorporates them into subsequent translations. The machine learning algorithms analyze user revision patterns and trends and predict where similar revisions will be needed in future translations. This allows the learning unit to provide translations tailored to the user's preferences and style. Furthermore, the learning unit continuously improves the translation model based on user feedback. For example, it improves translation accuracy by analyzing user feedback and adjusting the parameters of the translation model. This allows the learning unit to provide highly accurate translations that meet user needs and improve the overall system performance.

[0076] The translation department can accurately translate technical terms and expressions in technical documents. For example, the translation department accurately translates technical terms in technical documents. For example, the translation department accurately translates technical terms in patent documents. The translation department can also accurately translate technical expressions in technical specifications. For example, the translation department accurately translates the technical content described in technical specifications into English. The translation department can also accurately translate technical terms and expressions in technical reports. For example, the translation department accurately translates the technical content described in technical reports into English. This enables the accurate translation of technical terms and expressions in technical documents. Technical documents include, but are not limited to, patent documents, technical specifications, and technical reports. Technical terms and expressions include, but are not limited to, terms in a specific technical field.

[0077] The translation department can translate business documents using appropriate language while maintaining a formal tone. For example, in business documents, the translation department can translate contracts using formal language. The translation department can also translate reports using appropriate language while maintaining a formal tone. For example, in business reports, the translation department can translate formal language. The translation department can also translate official statements using appropriate language while maintaining a formal tone. For example, the translation department can translate the content of official statements into English using formal language. This allows for translation of business documents using appropriate language while maintaining a formal tone. Business documents include, but are not limited to, contracts, reports, and official statements. A formal tone includes, but is not limited to, the use of honorifics and formal language.

[0078] The translation tool can translate casual content using friendly language. For example, the translation tool translates casual content using friendly language. For example, the translation tool translates everyday conversation using friendly language. The translation tool can also translate informal emails using friendly language. For example, the translation tool translates emails between friends using friendly language. The translation tool can also translate casual blog posts using friendly language. For example, the translation tool translates the content of a casual blog post into English using friendly language. This allows for the use of friendly language in translations of casual content. Casual content includes, but is not limited to, everyday conversation, informal emails, and casual blog posts. Friendly language includes, but is not limited to, friendly language and simple expressions.

[0079] The Coordination Department can translate formal business documents using formal language. For example, the Coordination Department translates formal business documents using formal language. For example, the Coordination Department translates official statements using formal language. The Coordination Department can also translate corporate reports using formal language. For example, the Coordination Department translates corporate annual reports using formal language. The Coordination Department can also translate formal business letters using formal language. For example, the Coordination Department translates the contents of a formal business letter into English using formal language. This allows for the use of formal language in the translation of formal business documents. Formal business documents include, but are not limited to, official statements, corporate reports, and formal business letters. Formal language includes, but is not limited to, the use of honorifics and formal expressions.

[0080] The editorial team allows users to modify and edit translations. For example, the editorial team can allow users to review translations and make corrections as needed. The editorial team also provides an interface for users to edit translations. For example, the editorial team provides intuitive editing tools to allow users to easily modify and edit translations. For example, the editorial team provides tools for grammatical corrections and changes in expression. Furthermore, the editorial team can enable users to edit translations in real time. For example, the editorial team provides an interface that allows users to modify translations in real time and have the results reflected immediately. This enables users to modify and edit translations. Modifications and edits include, but are not limited to, grammatical corrections and changes in expression.

[0081] The learning unit can learn from user corrections and incorporate them into subsequent translations. For example, the learning unit can learn from user corrections using machine learning algorithms. Based on user corrections, the learning unit can improve the accuracy of subsequent translations. For example, the learning unit can save user-corrected translations to a database and incorporate them into subsequent translations. The learning unit can also analyze user corrections and optimize the translation algorithm. For example, the learning unit can adjust the parameters of the translation algorithm based on user corrections. This allows the learning unit to learn from user corrections and incorporate them into subsequent translations. Learning includes, but is not limited to, the use of machine learning algorithms and methods for incorporating feedback.

