system

Abstract

The system according to the embodiment aims to efficiently manage tasks and schedules that arise in everyday conversations. [Solution] A system according to an embodiment includes a speech recognition unit, an extraction unit, and an organization unit. The speech recognition unit transcribes conversations. The extraction unit extracts tasks and schedules from the text transcribed by the speech recognition unit. The organization unit organizes the tasks and schedules extracted by the extraction unit based on specific criteria.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have had the problem of making it difficult to efficiently manage tasks and schedules that arise in everyday conversations.

[0005] The system according to the embodiment aims to efficiently manage tasks and schedules that arise in everyday conversations. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, an extraction unit, and an organization unit. The speech recognition unit transcribes a conversation. The extraction unit extracts tasks and schedules from the text transcribed by the speech recognition unit. The organization unit organizes the tasks and schedules extracted by the extraction unit based on specific criteria. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently manage tasks and schedules that arise in everyday conversations. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A home task management system according to an embodiment of the present invention transcribes everyday conversations within a household and automatically organizes tasks and schedules. This home task management system converts conversations into text using speech recognition technology and extracts tasks and schedules using natural language processing. The system then organizes the conversations into categories in a management tool. For example, if a conversation includes the phrase "I need to buy milk tomorrow," the system automatically organizes the conversation into a "shopping" category. The system also includes features for prioritizing tasks, setting reminders, and allowing multiple household members to use the system simultaneously. Furthermore, from the perspective of privacy protection, the system also manages the method for storing voice data and access permissions. This improves the efficiency of home task and schedule management and supports housework. For example, the home task management system converts conversations into text using speech recognition technology. For example, the speech recognition technology converts conversations within a household into text in real time, and then uses natural language processing to extract tasks and schedules. The home task management system then organizes the extracted tasks and schedules into categories. For example, the tasks are automatically classified into categories such as "shopping" and "family events." The home task management system also prioritizes tasks. For example, it determines the priority of tasks based on urgency and importance. The home task management system also provides a reminder function. For example, it notifies users when a task deadline is approaching. Furthermore, the home task management system has a function that can be used by multiple members of the household at the same time. For example, it centrally manages and adjusts each member's schedule. Finally, the home task management system manages the method of storing voice data and access permissions to protect privacy. For example, it encrypts and stores voice data and sets access permissions. As a result, the home task management system can efficiently manage household tasks and schedules and reduce the burden of housework.

[0029] A home task management system according to an embodiment includes a voice recognition unit, an extraction unit, and an organization unit. The voice recognition unit transcribes everyday conversations held within a household. For example, the voice recognition unit converts conversations into text in real time using voice recognition technology. The voice recognition unit performs highly accurate transcription using, for example, a voice recognition algorithm. The voice recognition unit can also identify the voices of multiple household members and perform individual transcriptions. For example, the voice recognition unit learns the voice characteristics of each member and applies an individually optimized recognition model. The extraction unit extracts tasks and schedules from the text transcribed by the voice recognition unit. For example, the extraction unit analyzes the text using natural language processing technology to extract tasks and schedules. The extraction unit identifies important tasks and schedules using, for example, keyword extraction technology. The extraction unit can also analyze the context of the conversation and evaluate the importance of the tasks and schedules. For example, the extraction unit evaluates tasks and schedules that are emphasized in the conversation as being highly important. The organization unit organizes the tasks and schedules extracted by the extraction unit based on specific criteria. For example, the organizing unit classifies tasks and schedules by category. The organizing unit automatically classifies tasks into categories such as "shopping" and "family events." The organizing unit can also prioritize tasks. For example, the organizing unit determines the priority of tasks based on urgency and importance. Furthermore, the organizing unit can provide a reminder function. For example, the organizing unit notifies users when a task deadline is approaching. As a result, the home task management system according to the embodiment can efficiently manage home tasks and schedules and reduce the burden of housework.

[0030] The organizing unit can prioritize tasks. The organizing unit determines the priorities based on, for example, the urgency and importance of the tasks. For example, the organizing unit prioritizes tasks with a high urgency. The organizing unit can also prioritize tasks with a high importance. Furthermore, the organizing unit can determine the priorities based on task deadlines. For example, the organizing unit prioritizes tasks with an upcoming deadline. In this way, by prioritizing tasks, important tasks can be prioritized. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can determine the priorities using an AI model that evaluates the urgency and importance of tasks.

[0031] The organizing unit can set reminders. For example, the organizing unit notifies the user when a task deadline is approaching. For example, the organizing unit sets the timing of the reminder notification. The organizing unit can also set the method of reminder notification. For example, the organizing unit provides methods such as voice notification or text notification. Furthermore, the organizing unit can also set the priority of reminders. For example, the organizing unit prioritizes reminders for important tasks. This makes it possible to prevent tasks from being forgotten by setting reminders. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can set reminders using an AI model that determines the timing and method of reminder notification.

[0032] The management unit can centrally manage the schedules of multiple members in a household. The management unit, for example, collects and centrally manages the schedules of each member in a household. For example, the management unit displays each member's schedule in a calendar format. The management unit can also adjust each member's schedule. For example, the management unit adjusts overlapping schedules and proposes an optimal schedule. Furthermore, the management unit can set reminders based on each member's schedule. For example, the management unit sets reminders for important schedules. This centralized management of the schedules of multiple members in a household makes it easier to adjust the schedules. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can centrally manage the schedules using an AI model that analyzes each member's schedule and proposes an optimal schedule.

[0033] The privacy management unit can manage the storage method and access authority of the audio data. The privacy management unit, for example, encrypts and stores the audio data. For example, the privacy management unit sets the storage period of the audio data. The privacy management unit can also set access authority of the audio data. For example, the privacy management unit sets the access authority based on the user role. Furthermore, the privacy management unit can also manage an access log of the audio data. For example, the privacy management unit records a log of users who access the audio data. In this way, privacy protection is enhanced by managing the storage method and access authority of the audio data. Some or all of the above-mentioned processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can enhance privacy protection by using an AI model that manages the storage method and access authority of the audio data.

[0034] The voice recognition unit can improve the accuracy of voice recognition by removing background sounds in the home during voice recognition. The voice recognition unit can remove background sounds in the home using, for example, noise canceling technology. For example, the voice recognition unit can filter out television sounds and recognize only conversation sounds. The voice recognition unit can also filter out kitchen noise and recognize only conversation sounds. Furthermore, the voice recognition unit can filter out children's playing sounds and recognize only conversation sounds. In this way, the accuracy of voice recognition is improved by removing background sounds in the home. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition by using an AI model that removes background sounds using noise canceling technology.

[0035] During voice recognition, the voice recognition unit can learn the characteristics of a speaker's voice and apply an individually optimized recognition model. The voice recognition unit can learn, for example, the speaker's tone and accent. For example, the voice recognition unit can learn the characteristics of the voices of all family members and apply individually optimized recognition models. The voice recognition unit can also learn the speed and rhythm of a speaker's voice to improve recognition accuracy. Furthermore, the voice recognition unit can collect voice samples to learn the characteristics of a speaker's voice. For example, the voice recognition unit can collect voice samples of each member and learn the voice characteristics using a learning algorithm. In this way, learning the characteristics of a speaker's voice improves the accuracy of voice recognition. Some or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition using an AI model that learns the characteristics of a speaker's voice and applies individually optimized recognition models.

[0036] The voice recognition unit can switch the recognition mode during voice recognition depending on a specific location in the home. The voice recognition unit switches the recognition mode depending on, for example, each location in the home. For example, in the kitchen, the voice recognition unit filters cooking sounds and switches to a mode that recognizes only conversational voices. The voice recognition unit can also filter television sounds in the living room and switch to a mode that recognizes only conversational voices. Furthermore, the voice recognition unit can switch to a mode that adjusts voice recognition sensitivity to a quiet environment in the bedroom. In this way, switching the recognition mode depending on a specific location in the home improves the accuracy of voice recognition. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition using an AI model that switches the recognition mode depending on each location in the home.

[0037] The voice recognition unit can improve the accuracy of voice recognition by working with multiple devices in the home. For example, the voice recognition unit can improve the accuracy of voice recognition by working with a smart speaker and using multiple microphones. For example, the voice recognition unit can improve the accuracy of voice recognition based on location information by working with a smartphone. The voice recognition unit can also improve the accuracy of voice recognition by working with a smart TV. This improves the accuracy of voice recognition by working with multiple devices in the home. Some or all of the above-mentioned processing in the voice recognition unit may be performed using AI, for example, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition by using an AI model that works with multiple devices in the home to improve the accuracy of voice recognition.

