System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a voice instruction from a user; means for converting the voice instruction into text data; means for analyzing the text data and setting an alarm based on a date and time and a condition; means for activating the alarm at the set date and time; and means for continuing the alarm until the user wakes up.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] Many users suffer from irregular lifestyles and lack of sleep, and a common problem is waking up in the morning, turning off the alarm and going back to sleep. This leads to issues such as not being able to wake up on schedule and disrupting a healthy lifestyle. Furthermore, conventional alarms only allow for simple time settings, making them unable to accommodate users' complex schedules. Another major problem is that users may not wake up even if the alarm continues to ring. [Means for solving the problem]

[0005] The present invention provides a means for receiving voice instructions from a user and converting the voice instructions into text data. It also provides a means for analyzing the converted text data and setting an alarm based on a date, time, and conditions. The set alarm also includes a means for activating the alarm at a specified date and time and continuing the alarm until the user wakes up. It also provides a means for receiving and analyzing feedback provided by the user, thereby optimizing future alarm settings. Furthermore, it provides a means for confirming the user's wakefulness in cooperation with a smartwatch or a motion sensor, with the aim of more effectively waking the user up. In this way, the system aims to improve the user's daily rhythm and promote a healthy lifestyle.

[0006] "Voice commands" refer to words or phrases spoken by a user that are input into an application or device to be recognized and perform some action.

[0007] "Text data" is voice instructions converted into character data, and is information in a digital format that can be used for analysis and processing.

[0008] "Analysis" is the process of logically understanding input text data and extracting and identifying specific conditions and commands.

[0009] "Date and time" means a specific date and time, and is time information for setting an alarm.

[0010] A "condition" refers to a particular factor or situation that must be taken into consideration when setting an alarm, and upon which behavior may be changed.

[0011] An "alarm" is a sound, vibration, or other form of signal intended to notify or alert a user at a specific time.

[0012] "Waking up" refers to the user waking up from sleep, and is the action that will cause the alarm to stop.

[0013] "Feedback" refers to the opinions and reactions that users provide regarding alarm settings and behavior, and is information that is used to improve the system.

[0014] A "smartwatch" is an electronic device worn on the user's body that has the ability to monitor heart rate and movement.

[0015] A "motion sensor" is a device that detects the movement or presence of a user and is used to check whether the user has woken up. [Brief explanation of the drawings]

[0016] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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, a 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), and an APU (Accelerated Processing Unit).

[0020] 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.

[0021] 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.

[0022] 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), Bluetooth (registered trademark), etc.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0028] 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.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system that improves a user's daily rhythm and assists in waking up efficiently. This system sets an alarm based on the user's voice instruction and continues to operate until the alarm wakes the user up. Furthermore, it has a function that uses a smartwatch or a motion sensor to confirm whether the user is actually awake, and optimizes the system through feedback. A specific embodiment of this system is shown below.

[0038] System Overview

[0039] 1. Accepting and converting voice commands

[0040] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6am tomorrow morning" or "Set the alarm for 7am every Monday morning, except for 8am on public holidays."

[0041] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[0042] 2. Text data analysis and alarm setting

[0043] (Terminal) The converted text data is sent to the server.

[0044] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and conditions.

[0045] For example, it can handle complex settings such as "set the alarm for 6:30 every Monday, and for 7:00 if the previous day is a holiday."

[0046] 3. Triggering and continuing alarms

[0047] (Device) When the set alarm time arrives, the device will activate the alarm, notifying the user with sound, vibration, or both.

[0048] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[0049] 4. Receiving and analyzing feedback

[0050] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm went off at the right time" or "The alarm was too loud" through the app.

[0051] (Server) The server receives this feedback and the generating AI analyzes it, which then optimizes future alarm settings.

[0052] Specific examples

[0053] Specific examples are given below.

[0054] Example 1:

[0055] (User) The user instructs, "Set it to wake me up at 7:00 tomorrow."

[0056] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[0057] (Server) The generation AI analyzes the text data and extracts the information "Set the alarm for 7am the next morning."

[0058] (Device) The alarm will start ringing at 7am the next morning. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[0059] Example 2:

[0060] (User) The user instructs "Wake me up at 6:00 every Monday." He also adds, "However, if it is a public holiday, wake me up at 7:00."

[0061] (Device) The voice recognition function converts voice into text data.

[0062] (Server) The generation AI analyzes the text data and processes the condition "Set the alarm at 6:00 every Monday, but set it to 7:00 on holidays."

[0063] (Device) The alarm is set for 6:00 AM on the following Monday. If a public holiday falls on the same day, the alarm will go off at 7:00 AM.

[0064] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] (User) The user issues a voice command to set the alarm, saying, "Set the alarm for 7:00 tomorrow morning."

[0068] Step 2:

[0069] (Device) The device's microphone captures the user's voice instructions, and the internal voice recognition engine converts the voice data into text data.

[0070] Step 3:

[0071] (Terminal) The terminal sends the converted text data to the server.

[0072] Step 4:

[0073] (Server) The server's generated AI receives the text data and analyzes it. During the analysis, it extracts the instruction content ("Set an alarm for 7am tomorrow") and clarifies the specific date and time and setting conditions.

[0074] Step 5:

[0075] (Server) The generation AI generates alarm setting information (date and time: tomorrow at 7:00, repetition: none, special conditions: none) based on the conditions.

[0076] Step 6:

[0077] (Server) Sends the generated alarm setting information to the terminal.

[0078] Step 7:

[0079] (Device) Based on the received alarm setting information, the device registers the alarm in its internal calendar app or alarm function.

[0080] Step 8:

[0081] (Device) When the set alarm time approaches, the device will activate the alarm.

[0082] Step 9:

[0083] (Device) The alarm will start ringing and notify the user with sound and vibration.

[0084] Step 10:

[0085] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[0086] Step 11:

[0087] (Smartwatch / Motion Sensor) If it determines that the user has woken up, it sends a signal to the device to stop the alarm.

[0088] Step 12:

[0089] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[0090] Step 13:

[0091] (User) After waking up, the user provides feedback on the effectiveness of the alarm through the app, such as "The alarm was just right" or "The alarm was too loud."

[0092] Step 14:

[0093] (Device) The device sends the user's feedback to the server.

[0094] Step 15:

[0095] (Server) The server receives the feedback, and the generating AI analyzes it. Based on the feedback, it optimizes future alarm settings.

[0096] Example 1

[0097] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0098] For many people living busy lives in modern society, maintaining a regular rhythm and waking up efficiently is important. However, existing alarm systems lack a means to accurately confirm the user's wake-up status, making it difficult to reliably wake them up. Furthermore, the flexibility of alarm settings is limited, making it difficult to meet individual user needs. Furthermore, there is no well-established mechanism for effectively utilizing feedback to optimize the system, making it difficult to provide optimal alarm settings for each individual user.

[0099] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0100] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for confirming the user's wakefulness in cooperation with a smartwatch or a motion sensor, and means for receiving feedback provided by the user and analyzing it using a generative AI model. This allows the system to set an appropriate alarm based on the user's individual needs, helping the user wake up reliably, and enabling system optimization based on the feedback.

[0101] "Means for receiving voice instructions from the user" refers to devices or software that receive voice instructions when a user gives voice instructions to the system in natural language to set alarms or perform other operations.

[0102] The "means for converting voice instructions into text data" refers to a device or software that recognizes received voice instructions and converts the content into text format, such as a voice recognition engine.

[0103] "Means for analyzing text data and setting alarms based on the date, time, and conditions" refers to a device or software that analyzes the converted text data and sets appropriate alarms based on the date, time, and conditions specified by the user.

[0104] "Means for activating an alarm at a set date and time" refers to a device or software that activates an alarm using sound, vibration, or other means at a set date and time.

[0105] "Means for keeping the alarm going until the user wakes up" refers to a device or software that keeps the alarm set so that it does not stop until the user actually wakes up.

[0106] "Means for verifying user alertness in conjunction with a smartwatch or motion sensor" refers to devices or software that use data from a smartwatch or motion sensor to verify the user's physical movement and alertness.

[0107] "Means for receiving and analyzing user-provided feedback using a generative AI model" refers to devices or software that receive user feedback, analyze it using a generative AI model, and optimize system performance or settings.

[0108] This invention is a system for improving a user's daily rhythm and helping them wake up efficiently. The system aims to allow the user to set an alarm by voice and operate until the alarm wakes the user up reliably. Furthermore, it has a function for optimizing the system through feedback.