[0082] The reception desk can estimate the user's emotions and adjust the timing of document submission based on the estimated emotions. For example, if the user is stressed, the reception desk can immediately accept the document and begin processing it quickly. The reception desk can also suggest the optimal time for the user to submit the document if the user is relaxed. For example, the reception desk can analyze the user's relaxed periods and suggest submitting the document during those times. Furthermore, if the user is in a hurry, the reception desk can prioritize accepting the document and postpone other processing. For example, the reception desk can detect that the user is in a hurry using an emotion estimation algorithm and prioritize accepting urgent documents. This allows for adjustment of the document submission timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, stress, relaxation, and urgency. Submission timing includes, but is not limited to, time of day and user situation.

[0083] The reception desk can analyze a user's past document submission history and select the optimal submission method. For example, the reception desk can automatically recognize the format of documents that a user has frequently submitted in the past and prompt them to submit in the same format. The reception desk can also prioritize suggesting submission methods (online, offline, etc.) that the user has used in the past. For example, the reception desk can suggest online submission based on the user's past online submission history. The reception desk can also analyze a user's past submission history to suggest a submission time at a specific time. For example, the reception desk can suggest submitting at a specific time based on the user's past submission history at a specific time. This allows the reception desk to analyze a user's past document submission history and select the optimal submission method. Some or all of the above processes in the reception desk may be performed using AI, for example, or not. Optimal submission methods include, but are not limited to, online submission and in-person submission.

[0084] The reception system can filter materials upon receipt based on the user's current projects and areas of interest. For example, it can prioritize receiving materials related to the user's current projects. It can also automatically filter highly relevant materials based on the user's areas of interest. For example, it can prioritize receiving materials related to areas the user has shown interest in. Furthermore, it can prioritize receiving materials related to areas the user has shown interest in in the past. For example, it can prioritize receiving materials related to areas the user has shown interest in in the past. This allows for filtering materials based on the user's current projects and areas of interest. Some or all of the above processing in the reception system may be performed using AI, for example, or not. Filtering includes, but is not limited to, the type of project and the method of identifying areas of interest.

[0085] The reception desk can estimate the user's emotions and determine the priority of the documents to be received based on the estimated emotions. For example, if the user is stressed, the reception desk will prioritize important documents. Conversely, if the user is relaxed, the reception desk can also accept documents with normal priority. For example, the reception desk can detect that the user is relaxed using an emotion estimation algorithm and accept documents with normal priority. Furthermore, if the user is in a hurry, the reception desk can prioritize highly urgent documents. For example, the reception desk can detect that the user is in a hurry using an emotion estimation algorithm and accept highly urgent documents with highest priority. This allows for the prioritization of documents based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, stress, relaxation, and urgency. Prioritization includes, but is not limited to, urgency and importance.

[0086] The reception desk can prioritize receiving highly relevant materials by considering the user's geographical location when receiving materials. For example, if the user is in a specific region, the reception desk will prioritize receiving materials related to that region. The reception desk can also prioritize receiving materials related to locations close to the user's current location. For example, the reception desk will prioritize receiving materials related to locations close to the user's current location. Furthermore, if the user is traveling, the reception desk can prioritize receiving materials related to their travel destination. For example, the reception desk will detect that the user is traveling and prioritize receiving materials related to their travel destination. This allows the reception desk to prioritize receiving highly relevant materials by considering the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. Geographical location information includes, but is not limited to, GPS data and IP addresses. Highly relevant materials include, but are not limited to, the user's areas of interest and past browsing history.

[0087] The reception desk can analyze a user's social media activity when receiving materials and accept relevant materials. For example, the reception desk can prioritize accepting relevant materials based on information shared by the user on social media. The reception desk can also analyze a user's social media activity history and accept highly relevant materials. For example, the reception desk can prioritize accepting relevant materials based on information shared by the user on social media. The reception desk can also prioritize accepting materials related to accounts that the user follows on social media. For example, the reception desk can prioritize accepting materials related to accounts that the user follows. This allows the reception desk to analyze a user's social media activity and accept relevant materials. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. Social media activity includes, but is not limited to, analysis of posts and followers.

[0088] The translation unit can estimate the user's emotions and adjust the translation's expression based on the estimated emotions. For example, if the user is relaxed, the translation unit will use friendly language. Conversely, if the user is tense, the translation unit can use formal language. For example, if the emotion estimation algorithm detects that the user is tense, the translation unit will use formal language. Furthermore, if the user is in a hurry, the translation unit can use concise and to-the-point language. For example, if the emotion estimation algorithm detects that the user is in a hurry, the translation unit will use concise and to-the-point language. This allows the translation's expression to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, relaxed, tense, or in a hurry. Methods of expression include, but are not limited to, changes in word choice or writing style.

