System

Abstract

An object of a system according to an embodiment is to set an optimum alarm time in consideration of sleep information of a user and external information.SOLUTION: A system according to an embodiment includes a sleep-information collecting unit, a generation AI, an alarm setting unit, and a notifying unit. The sleep information collection unit collects sleep information. The generation AI analyzes the sleeping information collected by the sleeping information collection unit. The alarm setting unit sets an alarm time based on the sleeping information analyzed by the generating AI. The notification unit notifies the user of the alarm time set by the alarm setting unit.SELECTED DRAWING: Figure 1

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 techniques do not adequately take into consideration the user's sleep information and external information when setting an optimal alarm time, and there is room for improvement.

[0005] The system according to the embodiment aims to set an optimal alarm time in consideration of the user's sleep information and external information. [Means for solving the problem]

[0006] The system according to the embodiment includes a sleep information collection unit, a generation AI, an alarm setting unit, and a notification unit. The sleep information collection unit collects sleep information. The generation AI analyzes the sleep information collected by the sleep information collection unit. The alarm setting unit sets an alarm time based on the sleep information analyzed by the generation AI. The notification unit notifies the user of the alarm time set by the alarm setting unit. [Effects of the Invention]

[0007] The system according to the embodiment can set an optimal alarm time in consideration of the user's sleep information and external information. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 alarm setting system according to the embodiment of the present invention automatically sets an alarm based on a user's sleep information and chat history, taking into account weather and traffic information, thereby preventing the user from oversleeping or being late.

[0029] An alarm setting system according to an embodiment includes a sleep information collection unit, a generation AI, an alarm setting unit, and a notification unit. The sleep information collection unit collects sleep information about a user. For example, the sleep information collection unit monitors the user's sleep patterns and sleep quality using sensors in a smartwatch or smartphone. The sleep information collection unit can also record the user's sleep time and store it in a database. For example, the smartwatch can detect the user's heart rate and movements to evaluate the depth of sleep. The generation AI analyzes the sleep information collected by the sleep information collection unit. For example, the generation AI can analyze the sleep data and identify an optimal alarm time using a text generation AI (e.g., LLM). The generation AI can also integrate and analyze multiple data sources using a multimodal generation AI. For example, the generation AI can compare the user's sleep pattern with past data and calculate the optimal wake-up timing. The alarm setting unit sets the alarm time based on the sleep information analyzed by the generation AI. For example, the alarm setting unit sets the alarm to match the user's sleep cycle. The alarm setting unit can also adjust the alarm time according to the user's schedule. For example, the alarm setting unit sets an alarm earlier than usual when the user needs to wake up early. The notification unit notifies the user of the alarm time set by the alarm setting unit. For example, the notification unit displays the alarm using a notification function of the smartphone. The notification unit can also notify the user using an audio alarm. For example, the notification unit plays music or an audio message set by the user. In this way, the alarm setting system according to the embodiment can set an optimal alarm time based on the user's sleep information, preventing the user from oversleeping or being late.

[0030] The sleep information collection unit can monitor the user's sleep patterns and sleep quality using sensors in the smartwatch or smartphone. For example, the sleep information collection unit can monitor the user's heart rate and breathing patterns using sensors in the smartwatch or smartphone to analyze the sleep patterns and sleep quality. For example, the smartwatch can detect fluctuations in the user's heart rate to evaluate the depth of sleep. The sleep information collection unit can also detect the user's movements and analyze the frequency of movements during sleep. For example, the smartphone's acceleration sensor can be used to record the user's movements and evaluate the quality of sleep. The sleep information collection unit can also record the user's sleep time and store the data in a database. For example, the smartwatch can automatically record the user's bedtime and wake-up time and store the sleep data. This allows the user's sleep patterns and sleep quality to be monitored in detail.

[0031] The generation AI can analyze a user's chat history and identify the next day's schedule or important events. For example, the generation AI can analyze the content of the chat history and extract keywords related to the schedule or events using a text generation AI (e.g., LLM). The generation AI can also use a multimodal generation AI to integrate and analyze the chat history and calendar information. For example, the generation AI can detect content such as "I have a meeting tomorrow" in the chat history and compare it with the calendar information to identify the schedule. The generation AI can also identify important events from the user's chat history and adjust the alarm time. For example, if the user says, "I have to get up early tomorrow," the generation AI can set the alarm earlier. This makes it possible to identify the next day's schedule or important events from the user's chat history.

[0032] The generation AI can collect and analyze weather information. For example, the generation AI collects and analyzes weather information. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze weather data and predict the weather for the next day. The generation AI can also use a multimodal generation AI to integrate and analyze weather data and traffic information. For example, the generation AI can predict traffic congestion based on weather data and adjust the alarm time. The generation AI can also evaluate the safety of a user's commute route based on weather information. For example, the generation AI can set an earlier alarm if heavy rain or snow is forecast. In this way, the alarm time can be adjusted by collecting and analyzing weather information.

[0033] The generation AI can collect and analyze traffic information. For example, the generation AI collects and analyzes traffic information. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze traffic data and predict the congestion level of commute routes. The generation AI can also use a multimodal generation AI to integrate and analyze traffic data and weather information. For example, the generation AI analyzes public transportation delay information based on traffic data and adjusts the alarm time. The generation AI can also optimize the user's commute based on traffic information. For example, if traffic congestion is predicted, the generation AI proposes an alternative route and sets the alarm time. In this way, the alarm time can be adjusted by collecting and analyzing traffic information.

[0034] The generation AI can comprehensively analyze sleep information, chat history, weather information, and traffic information to automatically set the optimal alarm time. For example, the generation AI can comprehensively analyze sleep information, chat history, weather information, and traffic information to automatically set the optimal alarm time. For example, the generation AI can use text generation AI (e.g., LLM) to integrate and analyze multiple data sources. The generation AI can also use multimodal generation AI to analyze data correlations and identify the optimal alarm time. For example, the generation AI can calculate the optimal wake-up timing based on the user's sleep patterns, next day's schedule, weather information, and traffic information. The generation AI can also learn the user's past data and set an individually optimized alarm time. This allows for comprehensive analysis of multiple pieces of information to automatically set the optimal alarm time.

[0035] The sleep information collection unit can monitor the user's heart rate or breathing pattern and estimate the stress level. The sleep information collection unit can monitor the user's heart rate and breathing pattern using, for example, a sensor in a smartwatch or smartphone, and estimate the stress level. For example, the sleep information collection unit can analyze heart rate fluctuations to evaluate the stress level. The sleep information collection unit can also analyze breathing patterns to estimate the stress level. For example, the sleep information collection unit can analyze the rhythm and depth of breathing to detect signs of stress. The sleep information collection unit can also adjust the alarm time based on the user's stress level. For example, if the user is highly stressed, the alarm can be set to a time when the user is able to relax. In this way, the user's heart rate and breathing pattern can be monitored and the stress level can be estimated.

