system

Abstract

The system according to this embodiment aims to provide opportunities for learning English related to work and to efficiently improve English proficiency. [Solution] The system according to the embodiment comprises an information gathering unit, a word extraction unit, an email generation unit, a conversation practice unit, and a notification unit. The information gathering unit reads business-related documents and emails. The word extraction unit picks up English words and phrases based on the information collected by the information gathering unit. The email generation unit automatically creates a draft English email based on the English words and phrases picked up by the word extraction unit. The conversation practice unit provides English conversation practice using conference audio collected by the information gathering unit. The notification unit notifies the user of the learning time.

Description

Technical Field

[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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to create opportunities for English learning related to work, and there is a problem that there is a lack of opportunities for practicing speaking and writing, especially in workplaces where English is not used.

[0005] The system according to the embodiment aims to provide opportunities for English learning related to work and effectively improve English application ability.

Means for Solving the Problems

[0006] ​​​The system according to this embodiment comprises an information gathering unit, a word extraction unit, an email generation unit, a conversation practice unit, and a notification unit. The information gathering unit reads business-related documents and emails. The word extraction unit picks up English words and phrases based on the information collected by the information gathering unit. The email generation unit automatically creates a draft English email based on the English words and phrases picked up by the word extraction unit. The conversation practice unit provides English conversation practice using conference audio collected by the information gathering unit. The notification unit notifies the user of their study time. [Effects of the Invention]

[0007] The system according to this embodiment can provide opportunities for learning English related to work and efficiently improve English proficiency. [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, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable 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 English learning support system according to an embodiment of the present invention is a system that supports English learning by linking an AI agent with an email application and work folders, reading work-related documents and emails, and based on that information. The English learning support system reads work-related documents and emails, picks out English words and phrases based on that information, and presents them as questions. The English learning support system also automatically creates draft English emails. Furthermore, the English learning support system provides an AI-powered English conversation practice service using the day's work content and meeting audio. In addition, the English learning support system is equipped with a calendar-based notification function for study time. For example, the English learning support system can cultivate practical English skills by presenting quizzes on work-related English words and phrases. Furthermore, the English learning support system can improve English communication skills through its automatic creation and correction functions for draft English emails. Furthermore, the English learning support system can improve speaking and listening skills through its English conversation practice service that utilizes meeting content. The calendar-based notification function for study time creates an environment where busy business people can learn efficiently in their spare time, supporting improved English skills and career advancement. This allows the English learning support system to efficiently improve users' English proficiency.

[0029] The English learning support system according to this embodiment comprises an information gathering unit, a word extraction unit, an email generation unit, a conversation practice unit, and a notification unit. The information gathering unit reads business-related documents and emails. Business-related documents and emails include, but are not limited to, technical documents, business emails, and reports. The information gathering unit digitizes and reads business-related documents using scanning technology, for example. The information gathering unit can also directly read documents submitted in digital format. Furthermore, the information gathering unit can read printed documents using OCR technology. For example, the information gathering unit scans a technical document with a high-resolution scanner and converts it into text information using OCR technology. Digital documents can be directly read if they are submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The word extraction unit picks up English words and phrases based on the information collected by the information gathering unit. The word extraction unit picks up English words and phrases based on criteria such as frequency, importance, and context, for example. For example, the word extraction unit prioritizes picking up frequently used English words. The word extraction unit can also pick up English words of high importance. Furthermore, the word extraction unit can pick up English words based on context. For example, the word extraction unit picks up English words that are frequently used in business-related documents. High-importance English words are those that have particularly important meaning in business and are therefore prioritized for selection. Context-based selection is a method of selecting appropriate English words according to the content of business-related documents. The email generation unit automatically creates draft English emails based on the English words and phrases picked up by the word extraction unit. The email generation unit automatically creates draft English emails based on criteria such as template usage, grammar checks, and content consistency. For example, the email generation unit creates draft English emails using templates. It can also perform grammar checks to create accurate draft English emails. Furthermore, it can verify content consistency to create appropriate draft English emails. For example, the email generation unit selects an appropriate template based on the content of business-related documents and creates a draft English email.Grammar checking is a process that verifies the grammatical accuracy of draft English emails and is performed automatically by the email generation unit. Content consistency is a process that verifies whether the content of the draft English email matches business-related documents and is performed automatically by the email generation unit. The conversation practice unit provides English conversation practice using meeting audio collected by the information gathering unit. The conversation practice unit provides English conversation practice based on criteria such as how the audio is played and the practice scenarios. For example, the conversation practice unit plays meeting audio and allows the user to practice listening to its content. The conversation practice unit can also provide practice scenarios, allowing the user to simulate actual conversations. Furthermore, the conversation practice unit can use speech recognition technology to evaluate the user's pronunciation and provide feedback. For example, the conversation practice unit plays meeting audio and allows the user to practice listening to its content. The practice scenarios are based on actual work and are designed to help the user acquire practical English conversation skills. Speech recognition technology is used to evaluate the user's pronunciation and provide accurate feedback. The notification unit provides notifications of learning time. The notification unit provides notifications about study time based on criteria such as how the calendar is used and the timing of notifications. For example, the notification unit sets study time based on the calendar and notifies the user. The notification unit can also adjust the timing of notifications to help users efficiently allocate study time. Furthermore, the notification unit can select a notification method (email, alarm, etc.) and notify the user in an appropriate manner. For example, the notification unit sets study time based on the calendar and notifies the user. The timing of notifications is adjusted to match the user's schedule, supporting efficient learning. The notification method is selected according to the user's preference, and notifications are made via methods such as email or alarms. As a result, the English learning support system according to this embodiment can efficiently improve the user's English proficiency.

[0030] The Information Gathering Department reads business-related documents and emails. These include, but are not limited to, technical documents, business emails, and reports. For example, the Information Gathering Department digitizes and reads business-related documents using scanning technology. Specifically, it scans paper documents using a high-resolution scanner and converts them into text information using OCR (Optical Character Recognition) technology. OCR technology can recognize printed characters with high accuracy and convert them into digital text. This makes it possible to manage paper documents in a digital format. The Information Gathering Department can also directly read documents submitted in digital format. For example, it reads documents submitted in file formats such as PDF and Word documents and analyzes their contents. Furthermore, the Information Gathering Department can also read the contents of emails. Email is a frequently used means of communication in business, and by analyzing its contents, important business-related information can be collected. This allows the Information Gathering Department to collect a wide range of information from diverse document formats and store it in the system-wide database.

[0031] The word extraction unit picks up English words and phrases based on information collected by the information gathering unit. Specifically, it uses natural language processing (NLP) technology to extract English words and phrases from the collected text data. NLP technology analyzes the text data and selects appropriate words and phrases based on information such as word frequency, importance, and context. For example, the word extraction unit prioritizes picking up high-frequency English words. High-frequency words are used frequently in work, so they have a high priority for learning. The word extraction unit can also pick up high-importance English words. High-importance words are words that have particularly important meaning in work and should be prioritized for learning. Furthermore, the word extraction unit can also pick up English words based on context. Context-based selection is a method of selecting appropriate English words according to the content of work-related materials, and it can extract words that are important in specific topics and situations related to work. In this way, the word extraction unit supports users in efficiently learning English words and phrases.

[0032] The email generation unit automatically creates draft English emails based on English words and phrases picked up by the word extraction unit. Specifically, it automatically creates draft English emails based on criteria such as template usage, grammar checks, and content consistency. Using templates provides a standardized email structure, making it easy for users to create emails. For example, templates for greetings, body text, and closing remarks are used to create the basic structure of an email. The email generation unit can also perform grammar checks to create accurate draft English emails. Grammar checks are a process to verify the grammatical accuracy of the draft English emails and are performed automatically using natural language processing technology. Furthermore, the email generation unit can also verify content consistency and create appropriate draft English emails. Content consistency is a process to verify that the content of the draft English email matches business-related documents and is performed automatically by the email generation unit. For example, it selects an appropriate template based on the content of business-related documents and creates a draft English email. In this way, the email generation unit supports users in efficiently creating accurate English emails.

[0033] The Conversation Practice Department provides English conversation practice using conference audio collected by the Information Gathering Department. Specifically, it provides English conversation practice based on criteria such as how the audio is played and the practice scenarios. For example, the Conversation Practice Department plays conference audio and allows users to practice listening to its content. The conference audio is relevant to actual work situations and is designed to help users acquire practical English conversation skills. The Conversation Practice Department also provides practice scenarios, allowing users to simulate actual conversations. The practice scenarios are created assuming specific situations related to work and are designed to help users acquire practical English conversation skills. Furthermore, the Conversation Practice Department can also evaluate the user's pronunciation and provide feedback using speech recognition technology. Speech recognition technology is used to analyze the user's pronunciation and provide accurate feedback. For example, it analyzes English words and phrases pronounced by the user and evaluates the accuracy and fluency of their pronunciation. In this way, the Conversation Practice Department provides support for users to efficiently improve their English conversation skills.