[0038] The extraction unit can analyze the context of the conversation during extraction to evaluate the importance of tasks and schedules. The extraction unit analyzes the context of the conversation using, for example, natural language processing technology. For example, the extraction unit evaluates tasks and schedules that are emphasized in the conversation as being highly important. The extraction unit can also evaluate tasks and schedules that are frequently mentioned in the conversation as being highly important. Furthermore, the extraction unit can evaluate tasks and schedules that include specific keywords in the conversation as being highly important. In this way, the importance of tasks and schedules can be evaluated by analyzing the context of the conversation. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can evaluate the importance using an AI model that analyzes the context of the conversation to evaluate the importance of tasks and schedules.

[0039] During extraction, the extraction unit can automatically extract similar tasks and schedules by referring to past conversation histories. The extraction unit, for example, automatically extracts similar tasks and schedules by referring to past conversation histories. For example, the extraction unit prioritizes extraction of frequently mentioned tasks and schedules based on the past conversation histories. The extraction unit can also analyze past conversation histories to find patterns and extract tasks and schedules. This allows similar tasks and schedules to be automatically extracted by referring to past conversation histories. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can improve extraction accuracy by using an AI model that automatically extracts similar tasks and schedules by referring to past conversation histories.

[0040] During extraction, the extraction unit can prioritize extracting tasks related to specific events in the home. For example, the extraction unit prioritizes extracting tasks related to specific events in the home (e.g., birthdays and anniversaries). For example, the extraction unit prioritizes extracting tasks related to birthdays. The extraction unit can also prioritize extracting tasks related to anniversaries. Furthermore, the extraction unit can prioritize extracting tasks related to family events. In this way, by preferentially extracting tasks related to specific events in the home, important events will not be missed. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can improve extraction accuracy by using an AI model that prioritizes extracting tasks related to specific events in the home.

[0041] During extraction, the extraction unit can extract tasks and schedules by integrating conversations between multiple household members. For example, the extraction unit extracts tasks and schedules by integrating conversations between multiple household members. For example, the extraction unit analyzes conversations between multiple household members and extracts common tasks and schedules. The extraction unit can also extract overlapping tasks and schedules based on conversations between multiple household members. Furthermore, the extraction unit can extract optimal tasks and schedules based on conversations between multiple household members. In this way, common tasks and schedules can be extracted by integrating conversations between multiple household members. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can improve extraction accuracy by using an AI model that integrates conversations between multiple household members to extract tasks and schedules.

[0042] The organizing unit can analyze the relevance of tasks and schedules and automatically group them when organizing. For example, the organizing unit analyzes the relevance of tasks and schedules and automatically groups them. For example, the organizing unit automatically groups related tasks and schedules. The organizing unit can also automatically group tasks and schedules in the same category. Furthermore, the organizing unit can automatically group tasks and schedules that are close in time. In this way, tasks and schedules can be automatically grouped by analyzing the relevance of tasks and schedules. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can perform grouping using an AI model that analyzes the relevance of tasks and schedules and automatically groups them.

[0043] When organizing, the organizing unit can learn past organizing patterns and propose an optimal organizing method. For example, the organizing unit learns past organizing patterns and proposes an optimal organizing method. For example, the organizing unit proposes an optimal organizing method based on past organizing patterns. The organizing unit can also analyze the user's organizing patterns and propose an optimal organizing method. Furthermore, the organizing unit can learn organizing patterns within the home and propose an optimal organizing method. In this way, the optimal organizing method can be proposed by learning past organizing patterns. Some or all of the above-mentioned processing in the organizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the organizing unit can propose an organizing method using an AI model that learns past organizing patterns and proposes an optimal organizing method.

[0044] When organizing, the organizing unit can prioritize displaying tasks related to a specific member of the household. For example, the organizing unit prioritizes displaying tasks related to a specific member of the household. For example, the organizing unit prioritizes displaying tasks of a specific member of the household. The organizing unit can also prioritize displaying schedules of a specific member of the household. Furthermore, the organizing unit can also prioritize displaying tasks and schedules of a specific member of the household. This makes it possible to meet individual needs by prioritized displaying tasks related to a specific member of the household. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can adjust the display order using an AI model that prioritizes displaying tasks related to a specific member of the household.

[0045] During organization, the organization unit can provide a display method optimized for a specific device in the home. The organization unit, for example, provides a display method optimized for a specific device in the home (e.g., a smartphone or a tablet). For example, the organization unit provides a display method optimized for a smartphone. The organization unit can also provide a display method optimized for a tablet. Furthermore, the organization unit can also provide a display method optimized for a smart TV. This improves visibility by providing a display method optimized for a specific device in the home. Some or all of the above-described processing in the organization unit may be performed using, for example, AI, or may be performed without using AI. For example, the organization unit can optimize the display method using an AI model that provides a display method optimized for a specific device in the home.

[0046] The prioritization unit can automatically determine the priorities by evaluating the urgency and importance of tasks when prioritizing. For example, the prioritization unit can automatically determine the priorities by evaluating the urgency and importance of tasks. For example, the prioritization unit can evaluate the urgency of tasks and determine the priorities. The prioritization unit can also evaluate the importance of tasks and determine the priorities. Furthermore, the prioritization unit can comprehensively evaluate the urgency and importance of tasks and determine the priorities. In this way, optimal priorities can be determined by evaluating the urgency and importance of tasks. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can determine the priorities using an AI model that evaluates the urgency and importance of tasks.

[0047] The prioritization unit can suggest optimal priorities by referring to past task completion histories when prioritizing tasks. The prioritization unit, for example, suggests optimal priorities by referring to past task completion histories. For example, the prioritization unit suggests optimal priorities based on past task completion histories. The prioritization unit can also analyze the user's task completion history and suggest optimal priorities. Furthermore, the prioritization unit can also suggest optimal priorities based on task completion histories within the home. In this way, optimal priorities can be suggested by referring to past task completion histories. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can suggest priorities using an AI model that suggests optimal priorities by referring to past task completion histories.

[0048] During prioritization, the prioritization unit can prioritize tasks related to specific household events. For example, the prioritization unit prioritizes tasks related to specific household events (e.g., birthdays and anniversaries). For example, the prioritization unit prioritizes tasks related to birthdays. The prioritization unit can also prioritize tasks related to anniversaries. Furthermore, the prioritization unit can also prioritize tasks related to family events. In this way, by prioritizing tasks related to specific household events, important events will not be missed. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can set priorities using an AI model that prioritizes tasks related to specific household events.

[0049] When prioritizing tasks, the prioritization unit can determine the priorities by integrating the opinions of multiple household members. For example, the prioritization unit determines the priorities by integrating the opinions of multiple household members. For example, the prioritization unit determines the priorities of tasks based on the opinions of multiple household members. The prioritization unit can also adjust the priorities of tasks by reflecting the opinions of multiple household members. Furthermore, the prioritization unit can determine optimal priorities based on the opinions of multiple household members. In this way, optimal priorities can be determined by integrating the opinions of multiple household members. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can determine the priorities using an AI model that determines priorities by integrating the opinions of multiple household members.

[0050] When setting a reminder, the reminder unit can evaluate the urgency and importance of a task and determine the optimal notification timing. The reminder unit, for example, evaluates the urgency and importance of a task and determines the optimal notification timing. For example, the reminder unit evaluates the urgency of a task and determines the optimal notification timing. The reminder unit can also evaluate the importance of a task and determine the optimal notification timing. Furthermore, the reminder unit can comprehensively evaluate the urgency and importance of a task and determine the optimal notification timing. In this way, the optimal notification timing can be determined by evaluating the urgency and importance of a task. Some or all of the above-described processing in the reminder unit may be performed using, for example, AI, or may be performed without using AI. For example, the reminder unit can determine the notification timing using an AI model that evaluates the urgency and importance of a task.

[0051] When setting a reminder, the reminder unit can suggest the optimal notification method by referring to past reminder history. For example, the reminder unit can suggest the optimal notification method by referring to past reminder history. For example, the reminder unit can suggest the optimal notification method based on the past reminder history. The reminder unit can also analyze the user's reminder history and suggest the optimal notification method. Furthermore, the reminder unit can also suggest the optimal notification method based on the reminder history within the home. In this way, the optimal notification method can be suggested by referring to the past reminder history. Some or all of the above-mentioned processing in the reminder unit may be performed using, for example, AI, or may be performed without using AI. For example, the reminder unit can suggest the notification method using an AI model that suggests the optimal notification method by referring to the past reminder history.

[0052] When setting a reminder, the reminder unit can prioritize reminders related to specific events in the home. For example, the reminder unit prioritizes reminders related to specific events in the home (e.g., birthdays and anniversaries). For example, the reminder unit prioritizes reminders related to birthdays. The reminder unit can also prioritize reminders related to anniversaries. Furthermore, the reminder unit can also prioritize reminders related to family events. In this way, by prioritizing reminders related to specific events in the home, important events will not be missed. Some or all of the above-described processing in the reminder unit may be performed using, for example, AI, or may be performed without using AI. For example, the reminder unit can set reminders using an AI model that prioritizes reminders related to specific events in the home.