[0036] The sleep information collection unit can analyze environmental sounds during sleep and identify the optimal timing to wake up. The sleep information collection unit, for example, uses a microphone on a smartphone to record environmental sounds during sleep and analyze the noise level. For example, it sets an alarm for a time period with little noise. The sleep information collection unit can also detect specific sounds and identify the optimal timing to wake up. For example, it sets an alarm for a time period with continuous silence. The sleep information collection unit can also analyze the type of environmental sound and adjust the timing to wake up. For example, it sets an alarm for a time period with a lot of natural sounds. In this way, it is possible to analyze environmental sounds during sleep and identify the optimal timing to wake up.

[0037] The sleep information collection unit can analyze the user's eating or exercise patterns based on the sleep information and set an alarm time accordingly. The sleep information collection unit, for example, analyzes the user's eating and exercise patterns based on the sleep information. For example, it integrates sleep data and dietary data to analyze the user's digestive state. The sleep information collection unit can also analyze exercise data to identify the user's exercise pattern. For example, it analyzes the type and amount of exercise and adjusts the alarm time. The sleep information collection unit can also set the alarm time based on the user's eating and exercise patterns. For example, it can set the alarm for a time period when digestion is progressing. This makes it possible to analyze the user's eating and exercise patterns and set the alarm time accordingly.

[0038] The chat history analysis unit can extract the user's work deadlines or important tasks from the chat history and set an alarm time based on this. The chat history analysis unit, for example, analyzes the chat history and extracts the user's work deadlines and important tasks. For example, it detects content such as "submit by tomorrow morning" in the chat history and sets an alarm. The chat history analysis unit can also work with the user's task management tool to identify important tasks. For example, it analyzes data from the task management tool and adjusts the alarm time. The chat history analysis unit can also set an alarm time based on the user's work deadlines. For example, if the deadline is approaching, it sets an alarm earlier. This makes it possible to extract work deadlines and important tasks from the chat history and set an alarm time based on this.

[0039] The chat history analysis unit can analyze keywords that frequently appear in the chat history, identify the user's interests or priorities, and adjust the alarm time accordingly. The chat history analysis unit, for example, analyzes the chat history and extracts frequently appearing keywords. For example, an alarm can be set based on keywords such as "project" or "meeting." The chat history analysis unit can also use text mining technology to identify the user's interests and priorities. For example, it can perform frequency analysis and extract important keywords. The chat history analysis unit can also adjust the alarm time based on the user's interests and priorities. For example, if there is an important meeting, the alarm can be set earlier. In this way, the chat history analysis unit can analyze keywords that frequently appear in the chat history, identify the user's interests and priorities, and adjust the alarm time accordingly.

[0040] The chat history analysis unit can analyze the chat history to identify the user's social activity pattern and set an alarm time accordingly. The chat history analysis unit, for example, analyzes the chat history to identify the user's social activity pattern. For example, it analyzes the frequency of conversations with friends in the chat history to identify the social activity pattern. The chat history analysis unit can also analyze the user's participation in social events. For example, it can detect content such as "party this weekend" in the chat history and adjust the alarm time. The chat history analysis unit can also set an alarm time based on the user's social activity pattern. For example, it can set an alarm for a time period when the user frequently meets with friends. In this way, it is possible to analyze the chat history to identify the user's social activity pattern and set an alarm time accordingly.

[0041] The chat history analysis unit can integrate chat history with other communication means and adjust the alarm time based on comprehensive schedule management. The chat history analysis unit, for example, integrates chat history with email data to comprehensively manage the user's schedule. For example, it can set an alarm based on the content of an important email. The chat history analysis unit can also integrate SNS data and analyze the user's schedule. For example, it can analyze the content of posts on SNS and adjust the alarm time. The chat history analysis unit can also set the alarm time based on the user's comprehensive schedule management. For example, it can work with a calendar app or a task management tool to adjust the alarm time. This allows the chat history to be integrated with other communication means and the alarm time to be adjusted based on comprehensive schedule management.

[0042] The weather information analysis unit can evaluate the safety of the user's commuting route based on weather information and set an alarm for a safe time period. The weather information analysis unit can evaluate the safety of the user's commuting route based on weather data, for example. For example, if heavy rain or snow is forecast, the alarm can be set earlier. The weather information analysis unit can also evaluate the risk of the user's commuting route based on weather information. For example, the weather information analysis unit can analyze road conditions and traffic accident rates and set an alarm for a safe time period. The weather information analysis unit can also adjust the alarm time based on the safety of the user's commuting route. For example, if the weather is bad, the alarm can be set earlier. This allows the safety of the commuting route to be evaluated based on weather information and the alarm to be set for a safe time period.

[0043] The weather information analysis unit can adjust the alarm time based on weather information, taking into account the time it takes for the user to prepare their clothes and belongings. The weather information analysis unit, for example, analyzes the time it takes for the user to prepare their clothes and belongings based on weather data. For example, on a rainy day, it sets an alarm taking into account the time it takes to prepare an umbrella or raincoat. The weather information analysis unit can also adjust the time it takes for the user to prepare their clothes and belongings based on weather information. For example, on a cold day, it sets an alarm taking into account the time it takes to prepare cold weather gear. The weather information analysis unit can also set the alarm time based on the user's preparation time. For example, if it takes a long time to get ready, it sets the alarm earlier. In this way, the alarm time can be adjusted based on weather information, taking into account the time it takes for the user to prepare their clothes and belongings.

[0044] The weather information analysis unit can integrate weather information with other environmental data and adjust the alarm time based on a comprehensive environmental assessment. The weather information analysis unit, for example, integrates weather data and air quality data to set an alarm time that takes into account the user's health condition. For example, the alarm can be set for a time period when the air quality is good. The weather information analysis unit can also integrate weather data and a UV index to evaluate the user's health condition. For example, the alarm can be set for a time period when the UV index is low. The weather information analysis unit can also adjust the alarm time based on a comprehensive environmental assessment. For example, the weather, air quality, and UV index can be evaluated comprehensively to set an optimal alarm time. This allows the weather information to be integrated with other environmental data and the alarm time to be adjusted based on a comprehensive environmental assessment.

[0045] The traffic information analysis unit can analyze the congestion level of the user's commute route in real time based on traffic information and set an optimal departure time. The traffic information analysis unit can, for example, analyze the congestion level of the user's commute route in real time based on traffic data. For example, it can set an alarm for a less congested time period. The traffic information analysis unit can also predict the congestion level of the user's commute route based on traffic information. For example, it can predict peak congestion times based on past data and adjust the alarm time. The traffic information analysis unit can also set the alarm time based on the congestion level of the user's commute route. For example, it can set an alarm to depart during a less congested time period. This allows the congestion level of the commute route to be analyzed in real time based on traffic information and an optimal departure time to be set.