[0034] The notification unit provides notifications about study time. Specifically, it provides notifications based on criteria such as how the calendar is used and the timing of notifications. For example, the notification unit sets study time based on the calendar and notifies the user. The calendar is a tool for setting study time based on the user's schedule, enabling the user to efficiently allocate study time. The notification unit can also adjust the timing of notifications to enable the user to efficiently allocate study time. The timing of notifications is adjusted to match the user's schedule, supporting efficient learning. Furthermore, the notification unit can select a notification method (email, alarm, etc.) and notify the user in an appropriate manner. The notification method is selected according to the user's preference, and notifications are sent via email, alarm, etc. For example, if the user prefers email notifications, the notification unit will send study time notifications via email. If the user prefers alarm notifications, the notification unit will notify the user of study time via alarm. In this way, the notification unit supports the user in efficiently allocating study time and continuing their English learning.

[0035] The word extraction unit can pick out English words and phrases to be memorized based on the day's work content and present them as questions. For example, the word extraction unit can analyze the day's work content and pick out high-frequency English words and phrases. For example, the word extraction unit can select English words based on project progress or meeting content. The word extraction unit can also pick out English words based on task details. For example, the word extraction unit can analyze meeting minutes and pick out important English words. The word extraction unit can also analyze project progress reports and pick out high-frequency English words. Furthermore, the word extraction unit can analyze task details and pick out relevant English words. In this way, by picking out English words and phrases based on work content and presenting them as questions, the user's practical English skills can be improved. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or not using AI. For example, the word extraction unit can input work content into a generating AI, and the generating AI can pick out English words and phrases.

[0036] The email generation unit can automatically create draft English emails based on selected English words and phrases. For example, the email generation unit can create draft English emails using templates. For example, the email generation unit can select an appropriate template based on the content of business-related documents and create a draft English email. The email generation unit can also perform grammatical checks to create accurate draft English emails. For example, the email generation unit can verify the grammatical accuracy of the draft English email. Furthermore, the email generation unit can verify the consistency of the content and create appropriate draft English emails. For example, the email generation unit can verify that the content of business-related documents matches the draft English email. This allows for the automatic creation of draft English emails based on selected English words and phrases, thereby improving the user's English communication skills. Some or all of the above processes in the email generation unit may be performed using AI, or not. For example, the email generation unit can input selected English words and phrases into a generation AI, which can then create a draft English email.

[0037] The conversation practice unit can provide English conversation practice using the day's work content or meeting audio. For example, the conversation practice unit can play meeting audio and have the user practice listening to its content. For example, the conversation practice unit can provide a scenario based on the meeting content and have the user simulate an actual conversation. The conversation practice unit can also use speech recognition technology to evaluate the user's pronunciation and provide feedback. For example, the conversation practice unit can evaluate the user's pronunciation and provide accurate feedback. In this way, by providing English conversation practice using the day's work content or meeting audio, the user's speaking and listening skills can be improved. Some or all of the above processes in the conversation practice unit may be performed using AI, for example, or not using AI. For example, the conversation practice unit can input meeting audio into a generating AI, and the generating AI can create an English conversation practice scenario.

[0038] The notification unit can provide notifications of study time based on a calendar. For example, the notification unit sets study time based on the calendar and notifies the user. For example, the notification unit adjusts the timing of notifications according to the user's schedule. The notification unit can also select a notification method (email, alarm, etc.) and notify the user in an appropriate manner. For example, the notification unit sets study time based on the calendar and notifies the user. The timing of notifications is adjusted according to the user's schedule to support efficient learning. The notification method is selected according to the user's preference and notifications are made by methods such as email or alarm. This allows users to efficiently allocate study time by providing calendar-based study time notifications. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's schedule data into a generating AI, which can then suggest the optimal notification timing.

[0039] The information gathering unit can analyze the user's past work history and select the optimal information gathering method. For example, the information gathering unit may prioritize collecting information from sources that the user has frequently used in the past. For example, the information gathering unit may prioritize collecting highly relevant information from the user's work history. The information gathering unit can also analyze the user's work history and propose the optimal information gathering method. For example, the information gathering unit may analyze the user's work history and select the optimal information gathering method. This allows the optimal information gathering method to be selected by analyzing the user's past work history. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's work history data into a generating AI, which can then propose the optimal information gathering method.

[0040] The information gathering unit can filter information based on the user's current projects and areas of interest during the information gathering process. For example, the information gathering unit can prioritize collecting information related to the project the user is currently working on. For example, the information gathering unit can filter information based on the user's areas of interest. The information gathering unit can also collect necessary information according to the user's project progress. For example, the information gathering unit can analyze the user's project progress and collect relevant information. This allows for the collection of highly relevant information by filtering information based on the user's current projects and areas of interest. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's project data into a generating AI, which can then filter the relevant information.

[0041] The information gathering unit can prioritize collecting highly relevant information based on the user's geographical location information during information gathering. For example, the information gathering unit can prioritize collecting information related to the user's current location. For example, the information gathering unit can filter highly relevant information based on the user's geographical location information. The information gathering unit can also update the user's location information in real time and collect the most relevant information. For example, the information gathering unit can analyze the user's location information and collect relevant information. This enables more effective information gathering by prioritizing the collection of highly relevant information based on the user's geographical location information. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's location information data into a generating AI, which can then filter the relevant information.

[0042] The information gathering unit can analyze the user's social media activity and collect relevant information during the information gathering process. For example, the information gathering unit can collect information related to topics the user has shown interest in on social media. For example, the information gathering unit can analyze the user's social media activity and prioritize the collection of highly relevant information. The information gathering unit can also collect information shared by the user's social media followers and friends. For example, the information gathering unit can analyze the user's social media activity and collect relevant information. This allows for the collection of highly relevant information by analyzing the user's social media activity. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's social media data into a generating AI, which can then filter the relevant information.

[0043] The word extraction unit can determine the priority of words to extract based on the importance of the task during the word extraction process. For example, the word extraction unit may prioritize extracting words related to important tasks. For example, the word extraction unit may adjust the priority of words to extract according to the importance of the task. The word extraction unit can also postpone extracting words related to less important tasks. For example, the word extraction unit may evaluate the importance of the task and prioritize extracting related words. This allows for more effective word learning by determining the priority of words to extract based on the importance of the task. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input task importance data into a generating AI, and the generating AI can determine the priority of words.

[0044] The word extraction unit can apply different extraction algorithms depending on the category of the work during word extraction. For example, the word extraction unit can apply an algorithm that prioritizes the extraction of specialized terminology for technical work. For example, the word extraction unit can apply an algorithm that prioritizes the extraction of relevant terminology for marketing work. Furthermore, the word extraction unit can also apply an algorithm that prioritizes the extraction of general business terminology for administrative work. For example, the word extraction unit can select the optimal extraction algorithm according to the category of work. By applying different extraction algorithms according to the category of work, more effective word learning becomes possible. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input the category data of work into a generating AI, and the generating AI can apply the optimal extraction algorithm.

[0045] The word extraction unit can determine the priority of words to extract based on the submission deadline of the task. For example, the word extraction unit may prioritize extracting words related to tasks with approaching deadlines. For example, the word extraction unit may adjust the priority of words to extract according to the submission deadline. The word extraction unit can also postpone extracting words related to tasks with distant deadlines. For example, the word extraction unit may evaluate the submission deadline of the task and prioritize extracting related words. This allows for more effective word learning by determining the priority of words to extract based on the submission deadline of the task. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input task submission deadline data into a generating AI, which can then determine the priority of words.

[0046] The word extraction unit can adjust the order of words extracted based on their relevance to the business. For example, the word extraction unit can prioritize extracting the words most relevant to the business. For example, the word extraction unit can adjust the order of words extracted according to their relevance to the business. The word extraction unit can also postpone extracting less relevant words. For example, the word extraction unit can evaluate the relevance to the business and prioritize extracting relevant words. By adjusting the order of words extracted based on their relevance to the business, more effective word learning becomes possible. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input business relevance data into a generating AI, which can then adjust the order of the words.

[0047] The email generation unit can adjust the level of detail in emails based on the importance of the task during email generation. For example, the email generation unit can include detailed information in emails related to important tasks. For example, the email generation unit adjusts the level of detail in emails according to the importance of the task. The email generation unit can also make emails related to less important tasks concise. For example, the email generation unit can evaluate the importance of the task and adjust the level of detail in the relevant email. This allows for more effective communication by adjusting the level of detail in emails based on the importance of the task. Some or all of the above processing in the email generation unit may be performed using AI, for example, or not using AI. For example, the email generation unit can input task importance data into a generation AI, and the generation AI can adjust the level of detail in the emails.

