system

Abstract

The system according to the embodiment aims to comprehensively manage information about the user's entire life and provide appropriate advice and suggestions. [Solution] The system according to the embodiment includes a collection unit, a reminder unit, an analysis unit, an evaluation unit, a provision unit, a suggestion unit, an asset management unit, a disaster prevention unit, and a knowledge unit. The collection unit collects the user's schedule. The reminder unit provides reminders based on the schedule collected by the collection unit. The analysis unit analyzes camera images of meals. The evaluation unit evaluates the data from the smartwatch. The provision unit provides a health guide based on the data obtained by the analysis unit and the evaluation unit. The suggestion unit suggests recommended recipes based on the health guide provided by the provision unit. The asset management unit analyzes household data and suggests investment methods and tax savings. The disaster prevention unit analyzes weather forecast data and suggests necessary preparations. The knowledge unit analyzes search history and interactions and suggests recommended information, books, and goods.

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 not adequately managed information covering all aspects of a user's life in an integrated manner and provided appropriate advice and suggestions, and there is room for improvement.

[0005] The system according to the embodiment aims to comprehensively manage information about the user's entire life and provide appropriate advice and suggestions. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a reminder unit, an analysis unit, an evaluation unit, a provision unit, a suggestion unit, an asset management unit, a disaster prevention unit, and a knowledge unit. The collection unit collects the user's schedule. The reminder unit provides reminders based on the schedule collected by the collection unit. The analysis unit analyzes camera images of meals. The evaluation unit evaluates the data from the smartwatch. The provision unit provides a health guide based on the data obtained by the analysis unit and the evaluation unit. The suggestion unit suggests recommended recipes based on the health guide provided by the provision unit. The asset management unit analyzes household data and suggests investment methods and tax savings. The disaster prevention unit analyzes weather forecast data and suggests necessary preparations. The knowledge unit analyzes search history and interactions and suggests recommended information, books, and goods. [Effects of the Invention]

[0007] The system according to the embodiment can comprehensively manage information about the user's entire life and provide appropriate advice and suggestions. [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) The AI ​​concierge system for everyday life, according to an embodiment of the present invention, supports users' lives in all aspects of their lives. This system collects the user's schedule, sends reminders, analyzes camera-captured meal images, evaluates smartwatch data, provides health guidance, suggests recipe recommendations, analyzes household finance data, offers management and tax-saving suggestions, analyzes weather forecast data, suggests necessary preparations, analyzes search history and interactions, and suggests recommended information, books, and goods. For example, the schedule management function provides daily morning reminders of the user's plans for the day, the next day, and the week ahead, both for work and personal use. It also provides reminders for doctor visits, local events, family birthdays, anniversaries, tax payments, and travel ticket arrangements. The health management function provides health guidance by linking camera-captured meal images, smartwatch data, medical checkup results, and medication information. The recommended recipe function works in conjunction with the health management function to suggest seasonal recipes. The asset management function provides recommended management methods and tax-saving suggestions based on household finances and asset status. The disaster prevention function works in conjunction with the weather forecast and schedule management function to suggest necessary preparations based on the weather forecast for the week ahead. The knowledge function suggests recommended information, books, and goods based on searches and interactions. This allows users to receive AI support in all aspects of their lives. For example, in the schedule management function, AI analyzes the user's schedule and sends reminders. When a doctor's appointment is scheduled, the health management function provides health guidance. In the health management function, AI analyzes camera images of meals to evaluate nutritional balance. AI also analyzes smartwatch data and health checkup results to provide a comprehensive health guide. In the recommended recipe function, AI suggests seasonal recipes based on data from the health management function. In the asset management function, AI analyzes household data to suggest optimal management methods and tax savings. In the disaster prevention function, AI analyzes weather forecast data and suggests necessary preparations in conjunction with the schedule management function. In the knowledge function, AI analyzes the user's search history and interactions to suggest recommended information, books, and goods. This allows the lifestyle-focused AI concierge system to support users in all aspects of their lives and manage them efficiently and effectively.

[0029] The daily life AI concierge system according to the embodiment includes a collection unit, a reminder unit, an analysis unit, an evaluation unit, a provision unit, a proposal unit, an asset management unit, a disaster prevention unit, and a knowledge unit. The collection unit collects a user's schedule. The user's schedule includes, but is not limited to, meetings, events, and tasks. The collection unit acquires schedules from, for example, the user's calendar app or task management app. The collection unit can also collect schedules from a user's voice input or text input. For example, when a user vocally instructs the collection unit to "add a meeting for tomorrow," the collection unit adds the schedule to the calendar. The reminder unit provides reminders based on the schedule collected by the collection unit. Reminders are provided based on, for example, but not limited to, notification formats and reminder frequency. The reminder unit, for example, sends notifications to the user's smartphone to remind the user of the schedule. The reminder unit can also send vibration notifications to the user's smartwatch. For example, the reminder unit provides reminders at a time set by the user to ensure that important schedules are not forgotten. The analysis unit analyzes camera images of meals. Camera images include, but are not limited to, still images, videos, and resolutions. For example, the analysis unit analyzes images of meals taken by a user to evaluate nutritional balance. For example, the analysis unit uses image recognition technology to identify ingredients and calculate calories and nutrients. The evaluation unit evaluates smartwatch data. Smartwatch data includes, but is not limited to, heart rate, step count, and sleep data. For example, the evaluation unit analyzes the user's heart rate data to evaluate the amount of exercise. The evaluation unit can also analyze the user's sleep data to evaluate the quality of sleep. The provision unit provides a health guide based on the data obtained by the analysis unit and the evaluation unit. The health guide includes, but is not limited to, dietary advice, exercise advice, and lifestyle advice. For example, the provision unit suggests a balanced diet based on the user's dietary data. The provision unit can also suggest an appropriate exercise plan based on the user's exercise data. The suggestion unit suggests recommended recipes based on the health guide provided by the provision unit.The recommended recipes include, but are not limited to, nutritional balance, seasonal ingredients, and user preferences. The suggestion unit suggests recipes based on the user's health condition. The asset management unit analyzes household data and suggests investment methods and tax savings. The household data includes, but is not limited to, income, expenses, and savings. The asset management unit analyzes, for example, the user's income data and suggests optimal investment methods. The asset management unit can also analyze the user's expense data and suggest savings methods. The disaster prevention unit analyzes weather forecast data and suggests necessary preparations. The weather forecast data includes, but is not limited to, temperature, precipitation probability, wind speed, and the like. The disaster prevention unit analyzes, for example, a weather forecast for one week ahead and suggests preparing necessary disaster prevention supplies. The knowledge unit analyzes search history and interactions and suggests recommended information, books, and goods. The search history includes, but is not limited to, web searches, in-app searches, and the like. The knowledge section, for example, suggests related books and goods based on information the user has searched for in the past. This allows the daily life AI concierge system according to the embodiment to support the user's overall life and manage their life efficiently and effectively.

[0030] The reminding unit can remind users about medical visits, local events, family birthdays, anniversaries, tax payments, and ticket arrangements for business trips. The reminding unit, for example, reminds users about scheduled medical visits. For example, the reminding unit reminds users of the date and time of a medical visit set by the user, notifying them so they do not forget. The reminding unit can also remind users about scheduled local events. For example, the reminding unit reminds users of the date and time of local festivals and events, encouraging them to participate. The reminding unit can also remind users about family birthdays and anniversaries. For example, the reminding unit reminds users of family birthdays and wedding anniversaries, encouraging them to prepare presents. The reminding unit can also remind users about tax payment deadlines. For example, the reminding unit reminds users of tax payment deadlines and encourages them to pay their taxes by the deadline. The reminding unit can also remind users to arrange tickets for business trips. For example, the reminding unit reminds users to arrange tickets based on the date and time of a business trip, supporting a smooth business trip. In this way, the reminding unit can reliably remind users of important plans.

[0031] The analysis unit can analyze camera images of meals and evaluate nutritional balance. The analysis unit can, for example, analyze images of meals taken by a user and evaluate nutritional balance. For example, the analysis unit can use image recognition technology to identify ingredients and calculate calories and nutrients. The analysis unit can also analyze camera images of meals and evaluate nutritional balance. For example, the analysis unit can analyze camera images of meals and evaluate vitamin and mineral balance. The analysis unit can also analyze camera images of meals and evaluate nutritional balance. For example, the analysis unit can analyze camera images of meals and evaluate protein and lipid balance. In this way, the analysis unit can analyze the user's dietary content and evaluate nutritional balance.

[0032] The evaluation unit can analyze smartwatch data or medical checkup results to provide a comprehensive health guide. The evaluation unit, for example, analyzes the user's smartwatch data to evaluate the amount of exercise. For example, the evaluation unit can analyze the user's heart rate data to evaluate the amount of exercise. The evaluation unit can also analyze the user's sleep data to evaluate the quality of sleep. For example, the evaluation unit can analyze the user's sleep data to evaluate the quality of sleep. The evaluation unit can also analyze medical checkup results to provide a comprehensive health guide. For example, the evaluation unit can analyze blood pressure data from the medical checkup to provide a health guide. The evaluation unit can also analyze blood glucose level data from the medical checkup to provide a health guide. For example, the evaluation unit can analyze blood glucose level data from the medical checkup to provide a health guide. The evaluation unit can also analyze cholesterol level data from the medical checkup to provide a health guide. For example, the evaluation unit can analyze cholesterol level data from the medical checkup to provide a health guide. In this way, the evaluation unit can comprehensively evaluate the user's health condition and provide a health guide.

[0033] The suggestion unit can suggest recipes according to the season based on data from the health management function. The suggestion unit, for example, suggests recipes according to the user's health condition. For example, the suggestion unit suggests balanced recipes based on the user's nutritional balance data. The suggestion unit can also suggest recipes according to the season. For example, the suggestion unit suggests recipes using seasonal ingredients. The suggestion unit can also suggest recipes according to the user's preferences. For example, the suggestion unit suggests recipes that suit the user's preferences based on the user's past eating history. This allows the suggestion unit to suggest appropriate recipes according to the user's health condition.

[0034] The asset management unit can analyze household data and suggest investment methods and tax-saving strategies. The asset management unit, for example, analyzes the user's income data and suggests optimal investment methods. For example, the asset management unit suggests investment trusts or stock investments based on the user's income data. The asset management unit can also analyze the user's expenditure data and suggest savings methods. For example, the asset management unit suggests ways to reduce wasteful expenditures based on the user's expenditure data. The asset management unit can also analyze the user's savings data and suggest optimal savings methods. For example, the asset management unit suggests fixed-term deposits or installment investments based on the user's savings data. This allows the asset management unit to efficiently manage the user's assets.

[0035] The disaster prevention department can analyze weather forecast data and suggest necessary preparations in conjunction with the schedule management function. The disaster prevention department can, for example, analyze the weather forecast for one week ahead and suggest preparing necessary disaster prevention goods. For example, the disaster prevention department can suggest preparing rain gear and cold weather gear based on the weather forecast data. The disaster prevention department can also analyze weather forecast data and suggest checking evacuation routes. For example, the disaster prevention department can suggest checking evacuation routes in the event of a flood or typhoon based on the weather forecast data. The disaster prevention department can also analyze weather forecast data and suggest preparing emergency food and drinking water. For example, the disaster prevention department can suggest stockpiling emergency food and drinking water based on the weather forecast data. This allows the disaster prevention department to efficiently implement disaster prevention measures.

[0036] The knowledge department can analyze search history and interactions to suggest recommended information, books, and goods. For example, the knowledge department can suggest related books and goods based on information that the user has searched for in the past. For example, the knowledge department can analyze the user's search history to suggest related books. The knowledge department can also analyze the user's interactions to suggest related information. For example, the knowledge department can analyze the content of the user's emails and chats to suggest related information. The knowledge department can also analyze the user's search history and interactions to suggest related goods. For example, the knowledge department can analyze the user's search history to suggest related goods. In this way, the knowledge department can provide useful information to the user.

[0037] The collection unit can analyze the user's past schedule history and select the optimal collection method. For example, the collection unit preferentially selects a collection method (voice, text, etc.) that the user has frequently used in the past. For example, the collection unit analyzes the user's past schedule history and, if the user has used voice input frequently, preferentially selects voice input. The collection unit can also suggest the optimal collection method for a specific time period based on the user's past schedule history. For example, if the user has added many appointments in the morning, the collection unit suggests collecting appointments in the morning. The collection unit can also analyze the user's past schedule history and select the most efficient collection method. For example, if text input is efficient based on the user's past schedule history, the collection unit preferentially selects text input. This allows the collection unit to select the optimal collection method based on the user's past history.

[0038] When collecting schedules, the collection unit can perform filtering based on the user's current lifestyle and areas of interest. For example, if the user is currently busy, the collection unit prioritizes collecting only important schedules. For example, the collection unit analyzes the user's lifestyle and collects only important schedules during busy periods. The collection unit can also prioritize collecting related schedules based on the user's areas of interest. For example, the collection unit analyzes the user's hobbies and topics of interest and collects related schedules. The collection unit can also perform appropriate filtering according to the user's lifestyle and collect schedules. For example, the collection unit analyzes the user's living environment and work situation and performs appropriate filtering. This allows the collection unit to collect schedules according to the user's lifestyle and areas of interest.