[0089] The translation department can adjust the level of detail of the translation based on the importance of the material. For example, the translation department will provide a detailed translation for important material. Alternatively, the translation department can provide a standard translation for general material. For example, the translation department will provide a standard translation for general material. Alternatively, the translation department can provide a concise translation for simple material. For example, the translation department will provide a concise translation for simple material. This allows the level of detail of the translation to be adjusted based on the importance of the material. Some or all of the above processing in the translation department may be performed using, for example, generative AI, or not using generative AI. The importance of the material includes, but is not limited to, urgency and impact. The level of detail of the translation includes, but is not limited to, detailed explanations and concise summaries.

[0090] The translation unit can apply different translation algorithms depending on the category of the document during translation. For example, in the case of technical documents, the translation unit can apply a translation algorithm specialized in technical terminology. Similarly, in the case of business documents, the translation unit can apply a translation algorithm specialized in formal expressions. For example, the translation unit can apply a translation algorithm specialized in formal expressions to business documents. Similarly, in the case of casual documents, the translation unit can apply a translation algorithm specialized in friendly expressions. For example, the translation unit can apply a translation algorithm specialized in friendly expressions to casual documents. This allows for the application of 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, for example, generative AI, or not using generative AI. The categories of documents include, for example, technical documents, business documents, and casual documents, but are not limited to these examples. The translation algorithms include, for example, neural networks and rule-based translation, but are not limited to these examples.

[0091] The translation unit can estimate the user's emotions and adjust the translation length based on the estimated emotions. For example, if the user is in a hurry, the translation unit will provide a short, concise translation. Alternatively, if the user is relaxed, the translation unit can provide a longer translation with more detailed explanations. For example, if the emotion estimation algorithm detects that the user is relaxed, the translation unit will provide a longer translation with more detailed explanations. Furthermore, if the user is excited, the translation unit can provide a translation with visually stimulating effects. For example, if the emotion estimation algorithm detects that the user is excited, the translation unit will provide a translation with visually stimulating effects. This allows the translation length to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, being in a hurry, relaxed, or excited. Translation length includes, but is not limited to, the number of characters or pages.

[0092] The translation department can determine translation priorities based on the submission date of the materials. For example, it may prioritize urgent materials. For regular materials, it may prioritize them according to a standard order of priority. For example, it may prioritize regular materials according to a standard order of priority. It may also postpone the translation of materials with longer deadlines. For example, it may postpone the translation of materials with longer deadlines. This allows the translation department to determine translation priorities based on the submission date of the materials. Some or all of the above processing in the translation department may be performed using, for example, generative AI, or not. The submission date of the materials includes, but is not limited to, the submission date and time. Priorities include, but are not limited to, urgency and importance.

[0093] The translation unit can adjust the order of translations based on the relevance of the materials during the translation process. For example, the unit may prioritize translating materials that are highly relevant to other materials. Alternatively, the unit may translate materials in the normal order if they are independent. For example, the unit may detect that a material is independent and translate it in the normal order. Furthermore, the unit may postpone translating materials that are less relevant. For example, the unit may detect that a material is less relevant and postpone translating it. This allows the translation order to be adjusted based on the relevance of the materials. Some or all of the above processing in the translation unit may be performed using, for example, generative AI, or without generative AI. Relevance of materials includes, but is not limited to, similarity of content or matching of themes. The order of translation includes, but is not limited to, priority or relevance.

[0094] The adjustment unit can estimate the user's emotions and change the adjustment method based on the estimated emotions. For example, if the user is relaxed, the adjustment unit will use friendly language. It can also adjust using formal language if the user is tense. For example, the adjustment unit can detect that the user is tense using an emotion estimation algorithm and adjust using formal language. Furthermore, if the user is in a hurry, the adjustment unit can adjust using concise and to-the-point language. For example, the adjustment unit can detect that the user is in a hurry using an emotion estimation algorithm and adjust using concise and to-the-point language. This allows the adjustment method to be changed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, relaxed, tense, or in a hurry. Methods of adjustment include, but are not limited to, changes in writing style or revisions to expressions.