[0046] The traffic information analysis unit can optimize the user's means of commuting based on traffic information and set an alarm time accordingly. The traffic information analysis unit can optimize the user's means of commuting based on, for example, traffic data. For example, it can set an alarm taking into account delay information for public transportation. The traffic information analysis unit can also suggest the user's means of commuting based on traffic information. For example, if traffic congestion is predicted, it can suggest an alternative route and set the alarm time. The traffic information analysis unit can also set the alarm time based on the user's means of commuting. For example, it can select car, bicycle, or public transportation and set the optimal alarm time. This makes it possible to optimize the user's means of commuting based on traffic information and set the alarm time accordingly.

[0047] The traffic information analysis unit can propose an alternative route for the user's commute based on traffic information and set an alarm time accordingly. The traffic information analysis unit, for example, proposes an alternative route for the user's commute based on traffic data. For example, if traffic congestion is expected, it proposes an alternative route and sets an alarm. The traffic information analysis unit can also propose an optimal route for the user's commute based on traffic information. For example, it selects an optimal route depending on traffic conditions and sets an alarm time. The traffic information analysis unit can also set an alarm time based on the user's commute route. For example, it proposes an alternative route and sets an optimal alarm time. In this way, an alternative route for the user's commute based on traffic information can be proposed and an alarm time can be set accordingly.

[0048] The traffic information analysis unit can integrate traffic information with other movement data and adjust the alarm time based on a healthy commuting method. The traffic information analysis unit, for example, integrates traffic data and walking distance data and sets an alarm time taking into account the user's health condition. For example, the alarm is set for a time period when walking distance is long. The traffic information analysis unit can also integrate traffic data and calorie consumption data to evaluate the user's health condition. For example, the alarm is set for a time period when calorie consumption is long. The traffic information analysis unit can also adjust the alarm time based on a healthy commuting method. For example, the optimal alarm time is set taking into account walking distance and calorie consumption. In this way, traffic information can be integrated with other movement data and the alarm time can be adjusted based on a healthy commuting method.

[0049] When setting an alarm, the alarm setting unit can analyze the user's past alarm history and identify the most effective alarm pattern. The alarm setting unit, for example, analyzes the past alarm history and identifies the time period when the user woke up most effectively. For example, it sets the optimal alarm time based on past data. The alarm setting unit can also identify an alarm pattern based on the user's alarm history. For example, it analyzes the type of alarm sound and the timing of the alarm and sets the optimal alarm pattern. The alarm setting unit can also learn the user's alarm history and set an individually optimized alarm time. In this way, when setting an alarm, the user's past alarm history can be analyzed and the most effective alarm pattern can be identified.

[0050] The alarm setting unit can customize the alarm sound or alarm message according to the user's preferences, providing an environment that is easy to wake up in. The alarm setting unit, for example, customizes the alarm sound according to the user's preferences. For example, it sets favorite music or nature sounds as the alarm sound. The alarm setting unit can also customize the alarm message according to the user's preferences. For example, it sets a text message or a voice message. The alarm setting unit can also adjust the alarm environment based on the user's preferences. For example, it adjusts the volume or playback time of the alarm sound. In this way, the alarm sound or alarm message can be customized according to the user's preferences, providing an environment that is easy to wake up in.

[0051] The alarm setting unit can adjust the alarm setting in conjunction with the schedules of the user's family or housemates so that everyone wakes up efficiently. The alarm setting unit, for example, analyzes the schedules of the user's family or housemates and sets an alarm time that will wake everyone up efficiently. For example, the alarm setting unit adjusts the alarm taking into account the schedules of all family members. The alarm setting unit can also set the alarm time based on the schedules of family members or housemates. For example, if all family members need to wake up at the same time, a common alarm time is set. The alarm setting unit can also monitor the schedules of family members or housemates in real time and adjust the alarm time. For example, if the family members' schedule changes, the alarm time is reset. In this way, the alarm setting can be adjusted in conjunction with the schedules of the user's family members and housemates so that everyone wakes up efficiently.

[0052] The alarm setting unit can link the alarm setting with the user's smart home device and adjust the lighting or temperature to provide a comfortable awakening. The alarm setting unit, for example, links with the smart home device and adjusts the lighting to match the alarm time. For example, it can set the lighting to gradually brighten. The alarm setting unit can also link with the smart home device and adjust the temperature. For example, it can adjust the room temperature to match the alarm time to provide a comfortable awakening. The alarm setting unit can also link with the user's smart home device and adjust the alarm environment. For example, it can control the air conditioner or heater to set an optimal room temperature. In this way, the alarm setting can link with the user's smart home device and adjust the lighting or temperature to provide a comfortable awakening.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The alarm setting system may further include an exercise information collection unit that collects and analyzes the user's exercise data. The exercise information collection unit records the user's exercise amount and type using, for example, a smartwatch or fitness tracker. For example, it may analyze the running or walking distance, calories burned, and exercise frequency to identify the user's exercise pattern. The exercise information collection unit may also adjust the alarm time based on the user's exercise data. For example, it may set an alarm taking into account recovery time after exercise. This allows the user's exercise data to be analyzed and the optimal alarm time to be set.

[0055] The alarm setting system may further include a meal information collection unit that collects and analyzes the user's meal data. The meal information collection unit, for example, uses an application that allows the user to record meals to record the contents of meals and calorie intake. For example, it analyzes the times and contents of breakfast, lunch, and dinner to identify the user's eating patterns. The meal information collection unit may also adjust the alarm time based on the user's meal data. For example, it may set the alarm for a time period when digestion is progressing. This allows the user's meal data to be analyzed and the optimal alarm time to be set.

[0056] The alarm setting system may further include a health information collection unit that collects and analyzes the user's health data. The health information collection unit may use, for example, a smartwatch or fitness tracker to record the user's health data, such as heart rate, blood pressure, and body temperature. For example, the health information collection unit may analyze heart rate and blood pressure fluctuations to identify the user's health condition. The health information collection unit may also adjust the alarm time based on the user's health data. For example, the alarm may be set for a time period when the user is in good health. This allows the user's health data to be analyzed and the optimal alarm time to be set.

[0057] The alarm setting system may further include a social information collection unit that analyzes the user's social activity patterns. The social information collection unit may, for example, analyze the user's chat history or social media posts to identify the user's social activity patterns. For example, it may analyze the frequency of conversations with friends or the participation status of social events. The social information collection unit may also adjust the alarm time based on the user's social activity patterns. For example, it may set the alarm for a time period when the user frequently meets with friends. This allows the user's social activity patterns to be analyzed and the optimal alarm time to be set.