[0039] When collecting schedules, the collection unit can prioritize collecting highly relevant schedules by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collecting schedules related to that area. For example, the collection unit analyzes the user's GPS data and collects schedules related to the user's current location. The collection unit can also prioritize collecting schedules in locations close to the user's current location. For example, the collection unit collects schedules for nearby events and meetings based on the user's current location. The collection unit can also analyze the user's movement patterns and prioritize collecting highly relevant schedules. For example, the collection unit analyzes the user's past movement data and collects highly relevant schedules. This allows the collection unit to collect highly relevant schedules based on the user's geographical location information.

[0040] The collection unit can analyze the user's social media activities and collect related events when collecting schedules. The collection unit, for example, collects events mentioned by the user on social media. For example, the collection unit analyzes the content of the user's social media posts and collects related event schedules. The collection unit can also collect events in which the user's social media friends will be attending. For example, the collection unit analyzes the content of the user's social media posts and collects related event schedules. The collection unit can also collect related schedules from the content of the user's social media posts. For example, the collection unit analyzes the content of the user's social media posts and collects related schedules. In this way, the collection unit can collect related schedules based on the user's social media activities.

[0041] The reminding unit can adjust the level of detail of the reminder based on the importance of the schedule when reminding. For example, the reminding unit provides a detailed reminder for a schedule with high importance. For example, the reminding unit analyzes the importance of the schedule of the user and provides a detailed reminder for a schedule with high importance. The reminding unit can also provide a brief reminder for a schedule with low importance. For example, the reminding unit analyzes the importance of the schedule of the user and provides a brief reminder for a schedule with low importance. The reminding unit can also adjust the frequency of reminders according to the importance of the schedule. For example, the reminding unit provides frequent reminders for schedules with high importance and reduces the frequency of reminders for schedules with low importance. This allows the reminding unit to adjust the level of detail of the reminder according to the importance of the schedule.

[0042] The reminding unit can apply different reminding algorithms depending on the category of the event when reminding. For example, the reminding unit performs a business-like reminder for work-related events. For example, the reminding unit analyzes the category of the user's events and performs a business-like reminder for work-related events. The reminding unit can also perform a casual reminder for private events. For example, the reminding unit analyzes the category of the user's events and performs a casual reminder for private events. The reminding unit can also perform a reminder linked with a health guide for health-related events. For example, the reminding unit analyzes the category of the user's events and performs a reminder linked with a health guide for health-related events. This allows the reminding unit to perform an appropriate reminder depending on the category of the event.

[0043] The reminding unit can determine the priority of reminders based on the submission time of the schedule when a reminder is issued. For example, the reminding unit prioritizes reminders for schedules with an upcoming submission deadline. For example, the reminding unit analyzes the submission time of the user's schedule and prioritizes reminders for schedules with an upcoming submission deadline. The reminding unit can also postpone schedules with a distant submission deadline. For example, the reminding unit analyzes the submission time of the user's schedule and postpones schedules with a distant submission deadline. The reminding unit can also adjust the frequency of reminders depending on the submission time. For example, the reminding unit frequently reminds schedules with an upcoming submission deadline and reduces the frequency of reminders for schedules with a distant submission deadline. This allows the reminding unit to determine the priority of reminders depending on the submission time of the schedule.

[0044] The reminding unit can adjust the order of reminders based on the relevance of the schedules when reminding. For example, the reminding unit gives priority to reminding highly relevant schedules. For example, the reminding unit analyzes the relevance of the user's schedules and gives priority to reminding highly relevant schedules. The reminding unit can also postpone less relevant schedules. For example, the reminding unit analyzes the relevance of the user's schedules and postpones less relevant schedules. The reminding unit can also adjust the order of reminders based on the relevance of the schedules. For example, the reminding unit gives priority to reminding highly relevant schedules and postpones less relevant schedules. In this way, the reminding unit can adjust the order of reminders based on the relevance of the schedules.

[0045] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the meal. For example, the analysis unit performs a detailed analysis on meals with high importance. For example, the analysis unit analyzes the importance of meals to the user and performs a detailed analysis on meals with high importance. The analysis unit can also perform a brief analysis on meals with low importance. For example, the analysis unit analyzes the importance of meals to the user and performs a brief analysis on meals with low importance. The analysis unit can also adjust the frequency of analysis according to the importance of the meal. For example, the analysis unit frequently analyzes meals with high importance and reduces the frequency of analysis on meals with low importance. This allows the analysis unit to adjust the level of detail of the analysis according to the importance of the meal.

[0046] During analysis, the analysis unit can apply different analysis algorithms depending on the food category. For example, for healthy food, the analysis unit performs an analysis that emphasizes nutritional balance. For example, the analysis unit analyzes the user's food category, and for healthy food, performs an analysis that emphasizes nutritional balance. The analysis unit can also perform an analysis that emphasizes calories for fast food. For example, the analysis unit analyzes the user's food category, and for fast food, performs an analysis that emphasizes calories. The analysis unit can also perform an analysis that emphasizes sugar content for desserts. For example, the analysis unit analyzes the user's food category, and for desserts, performs an analysis that emphasizes sugar content. This allows the analysis unit to apply an appropriate analysis algorithm depending on the food category.

[0047] During analysis, the analysis unit can determine the priority of analysis based on the time of meal submission. For example, the analysis unit prioritizes analysis of meals with an upcoming submission deadline. For example, the analysis unit analyzes the time of meal submission by the user and prioritizes analysis of meals with an upcoming submission deadline. The analysis unit can also postpone meals with a distant submission deadline. For example, the analysis unit analyzes the time of meal submission by the user and postpones meals with a distant submission deadline. The analysis unit can also adjust the frequency of analysis according to the submission time. For example, the analysis unit frequently analyzes meals with an upcoming submission deadline and reduces the frequency of analysis of meals with a distant submission deadline. This allows the analysis unit to determine the priority of analysis according to the time of meal submission.

[0048] During analysis, the analysis unit can adjust the order of analysis based on the relevance of meals. The analysis unit, for example, prioritizes analysis of meals with high relevance. For example, the analysis unit analyzes the relevance of meals of the user, and prioritizes analysis of meals with high relevance. The analysis unit can also postpone analysis of meals with low relevance. For example, the analysis unit analyzes the relevance of meals of the user, and postpones analysis of meals with low relevance. The analysis unit can also adjust the order of analysis according to the relevance of meals. For example, the analysis unit prioritizes analysis of meals with high relevance, and postpones analysis of meals with low relevance. This allows the analysis unit to adjust the order of analysis according to the relevance of meals.

[0049] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the data during evaluation. For example, the evaluation unit performs a detailed evaluation for data with high importance. For example, the evaluation unit analyzes the importance of the user's data and performs a detailed evaluation for data with high importance. The evaluation unit can also perform a brief evaluation for data with low importance. For example, the evaluation unit analyzes the importance of the user's data and performs a brief evaluation for data with low importance. The evaluation unit can also adjust the frequency of the evaluation according to the importance of the data. For example, the evaluation unit frequently evaluates data with high importance and reduces the frequency of evaluation for data with low importance. This allows the evaluation unit to adjust the level of detail of the evaluation according to the importance of the data.

[0050] The evaluation unit can apply different evaluation algorithms depending on the category of data during evaluation. For example, the evaluation unit performs evaluation in conjunction with a health guide for health data. For example, the evaluation unit analyzes the category of the user's data, and performs evaluation in conjunction with the health guide for the health data. The evaluation unit can also perform evaluation in conjunction with asset management for asset data. For example, the evaluation unit analyzes the category of the user's data, and performs evaluation in conjunction with the asset management for the asset data. The evaluation unit can also perform evaluation in conjunction with a disaster prevention guide for disaster prevention data. For example, the evaluation unit analyzes the category of the user's data, and performs evaluation in conjunction with the disaster prevention guide for the disaster prevention data. This allows the evaluation unit to apply an appropriate evaluation algorithm depending on the category of data.

[0051] During evaluation, the evaluation unit can determine the priority of evaluation based on the time of data submission. The evaluation unit, for example, prioritizes evaluation of data with an upcoming submission deadline. For example, the evaluation unit analyzes the time of user data submission and prioritizes evaluation of data with an upcoming submission deadline. The evaluation unit can also postpone data with a distant submission deadline. For example, the evaluation unit analyzes the time of user data submission and postpones data with a distant submission deadline. The evaluation unit can also adjust the frequency of evaluation depending on the submission time. For example, the evaluation unit frequently evaluates data with an upcoming submission deadline and reduces the frequency of evaluation for data with a distant submission deadline. This allows the evaluation unit to determine the priority of evaluation depending on the time of data submission.

[0052] The evaluation unit can adjust the order of evaluation based on the relevance of the data during evaluation. The evaluation unit, for example, prioritizes evaluation of highly relevant data. For example, the evaluation unit analyzes the relevance of the user's data and prioritizes evaluation of highly relevant data. The evaluation unit can also postpone evaluation of less relevant data. For example, the evaluation unit analyzes the relevance of the user's data and postpones evaluation of less relevant data. The evaluation unit can also adjust the order of evaluation according to the relevance of the data. For example, the evaluation unit prioritizes evaluation of highly relevant data and postpones evaluation of less relevant data. This allows the evaluation unit to adjust the order of evaluation according to the relevance of the data.

[0053] The providing unit can adjust the level of detail of the health guide provided based on the importance of the health guide when providing the health guide. For example, the providing unit provides detailed information for health guides with high importance. For example, the providing unit analyzes the importance of health guides for the user and provides detailed information for health guides with high importance. The providing unit can also provide concise information for health guides with low importance. For example, the providing unit analyzes the importance of health guides for the user and provides concise information for health guides with low importance. The providing unit can also adjust the frequency of provision according to the importance of the health guide. For example, the providing unit frequently provides information for health guides with high importance and reduces the frequency of provision for health guides with low importance. In this way, the providing unit can adjust the level of detail of provision according to the importance of the health guide.

[0054] The providing unit can apply different providing algorithms depending on the category of the health guide when providing the guide. For example, the providing unit provides a nutrition guide based on camera images of meals. For example, the providing unit analyzes the category of the user's health guide and provides the nutrition guide based on camera images of meals. The providing unit can also provide an exercise guide based on data from a smartwatch. For example, the providing unit analyzes the category of the user's health guide and provides the exercise guide based on data from the smartwatch. The providing unit can also provide a medication guide based on medication information. For example, the providing unit analyzes the category of the user's health guide and provides the medication guide based on the medication information. This allows the providing unit to apply an appropriate providing algorithm depending on the category of the health guide.

[0055] The providing unit can determine the priority of provision based on the submission timing of the health guide when providing the information. For example, the providing unit prioritizes the provision of health guides with an approaching submission deadline. For example, the providing unit analyzes the submission timing of the user's health guide and prioritizes the provision of health guides with an upcoming submission deadline. The providing unit can also postpone health guides with a distant submission deadline. For example, the providing unit analyzes the submission timing of the user's health guide and postpones health guides with a distant submission deadline. The providing unit can also adjust the frequency of provision depending on the submission timing. For example, the providing unit frequently provides information on health guides with an upcoming submission deadline and reduces the frequency of provision on health guides with a distant submission deadline. This allows the providing unit to determine the priority of provision depending on the submission timing of the health guide.

[0056] The providing unit can adjust the order of provision based on the relevance of the health guides when providing them. For example, the providing unit provides health guides with high relevance preferentially. For example, the providing unit analyzes the relevance of health guides to the user and provides health guides with high relevance preferentially. The providing unit can also postpone health guides with low relevance. For example, the providing unit analyzes the relevance of health guides to the user and provides health guides with low relevance preferentially. The providing unit can also adjust the order of provision based on the relevance of the health guides. For example, the providing unit provides health guides with high relevance preferentially and provides health guides with low relevance preferentially. In this way, the providing unit can adjust the order of provision based on the relevance of the health guides.

[0057] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the recipe when making a suggestion. For example, the suggestion unit makes detailed suggestions for recipes with high importance. For example, the suggestion unit analyzes the importance of the recipes for the user and makes detailed suggestions for recipes with high importance. The suggestion unit can also make brief suggestions for recipes with low importance. For example, the suggestion unit analyzes the importance of the recipes for the user and makes brief suggestions for recipes with low importance. The suggestion unit can also adjust the frequency of suggestions depending on the importance of the recipe. For example, the suggestion unit makes frequent suggestions for recipes with high importance and makes less frequent suggestions for recipes with low importance. This allows the suggestion unit to adjust the level of detail of the suggestion depending on the importance of the recipe.

[0058] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the recipe. For example, for healthy recipes, the suggestion unit makes suggestions that emphasize nutritional balance. For example, the suggestion unit analyzes the category of the user's recipes and makes suggestions for healthy recipes that emphasize nutritional balance. The suggestion unit can also make suggestions for seasonal recipes that emphasize seasonal ingredients. For example, the suggestion unit analyzes the category of the user's recipes and makes suggestions for seasonal recipes that emphasize seasonal ingredients. The suggestion unit can also make suggestions for dessert recipes that emphasize sugar content. For example, the suggestion unit analyzes the category of the user's recipes and makes suggestions for dessert recipes that emphasize sugar content. This allows the suggestion unit to apply an appropriate suggestion algorithm depending on the category of the recipe.