[0109] System Overview

[0110] 1. Accepting voice commands

[0111] (User) The user gives instructions to the system in natural language to set an alarm, such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[0112] (Device) The device uses voice recognition software (e.g., Google Speech-to-Text API) to convert the user's voice into text data.

[0113] 2. Text Data Analysis

[0114] (Terminal) The converted text data is sent to the server.

[0115] (Server) The generative AI model (e.g., OpenAI GPT-4) deployed on the server analyzes the text data sent and sets alarms based on the user's instructions. This analysis extracts the date, time, and conditions.

[0116] 3. Alarm settings and operation

[0117] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[0118] (Device) The device will activate the alarm with sound or vibration when the set alarm time arrives.

[0119] (Smartwatch / Motion Sensor) In addition, a smartwatch (e.g., Apple Watch) or a motion sensor can be used to monitor the user's waking state and the alarm will continue until the user wakes up.

[0120] 4. Receiving and analyzing feedback

[0121] (User) After the alarm is stopped, the user provides feedback through the smartphone app, such as "The alarm was appropriate" or "The alarm was too loud."

[0122] (Server) The server receives user feedback and the generative AI model analyzes it, allowing for future optimization of alarm settings.

[0123] Specific examples

[0124] A specific example will be given below.

[0125] Example 1:

[0126] (User) The user instructs, "Wake me up at 7 o'clock tomorrow."

[0127] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[0128] (Server) The generating AI analyzes and extracts the information "Set the alarm for 7am the next morning."

[0129] (Device) The alarm will start ringing at 7:00 the next morning. When the user wakes up, the smartwatch detects their movement and sends a signal to the device to stop the alarm, which stops the alarm.

[0130] Example 2:

[0131] (User) The user instructs, "Wake me up at 6:00 every Monday, except on public holidays, at 7:00."

[0132] (Device) The voice recognition function converts voice into text data.

[0133] (Server) The generation AI analyzes and extracts the condition "Set the alarm for 6:00 every Monday, but for holidays, set it for 7:00."

[0134] (Device) The alarm will ring at 6:00 a.m. the following Monday, or 7:00 a.m. if a public holiday falls on the same day.

[0135] As described above, the system of the present invention efficiently supports the user's life rhythm and promotes a healthy lifestyle.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1:

[0138] (User) The user issues a voice command to the system, such as "Wake me up at 6am tomorrow morning."

[0139] Input: User's voice command

[0140] Output: Audio data received by the device's microphone

[0141] Specific operation: When the user speaks into the device's microphone, the device picks up the audio.

[0142] Step 2:

[0143] (Device) The device converts the voice into text data using voice recognition software (e.g., Google Speech-to-Text API).

[0144] Input: Audio data

[0145] Output: Text data

[0146] What happens: The speech recognition engine analyzes the audio data and converts it into a corresponding text representation.

[0147] Step 3:

[0148] (Terminal) The terminal sends the converted text data to the server.

[0149] Input: Text data

[0150] Output: Text data sent to the server

[0151] What happens: Text data is sent to a server over an internet connection.

[0152] Step 4:

[0153] (Server) The server analyzes the text data using a generative AI model (e.g., OpenAI GPT-4) to extract date, time, and alarm setting information.

[0154] Input: Text data

[0155] Output: Analyzed alarm setting information (date and time and conditions)

[0156] Specific operation: The generative AI model analyzes the text data and extracts the date, time, and conditions specified by the user.

[0157] Step 5:

[0158] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[0159] Input: Parsed alarm setting information

[0160] Output: A data packet containing configuration information

[0161] Specific operation: The server generates a data packet containing instructions for setting an alarm and sends it to the device.

[0162] Step 6:

[0163] (Device) When the set time arrives, the device will activate an alarm.

[0164] Input: Set alarm information

[0165] Output: Alarm activation (sound, vibration, etc.)

[0166] Specific action: The device will emit an alarm or vibrate at the specified date and time.

[0167] Step 7:

[0168] (Smartwatch / motion sensor) A smartwatch or motion sensor checks whether the user is awake.

[0169] Input: User movement and environmental data

[0170] Output: Awakening confirmation data

[0171] What it does: The smartwatch monitors your movements and notifies your device when movement is detected.

[0172] Step 8:

[0173] (Device) When the user is confirmed awake, the alarm will stop.

[0174] Input: Awakening confirmation data

[0175] Output: Stop alarm

[0176] Specific operation: The device receives data from the smartwatch and stops the alarm.

[0177] Step 9:

[0178] (User) The user provides feedback through the smartphone app, for example, "The alarm was appropriate" or "The alarm was too loud."

[0179] Input: User feedback

[0180] Output: Feedback data entered into the smartphone app

[0181] What happens: A user uses the app's feedback feature to provide a rating.

[0182] Step 10:

[0183] (Server) The server receives the feedback and analyzes it using a generative AI model.

[0184] Input: Feedback data

[0185] Output: Analysis results and optimization information

[0186] What it does: A generative AI model analyzes feedback data and generates information to optimize system settings.

[0187] (Application example 1)

[0188] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0189] Conventional alarm systems only notified users at a time specified by the user, and did not adequately check the user's behavior or optimize the system based on feedback. Furthermore, in physical stores, there was no system in place to ensure that staff were awake and ready to work when it came to shift management. This resulted in staff being late or not performing their shifts, leading to problems with reduced work efficiency.

[0190] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0191] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for using a smartwatch to confirm the user's wakefulness and send a reminder before the user starts work, means for providing alarm setting and reminder functions specialized for store staff shift management, and means for receiving and analyzing feedback provided by the user. This improves the user's lifestyle and enables more efficient and reliable staff shift management in physical stores.

[0192] A "user" is an individual who uses the system to set alarms and receive wake-up and shift management notifications.

[0193] A "means for accepting voice instructions" is a device or system for recognizing and processing voice input from a user.

[0194] The "means for converting voice instructions into text data" is software or algorithms that use voice recognition technology to convert received voice into text data.

[0195] "Means for analyzing text data and setting alarms based on date, time, and conditions" refers to software or a process that extracts necessary information from the analyzed text data and sets the alarm date, time, and conditions based on that information.

[0196] The "means for activating an alarm at a set date and time" refers to software or hardware for triggering an alarm at a specified date and time and issuing a notification.

[0197] "Means for keeping the alarm going until the user wakes up" refers to the mechanism or process for keeping the alarm notification going until the user is sure to wake up.

[0198] "Method for utilizing a smartwatch to detect when a user is awake and send a reminder before the start of a shift" means a system or method for using a sensor in a smartwatch to detect when a user is awake and send a reminder notification before the start of a shift.

[0199] "A means for providing alarm setting and reminder functions specialized for store staff shift management" refers to software or a system for managing the shift schedules of staff working in physical stores and providing alarms and reminders at appropriate times.

[0200] "Means for receiving and analyzing feedback" refers to the mechanisms and processes used to collect feedback provided by users and analyze that data to optimize the system.

[0201] The system for implementing this invention has the ability to accept voice commands, set an alarm based on those commands, and keep the alarm running until the user wakes up. It also uses a smartwatch or motion sensor to check whether the user is awake and optimizes the system based on the feedback.

[0202] System configuration

[0203] 1. Accepting voice commands

[0204] The user issues natural language voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[0205] 2. Speech Recognition and Text Conversion

[0206] The device converts voice instructions received through a voice input device (e.g., a head-mounted display with a microphone) into text data using a voice recognition API. This text data is used as basic information for the entire system.

[0207] 3. Text data analysis and alarm setting

[0208] The converted text data is sent to a server, which uses a generative AI model to analyze the text data and set alarms based on the date, time, and other conditions.

[0209] 4. Alarm triggers and reminders

[0210] At the set time and date, the device will activate an alarm that will notify the user via sound, vibration, or both. Additionally, the smartwatch will be used to check the user's alertness and send reminders before the start of their shift.

[0211] 5. Confirmation of wake-up and alarm stop

[0212] Smartwatches and motion sensors monitor when a user wakes up and continue to ring the alarm until the user confirms they are awake, at which point the alarm automatically stops.

[0213] 6. Receiving and analyzing feedback

[0214] After the alarm is stopped, the user can provide feedback to the system, for example, by sending a comment through the app such as "The alarm was too loud." The server uses a feedback analysis system to analyze this data and optimize future alarm settings.