[0058] The alarm setting system may further include a family information collection unit that analyzes the schedules of the user's family members and housemates. The family information collection unit may, for example, analyze calendar information of family members and housemates to set an alarm time that will wake everyone up efficiently. For example, the alarm may be adjusted taking into account the schedules of all family members. The family information collection unit may also set an alarm time based on the schedules of family members and housemates. For example, if all family members need to wake up at the same time, a common alarm time may be set. This allows the schedules of family members and housemates to be analyzed and the optimal alarm time to be set.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The sleep information collection unit collects the user's sleep information. For example, it uses sensors in a smartwatch or smartphone to monitor the user's sleep patterns and quality. The sleep information collection unit can also record the user's sleep time and store it in a database. For example, a smartwatch can detect the user's heart rate and movements to evaluate the depth of sleep. Step 2: The generation AI analyzes the sleep information collected by the sleep information collection unit. For example, the generation AI may use a text generation AI (e.g., LLM) to analyze the sleep data and identify the optimal alarm time. The generation AI may also use a multimodal generation AI to integrate and analyze multiple data sources. For example, the generation AI may compare the user's sleep patterns with past data and calculate the optimal wake-up timing. Step 3: The alarm setting unit sets the alarm time based on the sleep information analyzed by the generation AI. For example, the alarm setting unit sets the alarm to match the user's sleep cycle. The alarm setting unit can also adjust the alarm time according to the user's schedule. For example, the alarm setting unit sets the alarm earlier than usual if the user needs to wake up early. Step 4: The notification unit notifies the user of the alarm time set by the alarm setting unit. For example, the notification unit displays the alarm using the notification function of the smartphone. The notification unit can also notify the user using an audio alarm. For example, the notification unit plays music or an audio message set by the user.

[0061] (Example 2) The alarm setting system according to the embodiment of the present invention automatically sets an alarm based on a user's sleep information and chat history, taking into account weather and traffic information, thereby preventing the user from oversleeping or being late.

[0062] An alarm setting system according to an embodiment includes a sleep information collection unit, a generation AI, an alarm setting unit, and a notification unit. The sleep information collection unit collects sleep information about a user. For example, the sleep information collection unit monitors the user's sleep patterns and sleep quality using sensors in a smartwatch or smartphone. The sleep information collection unit can also record the user's sleep time and store it in a database. For example, the smartwatch can detect the user's heart rate and movements to evaluate the depth of sleep. The generation AI analyzes the sleep information collected by the sleep information collection unit. For example, the generation AI can analyze the sleep data and identify an optimal alarm time using a text generation AI (e.g., LLM). The generation AI can also integrate and analyze multiple data sources using a multimodal generation AI. For example, the generation AI can compare the user's sleep pattern with past data and calculate the optimal wake-up timing. The alarm setting unit sets the alarm time based on the sleep information analyzed by the generation AI. For example, the alarm setting unit sets the alarm to match the user's sleep cycle. The alarm setting unit can also adjust the alarm time according to the user's schedule. For example, the alarm setting unit sets an alarm earlier than usual when the user needs to wake up early. The notification unit notifies the user of the alarm time set by the alarm setting unit. For example, the notification unit displays the alarm using a notification function of the smartphone. The notification unit can also notify the user using an audio alarm. For example, the notification unit plays music or an audio message set by the user. In this way, the alarm setting system according to the embodiment can set an optimal alarm time based on the user's sleep information, preventing the user from oversleeping or being late.

[0063] The sleep information collection unit can monitor the user's sleep patterns and sleep quality using sensors in the smartwatch or smartphone. For example, the sleep information collection unit can monitor the user's heart rate and breathing patterns using sensors in the smartwatch or smartphone to analyze the sleep patterns and sleep quality. For example, the smartwatch can detect fluctuations in the user's heart rate to evaluate the depth of sleep. The sleep information collection unit can also detect the user's movements and analyze the frequency of movements during sleep. For example, the smartphone's acceleration sensor can be used to record the user's movements and evaluate the quality of sleep. The sleep information collection unit can also record the user's sleep time and store the data in a database. For example, the smartwatch can automatically record the user's bedtime and wake-up time and store the sleep data. This allows the user's sleep patterns and sleep quality to be monitored in detail.

[0064] The generation AI can analyze a user's chat history and identify the next day's schedule or important events. For example, the generation AI can analyze the content of the chat history and extract keywords related to the schedule or events using a text generation AI (e.g., LLM). The generation AI can also use a multimodal generation AI to integrate and analyze the chat history and calendar information. For example, the generation AI can detect content such as "I have a meeting tomorrow" in the chat history and compare it with the calendar information to identify the schedule. The generation AI can also identify important events from the user's chat history and adjust the alarm time. For example, if the user says, "I have to get up early tomorrow," the generation AI can set the alarm earlier. This makes it possible to identify the next day's schedule or important events from the user's chat history.

[0065] The generation AI can collect and analyze weather information. For example, the generation AI collects and analyzes weather information. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze weather data and predict the weather for the next day. The generation AI can also use a multimodal generation AI to integrate and analyze weather data and traffic information. For example, the generation AI can predict traffic congestion based on weather data and adjust the alarm time. The generation AI can also evaluate the safety of a user's commute route based on weather information. For example, the generation AI can set an earlier alarm if heavy rain or snow is forecast. In this way, the alarm time can be adjusted by collecting and analyzing weather information.

[0066] The generation AI can collect and analyze traffic information. For example, the generation AI collects and analyzes traffic information. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze traffic data and predict the congestion level of commute routes. The generation AI can also use a multimodal generation AI to integrate and analyze traffic data and weather information. For example, the generation AI analyzes public transportation delay information based on traffic data and adjusts the alarm time. The generation AI can also optimize the user's commute based on traffic information. For example, if traffic congestion is predicted, the generation AI proposes an alternative route and sets the alarm time. In this way, the alarm time can be adjusted by collecting and analyzing traffic information.

[0067] The generation AI can comprehensively analyze sleep information, chat history, weather information, and traffic information to automatically set the optimal alarm time. For example, the generation AI can comprehensively analyze sleep information, chat history, weather information, and traffic information to automatically set the optimal alarm time. For example, the generation AI can use text generation AI (e.g., LLM) to integrate and analyze multiple data sources. The generation AI can also use multimodal generation AI to analyze data correlations and identify the optimal alarm time. For example, the generation AI can calculate the optimal wake-up timing based on the user's sleep patterns, next day's schedule, weather information, and traffic information. The generation AI can also learn the user's past data and set an individually optimized alarm time. This allows for comprehensive analysis of multiple pieces of information to automatically set the optimal alarm time.