[0059] When making a proposal, the proposal unit can determine the priority of the proposal based on the submission time of the recipe. For example, the proposal unit prioritizes proposals for recipes with an upcoming submission deadline. For example, the proposal unit analyzes the submission time of the user's recipes and prioritizes proposals for recipes with an upcoming submission deadline. The proposal unit can also postpone recipes with a distant submission deadline. For example, the proposal unit analyzes the submission time of the user's recipes and postpones recipes with a distant submission deadline. The proposal unit can also adjust the frequency of proposals depending on the submission time. For example, the proposal unit frequently proposes recipes with an upcoming submission deadline and reduces the frequency of proposals for recipes with a distant submission deadline. This allows the proposal unit to determine the priority of proposals depending on the submission time of the recipes.

[0060] When making suggestions, the suggestion unit can adjust the order of suggestions based on the relevance of the recipes. For example, the suggestion unit gives priority to suggesting highly relevant recipes. For example, the suggestion unit analyzes the relevance of the user's recipes and gives priority to suggesting highly relevant recipes. The suggestion unit can also postpone recipes with low relevance. For example, the suggestion unit analyzes the relevance of the user's recipes and postpones recipes with low relevance. The suggestion unit can also adjust the order of suggestions based on the relevance of the recipes. For example, the suggestion unit gives priority to suggesting highly relevant recipes and postpones recipes with low relevance. In this way, the suggestion unit can adjust the order of suggestions based on the relevance of the recipes.

[0061] The asset management unit can adjust the level of detail of asset management based on the importance of data during asset management. For example, the asset management unit performs detailed asset management for data with high importance. For example, the asset management unit analyzes the importance of user data and performs detailed asset management for data with high importance. The asset management unit can also perform simplified asset management for data with low importance. For example, the asset management unit analyzes the importance of user data and performs simplified asset management for data with low importance. The asset management unit can also adjust the frequency of asset management according to the importance of data. For example, the asset management unit performs asset management frequently for data with high importance and reduces the frequency of asset management for data with low importance. In this way, the asset management unit can adjust the level of detail of asset management according to the importance of data.

[0062] The asset management unit can apply different asset management algorithms depending on the category of data during asset management. For example, the asset management unit performs asset management with an emphasis on risk management for investment data. For example, the asset management unit analyzes the category of user data and performs asset management with an emphasis on risk management for the investment data. The asset management unit can also perform asset management linked to a tax guide for tax-saving data. For example, the asset management unit analyzes the category of user data and performs asset management linked to the tax guide for the tax-saving data. The asset management unit can also perform asset management linked to a household account book for household data. For example, the asset management unit analyzes the category of user data and performs asset management linked to the household account book for the household data. This allows the asset management unit to apply an appropriate asset management algorithm depending on the category of data.

[0063] During asset management, the asset management unit can determine the priority of asset management based on the time of data submission. For example, the asset management unit prioritizes asset management for data with an upcoming submission deadline. For example, the asset management unit analyzes the time of user data submission and prioritizes asset management for data with an upcoming submission deadline. The asset management unit can also postpone data with a distant submission deadline. For example, the asset management unit analyzes the time of user data submission and postpones data with a distant submission deadline. The asset management unit can also adjust the frequency of asset management according to the submission time. For example, the asset management unit frequently manages asset data with an upcoming submission deadline and reduces the frequency of asset management for data with a distant submission deadline. This allows the asset management unit to determine the priority of asset management according to the time of data submission.

[0064] The asset management unit can adjust the order of asset management based on the relevance of data during asset management. For example, the asset management unit prioritizes asset management for highly relevant data. For example, the asset management unit analyzes the relevance of user data and prioritizes asset management for highly relevant data. The asset management unit can also postpone data with low relevance. For example, the asset management unit analyzes the relevance of user data and postpones data with low relevance. The asset management unit can also adjust the order of asset management according to the relevance of data. For example, the asset management unit prioritizes asset management for highly relevant data and postpones data with low relevance. In this way, the asset management unit can adjust the order of asset management according to the relevance of data.

[0065] During a disaster prevention emergency, the disaster prevention unit can adjust the level of detail of the disaster prevention information based on the importance of the data. For example, the disaster prevention unit provides detailed disaster prevention information for data with a high level of importance. For example, the disaster prevention unit analyzes the importance of the user's data and provides detailed disaster prevention information for data with a high level of importance. The disaster prevention unit can also provide concise disaster prevention information for data with a low level of importance. For example, the disaster prevention unit analyzes the importance of the user's data and provides concise disaster prevention information for data with a low level of importance. The disaster prevention unit can also adjust the frequency of providing disaster prevention information according to the importance of the data. For example, the disaster prevention unit provides disaster prevention information frequently for data with a high level of importance and provides disaster prevention information less frequently for data with a low level of importance. This allows the disaster prevention unit to adjust the level of detail of the disaster prevention information according to the importance of the data.

[0066] The disaster prevention unit can apply different disaster prevention algorithms depending on the data category during disaster prevention. For example, for weather data, the disaster prevention unit provides disaster prevention information linked to a weather forecast. For example, the disaster prevention unit analyzes the category of the user's data and provides disaster prevention information linked to a weather forecast for the weather data. The disaster prevention unit can also provide disaster prevention information linked to an earthquake prediction for earthquake data. For example, the disaster prevention unit analyzes the category of the user's data and provides disaster prevention information linked to an earthquake prediction for the earthquake data. The disaster prevention unit can also provide disaster prevention information linked to river water level information for flood data. For example, the disaster prevention unit analyzes the category of the user's data and provides disaster prevention information linked to river water level information for the flood data. This allows the disaster prevention unit to apply an appropriate disaster prevention algorithm depending on the data category.

[0067] During a disaster, the disaster prevention department can determine disaster prevention priorities based on the timing of data submission. For example, the disaster prevention department prioritizes providing disaster prevention information for data whose submission deadline is approaching. For example, the disaster prevention department analyzes the timing of user data submission and prioritizes providing disaster prevention information for data whose submission deadline is approaching. The disaster prevention department can also postpone data whose submission deadline is far away. For example, the disaster prevention department analyzes the timing of user data submission and postpones data whose submission deadline is far away. The disaster prevention department can also adjust the frequency of providing disaster prevention information depending on the submission timing. For example, the disaster prevention department provides disaster prevention information frequently for data whose submission deadline is approaching and provides disaster prevention information less frequently for data whose submission deadline is far away. This allows the disaster prevention department to determine disaster prevention priorities depending on the timing of data submission.

[0068] The disaster prevention unit can adjust the order of disaster prevention measures based on the relevance of data during a disaster. For example, the disaster prevention unit provides disaster prevention information preferentially for highly relevant data. For example, the disaster prevention unit analyzes the relevance of user data and provides disaster prevention information preferentially for highly relevant data. The disaster prevention unit can also postpone data with low relevance. For example, the disaster prevention unit analyzes the relevance of user data and postpones data with low relevance. The disaster prevention unit can also adjust the order of providing disaster prevention information according to the relevance of data. For example, the disaster prevention unit provides disaster prevention information preferentially for highly relevant data and postpones data with low relevance. In this way, the disaster prevention unit can adjust the order of disaster prevention measures according to the relevance of data.

[0069] When providing knowledge, the knowledge department can adjust the level of detail of the knowledge based on the importance of the data. For example, the knowledge department provides detailed knowledge for data with high importance. For example, the knowledge department analyzes the importance of the user's data and provides detailed knowledge for data with high importance. The knowledge department can also provide concise knowledge for data with low importance. For example, the knowledge department analyzes the importance of the user's data and provides concise knowledge for data with low importance. The knowledge department can also adjust the frequency of providing knowledge according to the importance of the data. For example, the knowledge department frequently provides knowledge for data with high importance and reduces the frequency of providing knowledge for data with low importance. In this way, the knowledge department can adjust the level of detail of the knowledge according to the importance of the data.

[0070] When providing knowledge, the knowledge department can apply different knowledge algorithms depending on the category of data. For example, for health data, the knowledge department provides knowledge linked to a health guide. For example, the knowledge department analyzes the category of the user's data and provides knowledge linked to a health guide for the health data. The knowledge department can also provide knowledge linked to asset management for asset data. For example, the knowledge department analyzes the category of the user's data and provides knowledge linked to asset management for the asset data. The knowledge department can also provide knowledge linked to a disaster prevention guide for disaster prevention data. For example, the knowledge department analyzes the category of the user's data and provides knowledge linked to a disaster prevention guide for the disaster prevention data. This allows the knowledge department to apply an appropriate knowledge algorithm depending on the category of the data.

[0071] When providing knowledge, the knowledge department can determine the priority of the knowledge based on the time of data submission. For example, the knowledge department prioritizes providing knowledge for data with an upcoming submission deadline. For example, the knowledge department analyzes the time of user data submission and prioritizes providing knowledge for data with an upcoming submission deadline. The knowledge department can also postpone data with a distant submission deadline. For example, the knowledge department analyzes the time of user data submission and postpones data with a distant submission deadline. The knowledge department can also adjust the frequency of knowledge provision depending on the submission time. For example, the knowledge department frequently provides knowledge for data with an upcoming submission deadline and reduces the frequency of knowledge provision for data with a distant submission deadline. This allows the knowledge department to determine the priority of knowledge depending on the time of data submission.

[0072] When providing knowledge, the knowledge department can adjust the order of knowledge based on the relevance of the data. For example, the knowledge department provides knowledge preferentially for highly relevant data. For example, the knowledge department analyzes the relevance of the user's data and provides knowledge preferentially for highly relevant data. The knowledge department can also postpone providing knowledge for less relevant data. For example, the knowledge department analyzes the relevance of the user's data and postpone providing knowledge for less relevant data. The knowledge department can also adjust the order of knowledge provision based on the relevance of the data. For example, the knowledge department provides knowledge preferentially for highly relevant data and postpones providing knowledge for less relevant data. In this way, the knowledge department can adjust the order of knowledge based on the relevance of the data.

[0073] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0074] The daily life AI concierge system can also be equipped with an entertainment suggestion unit that is customized based on the user's hobbies and interests. The entertainment suggestion unit analyzes the user's past viewing history and music playback history to suggest movies, music, and events that suit the user's preferences. For example, it can provide information on new movie releases based on the genres and ratings of movies the user has previously watched. It can also analyze the genres of music the user frequently listens to and suggest concert information for related artists. It can also provide information on related events and workshops based on the user's hobbies. This allows users to enjoy entertainment that matches their interests.

[0075] When analyzing camera images of a user's meal, the analysis unit can also provide information about the origin and production method of ingredients. For example, the analysis unit can read the barcode or two-dimensional code (e.g., QR Code (registered trademark)) of an ingredient to identify the region where the ingredient was produced and the production method used. The analysis unit can also provide information not only about the nutritional value of ingredients but also about their environmental impact and sustainability. For example, the analysis unit can recommend the use of organic ingredients or fair trade ingredients. Furthermore, the analysis unit can evaluate the environmental impact of the user's food choices and suggest eco-friendly meals. This allows users to choose meals that are not only healthy but also environmentally friendly.

[0076] The suggestion unit can suggest exercise plans and relaxation methods based on the user's health condition. For example, the suggestion unit analyzes data from the user's smartwatch and suggests an appropriate exercise plan. For example, the suggestion unit suggests appropriate exercise intensity and exercise duration based on the user's heart rate data. The suggestion unit can also analyze the user's sleep data and suggest relaxation methods. For example, the suggestion unit suggests appropriate relaxation methods and stretching methods based on the user's sleep data. The suggestion unit can also analyze the user's stress level and suggest activities for stress reduction. For example, the suggestion unit suggests relaxation activities such as yoga and meditation based on the user's stress level. This allows the suggestion unit to suggest appropriate exercise plans and relaxation methods according to the user's health condition.

[0077] The disaster prevention department can provide region-specific disaster prevention information based on the user's geographical location information. For example, the disaster prevention department can analyze the user's current location and provide information about natural disasters (earthquakes, floods, typhoons, etc.) that are likely to occur in that region. The disaster prevention department can also provide information about local evacuation shelters and emergency contact information. For example, the disaster prevention department can provide information about the nearest evacuation shelter and emergency contact information based on the user's current location. The disaster prevention department can also provide information about local disaster prevention drills and disaster prevention events. For example, the disaster prevention department can provide information about disaster prevention drills and disaster prevention events held in the region based on the user's current location. This allows the disaster prevention department to efficiently obtain region-specific disaster prevention information for the user.

[0078] The collection unit can analyze the user's past schedule history and select the optimal collection method. For example, the collection unit prioritizes the collection method (voice, text, etc.) that the user has frequently used in the past. For example, the collection unit analyzes the user's past schedule history and, if the user has frequently used voice input, prioritizes voice input. The collection unit can also suggest the optimal collection method for a specific time period based on the user's past schedule history. For example, if the user has added many appointments in the morning, the collection unit suggests collecting during the morning. The collection unit can also analyze the user's past schedule history and select the most efficient collection method. For example, if the collection unit finds that text input is efficient based on the user's past schedule history, the collection unit prioritizes text input. This allows the collection unit to select the optimal collection method based on the user's past history.