[0215] Specific examples

[0216] As a specific example of this system, the following case can be given.

[0217] Example 1: A user issues a voice command such as "I want to be woken up at 6:00 AM next Saturday." This command is converted into text data by a speech recognition API, and the generative AI model analyzes it to set an alarm for "6:00 AM next Saturday."

[0218] Example 2: As an application example of staff shift management in a brick-and-mortar store, a smartwatch is used to send wake-up reminders to staff before they start their shift. Shift schedules are set through voice commands, and wake-up confirmation is performed on the smartwatch.

[0219] Prompt Sentence Examples

[0220] If a user requests "I want to be woken up at 6 AM next Saturday," the voice recognition API converts this into text data and sets an alarm for "6 AM next Saturday." The alarm will ring at the specified time, and the smartwatch will confirm that the user has woken up. The alarm will continue until the user has woken up, and feedback will be collected.

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] The user issues voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[0224] Input: User's voice command

[0225] Output: Audio data (analog signal)

[0226] Step 2:

[0227] The device collects the received voice data through a voice input device (a head-mounted display with a microphone) and converts the voice data into text data using a voice recognition API.

[0228] Input: Audio data (analog signal)

[0229] Output: Text data (digital format)

[0230] Step 3:

[0231] The converted text data is sent from the device to a server, which then analyzes the text data using a generative AI model to extract the necessary date, time, and condition information from the instructions.

[0232] Input: Text data (digital format)

[0233] Output: Analysis results (date and time, conditions)

[0234] Step 4:

[0235] The server generates an alarm schedule based on the extracted date and time and conditions, and transmits the information to the terminal.

[0236] Input: Analysis results (date and time, conditions)

[0237] Output: Alarm schedule

[0238] Step 5:

[0239] At the set date and time, the device will activate an alarm, which will notify the user by sound, vibration, or both.

[0240] Input: Alarm Schedule

[0241] Output: Alarm notification (sound, vibration)

[0242] Step 6:

[0243] At the same time as the alarm goes off, the smartwatch activates sensors to detect the user's movement and monitors their state of wakefulness.

[0244] Input: alarm notification, user movement data

[0245] Output: Awakening state information

[0246] Step 7:

[0247] If the user is awake, the smartwatch sends the information to the device, which then stops the alarm. If the user does not wake up, the alarm continues to ring.

[0248] Input: Awakening state information

[0249] Output: Alarm stop signal

[0250] Step 8:

[0251] After the alarm is stopped, the user provides feedback to the system, for example, by sending a comment such as "The alarm was too loud" through the app.

[0252] Input: User feedback

[0253] Output: Feedback data

[0254] Step 9:

[0255] The server analyzes the collected feedback data using a feedback analysis system to find improvements to optimize the system's performance.

[0256] Input: Feedback data

[0257] Output: Analysis results (improvement points)

[0258] This will improve users' daily routines and also make staff shift management in physical stores more efficient and reliable.

[0259] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0260] The present invention is a system that provides a user with sleep management and effective wake-up support, and further combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on the emotions. Specific embodiments of the present invention are described in detail below.

[0261] System Overview

[0262] 1. Accepting and converting voice commands

[0263] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[0264] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[0265] 2. Text data analysis and alarm setting

[0266] (Terminal) The converted text data is sent to the server.

[0267] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and other conditions. This makes it possible to set alarms based on complex conditions.

[0268] 3. Emotion analysis using an emotion engine

[0269] (Server) The generation AI recognizes the user's emotions from the text data, and the emotion engine analyzes it to understand the user's stress level and emotional state based on the user's tone and the words used.

[0270] For example, feedback such as "I want to wake you up again at 6 tomorrow morning, but the volume was too loud last time" can help us recognize that the user was dissatisfied with the previous alarm.

[0271] 4. Triggering and Continuing Alarms

[0272] (Device) When the set alarm time arrives, the device will activate the alarm. The alarm will notify the user by sound, vibration, or both. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[0273] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[0274] 5. Receiving and analyzing feedback

[0275] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm was just right" or "The alarm was too loud" through the app.

[0276] (Server) The server receives this feedback and the emotion engine analyzes it. Evaluations and improvements based on the user's emotions are extracted, and future alarm settings are optimized.

[0277] Specific examples

[0278] Specific examples are given below.

[0279] Example 1:

[0280] (User) The user instructs, "I want to be woken up at 7:00 tomorrow. However, the previous alarm sound was too loud and annoying."

[0281] (Device) The voice recognition function converts voice into text data.

[0282] (Server) The generation AI analyzes the text data and extracts the information, such as "set the alarm for 7am the next day and lower the volume," and the emotion engine recognizes the user's discomfort.

[0283] (Device) The next morning, the alarm will start ringing at 7:00 AM, with the volume set to an appropriate level based on the emotion engine analysis. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[0284] Example 2:

[0285] (User) The user instructs, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[0286] (Device) The voice recognition function converts voice into text data.

[0287] (Server) The generation AI analyzes the text data, and the emotion engine analyzes the user's gloomy emotions to understand setting information such as "Set the alarm for 6:00 every Monday, but notify gently."

[0288] (Device) The alarm will ring at 6am next Monday morning, but the notification method will be set to a soft, pleasant sound or vibration.

[0289] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle through emotion-based optimization.

[0290] The processing flow will be explained below.

[0291] Step 1:

[0292] (User) The user verbally instructs, "Set the alarm for 7:00 tomorrow morning, but the volume was too loud last time."

[0293] Step 2:

[0294] (Device) The device's microphone captures the user's voice commands and sends them to the internal voice recognition engine.

[0295] Step 3:

[0296] (Terminal) The voice recognition engine converts the voice data into text data and sends the text data to the server.

[0297] Step 4:

[0298] (Server) The generation AI installed on the server analyzes the received text data and extracts the instructions ("Set the alarm for 7am tomorrow morning" or "The volume was too loud last time").

[0299] Step 5:

[0300] (Server) The emotion engine analyzes the user's emotions from their instructions. For example, from the part "The volume was too loud last time," it recognizes that the user is dissatisfied with the previous alarm setting.

[0301] Step 6:

[0302] (Server) The generation AI takes into account the analysis results of the emotion engine and generates optimal alarm setting information, such as "Date and time: 7:00 the next day" and "Volume: Low."

[0303] Step 7:

[0304] (Server) Sends the generated alarm setting information to the terminal.

[0305] Step 8:

[0306] (Device) Based on the setting information received by the device, an alarm is registered in the internal calendar app or alarm function.

[0307] Step 9:

[0308] (Device) When the set alarm time approaches, the device will activate the alarm.

[0309] Step 10:

[0310] (Device) The alarm will start ringing and notify the user with sound and vibration. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[0311] Step 11:

[0312] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[0313] Step 12:

[0314] (Smartwatch) When it determines that the user has woken up, the smartwatch sends a signal to the device to stop the alarm.

[0315] Step 13:

[0316] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[0317] Step 14:

[0318] (User) After waking up, the user provides feedback through the app about the effectiveness of the alarm and areas for improvement, such as "The alarm volume this time was just right."

[0319] Step 15:

[0320] (Device) The device sends the user's feedback to the server.

[0321] Step 16:

[0322] (Server) The server receives the feedback, analyzes it with an emotion engine, evaluates it based on the user's emotions, and generates data to be reflected in future alarm settings.

[0323] Example 2

[0324] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0325] Conventional alarm systems often provide alarms in a uniform manner without considering the user's emotions or feedback, resulting in low user satisfaction. Furthermore, they lack a means to properly monitor whether the user is actually awake, making it difficult to provide effective sleep management and wake-up support. Therefore, it is necessary to provide a system that recognizes the user's emotions and sets alarms that reflect their feedback.

[0326] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0327] In this invention, the server includes means for recognizing and analyzing user emotions, means for optimizing alarm settings based on said emotions, and means for receiving and analyzing feedback provided by the user, thereby enabling optimal alarm settings based on individual user emotions and feedback.

[0328] "User" refers to an individual who uses this system to receive sleep management and wake-up support.

[0329] "Voice instructions" refers to instructions or commands given by a user to a system through voice.

[0330] "Text data" refers to character string information converted from voice instructions using voice recognition technology.

[0331] "Analysis" refers to the process of analyzing received text data and feedback data to understand its content.

[0332] "Alarm" refers to a notification method set by the system to help the user wake up.