[0053] When a reminder is set, the reminder unit can provide notifications in cooperation with multiple devices in the home. The reminder unit can provide notifications in cooperation with multiple devices in the home. For example, the reminder unit can provide notifications in cooperation with a smartphone. The reminder unit can also provide notifications in cooperation with a smart speaker. Furthermore, the reminder unit can provide notifications in cooperation with a smart watch. This allows for more efficient reminder notifications by linking with multiple devices in the home. Some or all of the above-described processing in the reminder unit can be performed using, for example, AI, or can be performed without using AI. For example, the reminder unit can optimize the notification method using an AI model that provides notifications in cooperation with multiple devices in the home.

[0054] During management, the management unit can analyze the schedule of each member of the household and propose an optimal schedule. For example, the management unit analyzes the schedule of each member of the household and proposes an optimal schedule. For example, the management unit proposes a common schedule based on the schedules of each member of the household. The management unit can also analyze the schedule of each member of the household and propose an optimal schedule. Furthermore, the management unit can analyze the schedule of each member of the household and propose an optimal schedule. In this way, an optimal schedule can be proposed by analyzing the schedule of each member of the household. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can propose a schedule using an AI model that analyzes the schedule of each member of the household and proposes an optimal schedule.

[0055] During management, the management unit can suggest an optimal schedule management method by referring to past schedule history. The management unit, for example, refers to past schedule history to suggest an optimal schedule management method. For example, the management unit suggests an optimal schedule management method based on past schedule history. The management unit can also analyze the user's schedule history and suggest an optimal schedule management method. Furthermore, the management unit can also suggest an optimal schedule management method based on schedule history within the home. In this way, the optimal schedule management method can be suggested by referring to past schedule history. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can suggest a management method using an AI model that suggests an optimal schedule management method by referring to past schedule history.

[0056] During management, the management unit can prioritize displaying schedules related to specific events in the home. For example, the management unit prioritizes displaying schedules related to specific events in the home (e.g., birthdays and anniversaries). For example, the management unit prioritizes displaying schedules related to birthdays. The management unit can also prioritize displaying schedules related to anniversaries. Furthermore, the management unit can also prioritize displaying schedules related to family events. In this way, by prioritized displaying schedules related to specific events in the home, important events will not be missed. Some or all of the above-described processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can display schedules using an AI model that prioritizes displaying schedules related to specific events in the home.

[0057] During management, the management unit can manage schedules in cooperation with multiple devices in the home. The management unit, for example, manages schedules in cooperation with multiple devices in the home. For example, the management unit manages schedules in cooperation with a smartphone. The management unit can also manage schedules in cooperation with a smart speaker. Furthermore, the management unit can also manage schedules in cooperation with a smart watch. In this way, schedule management becomes more efficient by working with multiple devices in the home. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can improve the efficiency of schedule management by using an AI model that manages schedules in cooperation with multiple devices in the home.

[0058] During privacy management, the privacy management unit can enhance security by optimizing the method of storing audio data. The privacy management unit, for example, encrypts and stores audio data. For example, the privacy management unit shortens the storage period of audio data. The privacy management unit can also strictly manage access rights to audio data. This optimizes the method of storing audio data, thereby enhancing security. Some or all of the above-described processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can enhance security by using an AI model that optimizes the method of storing audio data.

[0059] During privacy management, the privacy management unit can finely set access permissions to grant appropriate permissions to each member of the household. For example, the privacy management unit sets access permissions individually for each member of the household. For example, the privacy management unit sets access permissions for specific tasks or schedules. The privacy management unit can also set access permissions according to the role of each member of the household. This allows for finely setting access permissions to grant appropriate permissions to each member of the household. Some or all of the above-mentioned processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can set permissions using an AI model that finely sets access permissions.

[0060] During privacy management, the privacy management unit can prioritize protection of data related to specific events in the home. For example, the privacy management unit prioritizes protection of data related to specific events in the home (e.g., birthdays and anniversaries). For example, the privacy management unit prioritizes protection of data related to birthdays. The privacy management unit can also prioritize protection of data related to anniversaries. Furthermore, the privacy management unit can prioritize protection of data related to family events. This prioritizes protection of data related to specific events in the home, thereby enhancing the security of important data. Some or all of the above-described processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can enhance data protection using an AI model that prioritizes protection of data related to specific events in the home.

[0061] During privacy management, the privacy management unit can manage privacy settings in cooperation with multiple devices in the home. The privacy management unit, for example, manages privacy settings in cooperation with multiple devices in the home. For example, the privacy management unit manages privacy settings in cooperation with a smartphone. The privacy management unit can also manage privacy settings in cooperation with a smart speaker. Furthermore, the privacy management unit can also manage privacy settings in cooperation with a smartwatch. This improves the efficiency of privacy setting management by cooperation with multiple devices in the home. Some or all of the above-described processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can manage privacy settings using an AI model that manages privacy settings in cooperation with multiple devices in the home.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] The home task management system may further include a progress tracking unit that tracks the progress of tasks in real time. The progress tracking unit periodically checks the progress of each task and visualizes the progress. For example, the progress tracking unit may display the completion rate of a task as a percentage. The progress tracking unit may also issue an alert if the progress of a task is behind schedule. Furthermore, the progress tracking unit may automatically adjust reminders based on the progress of the task. This allows for efficient task management by understanding the progress of tasks in real time.

[0064] The home task management system may further include a dependency management unit that manages task dependencies. The dependency management unit analyzes dependencies between tasks and optimizes the order of tasks. For example, if a task cannot start until the next task is completed, the dependency management unit automatically adjusts the order. The dependency management unit can also set reminders based on task dependencies. Furthermore, the dependency management unit can notify users when task dependencies change. In this way, managing task dependencies enables efficient task progress.

[0065] The home task management system may further include a reward providing unit that provides a reward according to the progress of a task. The reward providing unit provides a reward to the user when the task is completed. For example, the reward providing unit may award points according to the completion of a task. The reward providing unit may also provide a system that allows the user to receive benefits by accumulating points. Furthermore, the reward providing unit may provide rewards in stages according to the progress of the task. This increases motivation for completing tasks and enables efficient task management.

[0066] The home task management system may further include a feedback providing unit that provides feedback according to the progress of the task. The feedback providing unit provides feedback to the user according to the progress of the task. For example, the feedback providing unit provides positive feedback when the task is progressing smoothly. The feedback providing unit may also suggest improvements when the progress of the task is delayed. Furthermore, the feedback providing unit may also provide advice based on the progress of the task. This allows for efficient task management by receiving feedback on the progress of the task.

[0067] The home task management system may further include a reallocation unit that automatically reallocates tasks according to the progress of the tasks. The reallocation unit reallocates tasks to other members according to the progress of the tasks. For example, if a member's task is behind schedule, the reallocation unit reallocates the task to another member. The reallocation unit may also reallocate a task to the most suitable member based on the progress of the task. Furthermore, the reallocation unit may notify when a task has been reallocated. This allows for efficient task management by flexibly reallocating tasks according to the progress of the task.

[0068] The processing flow of the first embodiment will be briefly explained below.

[0069] Step 1: The voice recognition unit transcribes everyday conversations within the home. For example, the voice recognition unit uses voice recognition technology to convert conversations into text in real time. The voice recognition unit performs highly accurate transcription using a voice recognition algorithm. The voice recognition unit can also identify the voices of multiple members within the home and transcribe them individually. For example, the voice recognition unit learns the voice characteristics of each member and applies an individually optimized recognition model. Step 2: The extraction unit extracts tasks and schedules from the text transcribed by the speech recognition unit. For example, the extraction unit analyzes the text using natural language processing technology and extracts tasks and schedules. The extraction unit identifies important tasks and schedules using keyword extraction technology. The extraction unit can also analyze the context of the conversation and evaluate the importance of the tasks and schedules. For example, the extraction unit evaluates tasks and schedules that are emphasized in the conversation as being highly important. Step 3: The organizer organizes the tasks and schedules extracted by the extractor based on specific criteria. For example, the organizer classifies tasks and schedules by category. The organizer automatically classifies them into categories such as "shopping" and "family events." The organizer can also prioritize tasks. For example, the organizer determines the priority of tasks based on urgency and importance. Furthermore, the organizer can provide a reminder function. For example, the organizer notifies the user when a task deadline is approaching.