[0079] When collecting schedules, the collection unit can perform filtering based on the user's current lifestyle and areas of interest. For example, if the user is currently busy, the collection unit prioritizes collecting only important schedules. For example, the collection unit analyzes the user's lifestyle and collects only important schedules during busy periods. The collection unit can also prioritize collecting related schedules based on the user's areas of interest. For example, the collection unit analyzes the user's hobbies and topics of interest and collects related schedules. The collection unit can also perform appropriate filtering according to the user's lifestyle and collect schedules. For example, the collection unit analyzes the user's living environment and work situation and performs appropriate filtering. This allows the collection unit to collect schedules according to the user's lifestyle and areas of interest.

[0080] The processing flow of the first embodiment will be briefly explained below.

[0081] Step 1: The collection unit collects the user's schedule. The user's schedule includes meetings, events, tasks, etc. The collection unit obtains schedules from the user's calendar app or task management app. The collection unit can also collect schedules from the user's voice input or text input. For example, if the user voice-instructs, "Add a meeting for tomorrow," the schedule is added to the calendar. Step 2: The reminder unit sends reminders based on the schedules collected by the collection unit. Reminding is performed based on the notification format and reminder frequency. The reminder unit sends notifications to the user's smartphone to remind them of the schedule. The reminder unit can also send vibration notifications to the user's smartwatch. For example, the reminder unit can send reminders at a time set by the user to ensure that they do not forget an important schedule. Step 3: The analysis unit analyzes the camera images of the meal. The camera images include still images, videos, and resolution. The analysis unit analyzes the images of the meal taken by the user and evaluates the nutritional balance. For example, it uses image recognition technology to identify ingredients and calculate calories and nutrients. Step 4: The evaluation unit evaluates the data from the smartwatch. The data from the smartwatch includes heart rate, step count, sleep data, etc. The evaluation unit analyzes the user's heart rate data to evaluate the amount of exercise. It can also analyze the user's sleep data to evaluate the quality of sleep. Step 5: The provider provides a health guide based on the data obtained by the analyzer and evaluator. The health guide includes dietary advice, exercise advice, and lifestyle advice. The provider suggests balanced meals based on the user's dietary data. It can also suggest an appropriate exercise plan based on the user's exercise data. Step 6: The suggestion unit suggests recommended recipes based on the health guide provided by the provision unit. The recommended recipes include nutritional balance, seasonal ingredients, and the user's preferences. The suggestion unit suggests recipes according to the user's health condition. Step 7: The asset management unit analyzes the household data and proposes investment methods and tax-saving strategies. Household data includes income, expenses, savings, etc. The asset management unit analyzes the user's income data and proposes optimal investment methods. It can also analyze the user's expense data and propose savings methods. Step 8: The Disaster Prevention Department analyzes the weather forecast data and suggests necessary preparations. Weather forecast data includes temperature, probability of precipitation, wind speed, etc. The Disaster Prevention Department analyzes the weather forecast for the next week and suggests preparing the necessary disaster prevention supplies. Step 9: The Knowledge Department analyzes the user's search history and interactions to recommend information, books, and goods. Search history includes web searches, in-app searches, etc. The Knowledge Department uses the user's past searches to suggest related books and goods.

[0082] (Example 2) The AI ​​concierge system for everyday life, according to an embodiment of the present invention, supports users' lives in all aspects of their lives. This system collects the user's schedule, sends reminders, analyzes camera-captured meal images, evaluates smartwatch data, provides health guidance, suggests recipe recommendations, analyzes household finance data, offers management and tax-saving suggestions, analyzes weather forecast data, suggests necessary preparations, analyzes search history and interactions, and suggests recommended information, books, and goods. For example, the schedule management function provides daily morning reminders of the user's plans for the day, the next day, and the week ahead, both for work and personal use. It also provides reminders for doctor visits, local events, family birthdays, anniversaries, tax payments, and travel ticket arrangements. The health management function provides health guidance by linking camera-captured meal images, smartwatch data, medical checkup results, and medication information. The recommended recipe function works in conjunction with the health management function to suggest seasonal recipes. The asset management function provides recommended management methods and tax-saving suggestions based on household finances and asset status. The disaster prevention function works in conjunction with the weather forecast and schedule management function to suggest necessary preparations based on the weather forecast for the week ahead. The knowledge function suggests recommended information, books, and goods based on searches and interactions. This allows users to receive AI support in all aspects of their lives. For example, in the schedule management function, AI analyzes the user's schedule and sends reminders. When a doctor's appointment is scheduled, the health management function provides health guidance. In the health management function, AI analyzes camera images of meals to evaluate nutritional balance. AI also analyzes smartwatch data and health checkup results to provide a comprehensive health guide. In the recommended recipe function, AI suggests seasonal recipes based on data from the health management function. In the asset management function, AI analyzes household data to suggest optimal management methods and tax savings. In the disaster prevention function, AI analyzes weather forecast data and suggests necessary preparations in conjunction with the schedule management function. In the knowledge function, AI analyzes the user's search history and interactions to suggest recommended information, books, and goods. This allows the lifestyle-focused AI concierge system to support users in all aspects of their lives and manage them efficiently and effectively.

[0083] The daily life AI concierge system according to the embodiment includes a collection unit, a reminder unit, an analysis unit, an evaluation unit, a provision unit, a proposal unit, an asset management unit, a disaster prevention unit, and a knowledge unit. The collection unit collects a user's schedule. The user's schedule includes, but is not limited to, meetings, events, and tasks. The collection unit acquires schedules from, for example, the user's calendar app or task management app. The collection unit can also collect schedules from a user's voice input or text input. For example, when a user vocally instructs the collection unit to "add a meeting for tomorrow," the collection unit adds the schedule to the calendar. The reminder unit provides reminders based on the schedule collected by the collection unit. Reminders are provided based on, for example, but not limited to, notification formats and reminder frequency. The reminder unit, for example, sends notifications to the user's smartphone to remind the user of the schedule. The reminder unit can also send vibration notifications to the user's smartwatch. For example, the reminder unit provides reminders at a time set by the user to ensure that important schedules are not forgotten. The analysis unit analyzes camera images of meals. Camera images include, but are not limited to, still images, videos, and resolutions. For example, the analysis unit analyzes images of meals taken by a user to evaluate nutritional balance. For example, the analysis unit uses image recognition technology to identify ingredients and calculate calories and nutrients. The evaluation unit evaluates smartwatch data. Smartwatch data includes, but is not limited to, heart rate, step count, and sleep data. For example, the evaluation unit analyzes the user's heart rate data to evaluate the amount of exercise. The evaluation unit can also analyze the user's sleep data to evaluate the quality of sleep. The provision unit provides a health guide based on the data obtained by the analysis unit and the evaluation unit. The health guide includes, but is not limited to, dietary advice, exercise advice, and lifestyle advice. For example, the provision unit suggests a balanced diet based on the user's dietary data. The provision unit can also suggest an appropriate exercise plan based on the user's exercise data. The suggestion unit suggests recommended recipes based on the health guide provided by the provision unit.The recommended recipes include, but are not limited to, nutritional balance, seasonal ingredients, and user preferences. The suggestion unit suggests recipes based on the user's health condition. The asset management unit analyzes household data and suggests investment methods and tax savings. The household data includes, but is not limited to, income, expenses, and savings. The asset management unit analyzes, for example, the user's income data and suggests optimal investment methods. The asset management unit can also analyze the user's expense data and suggest savings methods. The disaster prevention unit analyzes weather forecast data and suggests necessary preparations. The weather forecast data includes, but is not limited to, temperature, precipitation probability, wind speed, and the like. The disaster prevention unit analyzes, for example, a weather forecast for one week ahead and suggests preparing necessary disaster prevention supplies. The knowledge unit analyzes search history and interactions and suggests recommended information, books, and goods. The search history includes, but is not limited to, web searches, in-app searches, and the like. The knowledge section, for example, suggests related books and goods based on information the user has searched for in the past. This allows the daily life AI concierge system according to the embodiment to support the user's overall life and manage their life efficiently and effectively.

[0084] The reminding unit can remind users about medical visits, local events, family birthdays, anniversaries, tax payments, and ticket arrangements for business trips. The reminding unit, for example, reminds users about scheduled medical visits. For example, the reminding unit reminds users of the date and time of a medical visit set by the user, notifying them so they do not forget. The reminding unit can also remind users about scheduled local events. For example, the reminding unit reminds users of the date and time of local festivals and events, encouraging them to participate. The reminding unit can also remind users about family birthdays and anniversaries. For example, the reminding unit reminds users of family birthdays and wedding anniversaries, encouraging them to prepare presents. The reminding unit can also remind users about tax payment deadlines. For example, the reminding unit reminds users of tax payment deadlines and encourages them to pay their taxes by the deadline. The reminding unit can also remind users to arrange tickets for business trips. For example, the reminding unit reminds users to arrange tickets based on the date and time of a business trip, supporting a smooth business trip. In this way, the reminding unit can reliably remind users of important plans.

[0085] The analysis unit can analyze camera images of meals and evaluate nutritional balance. The analysis unit can, for example, analyze images of meals taken by a user and evaluate nutritional balance. For example, the analysis unit can use image recognition technology to identify ingredients and calculate calories and nutrients. The analysis unit can also analyze camera images of meals and evaluate nutritional balance. For example, the analysis unit can analyze camera images of meals and evaluate vitamin and mineral balance. The analysis unit can also analyze camera images of meals and evaluate nutritional balance. For example, the analysis unit can analyze camera images of meals and evaluate protein and lipid balance. In this way, the analysis unit can analyze the user's dietary content and evaluate nutritional balance.

[0086] The evaluation unit can analyze smartwatch data or medical checkup results to provide a comprehensive health guide. The evaluation unit, for example, analyzes the user's smartwatch data to evaluate the amount of exercise. For example, the evaluation unit can analyze the user's heart rate data to evaluate the amount of exercise. The evaluation unit can also analyze the user's sleep data to evaluate the quality of sleep. For example, the evaluation unit can analyze the user's sleep data to evaluate the quality of sleep. The evaluation unit can also analyze medical checkup results to provide a comprehensive health guide. For example, the evaluation unit can analyze blood pressure data from the medical checkup to provide a health guide. The evaluation unit can also analyze blood glucose level data from the medical checkup to provide a health guide. For example, the evaluation unit can analyze blood glucose level data from the medical checkup to provide a health guide. The evaluation unit can also analyze cholesterol level data from the medical checkup to provide a health guide. For example, the evaluation unit can analyze cholesterol level data from the medical checkup to provide a health guide. In this way, the evaluation unit can comprehensively evaluate the user's health condition and provide a health guide.

[0087] The suggestion unit can suggest recipes according to the season based on data from the health management function. The suggestion unit, for example, suggests recipes according to the user's health condition. For example, the suggestion unit suggests balanced recipes based on the user's nutritional balance data. The suggestion unit can also suggest recipes according to the season. For example, the suggestion unit suggests recipes using seasonal ingredients. The suggestion unit can also suggest recipes according to the user's preferences. For example, the suggestion unit suggests recipes that suit the user's preferences based on the user's past eating history. This allows the suggestion unit to suggest appropriate recipes according to the user's health condition.

[0088] The asset management unit can analyze household data and suggest investment methods and tax-saving strategies. The asset management unit, for example, analyzes the user's income data and suggests optimal investment methods. For example, the asset management unit suggests investment trusts or stock investments based on the user's income data. The asset management unit can also analyze the user's expenditure data and suggest savings methods. For example, the asset management unit suggests ways to reduce wasteful expenditures based on the user's expenditure data. The asset management unit can also analyze the user's savings data and suggest optimal savings methods. For example, the asset management unit suggests fixed-term deposits or installment investments based on the user's savings data. This allows the asset management unit to efficiently manage the user's assets.

[0089] The disaster prevention department can analyze weather forecast data and suggest necessary preparations in conjunction with the schedule management function. The disaster prevention department can, for example, analyze the weather forecast for one week ahead and suggest preparing necessary disaster prevention goods. For example, the disaster prevention department can suggest preparing rain gear and cold weather gear based on the weather forecast data. The disaster prevention department can also analyze weather forecast data and suggest checking evacuation routes. For example, the disaster prevention department can suggest checking evacuation routes in the event of a flood or typhoon based on the weather forecast data. The disaster prevention department can also analyze weather forecast data and suggest preparing emergency food and drinking water. For example, the disaster prevention department can suggest stockpiling emergency food and drinking water based on the weather forecast data. This allows the disaster prevention department to efficiently implement disaster prevention measures.

[0090] The knowledge department can analyze search history and interactions to suggest recommended information, books, and goods. For example, the knowledge department can suggest related books and goods based on information that the user has searched for in the past. For example, the knowledge department can analyze the user's search history to suggest related books. The knowledge department can also analyze the user's interactions to suggest related information. For example, the knowledge department can analyze the content of the user's emails and chats to suggest related information. The knowledge department can also analyze the user's search history and interactions to suggest related goods. For example, the knowledge department can analyze the user's search history to suggest related goods. In this way, the knowledge department can provide useful information to the user.