[0333] "Emotion" refers to the psychological state or feelings that users express through their speech and feedback.

[0334] An "emotion engine" refers to an analysis system that recognizes emotions from users' text data and optimizes settings based on that information.

[0335] "Smart devices" refers to electronic devices with internet connectivity and sensors, such as smartwatches and smartphones.

[0336] "Motion sensor" refers to a sensor unit that detects human movement and provides that information to the system.

[0337] The present invention is a system for providing users with sleep management and effective wake-up support, which combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on those emotions.

[0338] System configuration

[0339] 1. Hardware Configuration

[0340] (Terminal) This system uses a terminal (e.g., smartphone, smart speaker) to receive user voice commands. The terminal has a microphone for voice recognition and Internet connectivity.

[0341] (Smart devices / motion sensors) Furthermore, it works in conjunction with smart devices (e.g., smartwatches) and motion sensors (e.g., human sensors) to detect user movements.

[0342] 2. Software Configuration

[0343] (Voice recognition software) The device is installed with voice recognition software (e.g., Google Assistant, Amazon Alexa). This software converts the user's voice into text data in real time.

[0344] (Generative AI model) The server is equipped with a generative AI model (e.g., GPT-4) that analyzes text data and optimizes alarm settings based on date, time, and other conditions.

[0345] (Emotion engine) An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) is installed on the server, which recognizes and analyzes user emotions from text data.

[0346] Data processing and calculation

[0347] (Terminal) The terminal receives voice instructions from the user, converts them into text data using voice recognition software, and sends it to the server.

[0348] (Server) The server uses a generative AI model to analyze the text data and extract alarm setting information based on the date, time, and conditions. It also uses an emotion engine to analyze the user's emotions and optimize the alarm settings.

[0349] (Feedback Analysis) The server also receives feedback from users and analyzes it with the emotion engine. The results of this feedback analysis are used to further optimize future alarm settings.

[0350] Specific examples

[0351] Example 1:

[0352] (User) says, "I want to be woken up at 7:00 tomorrow. However, the previous alarm was too loud and annoying."

[0353] (Device) Use the voice recognition function to convert voice into text.

[0354] (Server) The generative AI model analyzes the text and extracts the information, "Set the alarm for 7am the next day and lower the volume." The emotion engine recognizes the user's discomfort.

[0355] (Device) The alarm will start ringing at 7am the next morning, with the volume set to an appropriate adjusted level.

[0356] Example 2:

[0357] (User) gives the command, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[0358] (Device) Use the voice recognition function to convert voice into text.

[0359] (Server) The generative AI model analyzes the text and determines, "Set an alarm for 6:00 every Monday, but gently." The emotion engine recognizes the user's depressed emotion.

[0360] (Device) At 6:00 AM the following Monday morning, the alarm will sound and vibrate to gently wake the user.

[0361] The above is an embodiment of the invention. This system realizes flexible and effective wake-up support that reflects the user's emotions and feedback.

[0362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0363] Step 1:

[0364] (User) The user gives instructions to set the alarm by voice.

[0365] Specific operation: The user speaks into the device, "Please wake me up at 6am tomorrow morning."

[0366] Input: User's voice command.

[0367] Output: Audio data.

[0368] Step 2:

[0369] (Terminal) The terminal uses voice recognition software to convert the voice data into text data.

[0370] What it does: Speech recognition software (e.g., Google Assistant) converts the user's speech into text, such as "Wake me up at 6am tomorrow morning."

[0371] Input: Audio data.

[0372] Output: Text data.

[0373] Step 3:

[0374] (Terminal) The converted text data is sent to the server.

[0375] Specific operation: Send text data to the server using an HTTP request.

[0376] Input: Text data.

[0377] Output: Text data is sent.

[0378] Step 4:

[0379] (Server) Analyzes text data using a generative AI model to extract dates, times, and conditions.

[0380] Specific operation: A generative AI model (e.g., GPT-4) analyzes the date and time "6:00 AM tomorrow" and the instruction "Wake me up."

[0381] Input: Text data.

[0382] Output: Alarm setting condition.

[0383] Step 5:

[0384] (Server) Analyze user emotions using an emotion engine.

[0385] Specific operation: An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) analyzes the user's emotions from text data and understands the user's psychological state.

[0386] Input: Text data.

[0387] Output: The user's emotional state.

[0388] Step 6:

[0389] (Server) Optimize alarm settings based on analysis results.

[0390] Specific behavior: Adjust the alarm volume and notification method based on the results of the emotion engine.

[0391] Input: Alarm setting conditions, user's emotional state.

[0392] Output: Optimized alarm settings.

[0393] Step 7:

[0394] (Server) Sends optimized alarm settings to the device.

[0395] Specific operation: Alarm setting information is returned to the terminal as an HTTP response.

[0396] Input: Optimized alarm settings.

[0397] Output: Alarm setting information.

[0398] Step 8:

[0399] (Device) The alarm will start when the set alarm time arrives.

[0400] Specific operation: An alarm sound or vibration will be generated at the specified time.

[0401] Input: Alarm setting information.

[0402] Output: Triggering an alarm.

[0403] Step 9:

[0404] (Smart device / motion sensor) Monitors whether the user is awake.

[0405] Specific operation: The smartwatch or motion sensor detects the user's movements and confirms that they have woken up.

[0406] Input: User behavior data.

[0407] Output: The user's wake-up status.

[0408] Step 10:

[0409] (User) Provide feedback after the alarm stops.

[0410] Specific behavior: The user enters feedback through the app, such as "The alarm was too loud."

[0411] Input: User feedback.

[0412] Output: Feedback data.

[0413] Step 11:

[0414] (Server) Analyze the feedback data and optimize future alarm settings.

[0415] Specific operation: The emotion engine analyzes the feedback and reflects it in the next alarm setting.

[0416] Input: Feedback data.

[0417] Output: Optimized alarm setting information.

[0418] (Application example 2)

[0419] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0420] In conventional food delivery services, there was a lack of adequate management of fatigue and stress among delivery personnel, which led to a decline in work efficiency and customer satisfaction.In addition, there was no system in place to effectively schedule delivery personnel's refreshment time and encourage them to take breaks at the optimal timing.

[0421] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0422] In this invention, the server includes means for receiving voice instructions from the user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on the date, time, and conditions, means including an emotion engine for analyzing the emotional state of the delivery person and detecting fatigue or stress, means for scheduling break times, means for activating the alarm at the set date and time, and means for continuing the alarm until the user wakes up. This makes it possible to monitor the emotional state of the delivery person and provide optimal refreshment time, thereby improving work efficiency and customer satisfaction.

[0423] "User" is a term that refers to a user of a food delivery service or a delivery person.

[0424] "Voice commands" is a term that refers to voice commands given by a user to a system.

[0425] "Text data" is a term that refers to data in which voice instructions are converted into text information.

[0426] "Analysis" is a term that refers to the act of evaluating dates, times, conditions, and even emotional states based on text data.

[0427] "Alarm" is a term that refers to a sound or vibration that is activated at a set date and time to notify the user.

[0428] "Emotion engine" is a term used to describe a system that recognizes and evaluates a user's emotional state from text data.

[0429] "Rest time" is a term that refers to the time a delivery person takes to rest.

[0430] "Scheduling" is a term that refers to the act of setting optimal rest times based on various conditions.

[0431] "Smart device" is a term that refers to devices that sense the user's actions and status, such as smartwatches and smartphones.

[0432] "Human presence sensor" is a term that refers to a sensor that detects surrounding movements and actions.

[0433] "Feedback" is a term that refers to the evaluations and opinions that users provide to a system.

[0434] "Food delivery service" is a term that refers to a service that delivers meals or food to a location specified by the customer.

[0435] "Delivery person" is a term used to refer to the staff member in a food delivery service who is responsible for actually delivering the goods.

[0436] The present invention provides a system for managing fatigue of delivery personnel in a food delivery service and efficiently notifying them of refreshment times. An embodiment of the present invention will be described in detail below.

[0437] System Overview

[0438] The present invention consists of a system that accepts a user's voice instructions, converts them into text data, analyzes them using an emotion engine, and schedules appropriate break times.

[0439] 1. Accepting and converting voice commands

[0440] Device: The user (delivery person) issues voice instructions to the system. For example, they might say, "I feel tired" or "I need a break." The device then uses voice recognition technology (e.g., Google Speech Recognition API) to convert the voice instructions into text data.