[0070] (Example 2) A home task management system according to an embodiment of the present invention transcribes everyday conversations within a household and automatically organizes tasks and schedules. This home task management system converts conversations into text using speech recognition technology and extracts tasks and schedules using natural language processing. The system then organizes the conversations into categories in a management tool. For example, if a conversation includes the phrase "I need to buy milk tomorrow," the system automatically organizes the conversation into a "shopping" category. The system also includes features for prioritizing tasks, setting reminders, and allowing multiple household members to use the system simultaneously. Furthermore, from the perspective of privacy protection, the system also manages the method for storing voice data and access permissions. This improves the efficiency of home task and schedule management and supports housework. For example, the home task management system converts conversations into text using speech recognition technology. For example, the speech recognition technology converts conversations within a household into text in real time, and then uses natural language processing to extract tasks and schedules. The home task management system then organizes the extracted tasks and schedules into categories. For example, the tasks are automatically classified into categories such as "shopping" and "family events." The home task management system also prioritizes tasks. For example, it determines the priority of tasks based on urgency and importance. The home task management system also provides a reminder function. For example, it notifies users when a task deadline is approaching. Furthermore, the home task management system has a function that can be used by multiple members of the household at the same time. For example, it centrally manages and adjusts each member's schedule. Finally, the home task management system manages the method of storing voice data and access permissions to protect privacy. For example, it encrypts and stores voice data and sets access permissions. As a result, the home task management system can efficiently manage household tasks and schedules and reduce the burden of housework.

[0071] A home task management system according to an embodiment includes a voice recognition unit, an extraction unit, and an organization unit. The voice recognition unit transcribes everyday conversations held within a household. For example, the voice recognition unit converts conversations into text in real time using voice recognition technology. The voice recognition unit performs highly accurate transcription using, for example, a voice recognition algorithm. The voice recognition unit can also identify the voices of multiple household members and perform individual transcriptions. For example, the voice recognition unit learns the voice characteristics of each member and applies an individually optimized recognition model. The extraction unit extracts tasks and schedules from the text transcribed by the voice recognition unit. For example, the extraction unit analyzes the text using natural language processing technology to extract tasks and schedules. The extraction unit identifies important tasks and schedules using, for example, keyword extraction technology. The extraction unit can also analyze the context of the conversation and evaluate the importance of the tasks and schedules. For example, the extraction unit evaluates tasks and schedules that are emphasized in the conversation as being highly important. The organization unit organizes the tasks and schedules extracted by the extraction unit based on specific criteria. For example, the organizing unit classifies tasks and schedules by category. The organizing unit automatically classifies tasks into categories such as "shopping" and "family events." The organizing unit can also prioritize tasks. For example, the organizing unit determines the priority of tasks based on urgency and importance. Furthermore, the organizing unit can provide a reminder function. For example, the organizing unit notifies users when a task deadline is approaching. As a result, the home task management system according to the embodiment can efficiently manage home tasks and schedules and reduce the burden of housework.

[0072] The organizing unit can prioritize tasks. The organizing unit determines the priorities based on, for example, the urgency and importance of the tasks. For example, the organizing unit prioritizes tasks with a high urgency. The organizing unit can also prioritize tasks with a high importance. Furthermore, the organizing unit can determine the priorities based on task deadlines. For example, the organizing unit prioritizes tasks with an upcoming deadline. In this way, by prioritizing tasks, important tasks can be prioritized. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can determine the priorities using an AI model that evaluates the urgency and importance of tasks.

[0073] The organizing unit can set reminders. For example, the organizing unit notifies the user when a task deadline is approaching. For example, the organizing unit sets the timing of the reminder notification. The organizing unit can also set the method of reminder notification. For example, the organizing unit provides methods such as voice notification or text notification. Furthermore, the organizing unit can also set the priority of reminders. For example, the organizing unit prioritizes reminders for important tasks. This makes it possible to prevent tasks from being forgotten by setting reminders. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can set reminders using an AI model that determines the timing and method of reminder notification.

[0074] The management unit can centrally manage the schedules of multiple members in a household. The management unit, for example, collects and centrally manages the schedules of each member in a household. For example, the management unit displays each member's schedule in a calendar format. The management unit can also adjust each member's schedule. For example, the management unit adjusts overlapping schedules and proposes an optimal schedule. Furthermore, the management unit can set reminders based on each member's schedule. For example, the management unit sets reminders for important schedules. This centralized management of the schedules of multiple members in a household makes it easier to adjust the schedules. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can centrally manage the schedules using an AI model that analyzes each member's schedule and proposes an optimal schedule.

[0075] The privacy management unit can manage the storage method and access authority of the audio data. The privacy management unit, for example, encrypts and stores the audio data. For example, the privacy management unit sets the storage period of the audio data. The privacy management unit can also set access authority of the audio data. For example, the privacy management unit sets the access authority based on the user role. Furthermore, the privacy management unit can also manage an access log of the audio data. For example, the privacy management unit records a log of users who access the audio data. In this way, privacy protection is enhanced by managing the storage method and access authority of the audio data. Some or all of the above-mentioned processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can enhance privacy protection by using an AI model that manages the storage method and access authority of the audio data.

[0076] The speech recognition unit can estimate a user's emotion and adjust the accuracy of speech recognition based on the estimated emotion. The speech recognition unit can estimate the emotion by, for example, analyzing the user's tone of voice and word choice. For example, the speech recognition unit can estimate the user's emotion using an emotion estimation algorithm. The speech recognition unit can also adjust the accuracy of speech recognition based on the estimated emotion. For example, if the user is stressed, the speech recognition unit can enhance noise cancellation to improve the accuracy of speech recognition. If the user is relaxed, the speech recognition unit can also adjust the accuracy of speech recognition to emphasize the natural flow of conversation. Furthermore, if the user is in a hurry, the speech recognition unit can prioritize the speed of speech recognition and quickly convert the speech to text. This improves the recognition accuracy by adjusting the accuracy of speech recognition according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit may improve the accuracy of speech recognition by using an AI model that estimates the user's emotion and adjusts the accuracy of speech recognition based on the estimated emotion.

[0077] The voice recognition unit can improve the accuracy of voice recognition by removing background sounds in the home during voice recognition. The voice recognition unit can remove background sounds in the home using, for example, noise canceling technology. For example, the voice recognition unit can filter out television sounds and recognize only conversation sounds. The voice recognition unit can also filter out kitchen noise and recognize only conversation sounds. Furthermore, the voice recognition unit can filter out children's playing sounds and recognize only conversation sounds. In this way, the accuracy of voice recognition is improved by removing background sounds in the home. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition by using an AI model that removes background sounds using noise canceling technology.

[0078] During voice recognition, the voice recognition unit can learn the characteristics of a speaker's voice and apply an individually optimized recognition model. The voice recognition unit can learn, for example, the speaker's tone and accent. For example, the voice recognition unit can learn the characteristics of the voices of all family members and apply individually optimized recognition models. The voice recognition unit can also learn the speed and rhythm of a speaker's voice to improve recognition accuracy. Furthermore, the voice recognition unit can collect voice samples to learn the characteristics of a speaker's voice. For example, the voice recognition unit can collect voice samples of each member and learn the voice characteristics using a learning algorithm. In this way, learning the characteristics of a speaker's voice improves the accuracy of voice recognition. Some or all of the above-mentioned processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition using an AI model that learns the characteristics of a speaker's voice and applies individually optimized recognition models.

[0079] The speech recognition unit can estimate a user's emotion and adjust the timing of speech recognition based on the estimated emotion. The speech recognition unit estimates the emotion by, for example, analyzing the user's tone of voice and word choice. For example, the speech recognition unit estimates the user's emotion using an emotion estimation algorithm. The speech recognition unit can also adjust the timing of speech recognition based on the estimated emotion. For example, if the user is stressed, the speech recognition unit can delay the timing of speech recognition to perform recognition in a relaxed state. Furthermore, if the user is relaxed, the speech recognition unit can adjust the timing of speech recognition to match the natural flow of conversation. Furthermore, if the user is in a hurry, the speech recognition unit can advance the timing of speech recognition to quickly convert the speech into text. This improves recognition accuracy by adjusting the timing of speech recognition according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit may improve the accuracy of speech recognition by using an AI model that estimates the user's emotion and adjusts the timing of speech recognition based on the estimated emotion.

[0080] The voice recognition unit can switch the recognition mode during voice recognition depending on a specific location in the home. The voice recognition unit switches the recognition mode depending on, for example, each location in the home. For example, in the kitchen, the voice recognition unit filters cooking sounds and switches to a mode that recognizes only conversational voices. The voice recognition unit can also filter television sounds in the living room and switch to a mode that recognizes only conversational voices. Furthermore, the voice recognition unit can switch to a mode that adjusts voice recognition sensitivity to a quiet environment in the bedroom. In this way, switching the recognition mode depending on a specific location in the home improves the accuracy of voice recognition. Some or all of the above-described processing in the voice recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition using an AI model that switches the recognition mode depending on each location in the home.