[0048] The email generation unit can apply different generation algorithms depending on the category of the business when generating emails. For example, the email generation unit can apply an algorithm that generates emails containing technical terms for technical tasks. For example, the email generation unit can apply an algorithm that generates emails containing relevant terms for marketing tasks. Furthermore, the email generation unit can also apply an algorithm that generates emails containing general business terms for administrative tasks. For example, the email generation unit selects the optimal generation algorithm according to the category of the business. By applying different generation algorithms according to the category of the business, more effective email generation becomes possible. Some or all of the above processing in the email generation unit may be performed using AI, for example, or without AI. For example, the email generation unit can input business category data into a generation AI, and the generation AI can apply the optimal generation algorithm.

[0049] The email generation unit can determine the priority of emails based on the submission deadlines of tasks when generating emails. For example, the email generation unit can prioritize the generation of emails related to tasks with approaching deadlines. For example, the email generation unit can adjust the priority of emails according to the submission deadline. The email generation unit can also postpone emails related to tasks with distant deadlines. For example, the email generation unit can evaluate the submission deadlines of tasks and determine the priority of related emails. This enables more effective email management by determining the priority of emails based on the submission deadlines of tasks. Some or all of the above processing in the email generation unit may be performed using AI, for example, or not using AI. For example, the email generation unit can input task submission data into a generation AI, and the generation AI can determine the priority of emails.

[0050] The email generation unit can adjust the order of emails based on their relevance to the business when generating them. For example, the email generation unit can prioritize generating emails that are most relevant to the business. For example, the email generation unit adjusts the order of emails according to their relevance to the business. The email generation unit can also postpone less relevant emails. For example, the email generation unit can evaluate the relevance of the business and prioritize generating relevant emails. This allows for more effective email management by adjusting the order of emails based on their relevance to the business. Some or all of the above processing in the email generation unit may be performed using AI, for example, or without AI. For example, the email generation unit can input business relevance data into a generation AI, which can then adjust the order of emails.

[0051] The conversation practice unit can optimize practice content by referring to past conversation history during conversation practice. For example, the conversation practice unit can focus on conversation topics that the user has struggled with in the past. For example, the conversation practice unit can prioritize practicing highly relevant content from the user's past conversation history. The conversation practice unit can also analyze the user's conversation history and suggest the most suitable practice content. For example, the conversation practice unit can analyze the user's conversation history and select the most suitable practice content. By optimizing practice content by referring to past conversation history, more effective conversation practice becomes possible. Some or all of the above processes in the conversation practice unit may be performed using AI, for example, or without AI. For example, the conversation practice unit can input the user's conversation history data into a generating AI, which can then suggest the most suitable practice content.

[0052] The conversation practice unit can apply different practice algorithms depending on the category of work during conversation practice. For example, the conversation practice unit can apply an algorithm that provides conversation practice including specialized terminology for technical work. For example, the conversation practice unit can apply an algorithm that provides conversation practice including relevant terminology for marketing work. Furthermore, the conversation practice unit can also apply an algorithm that provides conversation practice including general business terminology for management work. For example, the conversation practice unit selects the optimal practice algorithm according to the category of work. This makes it possible to perform more effective conversation practice by applying different practice algorithms according to the category of work. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or without using AI. For example, the conversation practice unit can input work category data into a generating AI, and the generating AI can apply the optimal practice algorithm.

[0053] The conversation practice unit can prioritize practice content based on the deadlines for tasks during conversation practice. For example, the conversation practice unit will prioritize practicing conversations related to tasks with approaching deadlines. For example, the conversation practice unit will adjust the priority of practice content according to the submission deadline. The conversation practice unit can also postpone conversations related to tasks with distant deadlines. For example, the conversation practice unit will evaluate the submission deadlines of tasks and prioritize practicing conversations related to those deadlines. This allows for more effective conversation practice by prioritizing practice content based on the submission deadlines of tasks. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or not using AI. For example, the conversation practice unit can input task submission deadline data into a generating AI, which can then determine the priority of practice content.

[0054] The conversation practice unit can adjust the order of practice content based on the relevance of the work during conversation practice. For example, the conversation practice unit prioritizes practicing conversation content that is most relevant to the work. For example, the conversation practice unit adjusts the order of practice content according to the relevance of the work. The conversation practice unit can also postpone conversation content that is less relevant. For example, the conversation practice unit evaluates the relevance of the work and prioritizes practicing relevant conversation content. By adjusting the order of practice content based on the relevance of the work, more effective conversation practice becomes possible. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or not using AI. For example, the conversation practice unit can input work relevance data into a generating AI, and the generating AI can adjust the order of practice content.

[0055] The notification unit can select the optimal notification method by referring to past notification history when sending a notification. For example, the notification unit may prioritize notification methods that the user has preferred to use in the past. For example, the notification unit may suggest the optimal notification method based on the user's past notification history. The notification unit can also analyze the user's notification history and select the optimal notification method. For example, the notification unit may analyze the user's notification history and select the optimal notification method. By selecting the optimal notification method by referring to past notification history, more effective notifications become possible. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's notification history data into a generating AI, which can then suggest the optimal notification method.

[0056] The notification unit can select the optimal notification method when sending a notification, taking into account the user's device information. For example, if the user is using a smartphone, the notification unit will prioritize push notifications. For example, if the user is using a tablet, the notification unit will provide a notification method optimized for a larger screen. The notification unit can also provide a concise and highly visible notification method if the user is using a smartwatch. For example, the notification unit will analyze the user's device information and select the optimal notification method. By selecting the optimal notification method considering the user's device information, more effective notifications become possible. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user device information data into a generating AI, which can then propose the optimal notification method.

[0057] The notification unit can select the optimal notification timing by referring to the user's calendar information when sending a notification. For example, the notification unit can adjust the notification timing by referring to appointments registered in the user's calendar. For example, the notification unit can suggest the optimal notification timing from the user's calendar information. The notification unit can also select a notification timing that matches the appointment based on the user's calendar information. For example, the notification unit can analyze the user's calendar information and select the optimal notification timing. By selecting the optimal notification timing by referring to the user's calendar information, more effective notifications become possible. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input the user's calendar information data into a generating AI, and the generating AI can suggest the optimal notification timing.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The information gathering unit can analyze the user's past learning history and select the most suitable learning materials. For example, the information gathering unit can prioritize collecting materials related to areas the user has struggled with in the past. It can also analyze the user's learning history and prioritize collecting highly relevant materials. Furthermore, the information gathering unit can analyze the user's learning history and suggest the most suitable learning materials. This allows for the selection of optimal learning materials by analyzing the user's past learning history. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's learning history data into a generating AI, which can then suggest the most suitable learning materials.

[0060] The email generation unit can analyze the user's past email history and select the most suitable email template. For example, the email generation unit can prioritize selecting templates that the user has used in the past. It can also analyze the user's email history and prioritize selecting templates with high relevance. Furthermore, the email generation unit can analyze the user's email history and suggest the most suitable template. This allows for the selection of the most suitable email template by analyzing the user's past email history. Some or all of the above processes in the email generation unit may be performed using AI, for example, or without AI. For example, the email generation unit can input the user's email history data into a generation AI, which can then suggest the most suitable template.

[0061] The notification unit can analyze the user's past notification history and select the optimal notification timing. For example, the notification unit can prioritize timings that the user has preferred to receive in the past. It can also analyze the user's notification history and prioritize timings that are highly relevant. Furthermore, the notification unit can analyze the user's notification history and suggest the optimal notification timing. This allows for the selection of the optimal notification timing by analyzing the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's notification history data into a generating AI, which can then suggest the optimal notification timing.

[0062] The word extraction unit can analyze the user's past learning history and extract the most suitable words. For example, the word extraction unit can prioritize extracting words that the user has struggled with in the past. It can also analyze the user's learning history and prioritize extracting highly relevant words. Furthermore, the word extraction unit can analyze the user's learning history and suggest the most suitable words. This allows for the extraction of optimal words by analyzing the user's past learning history. Some or all of the above-described processes in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input the user's learning history data into a generating AI, which can then suggest the most suitable words.