[0441] 2. Text data analysis and alarm setting

[0442] Server: The converted text data is sent to the server and analyzed using a generative AI model. The emotion engine recognizes the user's emotional state and performs analysis. For example, if the user says "I'm tired," the emotion engine will detect a high stress level.

[0443] 3. Analysis by Emotion Engine

[0444] Server: The server evaluates fatigue and stress levels from text data and schedules breaks. For example, it might suggest a delivery person with a high stress level take a break in 30 minutes.

[0445] 4. Triggering and Continuing Alarms

[0446] Device: When the scheduled break time arrives, the device will activate an alarm. The alarm will notify you with sound and vibration, and the volume and tone will be adjusted based on the analysis results of the emotion engine. The device will then check whether the user has woken up via the smartwatch or motion sensor and stop the alarm.

[0447] Hardware or software used

[0448] Hardware: Smartphones, smartwatches, motion sensors

[0449] Software: Google Speech Recognition API, TextBlob, generative AI model, emotion engine program

[0450] Specific examples

[0451] For example, consider a delivery person saying, "I'm pretty tired this morning. I'd like to take a break." The voice command is converted into text using voice recognition technology. The server then analyzes the text data using a generative AI model to assess the fatigue level. If high fatigue is detected, the system suggests a break in 30 minutes and sets a gentle alarm at an appropriate time. After 30 minutes, the smartphone will sound a gentle alarm, and the delivery person's return from the break will be confirmed on the smartwatch. In this way, the system effectively supports the delivery person's health management.

[0452] Examples of prompt statements

[0453] Please describe your current state in detail. For example, describe your feelings such as "I'm tired" or "I'm sleepy."

[0454] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0455] Step 1:

[0456] Device: The user (delivery person) verbally commands, "I feel tired" or "I need a break." This is the input. The device accepts the voice command. Speech recognition technology (e.g., Google Speech Recognition API) is used here. The voice input is sent to the device as audio data.

[0457] Step 2:

[0458] Terminal: The terminal converts the received voice data into text data using voice recognition technology. Specifically, the voice recognition engine analyzes the voice data and generates the corresponding text data. The input is voice data, and the output is text data.

[0459] Step 3:

[0460] Server: The converted text data is sent to the server. The server uses the generative AI model to analyze the text data. The specific data processing involves extracting emotional information from the text data using natural language processing technology. The input is text data, and the output is emotional information.

[0461] Step 4:

[0462] Server: The server uses an emotion engine to evaluate the emotion information and determine the user's fatigue and stress levels. In this process, the emotion engine analyzes keywords and tones in the text data and scores the emotional state. The input is emotion information, and the output is an emotion score.

[0463] Step 5:

[0464] Server: If the emotion score is high, schedule a break. The break time setting suggests an appropriate break timing, such as the next 30 minutes. The input is the emotion score, and the output is the break schedule. Specific operations include calculating the break time.

[0465] Step 6:

[0466] Server: Sets an alarm when the scheduled break time arrives. The volume and tone of the alarm are adjusted based on the evaluation results of the emotion engine. Specifically, if the emotion score is high, a gentler sound is selected. The input is the break schedule and emotion score, and the output is the adjusted alarm setting.

[0467] Step 7:

[0468] Terminal: When it is time for a break, the terminal will activate an alarm. The specific behavior is to notify the user using an alarm sound or vibration. The input is the alarm setting, and the output is the alarm notification.

[0469] Step 8:

[0470] Device: Checks whether the user has woken up via a smartwatch or motion sensor. Specifically, the sensor detects the user's movement and confirms that the user has woken up. The input is sensor data, and the output is the wake-up confirmation result.

[0471] Step 9:

[0472] Server: Once the wake-up is confirmed, the alarm is stopped. Specifically, the server sends a stop command to the terminal. The input is the wake-up confirmation result, and the output is the alarm stop.

[0473] This completes the entire process and effectively manages fatigue among food delivery personnel.

[0474] 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.

[0475] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0476] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0477] [Second embodiment]

[0478] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0479] 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.

[0480] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0481] 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.

[0482] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0483] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0484] 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.

[0485] 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.

[0486] 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 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.

[0487] 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.

[0488] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0489] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0490] The present invention is a system that improves a user's daily rhythm and assists in waking up efficiently. This system sets an alarm based on the user's voice instruction and continues to operate until the alarm wakes the user up. Furthermore, it has a function that uses a smartwatch or a motion sensor to confirm whether the user is actually awake, and optimizes the system through feedback. A specific embodiment of this system is shown below.

[0491] System Overview

[0492] 1. Accepting and converting voice commands

[0493] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6am tomorrow morning" or "Set the alarm for 7am every Monday morning, except for 8am on public holidays."

[0494] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[0495] 2. Text data analysis and alarm setting

[0496] (Terminal) The converted text data is sent to the server.

[0497] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and conditions.

[0498] For example, it can handle complex settings such as "set the alarm for 6:30 every Monday, and for 7:00 if the previous day is a holiday."

[0499] 3. Triggering and continuing alarms

[0500] (Device) When the set alarm time arrives, the device will activate the alarm, notifying the user with sound, vibration, or both.

[0501] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[0502] 4. Receiving and analyzing feedback

[0503] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm went off at the right time" or "The alarm was too loud" through the app.

[0504] (Server) The server receives this feedback and the generating AI analyzes it, which then optimizes future alarm settings.

[0505] Specific examples

[0506] Specific examples are given below.

[0507] Example 1:

[0508] (User) The user instructs, "Set it to wake me up at 7:00 tomorrow."

[0509] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[0510] (Server) The generation AI analyzes the text data and extracts the information "Set the alarm for 7am the next morning."

[0511] (Device) The alarm will start ringing at 7am the next morning. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[0512] Example 2:

[0513] (User) The user instructs "Wake me up at 6:00 every Monday." He also adds, "However, if it is a public holiday, wake me up at 7:00."

[0514] (Device) The voice recognition function converts voice into text data.

[0515] (Server) The generation AI analyzes the text data and processes the condition "Set the alarm at 6:00 every Monday, but set it to 7:00 on holidays."

[0516] (Device) The alarm is set for 6:00 AM on the following Monday. If a public holiday falls on the same day, the alarm will go off at 7:00 AM.

[0517] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle.

[0518] The processing flow will be explained below.

[0519] Step 1:

[0520] (User) The user issues a voice command to set the alarm, saying, "Set the alarm for 7:00 tomorrow morning."

[0521] Step 2:

[0522] (Device) The device's microphone captures the user's voice instructions, and the internal voice recognition engine converts the voice data into text data.

[0523] Step 3:

[0524] (Terminal) The terminal sends the converted text data to the server.

[0525] Step 4:

[0526] (Server) The server's generated AI receives the text data and analyzes it. During the analysis, it extracts the instruction content ("Set an alarm for 7am tomorrow") and clarifies the specific date and time and setting conditions.

[0527] Step 5:

[0528] (Server) The generation AI generates alarm setting information (date and time: tomorrow at 7:00, repetition: none, special conditions: none) based on the conditions.

[0529] Step 6:

[0530] (Server) Sends the generated alarm setting information to the terminal.

[0531] Step 7:

[0532] (Device) Based on the received alarm setting information, the device registers the alarm in its internal calendar app or alarm function.

[0533] Step 8:

[0534] (Device) When the set alarm time approaches, the device will activate the alarm.

[0535] Step 9:

[0536] (Device) The alarm will start ringing and notify the user with sound and vibration.

[0537] Step 10:

[0538] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[0539] Step 11:

[0540] (Smartwatch / Motion Sensor) If it determines that the user has woken up, it sends a signal to the device to stop the alarm.

[0541] Step 12:

[0542] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[0543] Step 13:

[0544] (User) After waking up, the user provides feedback on the effectiveness of the alarm through the app, such as "The alarm was just right" or "The alarm was too loud."

[0545] Step 14:

[0546] (Device) The device sends the user's feedback to the server.

[0547] Step 15:

[0548] (Server) The server receives the feedback, and the generating AI analyzes it. Based on the feedback, it optimizes future alarm settings.