[0081] The voice recognition unit can improve the accuracy of voice recognition by working with multiple devices in the home. For example, the voice recognition unit can improve the accuracy of voice recognition by working with a smart speaker and using multiple microphones. For example, the voice recognition unit can improve the accuracy of voice recognition based on location information by working with a smartphone. The voice recognition unit can also improve the accuracy of voice recognition by working with a smart TV. This improves the accuracy of voice recognition by working with multiple devices in the home. Some or all of the above-mentioned processing in the voice recognition unit may be performed using AI, for example, or may be performed without using AI. For example, the voice recognition unit can improve the accuracy of voice recognition by using an AI model that works with multiple devices in the home to improve the accuracy of voice recognition.

[0082] The extraction unit can estimate the user's emotions and adjust the extraction accuracy of tasks and schedules based on the estimated user emotions. The extraction unit, for example, estimates emotions by analyzing the user's voice tone and word choice. For example, the extraction unit estimates the user's emotions using an emotion estimation algorithm. The extraction unit can also adjust the extraction accuracy of tasks and schedules based on the estimated emotions. For example, if the user is feeling stressed, the extraction unit can prioritize and extract important tasks and schedules. If the user is relaxed, the extraction unit can equally extract all tasks and schedules. Furthermore, if the user is in a hurry, the extraction unit can prioritize and extract tasks and schedules with high urgency. This improves the extraction accuracy by adjusting the extraction accuracy of tasks and schedules according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can improve extraction accuracy by using an AI model that estimates a user's emotions and adjusts the extraction accuracy of tasks and schedules based on the estimated emotions.

[0083] The extraction unit can analyze the context of the conversation during extraction to evaluate the importance of tasks and schedules. The extraction unit analyzes the context of the conversation using, for example, natural language processing technology. For example, the extraction unit evaluates tasks and schedules that are emphasized in the conversation as being highly important. The extraction unit can also evaluate tasks and schedules that are frequently mentioned in the conversation as being highly important. Furthermore, the extraction unit can evaluate tasks and schedules that include specific keywords in the conversation as being highly important. In this way, the importance of tasks and schedules can be evaluated by analyzing the context of the conversation. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can evaluate the importance using an AI model that analyzes the context of the conversation to evaluate the importance of tasks and schedules.

[0084] During extraction, the extraction unit can automatically extract similar tasks and schedules by referring to past conversation histories. The extraction unit, for example, automatically extracts similar tasks and schedules by referring to past conversation histories. For example, the extraction unit prioritizes extraction of frequently mentioned tasks and schedules based on the past conversation histories. The extraction unit can also analyze past conversation histories to find patterns and extract tasks and schedules. This allows similar tasks and schedules to be automatically extracted by referring to past conversation histories. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can improve extraction accuracy by using an AI model that automatically extracts similar tasks and schedules by referring to past conversation histories.

[0085] The extraction unit can estimate the user's emotions and determine the priority of tasks and schedules to be extracted based on the estimated user emotions. The extraction unit, for example, estimates emotions by analyzing the user's voice tone and word choice. For example, the extraction unit can estimate the user's emotions using an emotion estimation algorithm. The extraction unit can also determine the priority of tasks and schedules based on the estimated emotions. For example, if the user is feeling stressed, the extraction unit can prioritize and extract important tasks and schedules. If the user is relaxed, the extraction unit can also extract all tasks and schedules equally. Furthermore, if the user is in a hurry, the extraction unit can prioritize and extract tasks and schedules with high urgency. In this way, by prioritizing tasks and schedules according to the user's emotions, important tasks can be preferentially extracted. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit may determine priorities using an AI model that estimates a user's emotions and determines the priorities of tasks and schedules based on the estimated emotions.

[0086] During extraction, the extraction unit can prioritize extracting tasks related to specific events in the home. For example, the extraction unit prioritizes extracting tasks related to specific events in the home (e.g., birthdays and anniversaries). For example, the extraction unit prioritizes extracting tasks related to birthdays. The extraction unit can also prioritize extracting tasks related to anniversaries. Furthermore, the extraction unit can prioritize extracting tasks related to family events. In this way, by preferentially extracting tasks related to specific events in the home, important events will not be missed. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can improve extraction accuracy by using an AI model that prioritizes extracting tasks related to specific events in the home.

[0087] During extraction, the extraction unit can extract tasks and schedules by integrating conversations between multiple household members. For example, the extraction unit extracts tasks and schedules by integrating conversations between multiple household members. For example, the extraction unit analyzes conversations between multiple household members and extracts common tasks and schedules. The extraction unit can also extract overlapping tasks and schedules based on conversations between multiple household members. Furthermore, the extraction unit can extract optimal tasks and schedules based on conversations between multiple household members. In this way, common tasks and schedules can be extracted by integrating conversations between multiple household members. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can improve extraction accuracy by using an AI model that integrates conversations between multiple household members to extract tasks and schedules.

[0088] The organizing unit can estimate a user's emotions and adjust how tasks and schedules are organized based on the estimated user emotions. The organizing unit, for example, estimates emotions by analyzing the user's tone of voice and word choice. For example, the organizing unit estimates the user's emotions using an emotion estimation algorithm. The organizing unit can also adjust how tasks and schedules are organized based on the estimated emotions. For example, the organizing unit can provide a simple organizing method when the user is stressed. The organizing unit can also provide a detailed organizing method when the user is relaxed. Furthermore, the organizing unit can also provide a method that allows the user to quickly organize tasks when the user is in a hurry. This improves the efficiency of organization by adjusting how tasks and schedules are organized based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the organizing unit can be performed using, for example, AI, or without AI. For example, the organizing unit can estimate the user's emotions and adjust the organizing method using an AI model that adjusts the organizing method for tasks and schedules based on the estimated emotions.

[0089] The organizing unit can analyze the relevance of tasks and schedules and automatically group them when organizing. For example, the organizing unit analyzes the relevance of tasks and schedules and automatically groups them. For example, the organizing unit automatically groups related tasks and schedules. The organizing unit can also automatically group tasks and schedules in the same category. Furthermore, the organizing unit can automatically group tasks and schedules that are close in time. In this way, tasks and schedules can be automatically grouped by analyzing the relevance of tasks and schedules. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can perform grouping using an AI model that analyzes the relevance of tasks and schedules and automatically groups them.

[0090] When organizing, the organizing unit can learn past organizing patterns and propose an optimal organizing method. For example, the organizing unit learns past organizing patterns and proposes an optimal organizing method. For example, the organizing unit proposes an optimal organizing method based on past organizing patterns. The organizing unit can also analyze the user's organizing patterns and propose an optimal organizing method. Furthermore, the organizing unit can learn organizing patterns within the home and propose an optimal organizing method. In this way, the optimal organizing method can be proposed by learning past organizing patterns. Some or all of the above-mentioned processing in the organizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the organizing unit can propose an organizing method using an AI model that learns past organizing patterns and proposes an optimal organizing method.

[0091] The organizing unit can estimate the user's emotions and adjust the display order of the organized tasks and schedules based on the estimated user emotions. The organizing unit, for example, estimates emotions by analyzing the user's tone of voice and word choice. For example, the organizing unit estimates the user's emotions using an emotion estimation algorithm. The organizing unit can also adjust the display order of the tasks and schedules based on the estimated emotions. For example, if the user is feeling stressed, the organizing unit can prioritize and display important tasks and schedules. If the user is relaxed, the organizing unit can also display all tasks and schedules evenly. Furthermore, if the user is in a hurry, the organizing unit can prioritize and display tasks and schedules with high urgency. In this way, by adjusting the display order of the tasks and schedules according to the user's emotions, important tasks can be displayed with priority. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can adjust the display order using an AI model that estimates the user's emotions and adjusts the display order of tasks and schedules based on the estimated emotions.

[0092] When organizing, the organizing unit can prioritize displaying tasks related to a specific member of the household. For example, the organizing unit prioritizes displaying tasks related to a specific member of the household. For example, the organizing unit prioritizes displaying tasks of a specific member of the household. The organizing unit can also prioritize displaying schedules of a specific member of the household. Furthermore, the organizing unit can also prioritize displaying tasks and schedules of a specific member of the household. This makes it possible to meet individual needs by prioritized displaying tasks related to a specific member of the household. Some or all of the above-described processing in the organizing unit may be performed using, for example, AI, or may be performed without using AI. For example, the organizing unit can adjust the display order using an AI model that prioritizes displaying tasks related to a specific member of the household.