[0063] The conversation practice unit can analyze the user's past conversation history and select the optimal conversation practice scenario. For example, the conversation practice unit can prioritize selecting conversation scenarios that the user has struggled with in the past. It can also analyze the user's conversation history and prioritize selecting scenarios with high relevance. Furthermore, the conversation practice unit can analyze the user's conversation history and propose the optimal scenario. This allows for the selection of the optimal conversation practice scenario by analyzing the user's past conversation history. Some or all of the above processes in the conversation practice unit may be performed using AI, for example, or without AI. For example, the conversation practice unit can input the user's conversation history data into a generating AI, which can then propose the optimal scenario.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The information gathering department reads business-related documents and emails. These include technical documents, business emails, and reports. The information gathering department can digitize and read these documents using scanning technology, and can also directly read documents submitted in digital format. Furthermore, it can read printed documents using OCR technology. Step 2: The word extraction unit picks out English words and phrases based on the information collected by the information gathering unit. The word extraction unit picks out English words and phrases based on criteria such as frequency, importance, and context. For example, it prioritizes picking out high-frequency and high-importance English words, and selects appropriate English words based on the context. Step 3: The email generation unit automatically creates a draft English email based on the English words and phrases picked up by the word extraction unit. The email generation unit automatically creates the draft English email based on criteria such as template usage, grammar checks, and content consistency. For example, it creates a draft English email using a template, performs a grammar check, and verifies content consistency. Step 4: The Conversation Practice Department provides English conversation practice using the conference audio collected by the Information Gathering Department. The Conversation Practice Department provides English conversation practice based on criteria such as how to play the audio and the practice scenarios. For example, it can play conference audio, allow users to practice listening to its contents, provide practice scenarios, and allow users to simulate actual conversations. It also uses speech recognition technology to evaluate the user's pronunciation and provide feedback. Step 5: The notification unit provides notifications about study time. The notification unit provides notifications about study time based on criteria such as how the calendar is used and the timing of notifications. For example, it sets study time based on the calendar and notifies the user. The timing of notifications is adjusted to match the user's schedule, and the notification method (email, alarm, etc.) is selected and the user is notified in an appropriate manner.

[0066] (Example of form 2) The English learning support system according to an embodiment of the present invention is a system that supports English learning by linking an AI agent with an email application and work folders, reading work-related documents and emails, and based on that information. The English learning support system reads work-related documents and emails, picks out English words and phrases based on that information, and presents them as questions. The English learning support system also automatically creates draft English emails. Furthermore, the English learning support system provides an AI-powered English conversation practice service using the day's work content and meeting audio. In addition, the English learning support system is equipped with a calendar-based notification function for study time. For example, the English learning support system can cultivate practical English skills by presenting quizzes on work-related English words and phrases. Furthermore, the English learning support system can improve English communication skills through its automatic creation and correction functions for draft English emails. Furthermore, the English learning support system can improve speaking and listening skills through its English conversation practice service that utilizes meeting content. The calendar-based notification function for study time creates an environment where busy business people can learn efficiently in their spare time, supporting improved English skills and career advancement. This allows the English learning support system to efficiently improve users' English proficiency.

[0067] The English learning support system according to this embodiment comprises an information gathering unit, a word extraction unit, an email generation unit, a conversation practice unit, and a notification unit. The information gathering unit reads business-related documents and emails. Business-related documents and emails include, but are not limited to, technical documents, business emails, and reports. The information gathering unit digitizes and reads business-related documents using scanning technology, for example. The information gathering unit can also directly read documents submitted in digital format. Furthermore, the information gathering unit can read printed documents using OCR technology. For example, the information gathering unit scans a technical document with a high-resolution scanner and converts it into text information using OCR technology. Digital documents can be directly read if they are submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The word extraction unit picks up English words and phrases based on the information collected by the information gathering unit. The word extraction unit picks up English words and phrases based on criteria such as frequency, importance, and context, for example. For example, the word extraction unit prioritizes picking up frequently used English words. The word extraction unit can also pick up English words of high importance. Furthermore, the word extraction unit can pick up English words based on context. For example, the word extraction unit picks up English words that are frequently used in business-related documents. High-importance English words are those that have particularly important meaning in business and are therefore prioritized for selection. Context-based selection is a method of selecting appropriate English words according to the content of business-related documents. The email generation unit automatically creates draft English emails based on the English words and phrases picked up by the word extraction unit. The email generation unit automatically creates draft English emails based on criteria such as template usage, grammar checks, and content consistency. For example, the email generation unit creates draft English emails using templates. It can also perform grammar checks to create accurate draft English emails. Furthermore, it can verify content consistency to create appropriate draft English emails. For example, the email generation unit selects an appropriate template based on the content of business-related documents and creates a draft English email.Grammar checking is a process that verifies the grammatical accuracy of draft English emails and is performed automatically by the email generation unit. Content consistency is a process that verifies whether the content of the draft English email matches business-related documents and is performed automatically by the email generation unit. The conversation practice unit provides English conversation practice using meeting audio collected by the information gathering unit. The conversation practice unit provides English conversation practice based on criteria such as how the audio is played and the practice scenarios. For example, the conversation practice unit plays meeting audio and allows the user to practice listening to its content. The conversation practice unit can also provide practice scenarios, allowing the user to simulate actual conversations. Furthermore, the conversation practice unit can use speech recognition technology to evaluate the user's pronunciation and provide feedback. For example, the conversation practice unit plays meeting audio and allows the user to practice listening to its content. The practice scenarios are based on actual work and are designed to help the user acquire practical English conversation skills. Speech recognition technology is used to evaluate the user's pronunciation and provide accurate feedback. The notification unit provides notifications of learning time. The notification unit provides notifications about study time based on criteria such as how the calendar is used and the timing of notifications. For example, the notification unit sets study time based on the calendar and notifies the user. The notification unit can also adjust the timing of notifications to help users efficiently allocate study time. Furthermore, the notification unit can select a notification method (email, alarm, etc.) and notify the user in an appropriate manner. For example, the notification unit sets study time based on the calendar and notifies the user. The timing of notifications is adjusted to match the user's schedule, supporting efficient learning. The notification method is selected according to the user's preference, and notifications are made via methods such as email or alarms. As a result, the English learning support system according to this embodiment can efficiently improve the user's English proficiency.

[0068] The Information Gathering Department reads business-related documents and emails. These include, but are not limited to, technical documents, business emails, and reports. For example, the Information Gathering Department digitizes and reads business-related documents using scanning technology. Specifically, it scans paper documents using a high-resolution scanner and converts them into text information using OCR (Optical Character Recognition) technology. OCR technology can recognize printed characters with high accuracy and convert them into digital text. This makes it possible to manage paper documents in a digital format. The Information Gathering Department can also directly read documents submitted in digital format. For example, it reads documents submitted in file formats such as PDF and Word documents and analyzes their contents. Furthermore, the Information Gathering Department can also read the contents of emails. Email is a frequently used means of communication in business, and by analyzing its contents, important business-related information can be collected. This allows the Information Gathering Department to collect a wide range of information from diverse document formats and store it in the system-wide database.

[0069] The word extraction unit picks up English words and phrases based on information collected by the information gathering unit. Specifically, it uses natural language processing (NLP) technology to extract English words and phrases from the collected text data. NLP technology analyzes the text data and selects appropriate words and phrases based on information such as word frequency, importance, and context. For example, the word extraction unit prioritizes picking up high-frequency English words. High-frequency words are used frequently in work, so they have a high priority for learning. The word extraction unit can also pick up high-importance English words. High-importance words are words that have particularly important meaning in work and should be prioritized for learning. Furthermore, the word extraction unit can also pick up English words based on context. Context-based selection is a method of selecting appropriate English words according to the content of work-related materials, and it can extract words that are important in specific topics and situations related to work. In this way, the word extraction unit supports users in efficiently learning English words and phrases.

[0070] The email generation unit automatically creates draft English emails based on English words and phrases picked up by the word extraction unit. Specifically, it automatically creates draft English emails based on criteria such as template usage, grammar checks, and content consistency. Using templates provides a standardized email structure, making it easy for users to create emails. For example, templates for greetings, body text, and closing remarks are used to create the basic structure of an email. The email generation unit can also perform grammar checks to create accurate draft English emails. Grammar checks are a process to verify the grammatical accuracy of the draft English emails and are performed automatically using natural language processing technology. Furthermore, the email generation unit can also verify content consistency and create appropriate draft English emails. Content consistency is a process to verify that the content of the draft English email matches business-related documents and is performed automatically by the email generation unit. For example, it selects an appropriate template based on the content of business-related documents and creates a draft English email. In this way, the email generation unit supports users in efficiently creating accurate English emails.

[0071] The Conversation Practice Department provides English conversation practice using conference audio collected by the Information Gathering Department. Specifically, it provides English conversation practice based on criteria such as how the audio is played and the practice scenarios. For example, the Conversation Practice Department plays conference audio and allows users to practice listening to its content. The conference audio is relevant to actual work situations and is designed to help users acquire practical English conversation skills. The Conversation Practice Department also provides practice scenarios, allowing users to simulate actual conversations. The practice scenarios are created assuming specific situations related to work and are designed to help users acquire practical English conversation skills. Furthermore, the Conversation Practice Department can also evaluate the user's pronunciation and provide feedback using speech recognition technology. Speech recognition technology is used to analyze the user's pronunciation and provide accurate feedback. For example, it analyzes English words and phrases pronounced by the user and evaluates the accuracy and fluency of their pronunciation. In this way, the Conversation Practice Department provides support for users to efficiently improve their English conversation skills.