[0549] Example 1

[0550] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0551] For many people living busy lives in modern society, maintaining a regular rhythm and waking up efficiently is important. However, existing alarm systems lack a means to accurately confirm the user's wake-up status, making it difficult to reliably wake them up. Furthermore, the flexibility of alarm settings is limited, making it difficult to meet individual user needs. Furthermore, there is no well-established mechanism for effectively utilizing feedback to optimize the system, making it difficult to provide optimal alarm settings for each individual user.

[0552] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0553] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for confirming the user's wakefulness in cooperation with a smartwatch or a motion sensor, and means for receiving feedback provided by the user and analyzing it using a generative AI model. This allows the system to set an appropriate alarm based on the user's individual needs, helping the user wake up reliably, and enabling system optimization based on the feedback.

[0554] "Means for receiving voice instructions from the user" refers to devices or software that receive voice instructions when a user gives voice instructions to the system in natural language to set alarms or perform other operations.

[0555] The "means for converting voice instructions into text data" refers to a device or software that recognizes received voice instructions and converts the content into text format, such as a voice recognition engine.

[0556] "Means for analyzing text data and setting alarms based on the date, time, and conditions" refers to a device or software that analyzes the converted text data and sets appropriate alarms based on the date, time, and conditions specified by the user.

[0557] "Means for activating an alarm at a set date and time" refers to a device or software that activates an alarm using sound, vibration, or other means at a set date and time.

[0558] "Means for keeping the alarm going until the user wakes up" refers to a device or software that keeps the alarm set so that it does not stop until the user actually wakes up.

[0559] "Means for verifying user alertness in conjunction with a smartwatch or motion sensor" refers to devices or software that use data from a smartwatch or motion sensor to verify the user's physical movement and alertness.

[0560] "Means for receiving and analyzing user-provided feedback using a generative AI model" refers to devices or software that receive user feedback, analyze it using a generative AI model, and optimize system performance or settings.

[0561] This invention is a system for improving a user's daily rhythm and helping them wake up efficiently. The system aims to allow the user to set an alarm by voice and operate until the alarm wakes the user up reliably. Furthermore, it has a function for optimizing the system through feedback.

[0562] System Overview

[0563] 1. Accepting voice commands

[0564] (User) The user gives instructions to the system in natural language to set an alarm, such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[0565] (Device) The device uses voice recognition software (e.g., Google Speech-to-Text API) to convert the user's voice into text data.

[0566] 2. Text Data Analysis

[0567] (Terminal) The converted text data is sent to the server.

[0568] (Server) The generative AI model (e.g., OpenAI GPT-4) deployed on the server analyzes the text data sent and sets alarms based on the user's instructions. This analysis extracts the date, time, and conditions.

[0569] 3. Alarm settings and operation

[0570] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[0571] (Device) The device will activate the alarm with sound or vibration when the set alarm time arrives.

[0572] (Smartwatch / Motion Sensor) In addition, a smartwatch (e.g., Apple Watch) or a motion sensor can be used to monitor the user's waking state and the alarm will continue until the user wakes up.

[0573] 4. Receiving and analyzing feedback

[0574] (User) After the alarm is stopped, the user provides feedback through the smartphone app, such as "The alarm was appropriate" or "The alarm was too loud."

[0575] (Server) The server receives user feedback and the generative AI model analyzes it, allowing for future optimization of alarm settings.

[0576] Specific examples

[0577] A specific example will be given below.

[0578] Example 1:

[0579] (User) The user instructs, "Wake me up at 7 o'clock tomorrow."

[0580] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[0581] (Server) The generating AI analyzes and extracts the information "Set the alarm for 7am the next morning."

[0582] (Device) The alarm will start ringing at 7:00 the next morning. When the user wakes up, the smartwatch detects their movement and sends a signal to the device to stop the alarm, which stops the alarm.

[0583] Example 2:

[0584] (User) The user instructs, "Wake me up at 6:00 every Monday, except on public holidays, at 7:00."

[0585] (Device) The voice recognition function converts voice into text data.

[0586] (Server) The generation AI analyzes and extracts the condition "Set the alarm for 6:00 every Monday, but for holidays, set it for 7:00."

[0587] (Device) The alarm will ring at 6:00 a.m. the following Monday, or 7:00 a.m. if a public holiday falls on the same day.

[0588] As described above, the system of the present invention efficiently supports the user's life rhythm and promotes a healthy lifestyle.

[0589] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0590] Step 1:

[0591] (User) The user issues a voice command to the system, such as "Wake me up at 6am tomorrow morning."

[0592] Input: User's voice command

[0593] Output: Audio data received by the device's microphone

[0594] Specific operation: When the user speaks into the device's microphone, the device picks up the audio.

[0595] Step 2:

[0596] (Device) The device converts the voice into text data using voice recognition software (e.g., Google Speech-to-Text API).

[0597] Input: Audio data

[0598] Output: Text data

[0599] What happens: The speech recognition engine analyzes the audio data and converts it into a corresponding text representation.

[0600] Step 3:

[0601] (Terminal) The terminal sends the converted text data to the server.

[0602] Input: Text data

[0603] Output: Text data sent to the server

[0604] What happens: Text data is sent to a server over an internet connection.

[0605] Step 4:

[0606] (Server) The server analyzes the text data using a generative AI model (e.g., OpenAI GPT-4) to extract date, time, and alarm setting information.

[0607] Input: Text data

[0608] Output: Analyzed alarm setting information (date and time and conditions)

[0609] Specific operation: The generative AI model analyzes the text data and extracts the date, time, and conditions specified by the user.

[0610] Step 5:

[0611] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[0612] Input: Parsed alarm setting information

[0613] Output: A data packet containing configuration information

[0614] Specific operation: The server generates a data packet containing instructions for setting an alarm and sends it to the device.

[0615] Step 6:

[0616] (Device) When the set time arrives, the device will activate an alarm.

[0617] Input: Set alarm information

[0618] Output: Alarm activation (sound, vibration, etc.)

[0619] Specific action: The device will emit an alarm or vibrate at the specified date and time.

[0620] Step 7:

[0621] (Smartwatch / motion sensor) A smartwatch or motion sensor checks whether the user is awake.

[0622] Input: User movement and environmental data

[0623] Output: Awakening confirmation data

[0624] What it does: The smartwatch monitors your movements and notifies your device when movement is detected.

[0625] Step 8:

[0626] (Device) When the user is confirmed awake, the alarm will stop.

[0627] Input: Awakening confirmation data

[0628] Output: Stop alarm

[0629] Specific operation: The device receives data from the smartwatch and stops the alarm.

[0630] Step 9:

[0631] (User) The user provides feedback through the smartphone app, for example, "The alarm was appropriate" or "The alarm was too loud."

[0632] Input: User feedback

[0633] Output: Feedback data entered into the smartphone app

[0634] What happens: A user uses the app's feedback feature to provide a rating.

[0635] Step 10:

[0636] (Server) The server receives the feedback and analyzes it using a generative AI model.

[0637] Input: Feedback data

[0638] Output: Analysis results and optimization information

[0639] What it does: A generative AI model analyzes feedback data and generates information to optimize system settings.

[0640] (Application example 1)

[0641] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0642] Conventional alarm systems only notified users at a time specified by the user, and did not adequately check the user's behavior or optimize the system based on feedback. Furthermore, in physical stores, there was no system in place to ensure that staff were awake and ready to work when it came to shift management. This resulted in staff being late or not performing their shifts, leading to problems with reduced work efficiency.

[0643] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0644] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for using a smartwatch to confirm the user's wakefulness and send a reminder before the user starts work, means for providing alarm setting and reminder functions specialized for store staff shift management, and means for receiving and analyzing feedback provided by the user. This improves the user's lifestyle and enables more efficient and reliable staff shift management in physical stores.

[0645] A "user" is an individual who uses the system to set alarms and receive wake-up and shift management notifications.

[0646] A "means for accepting voice instructions" is a device or system for recognizing and processing voice input from a user.

[0647] The "means for converting voice instructions into text data" is software or algorithms that use voice recognition technology to convert received voice into text data.

[0648] "Means for analyzing text data and setting alarms based on date, time, and conditions" refers to software or a process that extracts necessary information from the analyzed text data and sets the alarm date, time, and conditions based on that information.

[0649] The "means for activating an alarm at a set date and time" refers to software or hardware for triggering an alarm at a specified date and time and issuing a notification.

[0650] "Means for keeping the alarm going until the user wakes up" refers to the mechanism or process for keeping the alarm notification going until the user is sure to wake up.