[0095] The adjustment unit can select the optimal adjustment method by referring to the document's past adjustment history during the adjustment process. For example, the adjustment unit can select the optimal adjustment method by referring to how similar documents have been adjusted in the past. The adjustment unit can also select the most effective adjustment method from the document's past adjustment history. For example, the adjustment unit can analyze the document's past adjustment history and propose the optimal adjustment method. This allows the adjustment unit to select the optimal adjustment method by referring to the document's past adjustment history. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without AI. Past adjustment history includes, but is not limited to, database referencing and history analysis. Optimal adjustment methods include, but are not limited to, user feedback and past success stories.

[0096] The adjustment unit can apply different adjustment methods depending on the category of the document during the adjustment process. For example, in the case of a technical document, the adjustment unit can apply an adjustment method specialized in technical terminology. Similarly, in the case of a business document, the adjustment unit can apply an adjustment method specialized in formal expression. For example, the adjustment unit can apply an adjustment method specialized in formal expression to a business document. Furthermore, in the case of a casual document, the adjustment unit can apply an adjustment method specialized in approachable expression. For example, the adjustment unit can apply an adjustment method specialized in approachable expression to a casual document. This allows for the application of different adjustment methods depending on the category of the document. Some or all of the above processing in the adjustment unit may be performed using, for example, AI, or not using AI. The categories of documents include, but are not limited to, technical documents, business documents, and casual documents. The adjustment methods include, but are not limited to, changes in writing style and revisions to expressions.

[0097] The adjustment unit can estimate the user's emotions and determine the priority of adjustments based on the estimated emotions. For example, if the user is stressed, the adjustment unit will prioritize important adjustments. It can also adjust adjustments according to normal priorities if the user is relaxed. For example, the adjustment unit can detect that the user is relaxed using an emotion estimation algorithm and adjust adjustments according to normal priorities. Furthermore, if the user is in a hurry, the adjustment unit can prioritize adjustments of high urgency. For example, the adjustment unit can detect that the user is in a hurry using an emotion estimation algorithm and prioritize adjustments of high urgency. This allows the adjustment unit to determine the priority of adjustments based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, stress, relaxation, and urgency. Priorities include, but are not limited to, urgency and importance.

[0098] The coordination unit can change the order of coordination based on the submission timing of the documents. For example, the coordination unit will prioritize urgent documents. For regular documents, the coordination unit can also coordinate them in a standard order. For example, the coordination unit will coordinate regular documents in a standard order. The coordination unit can also postpone the coordination of documents with long deadlines. For example, the coordination unit will postpone the coordination of documents with long deadlines. This allows the order of coordination to be changed based on the submission timing of the documents. Some or all of the above processing in the coordination unit may be performed using AI, for example, or not using AI. The submission timing of documents includes, but is not limited to, the submission date and time. The order of coordination includes, but is not limited to, priority and relevance.

[0099] The adjustment unit can change its adjustment method based on the relevance of the materials during the adjustment process. For example, the adjustment unit may prioritize adjustments to materials that are highly relevant to other materials. It can also adjust materials in the usual way if they are independent. For example, the adjustment unit may detect that the materials are independent and adjust them in the usual way. Furthermore, the adjustment unit may postpone adjustments to materials that are less relevant. For example, the adjustment unit may detect that the materials are less relevant and postpone adjustments. This allows the adjustment method to be changed based on the relevance of the materials. Some or all of the above-described processes in the adjustment unit may be performed using AI, for example, or without AI. Relevance of materials includes, but is not limited to, similarity of content or matching of themes. Adjustment methods include, but are not limited to, changes in writing style or revisions of expression.

[0100] The editorial team can estimate the user's emotions and adjust the editing method based on the estimated emotions. For example, if the user is relaxed, the editorial team may use friendly language. Conversely, if the user is tense, the editorial team may use formal language. For example, the editorial team may detect that the user is tense using an emotion estimation algorithm and edit using formal language. Conversely, if the user is in a hurry, the editorial team may edit using concise and to-the-point language. For example, the editorial team may detect that the user is in a hurry using an emotion estimation algorithm and edit using concise and to-the-point language. This allows the editing method to be adjusted based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, relaxed, tense, or in a hurry. Editing methods include, but are not limited to, grammatical corrections or changes in expression.