[0091] The collection unit can estimate the user's emotions and adjust the timing of schedule collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit delays the collection timing and collects schedules in a relaxed state. For example, the collection unit uses a user's facial expression recognition technology to determine whether the user is feeling stressed and adjusts the collection timing. The collection unit can also collect schedules immediately and efficiently manage the schedule when the user is relaxed. For example, the collection unit uses a user's voice analysis technology to determine whether the user is relaxed and adjusts the collection timing. The collection unit can also advance the collection timing and collect schedules quickly when the user is in a hurry. For example, the collection unit uses a user's text analysis technology to determine whether the user is in a hurry and adjusts the collection timing. This allows the collection unit to collect schedules at the optimal timing according to the user's emotions.

[0092] The collection unit can analyze the user's past schedule history and select the optimal collection method. For example, the collection unit preferentially selects a collection method (voice, text, etc.) that the user has frequently used in the past. For example, the collection unit analyzes the user's past schedule history and, if the user has used voice input frequently, preferentially selects voice input. The collection unit can also suggest the optimal collection method for a specific time period based on the user's past schedule history. For example, if the user has added many appointments in the morning, the collection unit suggests collecting appointments in the morning. The collection unit can also analyze the user's past schedule history and select the most efficient collection method. For example, if text input is efficient based on the user's past schedule history, the collection unit preferentially selects text input. This allows the collection unit to select the optimal collection method based on the user's past history.

[0093] When collecting schedules, the collection unit can perform filtering based on the user's current lifestyle and areas of interest. For example, if the user is currently busy, the collection unit prioritizes collecting only important schedules. For example, the collection unit analyzes the user's lifestyle and collects only important schedules during busy periods. The collection unit can also prioritize collecting related schedules based on the user's areas of interest. For example, the collection unit analyzes the user's hobbies and topics of interest and collects related schedules. The collection unit can also perform appropriate filtering according to the user's lifestyle and collect schedules. For example, the collection unit analyzes the user's living environment and work situation and performs appropriate filtering. This allows the collection unit to collect schedules according to the user's lifestyle and areas of interest.

[0094] The collection unit can estimate the user's emotions and determine the priority of the events to be collected based on the estimated user's emotions. For example, if the user is feeling stressed, the collection unit postpones events of lower importance. For example, the collection unit uses a user's facial expression recognition technology to determine whether the user is feeling stressed and determines the priority of the events to be collected. The collection unit can also collect all events equally if the user is relaxed. For example, the collection unit uses a user's voice analysis technology to determine whether the user is relaxed and determines the priority of the events to be collected. The collection unit can also prioritize collection of events of higher importance if the user is in a hurry. For example, the collection unit uses a user's text analysis technology to determine whether the user is in a hurry and determines the priority of the events to be collected. In this way, the collection unit can determine the priority of the events according to the user's emotions.

[0095] When collecting schedules, the collection unit can prioritize collecting highly relevant schedules by taking into account the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collecting schedules related to that area. For example, the collection unit analyzes the user's GPS data and collects schedules related to the user's current location. The collection unit can also prioritize collecting schedules in locations close to the user's current location. For example, the collection unit collects schedules for nearby events and meetings based on the user's current location. The collection unit can also analyze the user's movement patterns and prioritize collecting highly relevant schedules. For example, the collection unit analyzes the user's past movement data and collects highly relevant schedules. This allows the collection unit to collect highly relevant schedules based on the user's geographical location information.

[0096] The collection unit can analyze the user's social media activities and collect related events when collecting schedules. The collection unit, for example, collects events mentioned by the user on social media. For example, the collection unit analyzes the content of the user's social media posts and collects related event schedules. The collection unit can also collect events in which the user's social media friends will be attending. For example, the collection unit analyzes the content of the user's social media posts and collects related event schedules. The collection unit can also collect related schedules from the content of the user's social media posts. For example, the collection unit analyzes the content of the user's social media posts and collects related schedules. In this way, the collection unit can collect related schedules based on the user's social media activities.

[0097] The reminding unit can estimate the user's emotions and adjust the way the reminder is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the reminding unit uses gentle expressions to give the reminder. For example, the reminding unit uses facial expression recognition technology to determine whether the user is feeling stressed and uses gentle expressions to give the reminder. The reminding unit can also provide a reminder with detailed information if the user is relaxed. For example, the reminding unit uses user voice analysis technology to determine whether the user is relaxed and provides a reminder with detailed information. The reminding unit can also provide a concise and quick reminder if the user is in a hurry. For example, the reminding unit uses user text analysis technology to determine whether the user is in a hurry and provides a concise and quick reminder. This allows the reminding unit to adjust the way the reminder is expressed depending on the user's emotions.

[0098] The reminding unit can adjust the level of detail of the reminder based on the importance of the schedule when reminding. For example, the reminding unit provides a detailed reminder for a schedule with high importance. For example, the reminding unit analyzes the importance of the schedule of the user and provides a detailed reminder for a schedule with high importance. The reminding unit can also provide a brief reminder for a schedule with low importance. For example, the reminding unit analyzes the importance of the schedule of the user and provides a brief reminder for a schedule with low importance. The reminding unit can also adjust the frequency of reminders according to the importance of the schedule. For example, the reminding unit provides frequent reminders for schedules with high importance and reduces the frequency of reminders for schedules with low importance. This allows the reminding unit to adjust the level of detail of the reminder according to the importance of the schedule.

[0099] The reminding unit can apply different reminding algorithms depending on the category of the event when reminding. For example, the reminding unit performs a business-like reminder for work-related events. For example, the reminding unit analyzes the category of the user's events and performs a business-like reminder for work-related events. The reminding unit can also perform a casual reminder for private events. For example, the reminding unit analyzes the category of the user's events and performs a casual reminder for private events. The reminding unit can also perform a reminder linked with a health guide for health-related events. For example, the reminding unit analyzes the category of the user's events and performs a reminder linked with a health guide for health-related events. This allows the reminding unit to perform an appropriate reminder depending on the category of the event.

[0100] The reminding unit can estimate the user's emotions and adjust the timing of the reminder based on the estimated user emotions. For example, the reminding unit delays the timing of the reminder if the user is feeling stressed. For example, the reminding unit uses facial expression recognition technology to determine whether the user is feeling stressed and adjusts the timing of the reminder. The reminding unit can also immediately remind the user if the user is relaxed. For example, the reminding unit uses user voice analysis technology to determine whether the user is relaxed and adjusts the timing of the reminder. The reminding unit can also advance the timing of the reminder if the user is in a hurry. For example, the reminding unit uses user text analysis technology to determine whether the user is in a hurry and adjusts the timing of the reminder. This allows the reminding unit to adjust the timing of the reminder according to the user's emotions.

[0101] The reminding unit can determine the priority of reminders based on the submission time of the schedule when a reminder is issued. For example, the reminding unit prioritizes reminders for schedules with an upcoming submission deadline. For example, the reminding unit analyzes the submission time of the user's schedule and prioritizes reminders for schedules with an upcoming submission deadline. The reminding unit can also postpone schedules with a distant submission deadline. For example, the reminding unit analyzes the submission time of the user's schedule and postpones schedules with a distant submission deadline. The reminding unit can also adjust the frequency of reminders depending on the submission time. For example, the reminding unit frequently reminds schedules with an upcoming submission deadline and reduces the frequency of reminders for schedules with a distant submission deadline. This allows the reminding unit to determine the priority of reminders depending on the submission time of the schedule.

[0102] The reminding unit can adjust the order of reminders based on the relevance of the schedules when reminding. For example, the reminding unit gives priority to reminding highly relevant schedules. For example, the reminding unit analyzes the relevance of the user's schedules and gives priority to reminding highly relevant schedules. The reminding unit can also postpone less relevant schedules. For example, the reminding unit analyzes the relevance of the user's schedules and postpones less relevant schedules. The reminding unit can also adjust the order of reminders based on the relevance of the schedules. For example, the reminding unit gives priority to reminding highly relevant schedules and postpones less relevant schedules. In this way, the reminding unit can adjust the order of reminders based on the relevance of the schedules.

[0103] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit provides the analysis result in a calm expression. For example, the analysis unit uses facial expression recognition technology to determine whether the user is feeling stressed and provides the analysis result in a calm expression. The analysis unit can also provide a detailed analysis result if the user is relaxed. For example, the analysis unit uses user voice analysis technology to determine whether the user is relaxed and provides a detailed analysis result. The analysis unit can also provide a concise and quick analysis result if the user is in a hurry. For example, the analysis unit uses user text analysis technology to determine whether the user is in a hurry and provides a concise and quick analysis result. This allows the analysis unit to adjust the way the analysis is presented depending on the user's emotions.

[0104] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the meal. For example, the analysis unit performs a detailed analysis on meals with high importance. For example, the analysis unit analyzes the importance of meals to the user and performs a detailed analysis on meals with high importance. The analysis unit can also perform a brief analysis on meals with low importance. For example, the analysis unit analyzes the importance of meals to the user and performs a brief analysis on meals with low importance. The analysis unit can also adjust the frequency of analysis according to the importance of the meal. For example, the analysis unit frequently analyzes meals with high importance and reduces the frequency of analysis on meals with low importance. This allows the analysis unit to adjust the level of detail of the analysis according to the importance of the meal.

[0105] During analysis, the analysis unit can apply different analysis algorithms depending on the food category. For example, for healthy food, the analysis unit performs an analysis that emphasizes nutritional balance. For example, the analysis unit analyzes the user's food category, and for healthy food, performs an analysis that emphasizes nutritional balance. The analysis unit can also perform an analysis that emphasizes calories for fast food. For example, the analysis unit analyzes the user's food category, and for fast food, performs an analysis that emphasizes calories. The analysis unit can also perform an analysis that emphasizes sugar content for desserts. For example, the analysis unit analyzes the user's food category, and for desserts, performs an analysis that emphasizes sugar content. This allows the analysis unit to apply an appropriate analysis algorithm depending on the food category.

[0106] The analysis unit can estimate the user's emotions and adjust the timing of the analysis based on the estimated user emotions. For example, the analysis unit delays the timing of the analysis when the user is feeling stressed. For example, the analysis unit uses facial expression recognition technology to determine whether the user is feeling stressed and adjusts the timing of the analysis. The analysis unit can also perform analysis immediately when the user is relaxed. For example, the analysis unit uses user voice analysis technology to determine whether the user is relaxed and adjusts the timing of the analysis. The analysis unit can also advance the timing of the analysis when the user is in a hurry. For example, the analysis unit uses user text analysis technology to determine whether the user is in a hurry and adjusts the timing of the analysis. This allows the analysis unit to adjust the timing of the analysis according to the user's emotions.

[0107] During analysis, the analysis unit can determine the priority of analysis based on the time of meal submission. For example, the analysis unit prioritizes analysis of meals with an upcoming submission deadline. For example, the analysis unit analyzes the time of meal submission by the user and prioritizes analysis of meals with an upcoming submission deadline. The analysis unit can also postpone meals with a distant submission deadline. For example, the analysis unit analyzes the time of meal submission by the user and postpones meals with a distant submission deadline. The analysis unit can also adjust the frequency of analysis according to the submission time. For example, the analysis unit frequently analyzes meals with an upcoming submission deadline and reduces the frequency of analysis of meals with a distant submission deadline. This allows the analysis unit to determine the priority of analysis according to the time of meal submission.

[0108] During analysis, the analysis unit can adjust the order of analysis based on the relevance of meals. The analysis unit, for example, prioritizes analysis of meals with high relevance. For example, the analysis unit analyzes the relevance of meals of the user, and prioritizes analysis of meals with high relevance. The analysis unit can also postpone analysis of meals with low relevance. For example, the analysis unit analyzes the relevance of meals of the user, and postpones analysis of meals with low relevance. The analysis unit can also adjust the order of analysis according to the relevance of meals. For example, the analysis unit prioritizes analysis of meals with high relevance, and postpones analysis of meals with low relevance. This allows the analysis unit to adjust the order of analysis according to the relevance of meals.

[0109] The evaluation unit can estimate the user's emotions and adjust the way the evaluation is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the evaluation unit provides the evaluation result in a calm expression. For example, the evaluation unit uses facial expression recognition technology to determine whether the user is feeling stressed and provides the evaluation result in a calm expression. The evaluation unit can also provide a detailed evaluation result if the user is relaxed. For example, the evaluation unit can use user voice analysis technology to determine whether the user is relaxed and provide a detailed evaluation result. The evaluation unit can also provide a concise and quick evaluation result if the user is in a hurry. For example, the evaluation unit can use user text analysis technology to determine whether the user is in a hurry and provide a concise and quick evaluation result. This allows the evaluation unit to adjust the way the evaluation is expressed depending on the user's emotions.

[0110] The evaluation unit can adjust the level of detail of the evaluation based on the importance of the data during evaluation. For example, the evaluation unit performs a detailed evaluation for data with high importance. For example, the evaluation unit analyzes the importance of the user's data and performs a detailed evaluation for data with high importance. The evaluation unit can also perform a brief evaluation for data with low importance. For example, the evaluation unit analyzes the importance of the user's data and performs a brief evaluation for data with low importance. The evaluation unit can also adjust the frequency of the evaluation according to the importance of the data. For example, the evaluation unit frequently evaluates data with high importance and reduces the frequency of evaluation for data with low importance. This allows the evaluation unit to adjust the level of detail of the evaluation according to the importance of the data.