[0651] "Method for utilizing a smartwatch to detect when a user is awake and send a reminder before the start of a shift" means a system or method for using a sensor in a smartwatch to detect when a user is awake and send a reminder notification before the start of a shift.

[0652] "A means for providing alarm setting and reminder functions specialized for store staff shift management" refers to software or a system for managing the shift schedules of staff working in physical stores and providing alarms and reminders at appropriate times.

[0653] "Means for receiving and analyzing feedback" refers to the mechanisms and processes used to collect feedback provided by users and analyze that data to optimize the system.

[0654] The system for implementing this invention has the ability to accept voice commands, set an alarm based on those commands, and keep the alarm running until the user wakes up. It also uses a smartwatch or motion sensor to check whether the user is awake and optimizes the system based on the feedback.

[0655] System configuration

[0656] 1. Accepting voice commands

[0657] The user issues natural language voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[0658] 2. Speech Recognition and Text Conversion

[0659] The device converts voice instructions received through a voice input device (e.g., a head-mounted display with a microphone) into text data using a voice recognition API. This text data is used as basic information for the entire system.

[0660] 3. Text data analysis and alarm setting

[0661] The converted text data is sent to a server, which uses a generative AI model to analyze the text data and set alarms based on the date, time, and other conditions.

[0662] 4. Alarm triggers and reminders

[0663] At the set time and date, the device will activate an alarm that will notify the user via sound, vibration, or both. Additionally, the smartwatch will be used to check the user's alertness and send reminders before the start of their shift.

[0664] 5. Confirmation of wake-up and alarm stop

[0665] Smartwatches and motion sensors monitor when a user wakes up and continue to ring the alarm until the user confirms they are awake, at which point the alarm automatically stops.

[0666] 6. Receiving and analyzing feedback

[0667] After the alarm is stopped, the user can provide feedback to the system, for example, by sending a comment through the app such as "The alarm was too loud." The server uses a feedback analysis system to analyze this data and optimize future alarm settings.

[0668] Specific examples

[0669] As a specific example of this system, the following case can be given.

[0670] Example 1: A user issues a voice command such as "I want to be woken up at 6:00 AM next Saturday." This command is converted into text data by a speech recognition API, and the generative AI model analyzes it to set an alarm for "6:00 AM next Saturday."

[0671] Example 2: As an application example of staff shift management in a brick-and-mortar store, a smartwatch is used to send wake-up reminders to staff before they start their shift. Shift schedules are set through voice commands, and wake-up confirmation is performed on the smartwatch.

[0672] Prompt Sentence Examples

[0673] If a user requests "I want to be woken up at 6 AM next Saturday," the voice recognition API converts this into text data and sets an alarm for "6 AM next Saturday." The alarm will ring at the specified time, and the smartwatch will confirm that the user has woken up. The alarm will continue until the user has woken up, and feedback will be collected.

[0674] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0675] Step 1:

[0676] The user issues voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[0677] Input: User's voice command

[0678] Output: Audio data (analog signal)

[0679] Step 2:

[0680] The device collects the received voice data through a voice input device (a head-mounted display with a microphone) and converts the voice data into text data using a voice recognition API.

[0681] Input: Audio data (analog signal)

[0682] Output: Text data (digital format)

[0683] Step 3:

[0684] The converted text data is sent from the device to a server, which then analyzes the text data using a generative AI model to extract the necessary date, time, and condition information from the instructions.

[0685] Input: Text data (digital format)

[0686] Output: Analysis results (date and time, conditions)

[0687] Step 4:

[0688] The server generates an alarm schedule based on the extracted date and time and conditions, and transmits the information to the terminal.

[0689] Input: Analysis results (date and time, conditions)

[0690] Output: Alarm schedule

[0691] Step 5:

[0692] At the set date and time, the device will activate an alarm, which will notify the user by sound, vibration, or both.

[0693] Input: Alarm Schedule

[0694] Output: Alarm notification (sound, vibration)

[0695] Step 6:

[0696] At the same time as the alarm goes off, the smartwatch activates sensors to detect the user's movement and monitors their state of wakefulness.

[0697] Input: alarm notification, user movement data

[0698] Output: Awakening state information

[0699] Step 7:

[0700] If the user is awake, the smartwatch sends the information to the device, which then stops the alarm. If the user does not wake up, the alarm continues to ring.

[0701] Input: Awakening state information

[0702] Output: Alarm stop signal

[0703] Step 8:

[0704] After the alarm is stopped, the user provides feedback to the system, for example, by sending a comment such as "The alarm was too loud" through the app.

[0705] Input: User feedback

[0706] Output: Feedback data

[0707] Step 9:

[0708] The server analyzes the collected feedback data using a feedback analysis system to find improvements to optimize the system's performance.

[0709] Input: Feedback data

[0710] Output: Analysis results (improvement points)

[0711] This will improve users' daily routines and also make staff shift management in physical stores more efficient and reliable.

[0712] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0713] The present invention is a system that provides a user with sleep management and effective wake-up support, and further combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on the emotions. Specific embodiments of the present invention are described in detail below.

[0714] System Overview

[0715] 1. Accepting and converting voice commands

[0716] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[0717] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[0718] 2. Text data analysis and alarm setting

[0719] (Terminal) The converted text data is sent to the server.

[0720] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and other conditions. This makes it possible to set alarms based on complex conditions.

[0721] 3. Emotion analysis using an emotion engine

[0722] (Server) The generation AI recognizes the user's emotions from the text data, and the emotion engine analyzes it to understand the user's stress level and emotional state based on the user's tone and the words used.

[0723] For example, feedback such as "I want to wake you up again at 6 tomorrow morning, but the volume was too loud last time" can help us recognize that the user was dissatisfied with the previous alarm.

[0724] 4. Triggering and Continuing Alarms

[0725] (Device) When the set alarm time arrives, the device will activate the alarm. The alarm will notify the user by sound, vibration, or both. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[0726] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[0727] 5. Receiving and analyzing feedback

[0728] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm was just right" or "The alarm was too loud" through the app.

[0729] (Server) The server receives this feedback and the emotion engine analyzes it. Evaluations and improvements based on the user's emotions are extracted, and future alarm settings are optimized.

[0730] Specific examples

[0731] Specific examples are given below.

[0732] Example 1:

[0733] (User) The user instructs, "I want to be woken up at 7:00 tomorrow. However, the previous alarm sound was too loud and annoying."

[0734] (Device) The voice recognition function converts voice into text data.

[0735] (Server) The generation AI analyzes the text data and extracts the information, such as "set the alarm for 7am the next day and lower the volume," and the emotion engine recognizes the user's discomfort.

[0736] (Device) The next morning, the alarm will start ringing at 7:00 AM, with the volume set to an appropriate level based on the emotion engine analysis. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[0737] Example 2:

[0738] (User) The user instructs, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[0739] (Device) The voice recognition function converts voice into text data.

[0740] (Server) The generation AI analyzes the text data, and the emotion engine analyzes the user's gloomy emotions to understand setting information such as "Set the alarm for 6:00 every Monday, but notify gently."

[0741] (Device) The alarm will ring at 6am next Monday morning, but the notification method will be set to a soft, pleasant sound or vibration.

[0742] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle through emotion-based optimization.

[0743] The processing flow will be explained below.

[0744] Step 1:

[0745] (User) The user verbally instructs, "Set the alarm for 7:00 tomorrow morning, but the volume was too loud last time."

[0746] Step 2:

[0747] (Device) The device's microphone captures the user's voice commands and sends them to the internal voice recognition engine.

[0748] Step 3:

[0749] (Terminal) The voice recognition engine converts the voice data into text data and sends the text data to the server.

[0750] Step 4:

[0751] (Server) The generation AI installed on the server analyzes the received text data and extracts the instructions ("Set the alarm for 7am tomorrow morning" or "The volume was too loud last time").

[0752] Step 5:

[0753] (Server) The emotion engine analyzes the user's emotions from their instructions. For example, from the part "The volume was too loud last time," it recognizes that the user is dissatisfied with the previous alarm setting.

[0754] Step 6:

[0755] (Server) The generation AI takes into account the analysis results of the emotion engine and generates optimal alarm setting information, such as "Date and time: 7:00 the next day" and "Volume: Low."

[0756] Step 7:

[0757] (Server) Sends the generated alarm setting information to the terminal.

[0758] Step 8:

[0759] (Device) Based on the setting information received by the device, an alarm is registered in the internal calendar app or alarm function.