[0101] The editorial department can select the optimal editing method by referring to the document's past editing history during the editing process. For example, the editorial department can select the optimal editing method by referring to how similar documents have been edited in the past. Alternatively, the editorial department can select the most effective editing method from the document's past editing history. For example, the editorial department can analyze the document's past editing history and propose the optimal editing method. This allows the editorial department to select the optimal editing method by referring to the document's past editing history. Some or all of the above processes performed by the editorial department may be carried out using AI, for example, or not. Past editing history includes, but is not limited to, database referencing and history analysis. Optimal editing methods include, but are not limited to, user feedback and past success stories.

[0102] The editorial department may apply different editing techniques depending on the category of the material during editing. For example, in the case of technical documents, the editorial department may apply editing techniques specialized in technical terminology. Similarly, in the case of business documents, the editorial department may apply editing techniques specialized in formal expression. For example, the editorial department may apply editing techniques specialized in formal expression to business documents. Similarly, in the case of casual documents, the editorial department may apply editing techniques specialized in approachable expression. For example, the editorial department may apply editing techniques specialized in approachable expression to casual documents. This allows for the application of different editing techniques depending on the category of the material. Some or all of the above processing by the editorial department may be performed using AI, for example, or not using AI. The categories of materials include, but are not limited to, technical documents, business documents, and casual documents. The editing techniques include, but are not limited to, grammatical corrections and changes in expression.

[0103] The editorial team can estimate the user's emotions and determine editing priorities based on those emotions. For example, if the user is stressed, the editorial team will prioritize important edits. Conversely, if the user is relaxed, the editorial team can edit with normal priorities. For example, the editorial team can detect that the user is relaxed using an emotion estimation algorithm and edit with normal priorities. Furthermore, if the user is in a hurry, the editorial team can prioritize highly urgent edits. For example, the editorial team can detect that the user is in a hurry using an emotion estimation algorithm and prioritize highly urgent edits. This allows for the determination of editing priorities based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, stress, relaxation, and urgency. Priorities include, but are not limited to, urgency and importance.

[0104] The editorial department may change the editing order based on the submission date of the materials. For example, the editorial department may prioritize editing urgent materials. For regular materials, the editorial department may also edit them in a standard order. For example, the editorial department may edit regular materials in a standard order. The editorial department may also postpone editing materials with long deadlines. For example, the editorial department may postpone editing materials with long deadlines. This allows the editing order to be changed based on the submission date of the materials. Some or all of the above processes by the editorial department may be performed using AI, for example, or not. The submission date of the materials includes, but is not limited to, the submission date and time. The editing order includes, but is not limited to, priority and relevance.

[0105] The editorial department may change its editing method based on the relevance of the materials during the editing process. For example, the editorial department may prioritize editing materials that are highly relevant to other materials. Alternatively, the editorial department may edit materials in the usual way if they are independent. For example, the editorial department may detect that a material is independent and edit it in the usual way. Furthermore, the editorial department may postpone editing materials that are less relevant. For example, the editorial department may detect that a material is less relevant and postpone editing it. This allows the editorial department to change its editing method based on the relevance of the materials. Some or all of the above processes performed by the editorial department may be carried out using AI, for example, or not. Relevance of materials includes, but is not limited to, similarity of content or matching of themes. Editing methods include, but are not limited to, changes in writing style or revisions of expression.

[0106] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, the learning unit will select training data containing friendly expressions. Similarly, if the user is tense, the learning unit can select training data containing formal expressions. For example, if the emotion estimation algorithm detects that the user is tense, the learning unit will select training data containing formal expressions. Similarly, if the user is in a hurry, the learning unit can select training data containing concise and to-the-point expressions. For example, if the emotion estimation algorithm detects that the user is in a hurry, the learning unit will select training data containing concise and to-the-point expressions. This allows for the selection of training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, relaxed, tense, or in a hurry. The training data may include, but is not limited to, examples of friendly expressions, formal expressions, and concise expressions.

[0107] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal learning algorithm. The learning unit can also extract effective learning patterns from past learning data and optimize the algorithm. For example, the learning unit can adjust the parameters of the learning algorithm based on past learning data. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. Past learning data includes, but is not limited to, database lookups and historical analysis. Learning algorithms include, but are not limited to, neural networks and rule-based learning.