[0111] The evaluation unit can apply different evaluation algorithms depending on the category of data during evaluation. For example, the evaluation unit performs evaluation in conjunction with a health guide for health data. For example, the evaluation unit analyzes the category of the user's data, and performs evaluation in conjunction with the health guide for the health data. The evaluation unit can also perform evaluation in conjunction with asset management for asset data. For example, the evaluation unit analyzes the category of the user's data, and performs evaluation in conjunction with the asset management for the asset data. The evaluation unit can also perform evaluation in conjunction with a disaster prevention guide for disaster prevention data. For example, the evaluation unit analyzes the category of the user's data, and performs evaluation in conjunction with the disaster prevention guide for the disaster prevention data. This allows the evaluation unit to apply an appropriate evaluation algorithm depending on the category of data.

[0112] The evaluation unit can estimate the user's emotions and adjust the timing of the evaluation based on the estimated user emotions. For example, the evaluation unit delays the timing of the evaluation when the user is feeling stressed. For example, the evaluation unit uses facial expression recognition technology to determine whether the user is feeling stressed and adjusts the timing of the evaluation. The evaluation unit can also make an immediate evaluation when the user is relaxed. For example, the evaluation unit uses user voice analysis technology to determine whether the user is relaxed and adjusts the timing of the evaluation. The evaluation unit can also advance the timing of the evaluation when the user is in a hurry. For example, the evaluation unit uses user text analysis technology to determine whether the user is in a hurry and adjusts the timing of the evaluation. This allows the evaluation unit to adjust the timing of the evaluation according to the user's emotions.

[0113] During evaluation, the evaluation unit can determine the priority of evaluation based on the time of data submission. The evaluation unit, for example, prioritizes evaluation of data with an upcoming submission deadline. For example, the evaluation unit analyzes the time of user data submission and prioritizes evaluation of data with an upcoming submission deadline. The evaluation unit can also postpone data with a distant submission deadline. For example, the evaluation unit analyzes the time of user data submission and postpones data with a distant submission deadline. The evaluation unit can also adjust the frequency of evaluation depending on the submission time. For example, the evaluation unit frequently evaluates data with an upcoming submission deadline and reduces the frequency of evaluation for data with a distant submission deadline. This allows the evaluation unit to determine the priority of evaluation depending on the time of data submission.

[0114] The evaluation unit can adjust the order of evaluation based on the relevance of the data during evaluation. The evaluation unit, for example, prioritizes evaluation of highly relevant data. For example, the evaluation unit analyzes the relevance of the user's data and prioritizes evaluation of highly relevant data. The evaluation unit can also postpone evaluation of less relevant data. For example, the evaluation unit analyzes the relevance of the user's data and postpones evaluation of less relevant data. The evaluation unit can also adjust the order of evaluation according to the relevance of the data. For example, the evaluation unit prioritizes evaluation of highly relevant data and postpones evaluation of less relevant data. This allows the evaluation unit to adjust the order of evaluation according to the relevance of the data.

[0115] The providing unit can estimate the user's emotions and adjust the way the health guide is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the providing unit can provide the health guide in a calm expression. For example, the providing unit can use facial expression recognition technology to determine whether the user is feeling stressed and provide the health guide in a calm expression. The providing unit can also provide a detailed health guide if the user is relaxed. For example, the providing unit can use user voice analysis technology to determine whether the user is relaxed and provide the detailed health guide. The providing unit can also provide a concise and quick health guide if the user is in a hurry. For example, the providing unit can use user text analysis technology to determine whether the user is in a hurry and provide the concise and quick health guide. This allows the providing unit to adjust the way the health guide is presented depending on the user's emotions.

[0116] The providing unit can adjust the level of detail of the health guide provided based on the importance of the health guide when providing the health guide. For example, the providing unit provides detailed information for health guides with high importance. For example, the providing unit analyzes the importance of health guides for the user and provides detailed information for health guides with high importance. The providing unit can also provide concise information for health guides with low importance. For example, the providing unit analyzes the importance of health guides for the user and provides concise information for health guides with low importance. The providing unit can also adjust the frequency of provision according to the importance of the health guide. For example, the providing unit frequently provides information for health guides with high importance and reduces the frequency of provision for health guides with low importance. In this way, the providing unit can adjust the level of detail of provision according to the importance of the health guide.

[0117] The providing unit can apply different providing algorithms depending on the category of the health guide when providing the guide. For example, the providing unit provides a nutrition guide based on camera images of meals. For example, the providing unit analyzes the category of the user's health guide and provides the nutrition guide based on camera images of meals. The providing unit can also provide an exercise guide based on data from a smartwatch. For example, the providing unit analyzes the category of the user's health guide and provides the exercise guide based on data from the smartwatch. The providing unit can also provide a medication guide based on medication information. For example, the providing unit analyzes the category of the user's health guide and provides the medication guide based on the medication information. This allows the providing unit to apply an appropriate providing algorithm depending on the category of the health guide.

[0118] The providing unit can estimate the user's emotions and adjust the timing of providing the health guide based on the estimated user emotions. For example, if the user is feeling stressed, the providing unit delays the timing of providing the health guide. For example, the providing unit can use facial expression recognition technology to determine whether the user is feeling stressed and adjust the timing of providing the health guide. The providing unit can also provide the health guide immediately if the user is relaxed. For example, the providing unit can use user voice analysis technology to determine whether the user is relaxed and adjust the timing of providing the health guide. The providing unit can also advance the timing of providing the health guide if the user is in a hurry. For example, the providing unit can use user text analysis technology to determine whether the user is in a hurry and adjust the timing of providing the health guide. This allows the providing unit to adjust the timing of providing the health guide according to the user's emotions.

[0119] The providing unit can determine the priority of provision based on the submission timing of the health guide when providing the information. For example, the providing unit prioritizes the provision of health guides with an approaching submission deadline. For example, the providing unit analyzes the submission timing of the user's health guide and prioritizes the provision of health guides with an upcoming submission deadline. The providing unit can also postpone health guides with a distant submission deadline. For example, the providing unit analyzes the submission timing of the user's health guide and postpones health guides with a distant submission deadline. The providing unit can also adjust the frequency of provision depending on the submission timing. For example, the providing unit frequently provides information on health guides with an upcoming submission deadline and reduces the frequency of provision on health guides with a distant submission deadline. This allows the providing unit to determine the priority of provision depending on the submission timing of the health guide.

[0120] The providing unit can adjust the order of provision based on the relevance of the health guides when providing them. For example, the providing unit provides health guides with high relevance preferentially. For example, the providing unit analyzes the relevance of health guides to the user and provides health guides with high relevance preferentially. The providing unit can also postpone health guides with low relevance. For example, the providing unit analyzes the relevance of health guides to the user and provides health guides with low relevance preferentially. The providing unit can also adjust the order of provision based on the relevance of the health guides. For example, the providing unit provides health guides with high relevance preferentially and provides health guides with low relevance preferentially. In this way, the providing unit can adjust the order of provision based on the relevance of the health guides.

[0121] The suggestion unit can estimate the user's emotions and adjust the way suggestions are expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the suggestion unit makes suggestions using calm expressions. For example, the suggestion unit uses a user's facial expression recognition technology to determine whether the user is feeling stressed and makes suggestions using calm expressions. The suggestion unit can also make detailed suggestions if the user is relaxed. For example, the suggestion unit uses a user's voice analysis technology to determine whether the user is relaxed and makes detailed suggestions. The suggestion unit can also make concise and quick suggestions if the user is in a hurry. For example, the suggestion unit uses a user's text analysis technology to determine whether the user is in a hurry and makes concise and quick suggestions. This allows the suggestion unit to adjust the way suggestions are expressed depending on the user's emotions.

[0122] The suggestion unit can adjust the level of detail of the suggestion based on the importance of the recipe when making a suggestion. For example, the suggestion unit makes detailed suggestions for recipes with high importance. For example, the suggestion unit analyzes the importance of the recipes for the user and makes detailed suggestions for recipes with high importance. The suggestion unit can also make brief suggestions for recipes with low importance. For example, the suggestion unit analyzes the importance of the recipes for the user and makes brief suggestions for recipes with low importance. The suggestion unit can also adjust the frequency of suggestions depending on the importance of the recipe. For example, the suggestion unit makes frequent suggestions for recipes with high importance and makes less frequent suggestions for recipes with low importance. This allows the suggestion unit to adjust the level of detail of the suggestion depending on the importance of the recipe.

[0123] When making a suggestion, the suggestion unit can apply different suggestion algorithms depending on the category of the recipe. For example, for healthy recipes, the suggestion unit makes suggestions that emphasize nutritional balance. For example, the suggestion unit analyzes the category of the user's recipes and makes suggestions for healthy recipes that emphasize nutritional balance. The suggestion unit can also make suggestions for seasonal recipes that emphasize seasonal ingredients. For example, the suggestion unit analyzes the category of the user's recipes and makes suggestions for seasonal recipes that emphasize seasonal ingredients. The suggestion unit can also make suggestions for dessert recipes that emphasize sugar content. For example, the suggestion unit analyzes the category of the user's recipes and makes suggestions for dessert recipes that emphasize sugar content. This allows the suggestion unit to apply an appropriate suggestion algorithm depending on the category of the recipe.

[0124] The suggestion unit can estimate the user's emotions and adjust the timing of suggestions based on the estimated user emotions. For example, the suggestion unit delays the timing of suggestions when the user is feeling stressed. For example, the suggestion unit uses a user's facial expression recognition technology to determine whether the user is feeling stressed and adjusts the timing of suggestions. The suggestion unit can also make suggestions immediately when the user is relaxed. For example, the suggestion unit uses a user's voice analysis technology to determine whether the user is relaxed and adjusts the timing of suggestions. The suggestion unit can also advance the timing of suggestions when the user is in a hurry. For example, the suggestion unit uses a user's text analysis technology to determine whether the user is in a hurry and adjusts the timing of suggestions. This allows the suggestion unit to adjust the timing of suggestions according to the user's emotions.

[0125] When making a proposal, the proposal unit can determine the priority of the proposal based on the submission time of the recipe. For example, the proposal unit prioritizes proposals for recipes with an upcoming submission deadline. For example, the proposal unit analyzes the submission time of the user's recipes and prioritizes proposals for recipes with an upcoming submission deadline. The proposal unit can also postpone recipes with a distant submission deadline. For example, the proposal unit analyzes the submission time of the user's recipes and postpones recipes with a distant submission deadline. The proposal unit can also adjust the frequency of proposals depending on the submission time. For example, the proposal unit frequently proposes recipes with an upcoming submission deadline and reduces the frequency of proposals for recipes with a distant submission deadline. This allows the proposal unit to determine the priority of proposals depending on the submission time of the recipes.

[0126] When making suggestions, the suggestion unit can adjust the order of suggestions based on the relevance of the recipes. For example, the suggestion unit gives priority to suggesting highly relevant recipes. For example, the suggestion unit analyzes the relevance of the user's recipes and gives priority to suggesting highly relevant recipes. The suggestion unit can also postpone recipes with low relevance. For example, the suggestion unit analyzes the relevance of the user's recipes and postpones recipes with low relevance. The suggestion unit can also adjust the order of suggestions based on the relevance of the recipes. For example, the suggestion unit gives priority to suggesting highly relevant recipes and postpones recipes with low relevance. In this way, the suggestion unit can adjust the order of suggestions based on the relevance of the recipes.

[0127] The asset management unit can estimate a user's emotions and adjust the manner in which asset management is presented based on the estimated user emotions. For example, if the user is feeling stressed, the asset management unit provides asset management information in a calm manner. For example, the asset management unit uses facial expression recognition technology to determine whether the user is feeling stressed and provides asset management information in a calm manner. The asset management unit can also provide detailed asset management information if the user is relaxed. For example, the asset management unit can use user voice analysis technology to determine whether the user is relaxed and provide detailed asset management information. The asset management unit can also provide concise and quick asset management information if the user is in a hurry. For example, the asset management unit can use user text analysis technology to determine whether the user is in a hurry and provide concise and quick asset management information. This allows the asset management unit to adjust the manner in which asset management is presented according to the user's emotions.

[0128] The asset management unit can adjust the level of detail of asset management based on the importance of data during asset management. For example, the asset management unit performs detailed asset management for data with high importance. For example, the asset management unit analyzes the importance of user data and performs detailed asset management for data with high importance. The asset management unit can also perform simplified asset management for data with low importance. For example, the asset management unit analyzes the importance of user data and performs simplified asset management for data with low importance. The asset management unit can also adjust the frequency of asset management according to the importance of data. For example, the asset management unit performs asset management frequently for data with high importance and reduces the frequency of asset management for data with low importance. In this way, the asset management unit can adjust the level of detail of asset management according to the importance of data.