[0068] The sleep information collection unit can monitor the user's heart rate or breathing pattern and estimate the stress level. The sleep information collection unit can monitor the user's heart rate and breathing pattern using, for example, a sensor in a smartwatch or smartphone, and estimate the stress level. For example, the sleep information collection unit can analyze heart rate fluctuations to evaluate the stress level. The sleep information collection unit can also analyze breathing patterns to estimate the stress level. For example, the sleep information collection unit can analyze the rhythm and depth of breathing to detect signs of stress. The sleep information collection unit can also adjust the alarm time based on the user's stress level. For example, if the user is highly stressed, the alarm can be set to a time when the user is able to relax. In this way, the user's heart rate and breathing pattern can be monitored and the stress level can be estimated.

[0069] The sleep information collection unit can analyze environmental sounds during sleep and identify the optimal timing to wake up. The sleep information collection unit, for example, uses a microphone on a smartphone to record environmental sounds during sleep and analyze the noise level. For example, it sets an alarm for a time period with little noise. The sleep information collection unit can also detect specific sounds and identify the optimal timing to wake up. For example, it sets an alarm for a time period with continuous silence. The sleep information collection unit can also analyze the type of environmental sound and adjust the timing to wake up. For example, it sets an alarm for a time period with a lot of natural sounds. In this way, it is possible to analyze environmental sounds during sleep and identify the optimal timing to wake up.

[0070] The sleep information collection unit can use the emotion estimation function to estimate the content of the user's dreams during sleep and set the timing to wake up from a positive dream. The sleep information collection unit, for example, uses the emotion estimation function to estimate the content of the user's dreams during sleep. For example, it analyzes electroencephalogram data during sleep to estimate the content of the dream. The sleep information collection unit can also set an alarm when a positive electroencephalogram pattern is detected. For example, it can identify the timing to wake up from a positive dream. The sleep information collection unit can also adjust the alarm time based on the content of the user's dream. For example, it can set an alarm for a time period during which positive dreams continue. This makes it possible to estimate the content of the user's dreams during sleep and set the timing to wake up from a positive dream.

[0071] The sleep information collection unit can analyze the user's eating or exercise patterns based on the sleep information and set an alarm time accordingly. The sleep information collection unit, for example, analyzes the user's eating and exercise patterns based on the sleep information. For example, it integrates sleep data and dietary data to analyze the user's digestive state. The sleep information collection unit can also analyze exercise data to identify the user's exercise pattern. For example, it analyzes the type and amount of exercise and adjusts the alarm time. The sleep information collection unit can also set the alarm time based on the user's eating and exercise patterns. For example, it can set the alarm for a time period when digestion is progressing. This makes it possible to analyze the user's eating and exercise patterns and set the alarm time accordingly.

[0072] The sleep information collection unit can use the emotion estimation function to analyze the user's emotional state before sleep and set an alarm time to wake up in a relaxed state. The sleep information collection unit, for example, uses the emotion estimation function to analyze the user's emotional state before sleep. For example, it analyzes the chat history before sleep and estimates the user's emotional state. The sleep information collection unit can also set an alarm time based on the user's emotional state. For example, it can set an alarm when a relaxed emotion is detected. The sleep information collection unit can also monitor the user's emotional state in real time and adjust the alarm time. For example, it can use the emotion estimation function to analyze the user's emotional state and identify the optimal timing to wake up. This makes it possible to analyze the user's emotional state before sleep and set an alarm time to wake up in a relaxed state.

[0073] The chat history analysis unit can extract the user's work deadlines or important tasks from the chat history and set an alarm time based on this. The chat history analysis unit, for example, analyzes the chat history and extracts the user's work deadlines and important tasks. For example, it detects content such as "submit by tomorrow morning" in the chat history and sets an alarm. The chat history analysis unit can also work with the user's task management tool to identify important tasks. For example, it analyzes data from the task management tool and adjusts the alarm time. The chat history analysis unit can also set an alarm time based on the user's work deadlines. For example, if the deadline is approaching, it sets an alarm earlier. This makes it possible to extract work deadlines and important tasks from the chat history and set an alarm time based on this.

[0074] The chat history analysis unit can analyze keywords that frequently appear in the chat history, identify the user's interests or priorities, and adjust the alarm time accordingly. The chat history analysis unit, for example, analyzes the chat history and extracts frequently appearing keywords. For example, an alarm can be set based on keywords such as "project" or "meeting." The chat history analysis unit can also use text mining technology to identify the user's interests and priorities. For example, it can perform frequency analysis and extract important keywords. The chat history analysis unit can also adjust the alarm time based on the user's interests and priorities. For example, if there is an important meeting, the alarm can be set earlier. In this way, the chat history analysis unit can analyze keywords that frequently appear in the chat history, identify the user's interests and priorities, and adjust the alarm time accordingly.

[0075] The chat history analysis unit can use the emotion estimation function to analyze the user's emotional fluctuations from the chat history and set an alarm time that will wake the user up at a time when the user will be less stressed. The chat history analysis unit, for example, uses the emotion estimation function to analyze the user's emotional fluctuations from the chat history. For example, it analyzes the content of the chat history and estimates the emotional fluctuations. The chat history analysis unit can also set an alarm time based on the user's emotional fluctuations. For example, it can set an alarm for a time period when the user is feeling a lot of positive emotions. The chat history analysis unit can also monitor the user's emotional state in real time and adjust the alarm time. For example, it can use the emotion estimation function to analyze the user's emotional state and set an alarm time that will wake the user up at a time when the user will be less stressed. In this way, it is possible to analyze the user's emotional fluctuations from the chat history and set an alarm time that will wake the user up at a time when the user will be less stressed.

[0076] The chat history analysis unit can analyze the chat history to identify the user's social activity pattern and set an alarm time accordingly. The chat history analysis unit, for example, analyzes the chat history to identify the user's social activity pattern. For example, it analyzes the frequency of conversations with friends in the chat history to identify the social activity pattern. The chat history analysis unit can also analyze the user's participation in social events. For example, it can detect content such as "party this weekend" in the chat history and adjust the alarm time. The chat history analysis unit can also set an alarm time based on the user's social activity pattern. For example, it can set an alarm for a time period when the user frequently meets with friends. In this way, it is possible to analyze the chat history to identify the user's social activity pattern and set an alarm time accordingly.

[0077] The chat history analysis unit can integrate chat history with other communication means and adjust the alarm time based on comprehensive schedule management. The chat history analysis unit, for example, integrates chat history with email data to comprehensively manage the user's schedule. For example, it can set an alarm based on the content of an important email. The chat history analysis unit can also integrate SNS data and analyze the user's schedule. For example, it can analyze the content of posts on SNS and adjust the alarm time. The chat history analysis unit can also set the alarm time based on the user's comprehensive schedule management. For example, it can work with a calendar app or a task management tool to adjust the alarm time. This allows the chat history to be integrated with other communication means and the alarm time to be adjusted based on comprehensive schedule management.