[0108] The learning unit can apply different learning methods depending on the category of the material during learning. For example, in the case of technical documents, the learning unit can apply a learning method specialized in technical terminology. Similarly, in the case of business documents, the learning unit can apply a learning method specialized in formal expressions. For example, the learning unit can apply a learning method specialized in formal expressions to business documents. Furthermore, in the case of casual documents, the learning unit can apply a learning method specialized in friendly expressions. For example, the learning unit can apply a learning method specialized in friendly expressions to casual documents. This allows for the application of different learning methods depending on the category of the material. Some or all of the processing described above in the learning unit may be performed using AI, for example, or without AI. The categories of materials include, but are not limited to, technical documents, business documents, and casual documents. The learning methods include, but are not limited to, neural networks and rule-based learning.

[0109] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is relaxed, the learning unit will learn at a normal frequency. The learning unit can also reduce the learning frequency to alleviate the burden if the user is stressed. For example, the learning unit can detect the user's stress using an emotion estimation algorithm and reduce the learning frequency to alleviate the burden. Furthermore, if the user is in a hurry, the learning unit can increase the learning frequency to respond quickly. For example, the learning unit can detect the user's hurried state using an emotion estimation algorithm and increase the learning frequency to respond quickly. This allows the learning frequency to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. User emotions include, but are not limited to, relaxed, stressed, or hurried. Learning frequency includes, but is not limited to, normal frequency, reduced frequency, or increased frequency.

[0110] The learning unit can weight the training data based on the submission timing of the materials during training. For example, the learning unit can set a higher weight for urgent materials. The learning unit can also train with a standard weight for regular materials. For example, the learning unit can train with a standard weight for regular materials. The learning unit can also set a lower weight for materials with longer deadlines. For example, the learning unit can set a lower weight for materials with longer deadlines. This allows the learning unit to weight the training data based on the submission timing of the materials. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. The submission timing of the materials includes, but is not limited to, the submission date and submission time. The weighting of the training data includes, but is not limited to, high weighting, standard weighting, and low weighting.

[0111] The learning unit can select training data based on the relevance of the materials during training. For example, the learning unit will prioritize selecting materials as training data if they are highly relevant to other materials. The learning unit can also select materials as training data in the usual way if they are independent. For example, the learning unit will detect that the materials are independent and select them as training data in the usual way. The learning unit can also postpone selecting materials as training data if they are not highly relevant. For example, the learning unit will detect that the materials are not highly relevant and postpone selecting them as training data. This allows for the selection of training data based on the relevance of the materials. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. The relevance of materials includes, but is not limited to, similarity of content or matching of themes. The training data includes, but is not limited to, highly relevant data, normal data, or unrelevant data.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The translation system can further estimate the user's emotions and adjust the tone of the translation based on those emotions. For example, if the user is stressed, the translator will use concise and clear language. If the user is relaxed, the translator can use detailed and friendly language. Furthermore, if the user is in a hurry, the translator can provide a concise and to-the-point translation. This allows the system to provide the most appropriate translation for the user's emotions.

[0114] The translation system can further analyze the user's past translation history and suggest the optimal translation style. For example, it can learn the expressions and styles the user has preferred to use in the past and translate based on that. Furthermore, if the user requests translations specific to a particular industry or field, the system can prioritize the use of terminology and expressions relevant to that field. This allows for more personalized translations based on the user's past translation history.

[0115] The translation system can further estimate the user's emotions and determine translation priorities based on those emotions. For example, if the user is stressed, important translations will be prioritized. If the user is relaxed, translations can be performed with normal priorities. Furthermore, if the user is in a hurry, urgent translations can be given top priority. This allows the translation priorities to be adjusted based on the user's emotions.

[0116] The translation system can also take the user's geographical location into consideration when performing translations. For example, if the user is in a specific region, it will prioritize the use of terminology and expressions related to that region. Furthermore, if the user is traveling, it can provide translations that include information related to their travel destination. This allows for more relevant translations based on the user's geographical location.

[0117] The translation system can further estimate the user's emotions and adjust the level of detail in the translation based on those emotions. For example, if the user is relaxed, it can provide a translation with detailed explanations. If the user is in a hurry, it can provide a concise and to-the-point translation. Furthermore, if the user is excited, it can provide a translation with visually stimulating effects. This allows the system to adjust the level of detail in the translation based on the user's emotions.

[0118] The translation system can further analyze the user's social media activity and provide relevant translations. For example, it can prioritize the use of relevant terminology and expressions based on information the user has shared on social media. It can also provide translations that include information related to the accounts the user follows. This allows for more relevant translations based on the user's social media activity.