[0129] The asset management unit can apply different asset management algorithms depending on the category of data during asset management. For example, the asset management unit performs asset management with an emphasis on risk management for investment data. For example, the asset management unit analyzes the category of user data and performs asset management with an emphasis on risk management for the investment data. The asset management unit can also perform asset management linked to a tax guide for tax-saving data. For example, the asset management unit analyzes the category of user data and performs asset management linked to the tax guide for the tax-saving data. The asset management unit can also perform asset management linked to a household account book for household data. For example, the asset management unit analyzes the category of user data and performs asset management linked to the household account book for the household data. This allows the asset management unit to apply an appropriate asset management algorithm depending on the category of data.

[0130] The asset management unit can estimate the user's emotions and adjust the timing of asset management based on the estimated user emotions. For example, the asset management unit delays the timing of asset management when the user is feeling stressed. For example, the asset management unit uses facial expression recognition technology to determine whether the user is feeling stressed and adjusts the timing of asset management. The asset management unit can also perform asset management immediately when the user is relaxed. For example, the asset management unit uses user voice analysis technology to determine whether the user is relaxed and adjusts the timing of asset management. The asset management unit can also advance the timing of asset management when the user is in a hurry. For example, the asset management unit uses user text analysis technology to determine whether the user is in a hurry and adjusts the timing of asset management. This allows the asset management unit to adjust the timing of asset management according to the user's emotions.

[0131] During asset management, the asset management unit can determine the priority of asset management based on the time of data submission. For example, the asset management unit prioritizes asset management for data with an upcoming submission deadline. For example, the asset management unit analyzes the time of user data submission and prioritizes asset management for data with an upcoming submission deadline. The asset management unit can also postpone data with a distant submission deadline. For example, the asset management unit analyzes the time of user data submission and postpones data with a distant submission deadline. The asset management unit can also adjust the frequency of asset management according to the submission time. For example, the asset management unit frequently manages asset data with an upcoming submission deadline and reduces the frequency of asset management for data with a distant submission deadline. This allows the asset management unit to determine the priority of asset management according to the time of data submission.

[0132] The asset management unit can adjust the order of asset management based on the relevance of data during asset management. For example, the asset management unit prioritizes asset management for highly relevant data. For example, the asset management unit analyzes the relevance of user data and prioritizes asset management for highly relevant data. The asset management unit can also postpone data with low relevance. For example, the asset management unit analyzes the relevance of user data and postpones data with low relevance. The asset management unit can also adjust the order of asset management according to the relevance of data. For example, the asset management unit prioritizes asset management for highly relevant data and postpones data with low relevance. In this way, the asset management unit can adjust the order of asset management according to the relevance of data.

[0133] The disaster prevention unit can estimate the user's emotions and adjust the disaster prevention presentation method based on the estimated user's emotions. For example, if the user is feeling stressed, the disaster prevention unit provides disaster prevention information in a calm manner. For example, the disaster prevention unit uses facial expression recognition technology to determine whether the user is feeling stressed and provides disaster prevention information in a calm manner. The disaster prevention unit can also provide detailed disaster prevention information if the user is relaxed. For example, the disaster prevention unit can use user voice analysis technology to determine whether the user is relaxed and provide detailed disaster prevention information. The disaster prevention unit can also provide concise and prompt disaster prevention information if the user is in a hurry. For example, the disaster prevention unit can use user text analysis technology to determine whether the user is in a hurry and provide concise and prompt disaster prevention information. This allows the disaster prevention unit to adjust the disaster prevention presentation method according to the user's emotions.

[0134] During a disaster prevention emergency, the disaster prevention unit can adjust the level of detail of the disaster prevention information based on the importance of the data. For example, the disaster prevention unit provides detailed disaster prevention information for data with a high level of importance. For example, the disaster prevention unit analyzes the importance of the user's data and provides detailed disaster prevention information for data with a high level of importance. The disaster prevention unit can also provide concise disaster prevention information for data with a low level of importance. For example, the disaster prevention unit analyzes the importance of the user's data and provides concise disaster prevention information for data with a low level of importance. The disaster prevention unit can also adjust the frequency of providing disaster prevention information according to the importance of the data. For example, the disaster prevention unit provides disaster prevention information frequently for data with a high level of importance and provides disaster prevention information less frequently for data with a low level of importance. This allows the disaster prevention unit to adjust the level of detail of the disaster prevention information according to the importance of the data.

[0135] The disaster prevention unit can apply different disaster prevention algorithms depending on the data category during disaster prevention. For example, for weather data, the disaster prevention unit provides disaster prevention information linked to a weather forecast. For example, the disaster prevention unit analyzes the category of the user's data and provides disaster prevention information linked to a weather forecast for the weather data. The disaster prevention unit can also provide disaster prevention information linked to an earthquake prediction for earthquake data. For example, the disaster prevention unit analyzes the category of the user's data and provides disaster prevention information linked to an earthquake prediction for the earthquake data. The disaster prevention unit can also provide disaster prevention information linked to river water level information for flood data. For example, the disaster prevention unit analyzes the category of the user's data and provides disaster prevention information linked to river water level information for the flood data. This allows the disaster prevention unit to apply an appropriate disaster prevention algorithm depending on the data category.

[0136] The disaster prevention unit can estimate the user's emotions and adjust the timing of disaster prevention measures based on the estimated user emotions. For example, if the user is feeling stressed, the disaster prevention unit delays the timing of providing disaster prevention information. For example, the disaster prevention unit uses facial expression recognition technology to determine whether the user is feeling stressed and adjusts the timing of providing the disaster prevention information. The disaster prevention unit can also provide disaster prevention information immediately if the user is relaxed. For example, the disaster prevention unit uses user voice analysis technology to determine whether the user is relaxed and adjusts the timing of providing the disaster prevention information. The disaster prevention unit can also advance the timing of providing the disaster prevention information if the user is in a hurry. For example, the disaster prevention unit uses user text analysis technology to determine whether the user is in a hurry and adjusts the timing of providing the disaster prevention information. This allows the disaster prevention unit to adjust the timing of disaster prevention measures according to the user's emotions.

[0137] During a disaster, the disaster prevention department can determine disaster prevention priorities based on the timing of data submission. For example, the disaster prevention department prioritizes providing disaster prevention information for data whose submission deadline is approaching. For example, the disaster prevention department analyzes the timing of user data submission and prioritizes providing disaster prevention information for data whose submission deadline is approaching. The disaster prevention department can also postpone data whose submission deadline is far away. For example, the disaster prevention department analyzes the timing of user data submission and postpones data whose submission deadline is far away. The disaster prevention department can also adjust the frequency of providing disaster prevention information depending on the submission timing. For example, the disaster prevention department provides disaster prevention information frequently for data whose submission deadline is approaching and provides disaster prevention information less frequently for data whose submission deadline is far away. This allows the disaster prevention department to determine disaster prevention priorities depending on the timing of data submission.

[0138] The disaster prevention unit can adjust the order of disaster prevention measures based on the relevance of data during a disaster. For example, the disaster prevention unit provides disaster prevention information preferentially for highly relevant data. For example, the disaster prevention unit analyzes the relevance of user data and provides disaster prevention information preferentially for highly relevant data. The disaster prevention unit can also postpone data with low relevance. For example, the disaster prevention unit analyzes the relevance of user data and postpones data with low relevance. The disaster prevention unit can also adjust the order of providing disaster prevention information according to the relevance of data. For example, the disaster prevention unit provides disaster prevention information preferentially for highly relevant data and postpones data with low relevance. In this way, the disaster prevention unit can adjust the order of disaster prevention measures according to the relevance of data.

[0139] The knowledge unit can estimate the user's emotions and adjust the way knowledge is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the knowledge unit provides knowledge in a calm expression. For example, the knowledge unit uses a user's facial expression recognition technology to determine whether the user is feeling stressed and provides knowledge in a calm expression. The knowledge unit can also provide detailed knowledge if the user is relaxed. For example, the knowledge unit uses a user's voice analysis technology to determine whether the user is relaxed and provides detailed knowledge. The knowledge unit can also provide concise and quick knowledge if the user is in a hurry. For example, the knowledge unit uses a user's text analysis technology to determine whether the user is in a hurry and provides concise and quick knowledge. This allows the knowledge unit to adjust the way knowledge is expressed according to the user's emotions.

[0140] When providing knowledge, the knowledge department can adjust the level of detail of the knowledge based on the importance of the data. For example, the knowledge department provides detailed knowledge for data with high importance. For example, the knowledge department analyzes the importance of the user's data and provides detailed knowledge for data with high importance. The knowledge department can also provide concise knowledge for data with low importance. For example, the knowledge department analyzes the importance of the user's data and provides concise knowledge for data with low importance. The knowledge department can also adjust the frequency of providing knowledge according to the importance of the data. For example, the knowledge department frequently provides knowledge for data with high importance and reduces the frequency of providing knowledge for data with low importance. In this way, the knowledge department can adjust the level of detail of the knowledge according to the importance of the data.

[0141] When providing knowledge, the knowledge department can apply different knowledge algorithms depending on the category of data. For example, for health data, the knowledge department provides knowledge linked to a health guide. For example, the knowledge department analyzes the category of the user's data and provides knowledge linked to a health guide for the health data. The knowledge department can also provide knowledge linked to asset management for asset data. For example, the knowledge department analyzes the category of the user's data and provides knowledge linked to asset management for the asset data. The knowledge department can also provide knowledge linked to a disaster prevention guide for disaster prevention data. For example, the knowledge department analyzes the category of the user's data and provides knowledge linked to a disaster prevention guide for the disaster prevention data. This allows the knowledge department to apply an appropriate knowledge algorithm depending on the category of the data.

[0142] The knowledge unit can estimate the user's emotions and adjust the timing of providing knowledge based on the estimated user emotions. For example, if the user is feeling stressed, the knowledge unit delays the timing of providing knowledge. For example, the knowledge unit uses facial expression recognition technology to determine whether the user is feeling stressed and adjusts the timing of providing knowledge. The knowledge unit can also provide knowledge immediately if the user is relaxed. For example, the knowledge unit uses user voice analysis technology to determine whether the user is relaxed and adjusts the timing of providing knowledge. The knowledge unit can also advance the timing of providing knowledge if the user is in a hurry. For example, the knowledge unit uses user text analysis technology to determine whether the user is in a hurry and adjusts the timing of providing knowledge. This allows the knowledge unit to adjust the timing of providing knowledge according to the user's emotions.

[0143] When providing knowledge, the knowledge department can determine the priority of the knowledge based on the time of data submission. For example, the knowledge department prioritizes providing knowledge for data with an upcoming submission deadline. For example, the knowledge department analyzes the time of user data submission and prioritizes providing knowledge for data with an upcoming submission deadline. The knowledge department can also postpone data with a distant submission deadline. For example, the knowledge department analyzes the time of user data submission and postpones data with a distant submission deadline. The knowledge department can also adjust the frequency of knowledge provision depending on the submission time. For example, the knowledge department frequently provides knowledge for data with an upcoming submission deadline and reduces the frequency of knowledge provision for data with a distant submission deadline. This allows the knowledge department to determine the priority of knowledge depending on the time of data submission.