[0078] The chat history analysis unit can use the emotion estimation function to identify content that elicits positive emotions from the user from the chat history and set the alarm time based on this. The chat history analysis unit, for example, uses the emotion estimation function to identify content that elicits positive emotions from the user from the chat history. For example, it analyzes the content of the chat history and extracts keywords that elicit positive emotions. The chat history analysis unit can also set the alarm time based on the user's positive emotions. For example, it can set the alarm for a time period when there are many pleasant conversations. The chat history analysis unit can also monitor the user's emotional state in real time and adjust the alarm time. For example, it can use the emotion estimation function to analyze the user's emotional state and set the alarm at a time that elicits positive emotions. This allows the content that elicits positive emotions from the user to be identified from the chat history and the alarm time to be set based on this.

[0079] The weather information analysis unit can evaluate the safety of the user's commuting route based on weather information and set an alarm for a safe time period. The weather information analysis unit can evaluate the safety of the user's commuting route based on weather data, for example. For example, if heavy rain or snow is forecast, the alarm can be set earlier. The weather information analysis unit can also evaluate the risk of the user's commuting route based on weather information. For example, the weather information analysis unit can analyze road conditions and traffic accident rates and set an alarm for a safe time period. The weather information analysis unit can also adjust the alarm time based on the safety of the user's commuting route. For example, if the weather is bad, the alarm can be set earlier. This allows the safety of the commuting route to be evaluated based on weather information and the alarm to be set for a safe time period.

[0080] The weather information analysis unit can adjust the alarm time based on weather information, taking into account the time it takes for the user to prepare their clothes and belongings. The weather information analysis unit, for example, analyzes the time it takes for the user to prepare their clothes and belongings based on weather data. For example, on a rainy day, it sets an alarm taking into account the time it takes to prepare an umbrella or raincoat. The weather information analysis unit can also adjust the time it takes for the user to prepare their clothes and belongings based on weather information. For example, on a cold day, it sets an alarm taking into account the time it takes to prepare cold weather gear. The weather information analysis unit can also set the alarm time based on the user's preparation time. For example, if it takes a long time to get ready, it sets the alarm earlier. In this way, the alarm time can be adjusted based on weather information, taking into account the time it takes for the user to prepare their clothes and belongings.

[0081] The weather information analysis unit uses the emotion estimation function to analyze the impact of weather on the user's emotions and can set an alarm at a timing that will elicit positive emotions. The weather information analysis unit, for example, uses the emotion estimation function to analyze the impact of weather on the user's emotions. For example, it analyzes the user's emotional state based on weather data. The weather information analysis unit can also set an alarm time based on the user's emotional state. For example, on a sunny day, it can set an alarm for a time period when positive emotions are strong. The weather information analysis unit can also monitor the user's emotional state in real time and adjust the alarm time. For example, it uses the emotion estimation function to analyze the user's emotional state and set an alarm at a timing that will elicit positive emotions. In this way, it is possible to analyze the impact of weather on the user's emotions and set an alarm at a timing that will elicit positive emotions.

[0082] The weather information analysis unit can integrate weather information with other environmental data and adjust the alarm time based on a comprehensive environmental assessment. The weather information analysis unit, for example, integrates weather data and air quality data to set an alarm time that takes into account the user's health condition. For example, the alarm can be set for a time period when the air quality is good. The weather information analysis unit can also integrate weather data and a UV index to evaluate the user's health condition. For example, the alarm can be set for a time period when the UV index is low. The weather information analysis unit can also adjust the alarm time based on a comprehensive environmental assessment. For example, the weather, air quality, and UV index can be evaluated comprehensively to set an optimal alarm time. This allows the weather information to be integrated with other environmental data and the alarm time to be adjusted based on a comprehensive environmental assessment.

[0083] The weather information analysis unit can use the emotion estimation function to predict the user's mood from weather information and set an alarm time that will wake them up at a time when they are in a good mood. The weather information analysis unit can, for example, use the emotion estimation function to predict the user's mood from weather information. For example, it can analyze the user's mood based on weather data. The weather information analysis unit can also set an alarm time based on the user's mood. For example, on a sunny day, it can set an alarm for a time period when positive moods are strongest. The weather information analysis unit can also monitor the user's mood in real time and adjust the alarm time. For example, it can use the emotion estimation function to analyze the user's mood and set an alarm at a time when the user is in a good mood. This makes it possible to predict the user's mood from weather information and set an alarm time that will wake them up at a time when they are in a good mood.

[0084] The traffic information analysis unit can analyze the congestion level of the user's commute route in real time based on traffic information and set an optimal departure time. The traffic information analysis unit can, for example, analyze the congestion level of the user's commute route in real time based on traffic data. For example, it can set an alarm for a less congested time period. The traffic information analysis unit can also predict the congestion level of the user's commute route based on traffic information. For example, it can predict peak congestion times based on past data and adjust the alarm time. The traffic information analysis unit can also set the alarm time based on the congestion level of the user's commute route. For example, it can set an alarm to depart during a less congested time period. This allows the congestion level of the commute route to be analyzed in real time based on traffic information and an optimal departure time to be set.

[0085] The traffic information analysis unit can optimize the user's means of commuting based on traffic information and set an alarm time accordingly. The traffic information analysis unit can optimize the user's means of commuting based on, for example, traffic data. For example, it can set an alarm taking into account delay information for public transportation. The traffic information analysis unit can also suggest the user's means of commuting based on traffic information. For example, if traffic congestion is predicted, it can suggest an alternative route and set the alarm time. The traffic information analysis unit can also set the alarm time based on the user's means of commuting. For example, it can select car, bicycle, or public transportation and set the optimal alarm time. This makes it possible to optimize the user's means of commuting based on traffic information and set the alarm time accordingly.

[0086] The traffic information analysis unit uses the emotion estimation function to analyze the impact of traffic information on the user's stress level and can set an alarm time that will wake the user up at a time when stress is low. The traffic information analysis unit, for example, uses the emotion estimation function to analyze the impact of traffic information on the user's stress level. For example, it analyzes the user's stress level based on traffic data. The traffic information analysis unit can also set an alarm time based on the user's stress level. For example, it can set an alarm for a time period with less traffic congestion. The traffic information analysis unit can also monitor the user's stress level in real time and adjust the alarm time. For example, it can use the emotion estimation function to analyze the user's stress level and set an alarm at a time when stress is low. This makes it possible to analyze the impact of traffic information on the user's stress level and set an alarm time that will wake the user up at a time when stress is low.