[0072] The notification unit provides notifications about study time. Specifically, it provides notifications based on criteria such as how the calendar is used and the timing of notifications. For example, the notification unit sets study time based on the calendar and notifies the user. The calendar is a tool for setting study time based on the user's schedule, enabling the user to efficiently allocate study time. The notification unit can also adjust the timing of notifications to enable the user to efficiently allocate study time. The timing of notifications is adjusted to match the user's schedule, supporting efficient learning. Furthermore, the notification unit can select a notification method (email, alarm, etc.) and notify the user in an appropriate manner. The notification method is selected according to the user's preference, and notifications are sent via email, alarm, etc. For example, if the user prefers email notifications, the notification unit will send study time notifications via email. If the user prefers alarm notifications, the notification unit will notify the user of study time via alarm. In this way, the notification unit supports the user in efficiently allocating study time and continuing their English learning.

[0073] The word extraction unit can pick out English words and phrases to be memorized based on the day's work content and present them as questions. For example, the word extraction unit can analyze the day's work content and pick out high-frequency English words and phrases. For example, the word extraction unit can select English words based on project progress or meeting content. The word extraction unit can also pick out English words based on task details. For example, the word extraction unit can analyze meeting minutes and pick out important English words. The word extraction unit can also analyze project progress reports and pick out high-frequency English words. Furthermore, the word extraction unit can analyze task details and pick out relevant English words. In this way, by picking out English words and phrases based on work content and presenting them as questions, the user's practical English skills can be improved. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or not using AI. For example, the word extraction unit can input work content into a generating AI, and the generating AI can pick out English words and phrases.

[0074] The email generation unit can automatically create draft English emails based on selected English words and phrases. For example, the email generation unit can create draft English emails using templates. For example, the email generation unit can select an appropriate template based on the content of business-related documents and create a draft English email. The email generation unit can also perform grammatical checks to create accurate draft English emails. For example, the email generation unit can verify the grammatical accuracy of the draft English email. Furthermore, the email generation unit can verify the consistency of the content and create appropriate draft English emails. For example, the email generation unit can verify that the content of business-related documents matches the draft English email. This allows for the automatic creation of draft English emails based on selected English words and phrases, thereby improving the user's English communication skills. Some or all of the above processes in the email generation unit may be performed using AI, or not. For example, the email generation unit can input selected English words and phrases into a generation AI, which can then create a draft English email.

[0075] The conversation practice unit can provide English conversation practice using the day's work content or meeting audio. For example, the conversation practice unit can play meeting audio and have the user practice listening to its content. For example, the conversation practice unit can provide a scenario based on the meeting content and have the user simulate an actual conversation. The conversation practice unit can also use speech recognition technology to evaluate the user's pronunciation and provide feedback. For example, the conversation practice unit can evaluate the user's pronunciation and provide accurate feedback. In this way, by providing English conversation practice using the day's work content or meeting audio, the user's speaking and listening skills can be improved. Some or all of the above processes in the conversation practice unit may be performed using AI, for example, or not using AI. For example, the conversation practice unit can input meeting audio into a generating AI, and the generating AI can create an English conversation practice scenario.

[0076] The notification unit can provide notifications of study time based on a calendar. For example, the notification unit sets study time based on the calendar and notifies the user. For example, the notification unit adjusts the timing of notifications according to the user's schedule. The notification unit can also select a notification method (email, alarm, etc.) and notify the user in an appropriate manner. For example, the notification unit sets study time based on the calendar and notifies the user. The timing of notifications is adjusted according to the user's schedule to support efficient learning. The notification method is selected according to the user's preference and notifications are made by methods such as email or alarm. This allows users to efficiently allocate study time by providing calendar-based study time notifications. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's schedule data into a generating AI, which can then suggest the optimal notification timing.

[0077] The information gathering unit can estimate the user's emotions and adjust the timing of information gathering based on the estimated emotions. For example, if the user is feeling stressed, the information gathering unit will gather information during a time when the user can relax. For example, if the information gathering unit is concentrating, it will gather information at that time. Also, if the user is tired, the information gathering unit can gather information after a break. For example, the information gathering unit can monitor the user's emotions in real time and gather information at the optimal time. By adjusting the timing of information gathering based on the user's emotions, more effective information gathering becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input user emotion data into the generative AI, and the generative AI can suggest the timing of information gathering.

[0078] The information gathering unit can analyze the user's past work history and select the optimal information gathering method. For example, the information gathering unit may prioritize collecting information from sources that the user has frequently used in the past. For example, the information gathering unit may prioritize collecting highly relevant information from the user's work history. The information gathering unit can also analyze the user's work history and propose the optimal information gathering method. For example, the information gathering unit may analyze the user's work history and select the optimal information gathering method. This allows the optimal information gathering method to be selected by analyzing the user's past work history. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's work history data into a generating AI, which can then propose the optimal information gathering method.

[0079] The information gathering unit can filter information based on the user's current projects and areas of interest during the information gathering process. For example, the information gathering unit can prioritize collecting information related to the project the user is currently working on. For example, the information gathering unit can filter information based on the user's areas of interest. The information gathering unit can also collect necessary information according to the user's project progress. For example, the information gathering unit can analyze the user's project progress and collect relevant information. This allows for the collection of highly relevant information by filtering information based on the user's current projects and areas of interest. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's project data into a generating AI, which can then filter the relevant information.

[0080] The information gathering unit can estimate the user's emotions and determine the priority of information to collect based on the estimated emotions. For example, if the user is stressed, the information gathering unit will postpone collecting less important information. For example, if the user is relaxed, the information gathering unit will prioritize collecting detailed information. Also, if the user is in a hurry, the information gathering unit can prioritize collecting highly important information. For example, the information gathering unit can monitor the user's emotions in real time and determine the optimal information priority. This makes it possible to collect information more effectively by determining the priority of information to collect based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or not using AI. For example, the information gathering unit can input user emotion data into a generative AI, and the generative AI can suggest information priorities.

[0081] The information gathering unit can prioritize collecting highly relevant information based on the user's geographical location information during information gathering. For example, the information gathering unit can prioritize collecting information related to the user's current location. For example, the information gathering unit can filter highly relevant information based on the user's geographical location information. The information gathering unit can also update the user's location information in real time and collect the most relevant information. For example, the information gathering unit can analyze the user's location information and collect relevant information. This enables more effective information gathering by prioritizing the collection of highly relevant information based on the user's geographical location information. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's location information data into a generating AI, which can then filter the relevant information.

[0082] The information gathering unit can analyze the user's social media activity and collect relevant information during the information gathering process. For example, the information gathering unit can collect information related to topics the user has shown interest in on social media. For example, the information gathering unit can analyze the user's social media activity and prioritize the collection of highly relevant information. The information gathering unit can also collect information shared by the user's social media followers and friends. For example, the information gathering unit can analyze the user's social media activity and collect relevant information. This allows for the collection of highly relevant information by analyzing the user's social media activity. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's social media data into a generating AI, which can then filter the relevant information.

[0083] The word extraction unit can estimate the user's emotions and adjust the difficulty level of the words extracted based on the estimated emotions. For example, if the user is stressed, the word extraction unit will prioritize extracting simpler words. For example, if the user is relaxed, the word extraction unit will extract more difficult words. The word extraction unit can also extract work-related technical terms if the user is focused. For example, the word extraction unit can monitor the user's emotions in real time and adjust the optimal word difficulty level. This allows for more effective word learning by adjusting the difficulty level of the words extracted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the word extraction unit may be performed using AI, or not using AI. For example, the word extraction unit can input user emotion data into the generative AI, which can then adjust the word difficulty level.

[0084] The word extraction unit can determine the priority of words to extract based on the importance of the task during the word extraction process. For example, the word extraction unit may prioritize extracting words related to important tasks. For example, the word extraction unit may adjust the priority of words to extract according to the importance of the task. The word extraction unit can also postpone extracting words related to less important tasks. For example, the word extraction unit may evaluate the importance of the task and prioritize extracting related words. This allows for more effective word learning by determining the priority of words to extract based on the importance of the task. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input task importance data into a generating AI, and the generating AI can determine the priority of words.

[0085] The word extraction unit can apply different extraction algorithms depending on the category of the work during word extraction. For example, the word extraction unit can apply an algorithm that prioritizes the extraction of specialized terminology for technical work. For example, the word extraction unit can apply an algorithm that prioritizes the extraction of relevant terminology for marketing work. Furthermore, the word extraction unit can also apply an algorithm that prioritizes the extraction of general business terminology for administrative work. For example, the word extraction unit can select the optimal extraction algorithm according to the category of work. By applying different extraction algorithms according to the category of work, more effective word learning becomes possible. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input the category data of work into a generating AI, and the generating AI can apply the optimal extraction algorithm.