[0119] The translation system can further estimate the user's emotions and adjust the translation's expression based on those emotions. For example, if the user is relaxed, it can use friendly language in the translation. If the user is nervous, it can use more formal language. Furthermore, if the user is in a hurry, it can use concise and to-the-point language. This allows the translation's expression to be adjusted based on the user's emotions.

[0120] The translation system can further perform translations based on the user's current projects and areas of interest. For example, it can prioritize the use of terminology and expressions related to the user's current projects. It can also provide translations that include highly relevant information based on the user's areas of interest. This allows for the provision of more relevant translations based on the user's current projects and areas of interest.

[0121] The translation system can further estimate the user's emotions and adjust the translation length based on those emotions. For example, if the user is in a hurry, it can provide a short, to-the-point translation. If the user is relaxed, it can provide a longer translation with more detailed explanations. Furthermore, if the user is excited, it can provide a translation with visually stimulating effects. This allows the translation length to be adjusted based on the user's emotions.

[0122] The translation system can further analyze the user's past document submission history and select the most suitable translation method. For example, it can automatically recognize the format of documents the user has frequently submitted in the past and prompt translation in the same format. It can also prioritize suggesting the submission method the user has used in the past (online, offline, etc.). This allows for the provision of more efficient translation methods based on the user's past document submission history.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The reception desk inputs Japanese documents. For example, it has a function to upload documents created by users in Japanese, and it can also scan paper documents and convert them into digital data. It can also accept documents using voice input, and uses speech recognition technology to convert the voice data into text data. Step 2: The translation department analyzes the documents submitted by the reception department and translates them into English, taking into account the context and industry-specific terminology. For example, it uses generative AI to translate Japanese documents into English, accurately translating specialized terms and technical expressions. Step 3: The adjustment team adjusts the content translated by the translation team to match the tone and purpose of the document. For example, they adjust the translation to use formal language for formal business documents and friendly language for casual content. Step 4: The editorial team allows users to modify and edit the translations that have been adjusted by the adjustment team. For example, they provide an intuitive editing tool so that users can review the translations and make corrections as needed. Step 5: The learning unit learns from the revisions made by the editorial unit and incorporates them into future translations. For example, it uses machine learning algorithms to learn from user revisions and improve the accuracy of future translations.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the reception unit, translation unit, adjustment unit, editing unit, and learning unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the reception unit inputs data using the reception device 38 of the smart device 14 and transmits the data via the communication I / F 26 of the data processing unit 12. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and translates Japanese documents into English using a generation AI. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and adjusts the translated content to match the tone and purpose of the document. The editing unit allows the user to modify and edit the translated content using the control unit 46A of the smart device 14. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's modifications and reflects them in subsequent translations. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

[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 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.

[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 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.

[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 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.

[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 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.

[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 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.

[0144] Each of the multiple elements described above, including the reception unit, translation unit, adjustment unit, editing unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the smart glasses 214 and transmits data via the communication I / F 26 of the data processing unit 12. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and translates Japanese documents into English using a generation AI. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and adjusts the translated content to match the tone and purpose of the document. The editing unit allows the user to modify and edit the translated content using the control unit 46A of the smart glasses 214. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's modifications and reflects them in subsequent translations. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

[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 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.

[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 (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).