[0087] The traffic information analysis unit can propose an alternative route for the user's commute based on traffic information and set an alarm time accordingly. The traffic information analysis unit, for example, proposes an alternative route for the user's commute based on traffic data. For example, if traffic congestion is expected, it proposes an alternative route and sets an alarm. The traffic information analysis unit can also propose an optimal route for the user's commute based on traffic information. For example, it selects an optimal route depending on traffic conditions and sets an alarm time. The traffic information analysis unit can also set an alarm time based on the user's commute route. For example, it proposes an alternative route and sets an optimal alarm time. In this way, an alternative route for the user's commute based on traffic information can be proposed and an alarm time can be set accordingly.

[0088] The traffic information analysis unit can integrate traffic information with other movement data and adjust the alarm time based on a healthy commuting method. The traffic information analysis unit, for example, integrates traffic data and walking distance data and sets an alarm time taking into account the user's health condition. For example, the alarm is set for a time period when walking distance is long. The traffic information analysis unit can also integrate traffic data and calorie consumption data to evaluate the user's health condition. For example, the alarm is set for a time period when calorie consumption is long. The traffic information analysis unit can also adjust the alarm time based on a healthy commuting method. For example, the optimal alarm time is set taking into account walking distance and calorie consumption. In this way, traffic information can be integrated with other movement data and the alarm time can be adjusted based on a healthy commuting method.

[0089] The traffic information analysis unit can use the emotion estimation function to identify a route that elicits positive emotions from the user from traffic information and set an alarm time based on this. The traffic information analysis unit, for example, uses the emotion estimation function to identify a route that elicits positive emotions from the user from traffic information. For example, the traffic information analysis unit analyzes routes that elicit positive emotions from the user based on traffic data. The traffic information analysis unit can also set an alarm time based on the user's positive emotions. For example, the traffic information analysis unit can suggest a route with a beautiful view and set an alarm. The traffic information analysis unit can also monitor the user's emotional state in real time and adjust the alarm time. For example, the emotion estimation function can be used to analyze the user's emotional state, identify a route that elicits positive emotions, and set an alarm. In this way, a route that elicits positive emotions from the user can be identified from traffic information and the alarm time can be set based on this.

[0090] When setting an alarm, the alarm setting unit can analyze the user's past alarm history and identify the most effective alarm pattern. The alarm setting unit, for example, analyzes the past alarm history and identifies the time period when the user woke up most effectively. For example, it sets the optimal alarm time based on past data. The alarm setting unit can also identify an alarm pattern based on the user's alarm history. For example, it analyzes the type of alarm sound and the timing of the alarm and sets the optimal alarm pattern. The alarm setting unit can also learn the user's alarm history and set an individually optimized alarm time. In this way, when setting an alarm, the user's past alarm history can be analyzed and the most effective alarm pattern can be identified.

[0091] The alarm setting unit can customize the alarm sound or alarm message according to the user's preferences, providing an environment that is easy to wake up in. The alarm setting unit, for example, customizes the alarm sound according to the user's preferences. For example, it sets favorite music or nature sounds as the alarm sound. The alarm setting unit can also customize the alarm message according to the user's preferences. For example, it sets a text message or a voice message. The alarm setting unit can also adjust the alarm environment based on the user's preferences. For example, it adjusts the volume or playback time of the alarm sound. In this way, the alarm sound or alarm message can be customized according to the user's preferences, providing an environment that is easy to wake up in.

[0092] The alarm setting unit can adjust the alarm setting in conjunction with the schedules of the user's family or housemates so that everyone wakes up efficiently. The alarm setting unit, for example, analyzes the schedules of the user's family or housemates and sets an alarm time that will wake everyone up efficiently. For example, the alarm setting unit adjusts the alarm taking into account the schedules of all family members. The alarm setting unit can also set the alarm time based on the schedules of family members or housemates. For example, if all family members need to wake up at the same time, a common alarm time is set. The alarm setting unit can also monitor the schedules of family members or housemates in real time and adjust the alarm time. For example, if the family members' schedule changes, the alarm time is reset. In this way, the alarm setting can be adjusted in conjunction with the schedules of the user's family members and housemates so that everyone wakes up efficiently.

[0093] The alarm setting unit can link the alarm setting with the user's smart home device and adjust the lighting or temperature to provide a comfortable awakening. The alarm setting unit, for example, links with the smart home device and adjusts the lighting to match the alarm time. For example, it can set the lighting to gradually brighten. The alarm setting unit can also link with the smart home device and adjust the temperature. For example, it can adjust the room temperature to match the alarm time to provide a comfortable awakening. The alarm setting unit can also link with the user's smart home device and adjust the alarm environment. For example, it can control the air conditioner or heater to set an optimal room temperature. In this way, the alarm setting can link with the user's smart home device and adjust the lighting or temperature to provide a comfortable awakening.

[0094] The alarm setting unit can use the emotion estimation function to fine-tune the timing of the alarm based on the user's emotional state, thereby achieving an optimal awakening. The alarm setting unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and fine-tune the optimal alarm time. For example, if a relaxed emotion is detected, the alarm is slightly delayed. The alarm setting unit can also adjust the timing of the alarm based on the user's emotional state. For example, if the user is highly stressed, the alarm is set for a time when the user can relax. The alarm setting unit can also monitor the user's emotional state and optimize the timing of the alarm. For example, the emotion estimation function can be used to analyze the user's emotional state and identify the optimal awakening timing. As a result, the emotion estimation function can be used to fine-tune the timing of the alarm based on the user's emotional state, thereby achieving an optimal awakening.

[0095] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0096] The alarm setting system may further include an exercise information collection unit that collects and analyzes the user's exercise data. The exercise information collection unit records the user's exercise amount and type using, for example, a smartwatch or fitness tracker. For example, it may analyze the running or walking distance, calories burned, and exercise frequency to identify the user's exercise pattern. The exercise information collection unit may also adjust the alarm time based on the user's exercise data. For example, it may set an alarm taking into account recovery time after exercise. This allows the user's exercise data to be analyzed and the optimal alarm time to be set.

[0097] The alarm setting system may further include a meal information collection unit that collects and analyzes the user's meal data. The meal information collection unit, for example, uses an application that allows the user to record meals to record the contents of meals and calorie intake. For example, it analyzes the times and contents of breakfast, lunch, and dinner to identify the user's eating patterns. The meal information collection unit may also adjust the alarm time based on the user's meal data. For example, it may set the alarm for a time period when digestion is progressing. This allows the user's meal data to be analyzed and the optimal alarm time to be set.