[0144] When providing knowledge, the knowledge department can adjust the order of knowledge based on the relevance of the data. For example, the knowledge department provides knowledge preferentially for highly relevant data. For example, the knowledge department analyzes the relevance of the user's data and provides knowledge preferentially for highly relevant data. The knowledge department can also postpone providing knowledge for less relevant data. For example, the knowledge department analyzes the relevance of the user's data and postpone providing knowledge for less relevant data. The knowledge department can also adjust the order of knowledge provision based on the relevance of the data. For example, the knowledge department provides knowledge preferentially for highly relevant data and postpones providing knowledge for less relevant data. In this way, the knowledge department can adjust the order of knowledge based on the relevance of the data. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, reminder unit, analysis unit, evaluation unit, provision unit, suggestion unit, asset management unit, disaster prevention unit, and knowledge unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects the user's schedule and emotions using the camera 42 and microphone 38B of the smart device 14, and adjusts the collection timing using the control unit 46A. The reminder unit issues reminders using the output device 40 of the smart device 14. The analysis unit analyzes camera images of meals using the specific processing unit 290 of the data processing device 12. The evaluation unit evaluates smartwatch data using the specific processing unit 290 of the data processing device 12. The provision unit provides health guides using the specific processing unit 290 of the data processing device 12. The suggestion unit suggests recommended recipes using the specific processing unit 290 of the data processing device 12. The asset management unit analyzes household data using the specific processing unit 290 of the data processing device 12 and makes investment methods and tax-saving suggestions. The disaster prevention department analyzes weather forecast data and suggests necessary preparations using the specific processing unit 290 of the data processing device 12. The knowledge department analyzes search history and interactions using the specific processing unit 290 of the data processing device 12 and suggests recommended information, books, and goods. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, reminder unit, analysis unit, evaluation unit, provision unit, suggestion unit, asset management unit, disaster prevention unit, and knowledge unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects the user's schedule and emotions using the camera 42 and microphone 238 of the smart glasses 214, and adjusts the collection timing using the control unit 46A. The reminder unit provides reminders using the speaker 240 of the smart glasses 214. The analysis unit analyzes camera images of meals using the specific processing unit 290 of the data processing device 12. The evaluation unit evaluates smartwatch data using the specific processing unit 290 of the data processing device 12. The provision unit provides health guides using the specific processing unit 290 of the data processing device 12. The suggestion unit suggests recommended recipes using the specific processing unit 290 of the data processing device 12. The asset management unit analyzes household data using the specific processing unit 290 of the data processing device 12 and makes investment methods and tax-saving suggestions. The disaster prevention department analyzes weather forecast data and suggests necessary preparations using the specific processing unit 290 of the data processing device 12. The knowledge department analyzes search history and interactions using the specific processing unit 290 of the data processing device 12 and suggests recommended information, books, and goods. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, reminding unit, analysis unit, evaluation unit, provision unit, suggestion unit, asset management unit, disaster prevention unit, and knowledge unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit collects the user's schedule and emotions using the camera 42 and microphone 238 of the headset terminal 314, and adjusts the collection timing using the control unit 46A. The reminding unit provides reminders using the speaker 240 of the headset terminal 314. The analysis unit analyzes camera images of meals using the specific processing unit 290 of the data processing device 12. The evaluation unit evaluates smartwatch data using the specific processing unit 290 of the data processing device 12. The provision unit provides health guides using the specific processing unit 290 of the data processing device 12. The suggestion unit suggests recommended recipes using the specific processing unit 290 of the data processing device 12. The asset management unit analyzes household data using the specific processing unit 290 of the data processing device 12 and makes investment methods and tax-saving suggestions. The disaster prevention department analyzes weather forecast data and suggests necessary preparations using the specific processing unit 290 of the data processing device 12. The knowledge department analyzes search history and interactions using the specific processing unit 290 of the data processing device 12 and suggests recommended information, books, and goods. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, reminding unit, analysis unit, evaluation unit, provision unit, suggestion unit, asset management unit, disaster prevention unit, and knowledge unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects the user's schedule and emotions using the camera 42 and microphone 238 of the robot 414, and adjusts the collection timing using the control unit 46A. The reminding unit provides reminders using the speaker 240 of the robot 414. The analysis unit analyzes camera images of meals using the specific processing unit 290 of the data processing device 12. The evaluation unit evaluates smartwatch data using the specific processing unit 290 of the data processing device 12. The provision unit provides health guides using the specific processing unit 290 of the data processing device 12. The suggestion unit suggests recommended recipes using the specific processing unit 290 of the data processing device 12. The asset management unit analyzes household data using the specific processing unit 290 of the data processing device 12 and makes investment methods and tax-saving suggestions. The disaster prevention department analyzes weather forecast data and suggests necessary preparations using the specific processing unit 290 of the data processing device 12. The knowledge department analyzes search history and interactions using the specific processing unit 290 of the data processing device 12 and suggests recommended information, books, and goods.

[0145] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0146] The daily life AI concierge system can also be equipped with an entertainment suggestion unit that is customized based on the user's hobbies and interests. The entertainment suggestion unit analyzes the user's past viewing history and music playback history to suggest movies, music, and events that suit the user's preferences. For example, it can provide information on new movie releases based on the genres and ratings of movies the user has previously watched. It can also analyze the genres of music the user frequently listens to and suggest concert information for related artists. It can also provide information on related events and workshops based on the user's hobbies. This allows users to enjoy entertainment that matches their interests.

[0147] The reminding unit can estimate the user's emotions and adjust the way the reminder is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the reminder can be expressed in a calm manner. For example, the reminding unit can use facial expression recognition technology to determine whether the user is feeling stressed and then use a calm manner to give the reminder. Furthermore, if the user is relaxed, the reminder can also provide a reminder with detailed information. For example, the reminder can use user voice analysis technology to determine whether the user is relaxed and then provide a reminder with detailed information. Furthermore, if the user is in a hurry, the reminder can also provide a concise and quick reminder. For example, the reminder can use user text analysis technology to determine whether the user is in a hurry and then provide a concise and quick reminder. This allows the reminder unit to adjust the way the reminder is expressed based on the user's emotions.

[0148] When analyzing camera images of a user's meal, the analysis unit can also provide information about the origin and production method of ingredients. For example, the analysis unit can read the barcode or two-dimensional code on an ingredient to determine the region where the ingredient was produced and the production method used. The analysis unit can also provide information about the ingredient's environmental impact and sustainability, in addition to its nutritional value. For example, the analysis unit can recommend the use of organic or fair-trade ingredients. Furthermore, the analysis unit can evaluate the environmental impact of the user's food choices and suggest eco-friendly meals. This allows users to choose meals that are not only healthy but also environmentally friendly.

[0149] The evaluation unit can estimate the user's emotions and adjust the way the evaluation is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the evaluation result can be provided in a calm expression. For example, the evaluation unit can use facial expression recognition technology to determine whether the user is feeling stressed and provide the evaluation result in a calm expression. The evaluation unit can also provide a detailed evaluation result if the user is relaxed. For example, the evaluation unit can use voice analysis technology to determine whether the user is relaxed and provide a detailed evaluation result. The evaluation unit can also provide a concise and quick evaluation result if the user is in a hurry. For example, the evaluation unit can use text analysis technology to determine whether the user is in a hurry and provide a concise and quick evaluation result. This allows the evaluation unit to adjust the way the evaluation is expressed depending on the user's emotions.

[0150] The suggestion unit can suggest exercise plans and relaxation methods based on the user's health condition. For example, the suggestion unit analyzes data from the user's smartwatch and suggests an appropriate exercise plan. For example, the suggestion unit suggests appropriate exercise intensity and exercise duration based on the user's heart rate data. The suggestion unit can also analyze the user's sleep data and suggest relaxation methods. For example, the suggestion unit suggests appropriate relaxation methods and stretching methods based on the user's sleep data. The suggestion unit can also analyze the user's stress level and suggest activities for stress reduction. For example, the suggestion unit suggests relaxation activities such as yoga and meditation based on the user's stress level. This allows the suggestion unit to suggest appropriate exercise plans and relaxation methods according to the user's health condition.

[0151] The asset management unit can estimate the user's emotions and adjust the way asset management is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the asset management unit provides asset management information in a calm manner. For example, the asset management unit uses facial expression recognition technology to determine whether the user is feeling stressed and provides asset management information in a calm manner. The asset management unit can also provide detailed asset management information if the user is relaxed. For example, the asset management unit can use user voice analysis technology to determine whether the user is relaxed and provide detailed asset management information. The asset management unit can also provide concise and quick asset management information if the user is in a hurry. For example, the asset management unit uses user text analysis technology to determine whether the user is in a hurry and provides concise and quick asset management information. This allows the asset management unit to adjust the way asset management is presented based on the user's emotions.

[0152] The disaster prevention department can provide region-specific disaster prevention information based on the user's geographical location information. For example, the disaster prevention department can analyze the user's current location and provide information about natural disasters (earthquakes, floods, typhoons, etc.) that are likely to occur in that region. The disaster prevention department can also provide information about local evacuation shelters and emergency contact information. For example, the disaster prevention department can provide information about the nearest evacuation shelter and emergency contact information based on the user's current location. The disaster prevention department can also provide information about local disaster prevention drills and disaster prevention events. For example, the disaster prevention department can provide information about disaster prevention drills and disaster prevention events held in the region based on the user's current location. This allows the disaster prevention department to efficiently obtain region-specific disaster prevention information for the user.

[0153] The knowledge unit can estimate the user's emotions and adjust the way knowledge is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, the knowledge unit provides knowledge in a calm expression. For example, the knowledge unit uses a user's facial expression recognition technology to determine whether the user is feeling stressed and provides knowledge in a calm expression. The knowledge unit can also provide detailed knowledge if the user is relaxed. For example, the knowledge unit uses a user's voice analysis technology to determine whether the user is relaxed and provides detailed knowledge. The knowledge unit can also provide concise and quick knowledge if the user is in a hurry. For example, the knowledge unit uses a user's text analysis technology to determine whether the user is in a hurry and provides concise and quick knowledge. This allows the knowledge unit to adjust the way knowledge is expressed depending on the user's emotions.

[0154] The collection unit can analyze the user's past schedule history and select the optimal collection method. For example, the collection unit prioritizes the collection method (voice, text, etc.) that the user has frequently used in the past. For example, the collection unit analyzes the user's past schedule history and, if the user has frequently used voice input, prioritizes voice input. The collection unit can also suggest the optimal collection method for a specific time period based on the user's past schedule history. For example, if the user has added many appointments in the morning, the collection unit suggests collecting during the morning. The collection unit can also analyze the user's past schedule history and select the most efficient collection method. For example, if the collection unit finds that text input is efficient based on the user's past schedule history, the collection unit prioritizes text input. This allows the collection unit to select the optimal collection method based on the user's past history.

[0155] When collecting schedules, the collection unit can perform filtering based on the user's current lifestyle and areas of interest. For example, if the user is currently busy, the collection unit prioritizes collecting only important schedules. For example, the collection unit analyzes the user's lifestyle and collects only important schedules during busy periods. The collection unit can also prioritize collecting related schedules based on the user's areas of interest. For example, the collection unit analyzes the user's hobbies and topics of interest and collects related schedules. The collection unit can also perform appropriate filtering according to the user's lifestyle and collect schedules. For example, the collection unit analyzes the user's living environment and work situation and performs appropriate filtering. This allows the collection unit to collect schedules according to the user's lifestyle and areas of interest.

[0156] The processing flow of the second embodiment will be briefly explained below.

[0157] Step 1: The collection unit collects the user's schedule. The user's schedule includes meetings, events, tasks, etc. The collection unit obtains schedules from the user's calendar app or task management app. The collection unit can also collect schedules from the user's voice input or text input. For example, if the user voice-instructs, "Add a meeting for tomorrow," the schedule is added to the calendar. Step 2: The reminder unit sends reminders based on the schedules collected by the collection unit. Reminding is performed based on the notification format and reminder frequency. The reminder unit sends notifications to the user's smartphone to remind them of the schedule. The reminder unit can also send vibration notifications to the user's smartwatch. For example, the reminder unit can send reminders at a time set by the user to ensure that they do not forget an important schedule. Step 3: The analysis unit analyzes the camera images of the meal. The camera images include still images, videos, and resolution. The analysis unit analyzes the images of the meal taken by the user and evaluates the nutritional balance. For example, it uses image recognition technology to identify ingredients and calculate calories and nutrients. Step 4: The evaluation unit evaluates the data from the smartwatch. The data from the smartwatch includes heart rate, step count, sleep data, etc. The evaluation unit analyzes the user's heart rate data to evaluate the amount of exercise. It can also analyze the user's sleep data to evaluate the quality of sleep. Step 5: The provider provides a health guide based on the data obtained by the analyzer and evaluator. The health guide includes dietary advice, exercise advice, and lifestyle advice. The provider suggests balanced meals based on the user's dietary data. It can also suggest an appropriate exercise plan based on the user's exercise data. Step 6: The suggestion unit suggests recommended recipes based on the health guide provided by the provision unit. The recommended recipes include nutritional balance, seasonal ingredients, and the user's preferences. The suggestion unit suggests recipes according to the user's health condition. Step 7: The asset management unit analyzes the household data and proposes investment methods and tax-saving strategies. Household data includes income, expenses, savings, etc. The asset management unit analyzes the user's income data and proposes optimal investment methods. It can also analyze the user's expense data and propose savings methods. Step 8: The Disaster Prevention Department analyzes the weather forecast data and suggests necessary preparations. Weather forecast data includes temperature, probability of precipitation, wind speed, etc. The Disaster Prevention Department analyzes the weather forecast for the next week and suggests preparing the necessary disaster prevention supplies. Step 9: The Knowledge Department analyzes the user's search history and interactions to recommend information, books, and goods. Search history includes web searches, in-app searches, etc. The Knowledge Department uses the user's past searches to suggest related books and goods.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0162] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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).

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0194] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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).

[0215] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0216] 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."

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] The hardware resource that executes the specific processing 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 processing may be a single processor.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Explanation of symbols]

[0230] 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 collection unit that collects user schedules; a reminding unit that reminds based on the schedule collected by the collecting unit; an analysis unit that analyzes camera images of meals; an evaluation unit that evaluates data from the smartwatch; a providing unit that provides a health guide based on the data obtained by the analysis unit and the evaluation unit; a suggestion unit that suggests recommended recipes based on the health guide provided by the provision unit; The asset management department analyzes household data and proposes investment methods and tax savings. Disaster Prevention Department, which analyzes weather forecast data and suggests necessary preparations; The Knowledge Department analyzes search history and interactions to recommend information, books, and goods. Equipped with A system characterized by:

2. The reminding unit Reminders for medical visits, local events, family birthdays, anniversaries, tax payments, and business trip ticket arrangements 2. The system of claim 1.

3. The analysis unit Analyzing camera images of meals to evaluate nutritional balance 2. The system of claim 1.

4. The evaluation unit Analyze data from your smartwatch or medical checkups to provide a comprehensive health guide 2. The system of claim 1.

5. The proposal unit Suggest seasonal recipes based on health management data 2. The system of claim 1.

6. The asset management department Analyze household data and propose management methods and tax savings 2. The system of claim 1.

7. The disaster prevention department Analyzes weather forecast data and suggests necessary preparations in conjunction with schedule management functions 2. The system of claim 1.

8. The knowledge section Analyzes search history and interactions to suggest recommended information, books, and goods 2. The system of claim 1.

Images