[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] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the reception unit, translation unit, adjustment unit, editing unit, and learning unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the headset terminal 314 and transmits data via the communication I / F 26 of the data processing unit 12. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and translates Japanese documents into English using a generation AI. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and adjusts the translated content to match the tone and purpose of the document. The editing unit allows the user to modify and edit the translated content using the control unit 46A of the headset terminal 314. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's modifications and reflects them in subsequent translations. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] Each of the multiple elements described above, including the reception unit, translation unit, adjustment unit, editing unit, and learning unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the robot 414 and transmits data via the communication I / F 26 of the data processing unit 12. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and translates Japanese documents into English using a generation AI. The adjustment unit is implemented by the specific processing unit 290 of the data processing unit 12 and adjusts the translated content to match the tone and purpose of the document. The editing unit allows the user to modify and edit the translated content using the control unit 46A of the robot 414. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's modifications and reflects them in subsequent translations. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] (Note 1) The reception desk for entering Japanese documents, The translation department analyzes the documents entered by the aforementioned reception department and translates them into English, taking into account the context and industry-specific terminology. An adjustment unit adjusts the content translated by the aforementioned translation unit to match the tone and purpose of the document, The editing unit allows the user to modify and edit the translated content adjusted by the aforementioned adjustment unit. It includes a learning unit that learns from the corrections made by the aforementioned editorial department and reflects them in subsequent translations. A system characterized by the following features. (Note 2) The aforementioned translation department, For technical documents, accurately translate specialized terminology and technical expressions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned translation department, For business documents, the translation should maintain a formal tone while using appropriate expressions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The adjustment unit is, For casual content, use friendly language in the translation. The system described in Appendix 1, characterized by the features described herein. (Note 5) The adjustment unit is, For official business documents, use formal language in your translation. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned editorial department, Users can modify and edit the translation. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, The system learns from user corrections and incorporates them into future translations. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of document submission based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is Analyze the user's past document submission history to select the most suitable submission method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving materials, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is The system estimates the user's emotions and prioritizes the materials to be received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving materials, the system prioritizes receiving materials that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When receiving materials, the system analyzes the user's social media activity and accepts relevant materials. The system described in Appendix 1, characterized by the features described herein. (Note 14) 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 15) The aforementioned translation department, During translation, adjust the level of detail based on the importance of the source material. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned translation department, When translating, different translation algorithms are applied depending on the category of the document. The system described in Appendix 1, characterized by the features described herein. (Note 17) 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 18) The aforementioned translation department, During the translation process, translation priorities are determined based on the submission dates of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned translation department, During translation, adjust the order of translations based on the relevance of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 20) The adjustment unit is, We estimate the user's emotions and change the adjustment method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The adjustment unit is, During the adjustment process, the optimal adjustment method is selected by referring to the past adjustment history of the document. The system described in Appendix 1, characterized by the features described herein. (Note 22) The adjustment unit is, During the adjustment process, different adjustment methods are applied depending on the category of the document. The system described in Appendix 1, characterized by the features described herein. (Note 23) The adjustment unit is, It estimates the user's emotions and determines the priority of adjustments based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The adjustment unit is, During the adjustment process, the order of adjustments will be changed based on when the documents were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The adjustment unit is, During the adjustment process, the adjustment method will be changed based on the relevance of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned editorial department, It estimates the user's emotions and adjusts the editing method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned editorial department, During editing, the system refers to the document's past editing history to select the most suitable editing method. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned editorial department, When editing, apply different editing methods depending on the category of the document. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned editorial department, It estimates the user's emotions and determines editing priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned editorial department, During editing, the editing order is changed based on when the documents were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned editorial department, When editing, change the editing method based on the relevance of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned learning unit, When learning, apply different learning methods depending on the category of the material. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned learning unit, During training, the training data is weighted based on the submission timing of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned learning unit, During training, training data is selected based on the relevance of the materials. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 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. The reception desk for entering Japanese documents, The translation department analyzes the documents entered by the aforementioned reception department and translates them into English, taking into account the context and industry-specific terminology. An adjustment unit adjusts the content translated by the aforementioned translation unit to match the tone and purpose of the document, The editing unit allows the user to modify and edit the translated content adjusted by the aforementioned adjustment unit. It includes a learning unit that learns from the corrections made by the aforementioned editorial department and reflects them in subsequent translations. A system characterized by the following features.

2. The aforementioned translation department, For technical documents, accurately translate specialized terminology and technical expressions. The system according to feature 1.

3. The aforementioned translation department, For business documents, the translation should maintain a formal tone while using appropriate expressions. The system according to feature 1.

4. The adjustment unit is, For casual content, use friendly language in the translation. The system according to feature 1.

5. The adjustment unit is, For official business documents, use formal language in your translation. The system according to feature 1.

6. The aforementioned editorial department, Users can modify and edit the translation. The system according to feature 1.

7. The aforementioned learning unit, The system learns from user corrections and incorporates them into future translations. The system according to feature 1.

8. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of document submission based on those estimated emotions. The system according to feature 1.

9. The aforementioned reception unit is Analyze the user's past document submission history to select the most suitable submission method. The system according to feature 1.

10. The aforementioned reception unit is When receiving materials, filtering is performed based on the user's current projects and areas of interest. The system according to feature 1.

Images