[0093] During organization, the organization unit can provide a display method optimized for a specific device in the home. The organization unit, for example, provides a display method optimized for a specific device in the home (e.g., a smartphone or a tablet). For example, the organization unit provides a display method optimized for a smartphone. The organization unit can also provide a display method optimized for a tablet. Furthermore, the organization unit can also provide a display method optimized for a smart TV. This improves visibility by providing a display method optimized for a specific device in the home. Some or all of the above-described processing in the organization unit may be performed using, for example, AI, or may be performed without using AI. For example, the organization unit can optimize the display method using an AI model that provides a display method optimized for a specific device in the home.

[0094] The prioritization unit can estimate the user's emotions and adjust the priority of tasks based on the estimated user emotions. The prioritization unit, for example, estimates emotions by analyzing the user's tone of voice and word choice. For example, the prioritization unit estimates the user's emotions using an emotion estimation algorithm. The prioritization unit can also adjust the priority of tasks based on the estimated emotions. For example, if the user is feeling stressed, the prioritization unit can prioritize and display important tasks. If the user is relaxed, the prioritization unit can also display all tasks equally. Furthermore, if the user is in a hurry, the prioritization unit can prioritize and display tasks with high urgency. This allows important tasks to be processed preferentially by adjusting the priority of tasks according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the prioritization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the prioritization unit can adjust the priorities using an AI model that estimates a user's emotions and adjusts task priorities based on the estimated emotions.

[0095] The prioritization unit can automatically determine the priorities by evaluating the urgency and importance of tasks when prioritizing. For example, the prioritization unit can automatically determine the priorities by evaluating the urgency and importance of tasks. For example, the prioritization unit can evaluate the urgency of tasks and determine the priorities. The prioritization unit can also evaluate the importance of tasks and determine the priorities. Furthermore, the prioritization unit can comprehensively evaluate the urgency and importance of tasks and determine the priorities. In this way, optimal priorities can be determined by evaluating the urgency and importance of tasks. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can determine the priorities using an AI model that evaluates the urgency and importance of tasks.

[0096] The prioritization unit can suggest optimal priorities by referring to past task completion histories when prioritizing tasks. The prioritization unit, for example, suggests optimal priorities by referring to past task completion histories. For example, the prioritization unit suggests optimal priorities based on past task completion histories. The prioritization unit can also analyze the user's task completion history and suggest optimal priorities. Furthermore, the prioritization unit can also suggest optimal priorities based on task completion histories within the home. In this way, optimal priorities can be suggested by referring to past task completion histories. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can suggest priorities using an AI model that suggests optimal priorities by referring to past task completion histories.

[0097] The prioritization unit can estimate the user's emotions and adjust the display method of the priorities based on the estimated user emotions. The prioritization unit can estimate emotions by, for example, analyzing the user's tone of voice and word choice. For example, the prioritization unit can estimate the user's emotions using an emotion estimation algorithm. The prioritization unit can also adjust the display method of the priorities based on the estimated emotions. For example, the prioritization unit can prominently display important tasks when the user is stressed. The prioritization unit can also display all tasks equally when the user is relaxed. Furthermore, the prioritization unit can prominently display highly urgent tasks when the user is in a hurry. In this way, by adjusting the display method of the priorities according to the user's emotions, important tasks can be prominently displayed. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the prioritization unit can be performed using, for example, AI, or without AI. For example, the prioritization unit can adjust the display method using an AI model that estimates the user's emotions and adjusts the display method of the priorities based on the estimated emotions.

[0098] During prioritization, the prioritization unit can prioritize tasks related to specific household events. For example, the prioritization unit prioritizes tasks related to specific household events (e.g., birthdays and anniversaries). For example, the prioritization unit prioritizes tasks related to birthdays. The prioritization unit can also prioritize tasks related to anniversaries. Furthermore, the prioritization unit can also prioritize tasks related to family events. In this way, by prioritizing tasks related to specific household events, important events will not be missed. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can set priorities using an AI model that prioritizes tasks related to specific household events.

[0099] When prioritizing tasks, the prioritization unit can determine the priorities by integrating the opinions of multiple household members. For example, the prioritization unit determines the priorities by integrating the opinions of multiple household members. For example, the prioritization unit determines the priorities of tasks based on the opinions of multiple household members. The prioritization unit can also adjust the priorities of tasks by reflecting the opinions of multiple household members. Furthermore, the prioritization unit can determine optimal priorities based on the opinions of multiple household members. In this way, optimal priorities can be determined by integrating the opinions of multiple household members. Some or all of the above-described processing in the prioritization unit may be performed using, for example, AI, or may be performed without using AI. For example, the prioritization unit can determine the priorities using an AI model that determines priorities by integrating the opinions of multiple household members.

[0100] The reminder unit can estimate a user's emotions and adjust the reminder notification method based on the estimated user's emotions. The reminder unit can estimate emotions by, for example, analyzing the user's voice tone and word choice. For example, the reminder unit can estimate the user's emotions using an emotion estimation algorithm. The reminder unit can also adjust the reminder notification method based on the estimated emotions. For example, the reminder unit can notify the user of a reminder using a gentle sound if the user is stressed. The reminder unit can also notify the user of a reminder using a cheerful sound if the user is relaxed. Furthermore, the reminder unit can provide a quick and concise notification method if the user is in a hurry. This allows for appropriate notification by adjusting the reminder notification method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the reminder unit may be performed using, for example, AI, or may be performed without AI. For example, the reminder unit may adjust the notification method using an AI model that estimates the user's emotions and adjusts the reminder notification method based on the estimated emotions.

[0101] When setting a reminder, the reminder unit can evaluate the urgency and importance of a task and determine the optimal notification timing. The reminder unit, for example, evaluates the urgency and importance of a task and determines the optimal notification timing. For example, the reminder unit evaluates the urgency of a task and determines the optimal notification timing. The reminder unit can also evaluate the importance of a task and determine the optimal notification timing. Furthermore, the reminder unit can comprehensively evaluate the urgency and importance of a task and determine the optimal notification timing. In this way, the optimal notification timing can be determined by evaluating the urgency and importance of a task. Some or all of the above-described processing in the reminder unit may be performed using, for example, AI, or may be performed without using AI. For example, the reminder unit can determine the notification timing using an AI model that evaluates the urgency and importance of a task.

[0102] When setting a reminder, the reminder unit can suggest the optimal notification method by referring to past reminder history. For example, the reminder unit can suggest the optimal notification method by referring to past reminder history. For example, the reminder unit can suggest the optimal notification method based on the past reminder history. The reminder unit can also analyze the user's reminder history and suggest the optimal notification method. Furthermore, the reminder unit can also suggest the optimal notification method based on the reminder history within the home. In this way, the optimal notification method can be suggested by referring to the past reminder history. Some or all of the above-mentioned processing in the reminder unit may be performed using, for example, AI, or may be performed without using AI. For example, the reminder unit can suggest the notification method using an AI model that suggests the optimal notification method by referring to the past reminder history.

[0103] The reminder unit can estimate a user's emotions and prioritize reminders based on the estimated user emotions. The reminder unit can estimate emotions by, for example, analyzing the user's voice tone and word choice. For example, the reminder unit can estimate the user's emotions using an emotion estimation algorithm. The reminder unit can also prioritize reminders based on the estimated emotions. For example, if the user is feeling stressed, the reminder unit can prioritize notifying important reminders. Also, if the user is relaxed, the reminder unit can prioritize notifying all reminders equally. Furthermore, if the user is in a hurry, the reminder unit can prioritize notifying reminders with a high level of urgency. In this way, by prioritizing reminders according to the user's emotions, important reminders can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reminder unit may be performed using, for example, AI, or may be performed without using AI. For example, the reminder unit may determine priorities using an AI model that estimates a user's emotions and determines reminder priorities based on the estimated emotions.

[0104] When setting a reminder, the reminder unit can prioritize reminders related to specific events in the home. For example, the reminder unit prioritizes reminders related to specific events in the home (e.g., birthdays and anniversaries). For example, the reminder unit prioritizes reminders related to birthdays. The reminder unit can also prioritize reminders related to anniversaries. Furthermore, the reminder unit can also prioritize reminders related to family events. In this way, by prioritizing reminders related to specific events in the home, important events will not be missed. Some or all of the above-described processing in the reminder unit may be performed using, for example, AI, or may be performed without using AI. For example, the reminder unit can set reminders using an AI model that prioritizes reminders related to specific events in the home.

[0105] When a reminder is set, the reminder unit can provide notifications in cooperation with multiple devices in the home. The reminder unit can provide notifications in cooperation with multiple devices in the home. For example, the reminder unit can provide notifications in cooperation with a smartphone. The reminder unit can also provide notifications in cooperation with a smart speaker. Furthermore, the reminder unit can provide notifications in cooperation with a smart watch. This allows for more efficient reminder notifications by linking with multiple devices in the home. Some or all of the above-described processing in the reminder unit can be performed using, for example, AI, or can be performed without using AI. For example, the reminder unit can optimize the notification method using an AI model that provides notifications in cooperation with multiple devices in the home.