[0086] The word extraction unit can estimate the user's emotions and adjust the number of words extracted based on the estimated emotions. For example, if the user is stressed, the word extraction unit will extract fewer words. For example, if the user is relaxed, the word extraction unit will extract more words. The word extraction unit can also extract an appropriate number of words if the user is focused. For example, the word extraction unit can monitor the user's emotions in real time and adjust the optimal number of words. This allows for more effective word learning by adjusting the number of words extracted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input user emotion data into the generative AI, which can then adjust the number of words.

[0087] The word extraction unit can determine the priority of words to extract based on the submission deadline of the task. For example, the word extraction unit may prioritize extracting words related to tasks with approaching deadlines. For example, the word extraction unit may adjust the priority of words to extract according to the submission deadline. The word extraction unit can also postpone extracting words related to tasks with distant deadlines. For example, the word extraction unit may evaluate the submission deadline of the task and prioritize extracting related words. This allows for more effective word learning by determining the priority of words to extract based on the submission deadline of the task. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input task submission deadline data into a generating AI, which can then determine the priority of words.

[0088] The word extraction unit can adjust the order of words extracted based on their relevance to the business. For example, the word extraction unit can prioritize extracting the words most relevant to the business. For example, the word extraction unit can adjust the order of words extracted according to their relevance to the business. The word extraction unit can also postpone extracting less relevant words. For example, the word extraction unit can evaluate the relevance to the business and prioritize extracting relevant words. By adjusting the order of words extracted based on their relevance to the business, more effective word learning becomes possible. Some or all of the above processing in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input business relevance data into a generating AI, which can then adjust the order of the words.

[0089] The email generation unit can estimate the user's emotions and adjust the email's wording based on the estimated emotions. For example, if the user is stressed, the email generation unit will use simple and clear language. For example, if the user is relaxed, the email generation unit will use language that includes detailed explanations. Also, if the user is in a hurry, the email generation unit can use concise language that gets straight to the point. For example, the email generation unit can monitor the user's emotions in real time and adjust the optimal wording. This allows for more effective communication by adjusting the email's wording based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the email generation unit may be performed using AI or not. For example, the email generation unit can input user emotion data into the generative AI, which can then adjust the email's wording.

[0090] The email generation unit can adjust the level of detail in emails based on the importance of the task during email generation. For example, the email generation unit can include detailed information in emails related to important tasks. For example, the email generation unit adjusts the level of detail in emails according to the importance of the task. The email generation unit can also make emails related to less important tasks concise. For example, the email generation unit can evaluate the importance of the task and adjust the level of detail in the relevant email. This allows for more effective communication by adjusting the level of detail in emails based on the importance of the task. Some or all of the above processing in the email generation unit may be performed using AI, for example, or not using AI. For example, the email generation unit can input task importance data into a generation AI, and the generation AI can adjust the level of detail in the emails.

[0091] The email generation unit can apply different generation algorithms depending on the category of the business when generating emails. For example, the email generation unit can apply an algorithm that generates emails containing technical terms for technical tasks. For example, the email generation unit can apply an algorithm that generates emails containing relevant terms for marketing tasks. Furthermore, the email generation unit can also apply an algorithm that generates emails containing general business terms for administrative tasks. For example, the email generation unit selects the optimal generation algorithm according to the category of the business. By applying different generation algorithms according to the category of the business, more effective email generation becomes possible. Some or all of the above processing in the email generation unit may be performed using AI, for example, or without AI. For example, the email generation unit can input business category data into a generation AI, and the generation AI can apply the optimal generation algorithm.

[0092] The email generation unit can estimate the user's emotions and adjust the length of the email based on the estimated emotions. For example, if the user is stressed, the email generation unit can generate a short email. For example, if the user is relaxed, the email generation unit can generate a longer email containing detailed information. The email generation unit can also generate a short, concise email if the user is in a hurry. For example, the email generation unit can monitor the user's emotions in real time and adjust the optimal email length. This allows for more effective communication by adjusting the email length based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the email generation unit may be performed using AI or not. For example, the email generation unit can input user emotion data into the generative AI, which can then adjust the length of the email.

[0093] The email generation unit can determine the priority of emails based on the submission deadlines of tasks when generating emails. For example, the email generation unit can prioritize the generation of emails related to tasks with approaching deadlines. For example, the email generation unit can adjust the priority of emails according to the submission deadline. The email generation unit can also postpone emails related to tasks with distant deadlines. For example, the email generation unit can evaluate the submission deadlines of tasks and determine the priority of related emails. This enables more effective email management by determining the priority of emails based on the submission deadlines of tasks. Some or all of the above processing in the email generation unit may be performed using AI, for example, or not using AI. For example, the email generation unit can input task submission data into a generation AI, and the generation AI can determine the priority of emails.

[0094] The email generation unit can adjust the order of emails based on their relevance to the business when generating them. For example, the email generation unit can prioritize generating emails that are most relevant to the business. For example, the email generation unit adjusts the order of emails according to their relevance to the business. The email generation unit can also postpone less relevant emails. For example, the email generation unit can evaluate the relevance of the business and prioritize generating relevant emails. This allows for more effective email management by adjusting the order of emails based on their relevance to the business. Some or all of the above processing in the email generation unit may be performed using AI, for example, or without AI. For example, the email generation unit can input business relevance data into a generation AI, which can then adjust the order of emails.

[0095] The conversation practice unit can estimate the user's emotions and adjust the content of the conversation practice based on the estimated emotions. For example, if the user is feeling stressed, the conversation practice unit can provide a relaxing conversation practice. For example, if the user is relaxed, the conversation practice unit can provide a more challenging conversation practice. Also, if the user is focused, the conversation practice unit can provide a work-related conversation practice. For example, the conversation practice unit can monitor the user's emotions in real time and adjust the content of the conversation practice to the optimal level. This allows for more effective conversation practice by adjusting the content of the conversation practice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or without AI. For example, the conversation practice unit can input user emotion data into the generative AI, which can then adjust the content of the conversation practice.

[0096] The conversation practice unit can optimize practice content by referring to past conversation history during conversation practice. For example, the conversation practice unit can focus on conversation topics that the user has struggled with in the past. For example, the conversation practice unit can prioritize practicing highly relevant content from the user's past conversation history. The conversation practice unit can also analyze the user's conversation history and suggest the most suitable practice content. For example, the conversation practice unit can analyze the user's conversation history and select the most suitable practice content. By optimizing practice content by referring to past conversation history, more effective conversation practice becomes possible. Some or all of the above processes in the conversation practice unit may be performed using AI, for example, or without AI. For example, the conversation practice unit can input the user's conversation history data into a generating AI, which can then suggest the most suitable practice content.

[0097] The conversation practice unit can apply different practice algorithms depending on the category of work during conversation practice. For example, the conversation practice unit can apply an algorithm that provides conversation practice including specialized terminology for technical work. For example, the conversation practice unit can apply an algorithm that provides conversation practice including relevant terminology for marketing work. Furthermore, the conversation practice unit can also apply an algorithm that provides conversation practice including general business terminology for management work. For example, the conversation practice unit selects the optimal practice algorithm according to the category of work. This makes it possible to perform more effective conversation practice by applying different practice algorithms according to the category of work. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or without using AI. For example, the conversation practice unit can input work category data into a generating AI, and the generating AI can apply the optimal practice algorithm.

[0098] The conversation practice unit can estimate the user's emotions and adjust the frequency of conversation practice based on the estimated emotions. For example, if the user is stressed, the conversation practice unit will reduce the frequency of practice. For example, if the user is relaxed, the conversation practice unit will increase the frequency of practice. The conversation practice unit can also provide practice at an appropriate frequency when the user is focused. For example, the conversation practice unit can monitor the user's emotions in real time and adjust the optimal frequency of practice. This allows for more effective conversation practice by adjusting the frequency of practice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or without AI. For example, the conversation practice unit can input user emotion data into a generative AI, which can then adjust the frequency of conversation practice.

[0099] The conversation practice unit can prioritize practice content based on the deadlines for tasks during conversation practice. For example, the conversation practice unit will prioritize practicing conversations related to tasks with approaching deadlines. For example, the conversation practice unit will adjust the priority of practice content according to the submission deadline. The conversation practice unit can also postpone conversations related to tasks with distant deadlines. For example, the conversation practice unit will evaluate the submission deadlines of tasks and prioritize practicing conversations related to those deadlines. This allows for more effective conversation practice by prioritizing practice content based on the submission deadlines of tasks. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or not using AI. For example, the conversation practice unit can input task submission deadline data into a generating AI, which can then determine the priority of practice content.