[0098] The alarm setting system may further include a stress information collection unit that estimates and analyzes the user's stress level. The stress information collection unit may use, for example, sensors in a smartwatch or smartphone to monitor the user's heart rate and breathing pattern to estimate the stress level. For example, it may analyze heart rate fluctuations and breathing rhythm to detect signs of stress. The stress information collection unit may also adjust the alarm time based on the user's stress level. For example, if the user is highly stressed, the alarm may be set to a time when the user is able to relax. This allows the user's stress level to be analyzed and the optimal alarm time to be set.

[0099] The alarm setting system may further include an emotion information collection unit that estimates and analyzes the user's emotional state. The emotion information collection unit may, for example, analyze the user's chat history or social media posts to estimate the user's emotional state. For example, it may detect positive or negative emotions and identify the user's emotional pattern. The emotion information collection unit may also adjust the alarm time based on the user's emotional state. For example, it may set the alarm for a time period when positive emotions are most prevalent. This allows the user's emotional state to be analyzed and the optimal alarm time to be set.

[0100] The alarm setting system may further include a health information collection unit that collects and analyzes the user's health data. The health information collection unit may use, for example, a smartwatch or fitness tracker to record the user's health data, such as heart rate, blood pressure, and body temperature. For example, the health information collection unit may analyze heart rate and blood pressure fluctuations to identify the user's health condition. The health information collection unit may also adjust the alarm time based on the user's health data. For example, the alarm may be set for a time period when the user is in good health. This allows the user's health data to be analyzed and the optimal alarm time to be set.

[0101] The alarm setting system may further include a dream information collection unit that estimates and analyzes the content of the user's dreams during sleep. The dream information collection unit, for example, analyzes electroencephalogram data during sleep to estimate the content of the dreams. For example, it detects positive dreams and negative dreams and identifies the user's dream pattern. The dream information collection unit may also adjust the alarm time based on the content of the user's dreams. For example, it may set the alarm for a time period when positive dreams continue. This allows the content of the user's dreams to be analyzed and the optimal alarm time to be set.

[0102] The alarm setting system may further include a social information collection unit that analyzes the user's social activity patterns. The social information collection unit may, for example, analyze the user's chat history or social media posts to identify the user's social activity patterns. For example, it may analyze the frequency of conversations with friends or the participation status of social events. The social information collection unit may also adjust the alarm time based on the user's social activity patterns. For example, it may set the alarm for a time period when the user frequently meets with friends. This allows the user's social activity patterns to be analyzed and the optimal alarm time to be set.

[0103] The alarm setting system may further include an emotion estimation unit that estimates and analyzes the user's emotional state. The emotion estimation unit may, for example, analyze the user's chat history or social media posts to estimate the user's emotional state. For example, it may detect positive or negative emotions and identify the user's emotional pattern. The emotion estimation unit may also adjust the alarm time based on the user's emotional state. For example, it may set the alarm for a time period when positive emotions are most prevalent. This allows the user's emotional state to be analyzed and the optimal alarm time to be set.

[0104] The alarm setting system may further include a family information collection unit that analyzes the schedules of the user's family members and housemates. The family information collection unit may, for example, analyze calendar information of family members and housemates to set an alarm time that will wake everyone up efficiently. For example, the alarm may be adjusted taking into account the schedules of all family members. The family information collection unit may also set an alarm time based on the schedules of family members and housemates. For example, if all family members need to wake up at the same time, a common alarm time may be set. This allows the schedules of family members and housemates to be analyzed and the optimal alarm time to be set.

[0105] The alarm setting system may further include an emotion estimation unit that estimates and analyzes the user's emotional state. The emotion estimation unit may, for example, analyze the user's chat history or social media posts to estimate the user's emotional state. For example, it may detect positive or negative emotions and identify the user's emotional pattern. The emotion estimation unit may also adjust the alarm time based on the user's emotional state. For example, it may set the alarm for a time period when positive emotions are most prevalent. This allows the user's emotional state to be analyzed and the optimal alarm time to be set.

[0106] The processing flow of the second embodiment will be briefly explained below.

[0107] Step 1: The sleep information collection unit collects the user's sleep information. For example, it uses sensors in a smartwatch or smartphone to monitor the user's sleep patterns and quality. The sleep information collection unit can also record the user's sleep time and store it in a database. For example, a smartwatch can detect the user's heart rate and movements to evaluate the depth of sleep. Step 2: The generation AI analyzes the sleep information collected by the sleep information collection unit. For example, the generation AI may use a text generation AI (e.g., LLM) to analyze the sleep data and identify the optimal alarm time. The generation AI may also use a multimodal generation AI to integrate and analyze multiple data sources. For example, the generation AI may compare the user's sleep patterns with past data and calculate the optimal wake-up timing. Step 3: The alarm setting unit sets the alarm time based on the sleep information analyzed by the generation AI. For example, the alarm setting unit sets the alarm to match the user's sleep cycle. The alarm setting unit can also adjust the alarm time according to the user's schedule. For example, the alarm setting unit sets the alarm earlier than usual if the user needs to wake up early. Step 4: The notification unit notifies the user of the alarm time set by the alarm setting unit. For example, the notification unit displays the alarm using the notification function of the smartphone. The notification unit can also notify the user using an audio alarm. For example, the notification unit plays music or an audio message set by the user.

[0108] 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.

[0109] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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 a data format such as voice data and text data. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] 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.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0121] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0122] 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.

[0123] 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.

[0124] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] 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.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0136] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0137] 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.

[0138] 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.

[0139] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0152] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0153] 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.

[0154] 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.

[0155] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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."

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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. [Explanation of symbols]

[0175] 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 sleep information collecting unit that collects sleep information; a generation AI that analyzes the sleep information collected by the sleep information collection unit; an alarm setting unit that sets an alarm time based on the sleep information analyzed by the generating AI; a notification unit that notifies a user of the alarm time set by the alarm setting unit. A system characterized by:

2. The generated AI is Analyzing the user's chat history to identify upcoming events or important events 2. The system of claim 1.

3. The sleep information collecting unit Based on the sleep information, the user's eating or exercise patterns are analyzed, and the alarm time is set accordingly.

2. The system of claim 1.

4. The weather information analysis department Evaluate the safety of the user's commute route based on weather information and set an alarm during a safe time period.

2. The system of claim 1.

5. The traffic information analysis department Based on traffic information, the congestion level of the user's commute route is analyzed in real time, and the optimal departure time is set.

2. The system of claim 1.

6. The alarm setting unit Generate an alarm sound or message according to the user's emotional state, so that the user wakes up with positive emotions.

2. The system of claim 1.

7. The sleep information collecting unit The content of the dream of the user is estimated during sleep, and a timing for waking up from a positive dream is set.

2. The system of claim 1.

8. The weather information analysis department Analyze the effect of weather on the user's emotions and set an alarm at a time that elicits positive emotions.

2. The system of claim 1.

Images