[0106] The management unit can estimate the user's emotions and adjust the schedule management method based on the estimated user emotions. The management unit, for example, estimates emotions by analyzing the user's tone of voice and word choice. For example, the management unit estimates the user's emotions using an emotion estimation algorithm. The management unit can also adjust the schedule management method based on the estimated emotions. For example, the management unit can provide a simple schedule management method when the user is stressed. The management unit can also provide a detailed schedule management method when the user is relaxed. Furthermore, the management unit can also provide a method for quickly managing the schedule when the user is in a hurry. This improves the efficiency of schedule management by adjusting the schedule management method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the management unit can be performed using, for example, AI, or without AI. For example, the management department can adjust the management method using an AI model that estimates the user's emotions and adjusts the schedule management method based on the estimated emotions.

[0107] During management, the management unit can analyze the schedule of each member of the household and propose an optimal schedule. For example, the management unit analyzes the schedule of each member of the household and proposes an optimal schedule. For example, the management unit proposes a common schedule based on the schedules of each member of the household. The management unit can also analyze the schedule of each member of the household and propose an optimal schedule. Furthermore, the management unit can analyze the schedule of each member of the household and propose an optimal schedule. In this way, an optimal schedule can be proposed by analyzing the schedule of each member of the household. Some or all of the above-mentioned processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can propose a schedule using an AI model that analyzes the schedule of each member of the household and proposes an optimal schedule.

[0108] During management, the management unit can suggest an optimal schedule management method by referring to past schedule history. The management unit, for example, refers to past schedule history to suggest an optimal schedule management method. For example, the management unit suggests an optimal schedule management method based on past schedule history. The management unit can also analyze the user's schedule history and suggest an optimal schedule management method. Furthermore, the management unit can also suggest an optimal schedule management method based on schedule history within the home. In this way, the optimal schedule management method can be suggested by referring to past schedule history. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can suggest a management method using an AI model that suggests an optimal schedule management method by referring to past schedule history.

[0109] The management unit can estimate the user's emotions and adjust the display method of the schedule based on the estimated user's emotions. The management unit, for example, estimates emotions by analyzing the user's tone of voice and word choice. For example, the management unit estimates the user's emotions using an emotion estimation algorithm. The management unit can also adjust the display method of the schedule based on the estimated emotions. For example, if the user is feeling stressed, the management unit can prominently display important schedules. If the user is relaxed, the management unit can also display all schedules evenly. Furthermore, if the user is in a hurry, the management unit can prominently display highly urgent schedules. In this way, by adjusting the display method of the schedule according to the user's emotions, important schedules can be prominently displayed. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the management unit can be performed using, for example, AI, or without AI. For example, the management department can adjust the display method using an AI model that estimates the user's emotions and adjusts the display method of the schedule based on the estimated emotions.

[0110] During management, the management unit can prioritize displaying schedules related to specific events in the home. For example, the management unit prioritizes displaying schedules related to specific events in the home (e.g., birthdays and anniversaries). For example, the management unit prioritizes displaying schedules related to birthdays. The management unit can also prioritize displaying schedules related to anniversaries. Furthermore, the management unit can also prioritize displaying schedules related to family events. In this way, by prioritized displaying schedules related to specific events in the home, important events will not be missed. Some or all of the above-described processing in the management unit may be performed, for example, using AI, or may be performed without using AI. For example, the management unit can display schedules using an AI model that prioritizes displaying schedules related to specific events in the home.

[0111] During management, the management unit can manage schedules in cooperation with multiple devices in the home. The management unit, for example, manages schedules in cooperation with multiple devices in the home. For example, the management unit manages schedules in cooperation with a smartphone. The management unit can also manage schedules in cooperation with a smart speaker. Furthermore, the management unit can also manage schedules in cooperation with a smart watch. In this way, schedule management becomes more efficient by working with multiple devices in the home. Some or all of the above-described processing in the management unit may be performed using, for example, AI, or may be performed without using AI. For example, the management unit can improve the efficiency of schedule management by using an AI model that manages schedules in cooperation with multiple devices in the home.

[0112] The privacy management unit can estimate a user's emotions and adjust privacy settings based on the estimated user emotions. The privacy management unit, for example, estimates emotions by analyzing the user's tone of voice and word choice. For example, the privacy management unit estimates the user's emotions using an emotion estimation algorithm. The privacy management unit can also adjust privacy settings based on the estimated emotions. For example, the privacy management unit can strengthen privacy settings when the user is stressed. The privacy management unit can also provide standard privacy settings when the user is relaxed. Furthermore, the privacy management unit can provide a method for quickly adjusting privacy settings when the user is in a hurry. This allows appropriate privacy protection by adjusting privacy settings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the privacy management unit can be performed using AI, for example, or without AI. For example, the privacy manager can adjust privacy settings using an AI model that infers a user's emotions and adjusts privacy settings based on the inferred emotions.

[0113] During privacy management, the privacy management unit can enhance security by optimizing the method of storing audio data. The privacy management unit, for example, encrypts and stores audio data. For example, the privacy management unit shortens the storage period of audio data. The privacy management unit can also strictly manage access rights to audio data. This optimizes the method of storing audio data, thereby enhancing security. Some or all of the above-described processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can enhance security by using an AI model that optimizes the method of storing audio data.

[0114] During privacy management, the privacy management unit can finely set access permissions to grant appropriate permissions to each member of the household. For example, the privacy management unit sets access permissions individually for each member of the household. For example, the privacy management unit sets access permissions for specific tasks or schedules. The privacy management unit can also set access permissions according to the role of each member of the household. This allows for finely setting access permissions to grant appropriate permissions to each member of the household. Some or all of the above-mentioned processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can set permissions using an AI model that finely sets access permissions.

[0115] The privacy management unit can estimate a user's emotions and prioritize privacy settings based on the estimated user emotions. The privacy management unit, for example, estimates emotions by analyzing the user's tone of voice and word choice. For example, the privacy management unit estimates the user's emotions using an emotion estimation algorithm. The privacy management unit can also prioritize privacy settings based on the estimated emotions. For example, the privacy management unit can prioritize important privacy settings when the user is stressed. The privacy management unit can also uniformly manage all privacy settings when the user is relaxed. Furthermore, the privacy management unit can quickly manage privacy settings when the user is in a hurry. This allows the priority of privacy settings to be prioritized based on the user's emotions, thereby prioritizing important privacy settings. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the privacy management unit can be performed using, for example, AI, or without AI. For example, the privacy manager can determine priorities using an AI model that estimates a user's emotions and prioritizes privacy settings based on the estimated emotions.

[0116] During privacy management, the privacy management unit can prioritize protection of data related to specific events in the home. For example, the privacy management unit prioritizes protection of data related to specific events in the home (e.g., birthdays and anniversaries). For example, the privacy management unit prioritizes protection of data related to birthdays. The privacy management unit can also prioritize protection of data related to anniversaries. Furthermore, the privacy management unit can prioritize protection of data related to family events. This prioritizes protection of data related to specific events in the home, thereby enhancing the security of important data. Some or all of the above-described processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can enhance data protection using an AI model that prioritizes protection of data related to specific events in the home.

[0117] During privacy management, the privacy management unit can manage privacy settings in cooperation with multiple devices in the home. The privacy management unit, for example, manages privacy settings in cooperation with multiple devices in the home. For example, the privacy management unit manages privacy settings in cooperation with a smartphone. The privacy management unit can also manage privacy settings in cooperation with a smart speaker. Furthermore, the privacy management unit can also manage privacy settings in cooperation with a smartwatch. This improves the efficiency of privacy setting management by cooperation with multiple devices in the home. Some or all of the above-described processing in the privacy management unit may be performed using, for example, AI, or may be performed without using AI. For example, the privacy management unit can manage privacy settings using an AI model that manages privacy settings in cooperation with multiple devices in the home. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned voice recognition unit, extraction unit, and organization unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the voice recognition unit converts everyday conversations at home into text in real time using the microphone 38B of the smart device 14, and the specific processing unit 290 of the data processing device 12 performs highly accurate transcription. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and extracts tasks and schedules from the text using natural language processing technology. The organization unit is realized, for example, by the control unit 46A of the smart device 14 and organizes the extracted tasks and schedules by category, providing prioritization and reminder functions. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned voice recognition unit, extraction unit, and organization unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice recognition unit converts everyday conversations at home into text in real time using the microphone 238 of the smart glasses 214, and the specific processing unit 290 of the data processing device 12 performs highly accurate transcription. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, extracts tasks and schedules from the text using natural language processing technology. The organization unit, realized, for example, by the control unit 46A of the smart glasses 214, organizes the extracted tasks and schedules by category and provides prioritization and reminder functions. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned voice recognition unit, extraction unit, and organization unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the voice recognition unit converts everyday conversations at home into text in real time using the microphone 238 of the headset-type terminal 314, and the specific processing unit 290 of the data processing device 12 performs highly accurate transcription. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts tasks and schedules from the text using natural language processing technology. The organization unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and organizes the extracted tasks and schedules by category, providing prioritization and reminder functions. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned voice recognition unit, extraction unit, and organization unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice recognition unit converts everyday conversations within the home into text in real time using the microphone 238 of the robot 414, and the specific processing unit 290 of the data processing device 12 performs highly accurate transcription. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and extracts tasks and schedules from the text using natural language processing technology. The organization unit is realized, for example, by the control unit 46A of the robot 414, and organizes the extracted tasks and schedules by category, providing prioritization and reminder functions.