[0100] The conversation practice unit can adjust the order of practice content based on the relevance of the work during conversation practice. For example, the conversation practice unit prioritizes practicing conversation content that is most relevant to the work. For example, the conversation practice unit adjusts the order of practice content according to the relevance of the work. The conversation practice unit can also postpone conversation content that is less relevant. For example, the conversation practice unit evaluates the relevance of the work and prioritizes practicing relevant conversation content. By adjusting the order of practice content based on the relevance of the work, more effective conversation practice becomes possible. Some or all of the above processing in the conversation practice unit may be performed using AI, for example, or not using AI. For example, the conversation practice unit can input work relevance data into a generating AI, and the generating AI can adjust the order of practice content.

[0101] The notification unit can estimate the user's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the user is feeling stressed, the notification unit will send a notification during a time when the user can relax. For example, if the notification unit is concentrating, it will send a notification at that time. Also, if the user is tired, the notification unit can send a notification after a break. For example, the notification unit can monitor the user's emotions in real time and adjust the optimal timing of notifications. This allows for more effective notifications by adjusting the timing of notifications based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI. For example, the notification unit can input user emotion data into the generative AI, and the generative AI can adjust the timing of notifications.

[0102] The notification unit can select the optimal notification method by referring to past notification history when sending a notification. For example, the notification unit may prioritize notification methods that the user has preferred to use in the past. For example, the notification unit may suggest the optimal notification method based on the user's past notification history. The notification unit can also analyze the user's notification history and select the optimal notification method. For example, the notification unit may analyze the user's notification history and select the optimal notification method. By selecting the optimal notification method by referring to past notification history, more effective notifications become possible. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's notification history data into a generating AI, which can then suggest the optimal notification method.

[0103] The notification unit can estimate the user's emotions and adjust the content of the notification based on the estimated emotions. For example, if the user is stressed, the notification unit will provide a concise notification. For example, if the user is relaxed, the notification unit will provide a detailed notification. The notification unit can also provide a to-the-point notification if the user is in a hurry. For example, the notification unit can monitor the user's emotions in real time and adjust the notification content to the optimal level. This allows for more effective notifications by adjusting the content of the notification 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not using AI. For example, the notification unit can input user emotion data into the generative AI, which can then adjust the content of the notification.

[0104] The notification unit can select the optimal notification method when sending a notification, taking into account the user's device information. For example, if the user is using a smartphone, the notification unit will prioritize push notifications. For example, if the user is using a tablet, the notification unit will provide a notification method optimized for a larger screen. The notification unit can also provide a concise and highly visible notification method if the user is using a smartwatch. For example, the notification unit will analyze the user's device information and select the optimal notification method. By selecting the optimal notification method considering the user's device information, more effective notifications become possible. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user device information data into a generating AI, which can then propose the optimal notification method.

[0105] The notification unit can select the optimal notification timing by referring to the user's calendar information when sending a notification. For example, the notification unit can adjust the notification timing by referring to appointments registered in the user's calendar. For example, the notification unit can suggest the optimal notification timing from the user's calendar information. The notification unit can also select a notification timing that matches the appointment based on the user's calendar information. For example, the notification unit can analyze the user's calendar information and select the optimal notification timing. By selecting the optimal notification timing by referring to the user's calendar information, more effective notifications become possible. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI. For example, the notification unit can input the user's calendar information data into a generating AI, and the generating AI can suggest the optimal notification timing.

[0106] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0107] The information gathering unit can analyze the user's past learning history and select the most suitable learning materials. For example, the information gathering unit can prioritize collecting materials related to areas the user has struggled with in the past. It can also analyze the user's learning history and prioritize collecting highly relevant materials. Furthermore, the information gathering unit can analyze the user's learning history and suggest the most suitable learning materials. This allows for the selection of optimal learning materials by analyzing the user's past learning history. Some or all of the above processing in the information gathering unit may be performed using AI, for example, or without AI. For example, the information gathering unit can input the user's learning history data into a generating AI, which can then suggest the most suitable learning materials.

[0108] The word extraction unit can estimate the user's emotions and adjust the types of words extracted based on the estimated emotions. For example, if the user is stressed, it can prioritize extracting words that promote relaxation. If the user is relaxed, it can also extract more difficult words. Furthermore, if the user is focused, it can extract specialized terminology related to their work. By adjusting the types of words extracted based on the user's emotions, more effective word learning becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the word extraction unit may be performed using AI, or not using AI. For example, the word extraction unit can input user emotion data into the generative AI, which can then adjust the types of words.

[0109] The email generation unit can analyze the user's past email history and select the most suitable email template. For example, the email generation unit can prioritize selecting templates that the user has used in the past. It can also analyze the user's email history and prioritize selecting templates with high relevance. Furthermore, the email generation unit can analyze the user's email history and suggest the most suitable template. This allows for the selection of the most suitable email template by analyzing the user's past email history. Some or all of the above processes in the email generation unit may be performed using AI, for example, or without AI. For example, the email generation unit can input the user's email history data into a generation AI, which can then suggest the most suitable template.

[0110] The conversation practice unit can estimate the user's emotions and adjust the feedback method during conversation practice based on the estimated emotions. For example, if the user is stressed, gentle feedback can be provided. If the user is relaxed, detailed feedback can be provided. Furthermore, if the user is focused, firm feedback can be provided. By adjusting the feedback method during conversation practice based on the user's emotions, more effective conversation practice becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversation practice unit may be performed using AI, or not using AI. For example, the conversation practice unit can input user emotion data into a generative AI, which can then adjust the feedback method.

[0111] The notification unit can analyze the user's past notification history and select the optimal notification timing. For example, the notification unit can prioritize timings that the user has preferred to receive in the past. It can also analyze the user's notification history and prioritize timings that are highly relevant. Furthermore, the notification unit can analyze the user's notification history and suggest the optimal notification timing. This allows for the selection of the optimal notification timing by analyzing the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's notification history data into a generating AI, which can then suggest the optimal notification timing.

[0112] The information gathering unit can estimate the user's emotions and adjust its information gathering methods based on the estimated emotions. For example, if the user is stressed, it can prioritize collecting simple information. If the user is relaxed, it can also collect detailed information. Furthermore, if the user is focused, it can also collect specialized information. By adjusting the information gathering method based on the user's emotions, more effective information gathering becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information gathering unit may be performed using AI, or not using AI. For example, the information gathering unit can input user emotion data into a generative AI, which can then adjust its information gathering methods.

[0113] The word extraction unit can analyze the user's past learning history and extract the most suitable words. For example, the word extraction unit can prioritize extracting words that the user has struggled with in the past. It can also analyze the user's learning history and prioritize extracting highly relevant words. Furthermore, the word extraction unit can analyze the user's learning history and suggest the most suitable words. This allows for the extraction of optimal words by analyzing the user's past learning history. Some or all of the above-described processes in the word extraction unit may be performed using AI, for example, or without AI. For example, the word extraction unit can input the user's learning history data into a generating AI, which can then suggest the most suitable words.

[0114] The email generation unit can estimate the user's emotions and adjust the tone of the email based on those emotions. For example, if the user is stressed, it can generate an email with a calm tone. If the user is relaxed, it can generate an email with a friendly tone. Furthermore, if the user is focused, it can generate an email with a professional tone. By adjusting the tone of the email based on the user's emotions, more effective communication becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the email generation unit may be performed using AI or not. For example, the email generation unit can input user emotion data into the generative AI, which can then adjust the tone of the email.

[0115] The conversation practice unit can analyze the user's past conversation history and select the optimal conversation practice scenario. For example, the conversation practice unit can prioritize selecting conversation scenarios that the user has struggled with in the past. It can also analyze the user's conversation history and prioritize selecting scenarios with high relevance. Furthermore, the conversation practice unit can analyze the user's conversation history and propose the optimal scenario. This allows for the selection of the optimal conversation practice scenario by analyzing the user's past conversation history. Some or all of the above processes in the conversation practice unit may be performed using AI, for example, or without AI. For example, the conversation practice unit can input the user's conversation history data into a generating AI, which can then propose the optimal scenario.

[0116] The notification unit can estimate the user's emotions and adjust the frequency of notifications based on the estimated emotions. For example, if the user is stressed, the notification frequency can be reduced. Conversely, if the user is relaxed, the notification frequency can be increased. Furthermore, if the user is focused, notifications can be sent at an appropriate frequency. This allows for more effective notifications by adjusting the notification frequency 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 may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI, or not using AI. For example, the notification unit can input user emotion data into a generative AI, which can then adjust the notification frequency.

[0117] The following briefly describes the processing flow for example form 2.