[0118] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0119] The home task management system may further include a progress tracking unit that tracks the progress of tasks in real time. The progress tracking unit periodically checks the progress of each task and visualizes the progress. For example, the progress tracking unit may display the completion rate of a task as a percentage. The progress tracking unit may also issue an alert if the progress of a task is behind schedule. Furthermore, the progress tracking unit may automatically adjust reminders based on the progress of the task. This allows for efficient task management by understanding the progress of tasks in real time.

[0120] The home task management system may further include a dependency management unit that manages task dependencies. The dependency management unit analyzes dependencies between tasks and optimizes the order of tasks. For example, if a task cannot start until the next task is completed, the dependency management unit automatically adjusts the order. The dependency management unit can also set reminders based on task dependencies. Furthermore, the dependency management unit can notify users when task dependencies change. In this way, managing task dependencies enables efficient task progress.

[0121] The home task management system may further include a reward providing unit that provides a reward according to the progress of a task. The reward providing unit provides a reward to the user when the task is completed. For example, the reward providing unit may award points according to the completion of a task. The reward providing unit may also provide a system that allows the user to receive benefits by accumulating points. Furthermore, the reward providing unit may provide rewards in stages according to the progress of the task. This increases motivation for completing tasks and enables efficient task management.

[0122] The home task management system may further include a feedback providing unit that provides feedback according to the progress of the task. The feedback providing unit provides feedback to the user according to the progress of the task. For example, the feedback providing unit provides positive feedback when the task is progressing smoothly. The feedback providing unit may also suggest improvements when the progress of the task is delayed. Furthermore, the feedback providing unit may also provide advice based on the progress of the task. This allows for efficient task management by receiving feedback on the progress of the task.

[0123] The home task management system may further include a reallocation unit that automatically reallocates tasks according to the progress of the tasks. The reallocation unit reallocates tasks to other members according to the progress of the tasks. For example, if a member's task is behind schedule, the reallocation unit reallocates the task to another member. The reallocation unit may also reallocate a task to the most suitable member based on the progress of the task. Furthermore, the reallocation unit may notify when a task has been reallocated. This allows for efficient task management by flexibly reallocating tasks according to the progress of the task.

[0124] The home task management system may further include an evaluation unit that evaluates the progress of a task based on the user's emotions. The evaluation unit estimates the user's emotions and evaluates the progress of the task based on the estimated emotions. For example, if the user is feeling stressed, the evaluation unit may evaluate that the progress of the task is delayed. Alternatively, if the user is relaxed, the evaluation unit may evaluate that the progress of the task is progressing smoothly. Furthermore, the evaluation unit may adjust the progress of the task based on the user's emotions. This enables efficient task management by evaluating the progress of the task according to the user's emotions.

[0125] The home task management system can further include a priority adjustment unit that adjusts task priorities based on the user's emotions. The priority adjustment unit estimates the user's emotions and adjusts task priorities based on the estimated emotions. For example, if the user is feeling stressed, the priority adjustment unit prioritizes processing of important tasks. Also, if the user is relaxed, the priority adjustment unit can process all tasks equally. Furthermore, if the user is in a hurry, the priority adjustment unit can prioritize processing of highly urgent tasks. In this way, efficient task management is possible by adjusting task priorities according to the user's emotions.

[0126] The home task management system may further include a notification adjustment unit that adjusts the reminder notification method based on the user's emotions. The notification adjustment unit estimates the user's emotions and adjusts the reminder notification method based on the estimated emotions. For example, if the user is feeling stressed, the notification adjustment unit may notify the user of a reminder with a gentle sound. Alternatively, if the user is relaxed, the notification adjustment unit may notify the user of a reminder with a cheerful sound. Furthermore, if the user is in a hurry, the notification adjustment unit may provide a quick and concise notification method. In this way, appropriate notifications can be provided by adjusting the reminder notification method according to the user's emotions.

[0127] The home task management system may further include a visualization unit that visualizes the progress of a task based on the user's emotions. The visualization unit estimates the user's emotions and visualizes the progress of the task based on the estimated emotions. For example, the visualization unit may simply display the progress of a task when the user is feeling stressed. The visualization unit may also display detailed progress when the user is relaxed. Furthermore, the visualization unit may provide a method for quickly checking the progress when the user is in a hurry. This enables efficient task management by visualizing the progress of a task according to the user's emotions.

[0128] The home task management system may further include a sharing unit that shares task progress status based on the user's emotions. The sharing unit estimates the user's emotions and shares task progress status with other members based on the estimated emotions. For example, if the user is feeling stressed, the sharing unit may briefly share task progress status. Alternatively, if the user is feeling relaxed, the sharing unit may share detailed progress status. Furthermore, if the user is in a hurry, the sharing unit may provide a method for quickly sharing progress status. This enables efficient task management by sharing task progress status according to the user's emotions.

[0129] The processing flow of the second embodiment will be briefly explained below.

[0130] Step 1: The voice recognition unit transcribes everyday conversations within the home. For example, the voice recognition unit uses voice recognition technology to convert conversations into text in real time. The voice recognition unit performs highly accurate transcription using a voice recognition algorithm. The voice recognition unit can also identify the voices of multiple members within the home and transcribe them individually. For example, the voice recognition unit learns the voice characteristics of each member and applies an individually optimized recognition model. Step 2: The extraction unit extracts tasks and schedules from the text transcribed by the speech recognition unit. For example, the extraction unit analyzes the text using natural language processing technology and extracts tasks and schedules. The extraction unit identifies important tasks and schedules using keyword extraction technology. The extraction unit can also analyze the context of the conversation and evaluate the importance of the tasks and schedules. For example, the extraction unit evaluates tasks and schedules that are emphasized in the conversation as being highly important. Step 3: The organizer organizes the tasks and schedules extracted by the extractor based on specific criteria. For example, the organizer classifies tasks and schedules by category. The organizer automatically classifies them into categories such as "shopping" and "family events." The organizer can also prioritize tasks. For example, the organizer determines the priority of tasks based on urgency and importance. Furthermore, the organizer can provide a reminder function. For example, the organizer notifies the user when a task deadline is approaching.

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0133] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0136] 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.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0149] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0152] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0158] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0159] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0165] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0168] 7, a 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.

[0169] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0170] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0171] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0173] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0174] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0175] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0176] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0177] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0178] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0179] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0180] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0181] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0182] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0183] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0184] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0185] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0186] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0187] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0188] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0189] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0191] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0192] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0193] 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.

[0194] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0195] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0196] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0197] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0198] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0199] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0200] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0201] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0202] [Explanation of symbols]

[0203] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A speech recognition unit that transcribes conversations; an extraction unit that extracts tasks and schedules from the text transcribed by the speech recognition unit; An organizing unit that organizes the tasks and schedules extracted by the extracting unit based on specific criteria. A system characterized by:

2. Equipped with a prioritization unit that prioritizes tasks 2. The system of claim 1.

3. Equipped with a reminder section for setting reminders 2. The system of claim 1.

4. Equipped with a management unit that centrally manages the schedules of multiple household members 2. The system of claim 1.

5. Equipped with a privacy management unit that manages the storage method and access rights of voice data 2. The system of claim 1.

6. The voice recognition unit Estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated user emotions.

2. The system of claim 1.

7. The voice recognition unit Improves voice recognition accuracy by removing background noise in the home 2. The system of claim 1.

8. The voice recognition unit During speech recognition, the system learns the characteristics of the speaker's voice and applies an individually optimized recognition model 2. The system of claim 1.

9. The voice recognition unit Estimate the user's emotion and adjust the timing of speech recognition based on the estimated user emotion.

2. The system of claim 1.

10. The voice recognition unit When using voice recognition, the recognition mode is switched depending on the location in the home.

2. The system of claim 1.

Images