[0118] Step 1: The information gathering department reads business-related documents and emails. These include technical documents, business emails, and reports. The information gathering department can digitize and read these documents using scanning technology, and can also directly read documents submitted in digital format. Furthermore, it can read printed documents using OCR technology. Step 2: The word extraction unit picks out English words and phrases based on the information collected by the information gathering unit. The word extraction unit picks out English words and phrases based on criteria such as frequency, importance, and context. For example, it prioritizes picking out high-frequency and high-importance English words, and selects appropriate English words based on the context. Step 3: The email generation unit automatically creates a draft English email based on the English words and phrases picked up by the word extraction unit. The email generation unit automatically creates the draft English email based on criteria such as template usage, grammar checks, and content consistency. For example, it creates a draft English email using a template, performs a grammar check, and verifies content consistency. Step 4: The Conversation Practice Department provides English conversation practice using the conference audio collected by the Information Gathering Department. The Conversation Practice Department provides English conversation practice based on criteria such as how to play the audio and the practice scenarios. For example, it can play conference audio, allow users to practice listening to its contents, provide practice scenarios, and allow users to simulate actual conversations. It also uses speech recognition technology to evaluate the user's pronunciation and provide feedback. Step 5: The notification unit provides notifications about study time. The notification unit provides notifications about study time based on criteria such as how the calendar is used and the timing of notifications. For example, it sets study time based on the calendar and notifies the user. The timing of notifications is adjusted to match the user's schedule, and the notification method (email, alarm, etc.) is selected and the user is notified in an appropriate manner.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] Each of the multiple elements described above, including the information gathering unit, word extraction unit, email generation unit, conversation practice unit, and notification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the information gathering unit reads business-related documents and emails using the camera 42 and communication I / F 44 of the smart device 14, and digitizes and performs OCR processing using the identification processing unit 290 of the data processing unit 12. The word extraction unit is implemented in the identification processing unit 290 of the data processing unit 12, for example, and picks up English words and phrases from the collected information. The email generation unit is implemented in the identification processing unit 290 of the data processing unit 12, for example, and automatically creates a draft English email based on the picked-up English words and phrases. The conversation practice unit plays back conference audio using the speaker 40B and microphone 38B of the smart device 14 and evaluates the user's pronunciation. The notification unit is implemented in the control unit 46A of the smart device 14, for example, and notifies the user of their study time based on a calendar. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0123] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] Each of the multiple elements described above, including the information gathering unit, word extraction unit, email generation unit, conversation practice unit, and notification unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the information gathering unit reads business-related documents and emails using the camera 42 and communication I / F 44 of the smart glasses 214, and digitizes and performs OCR processing using the identification processing unit 290 of the data processing unit 12. The word extraction unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and picks up English words and phrases from the collected information. The email generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, and automatically creates a draft English email based on the picked-up English words and phrases. The conversation practice unit plays back conference audio using the speaker 240 and microphone 238 of the smart glasses 214 and evaluates the user's pronunciation. The notification unit is implemented, for example, by the control unit 46A of the smart glasses 214, and notifies the user of the study time based on the calendar. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0139] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] Each of the multiple elements described above, including the information gathering unit, word extraction unit, email generation unit, conversation practice unit, and notification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the information gathering unit reads business-related documents and emails using the camera 42 and communication I / F 44 of the headset terminal 314, and digitizes and performs OCR processing using the specific processing unit 290 of the data processing unit 12. The word extraction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and picks up English words and phrases from the collected information. The email generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and automatically creates a draft English email based on the picked-up English words and phrases. The conversation practice unit plays conference audio using the speaker 240 and microphone 238 of the headset terminal 314 and evaluates the user's pronunciation. The notification unit is implemented, for example, by the control unit 46A of the headset terminal 314, and notifies the user of the learning time based on the calendar. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0155] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] Each of the multiple elements described above, including the information gathering unit, word extraction unit, email generation unit, conversation practice unit, and notification unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the information gathering unit reads business-related documents and emails using the camera 42 and communication I / F 44 of the robot 414, and digitizes and performs OCR processing using the identification processing unit 290 of the data processing unit 12. The word extraction unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, and picks up English words and phrases from the collected information. The email generation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, and automatically creates a draft English email based on the picked-up English words and phrases. The conversation practice unit plays back conference audio using the speaker 240 and microphone 238 of the robot 414 and evaluates the user's pronunciation. The notification unit is implemented by, for example, the control unit 46A of the robot 414, and notifies the user of the learning time based on the calendar. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] (Note 1) The information gathering department reads business-related documents and emails, A word extraction unit that picks out English words and phrases based on the information collected by the aforementioned information collection unit, The email generation unit automatically creates a draft English email based on the English words and phrases picked up by the word extraction unit, The Conversation Practice Department provides English conversation practice using conference audio collected by the aforementioned Information Gathering Department, It includes a notification unit that notifies the time spent studying. A system characterized by the following features. (Note 2) The word extraction unit, Based on the day's work, select English words and phrases that you should memorize and present them as questions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned email generation unit, Automatically generates draft English emails based on selected English words and phrases. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned conversation practice section, We provide English conversation practice using the day's work content and meeting audio. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, Calendar notifications for study time The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned information gathering unit, It estimates the user's emotions and adjusts the timing of information collection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned information gathering unit, Analyze the user's past work history and select the optimal information gathering method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned information gathering unit, When gathering information, 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 9) The aforementioned information gathering unit, It estimates the user's emotions and prioritizes the information to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned information gathering unit, When gathering information, the system prioritizes collecting highly relevant information based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned information gathering unit, When gathering information, we analyze users' social media activity and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The word extraction unit, It estimates the user's emotions and adjusts the difficulty level of the words extracted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The word extraction unit, When extracting words, prioritize the words to be extracted based on their importance in the business. The system described in Appendix 1, characterized by the features described herein. (Note 14) The word extraction unit, When extracting words, different extraction algorithms are applied depending on the category of the task. The system described in Appendix 1, characterized by the features described herein. (Note 15) The word extraction unit, It estimates the user's emotions and adjusts the number of words extracted based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The word extraction unit, When extracting words, prioritize the words to be extracted based on the submission deadline for the task. The system described in Appendix 1, characterized by the features described herein. (Note 17) The word extraction unit, When extracting words, adjust the order of the extracted words based on their relevance to the business. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned email generation unit, It estimates the user's emotions and adjusts the email's wording based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned email generation unit, When generating emails, adjust the level of detail based on the importance of the task. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned email generation unit, When generating emails, different generation algorithms are applied depending on the category of the business. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned email generation unit, It estimates the user's emotions and adjusts the length of the email based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned email generation unit, When generating emails, prioritize them based on the submission deadline for each task. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned email generation unit, When generating emails, the order of emails is adjusted based on their relevance to the business. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned conversation practice section, The system estimates the user's emotions and adjusts the content of the conversation practice based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned conversation practice section, During conversation practice, refer to past conversation history to optimize the practice content. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned conversation practice section, During conversation practice, different practice algorithms are applied depending on the category of work. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned conversation practice section, It estimates the user's emotions and adjusts the frequency of conversation practice based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned conversation practice section, When practicing conversation, prioritize the practice content based on the deadlines for submitting work assignments. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned conversation practice section, During conversation practice, adjust the order of practice content based on its relevance to the work. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, It estimates the user's emotions and adjusts the timing of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned notification unit, When sending a notification, the system will refer to past notification history to select the most suitable notification method. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned notification unit, It estimates the user's emotions and adjusts the content of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned notification unit, When sending notifications, the system selects the most suitable notification method, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned notification unit, When sending a notification, the system will refer to the user's calendar information to select the optimal notification timing. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0191] 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 information gathering department reads business-related documents and emails, A word extraction unit that picks out English words and phrases based on the information collected by the aforementioned information collection unit, The email generation unit automatically creates a draft English email based on the English words and phrases picked up by the word extraction unit, The Conversation Practice Department provides English conversation practice using conference audio collected by the aforementioned Information Gathering Department, It includes a notification unit that notifies the time spent studying. A system characterized by the following features.

2. The word extraction unit, Based on the day's work, select English words and phrases that you should memorize and present them as questions. The system according to feature 1.

3. The aforementioned email generation unit, Automatically generates draft English emails based on selected English words and phrases. The system according to feature 1.

4. The aforementioned conversation practice section, We provide English conversation practice using the day's work content and meeting audio. The system according to feature 1.

5. The aforementioned notification unit, Calendar notifications for study time The system according to feature 1.

6. The aforementioned information gathering unit, It estimates the user's emotions and adjusts the timing of information collection based on the estimated user emotions. The system according to feature 1.

7. The aforementioned information gathering unit, Analyze the user's past work history and select the optimal information gathering method. The system according to feature 1.

8. The aforementioned information gathering unit, When gathering information, filtering is performed based on the user's current projects and areas of interest. The system according to feature 1.

9. The aforementioned information gathering unit, It estimates the user's emotions and prioritizes the information to collect based on those estimated emotions. The system according to feature 1.

10. The aforementioned information gathering unit, When gathering information, the system prioritizes collecting highly relevant information based on the user's geographical location. The system according to feature 1.

Images