[0760] Step 9:

[0761] (Device) When the set alarm time approaches, the device will activate the alarm.

[0762] Step 10:

[0763] (Device) The alarm will start ringing and notify the user with sound and vibration. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[0764] Step 11:

[0765] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[0766] Step 12:

[0767] (Smartwatch) When it determines that the user has woken up, the smartwatch sends a signal to the device to stop the alarm.

[0768] Step 13:

[0769] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[0770] Step 14:

[0771] (User) After waking up, the user provides feedback through the app about the effectiveness of the alarm and areas for improvement, such as "The alarm volume this time was just right."

[0772] Step 15:

[0773] (Device) The device sends the user's feedback to the server.

[0774] Step 16:

[0775] (Server) The server receives the feedback, analyzes it with an emotion engine, evaluates it based on the user's emotions, and generates data to be reflected in future alarm settings.

[0776] Example 2

[0777] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0778] Conventional alarm systems often provide alarms in a uniform manner without considering the user's emotions or feedback, resulting in low user satisfaction. Furthermore, they lack a means to properly monitor whether the user is actually awake, making it difficult to provide effective sleep management and wake-up support. Therefore, it is necessary to provide a system that recognizes the user's emotions and sets alarms that reflect their feedback.

[0779] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0780] In this invention, the server includes means for recognizing and analyzing user emotions, means for optimizing alarm settings based on said emotions, and means for receiving and analyzing feedback provided by the user, thereby enabling optimal alarm settings based on individual user emotions and feedback.

[0781] "User" refers to an individual who uses this system to receive sleep management and wake-up support.

[0782] "Voice instructions" refers to instructions or commands given by a user to a system through voice.

[0783] "Text data" refers to character string information converted from voice instructions using voice recognition technology.

[0784] "Analysis" refers to the process of analyzing received text data and feedback data to understand its content.

[0785] "Alarm" refers to a notification method set by the system to help the user wake up.

[0786] "Emotion" refers to the psychological state or feelings that users express through their speech and feedback.

[0787] An "emotion engine" refers to an analysis system that recognizes emotions from users' text data and optimizes settings based on that information.

[0788] "Smart devices" refers to electronic devices with internet connectivity and sensors, such as smartwatches and smartphones.

[0789] "Motion sensor" refers to a sensor unit that detects human movement and provides that information to the system.

[0790] The present invention is a system for providing users with sleep management and effective wake-up support, which combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on those emotions.

[0791] System configuration

[0792] 1. Hardware Configuration

[0793] (Terminal) This system uses a terminal (e.g., smartphone, smart speaker) to receive user voice commands. The terminal has a microphone for voice recognition and Internet connectivity.

[0794] (Smart devices / motion sensors) Furthermore, it works in conjunction with smart devices (e.g., smartwatches) and motion sensors (e.g., human sensors) to detect user movements.

[0795] 2. Software Configuration

[0796] (Voice recognition software) The device is installed with voice recognition software (e.g., Google Assistant, Amazon Alexa). This software converts the user's voice into text data in real time.

[0797] (Generative AI model) The server is equipped with a generative AI model (e.g., GPT-4) that analyzes text data and optimizes alarm settings based on date, time, and other conditions.

[0798] (Emotion engine) An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) is installed on the server, which recognizes and analyzes user emotions from text data.

[0799] Data processing and calculation

[0800] (Terminal) The terminal receives voice instructions from the user, converts them into text data using voice recognition software, and sends it to the server.

[0801] (Server) The server uses a generative AI model to analyze the text data and extract alarm setting information based on the date, time, and conditions. It also uses an emotion engine to analyze the user's emotions and optimize the alarm settings.

[0802] (Feedback Analysis) The server also receives feedback from users and analyzes it with the emotion engine. The results of this feedback analysis are used to further optimize future alarm settings.

[0803] Specific examples

[0804] Example 1:

[0805] (User) says, "I want to be woken up at 7:00 tomorrow. However, the previous alarm was too loud and annoying."

[0806] (Device) Use the voice recognition function to convert voice into text.

[0807] (Server) The generative AI model analyzes the text and extracts the information, "Set the alarm for 7am the next day and lower the volume." The emotion engine recognizes the user's discomfort.

[0808] (Device) The alarm will start ringing at 7am the next morning, with the volume set to an appropriate adjusted level.

[0809] Example 2:

[0810] (User) gives the command, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[0811] (Device) Use the voice recognition function to convert voice into text.

[0812] (Server) The generative AI model analyzes the text and determines, "Set an alarm for 6:00 every Monday, but gently." The emotion engine recognizes the user's depressed emotion.

[0813] (Device) At 6:00 AM the following Monday morning, the alarm will sound and vibrate to gently wake the user.

[0814] The above is an embodiment of the invention. This system realizes flexible and effective wake-up support that reflects the user's emotions and feedback.

[0815] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0816] Step 1:

[0817] (User) The user gives instructions to set the alarm by voice.

[0818] Specific operation: The user speaks into the device, "Please wake me up at 6am tomorrow morning."

[0819] Input: User's voice command.

[0820] Output: Audio data.

[0821] Step 2:

[0822] (Terminal) The terminal uses voice recognition software to convert the voice data into text data.

[0823] What it does: Speech recognition software (e.g., Google Assistant) converts the user's speech into text, such as "Wake me up at 6am tomorrow morning."

[0824] Input: Audio data.

[0825] Output: Text data.

[0826] Step 3:

[0827] (Terminal) The converted text data is sent to the server.

[0828] Specific operation: Send text data to the server using an HTTP request.

[0829] Input: Text data.

[0830] Output: Text data is sent.

[0831] Step 4:

[0832] (Server) Analyzes text data using a generative AI model to extract dates, times, and conditions.

[0833] Specific operation: A generative AI model (e.g., GPT-4) analyzes the date and time "6:00 AM tomorrow" and the instruction "Wake me up."

[0834] Input: Text data.

[0835] Output: Alarm setting condition.

[0836] Step 5:

[0837] (Server) Analyze user emotions using an emotion engine.

[0838] Specific operation: An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) analyzes the user's emotions from text data and understands the user's psychological state.

[0839] Input: Text data.

[0840] Output: The user's emotional state.

[0841] Step 6:

[0842] (Server) Optimize alarm settings based on analysis results.

[0843] Specific behavior: Adjust the alarm volume and notification method based on the results of the emotion engine.

[0844] Input: Alarm setting conditions, user's emotional state.

[0845] Output: Optimized alarm settings.

[0846] Step 7:

[0847] (Server) Sends optimized alarm settings to the device.

[0848] Specific operation: Alarm setting information is returned to the terminal as an HTTP response.

[0849] Input: Optimized alarm settings.

[0850] Output: Alarm setting information.

[0851] Step 8:

[0852] (Device) The alarm will start when the set alarm time arrives.

[0853] Specific operation: An alarm sound or vibration will be generated at the specified time.

[0854] Input: Alarm setting information.

[0855] Output: Triggering an alarm.

[0856] Step 9:

[0857] (Smart device / motion sensor) Monitors whether the user is awake.

[0858] Specific operation: The smartwatch or motion sensor detects the user's movements and confirms that they have woken up.

[0859] Input: User behavior data.

[0860] Output: The user's wake-up status.

[0861] Step 10:

[0862] (User) Provide feedback after the alarm stops.

[0863] Specific behavior: The user enters feedback through the app, such as "The alarm was too loud."

[0864] Input: User feedback.

[0865] Output: Feedback data.

[0866] Step 11:

[0867] (Server) Analyze the feedback data and optimize future alarm settings.

[0868] Specific operation: The emotion engine analyzes the feedback and reflects it in the next alarm setting.

[0869] Input: Feedback data.

[0870] Output: Optimized alarm setting information.

[0871] (Application example 2)

[0872] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0873] In conventional food delivery services, there was a lack of adequate management of fatigue and stress among delivery personnel, which led to a decline in work efficiency and customer satisfaction.In addition, there was no system in place to effectively schedule delivery personnel's refreshment time and encourage them to take breaks at the optimal timing.

[0874] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0875] In this invention, the server includes means for receiving voice instructions from the user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on the date, time, and conditions, means including an emotion engine for analyzing the emotional state of the delivery person and detecting fatigue or stress, means for scheduling break times, means for activating the alarm at the set date and time, and means for continuing the alarm until the user wakes up. This makes it possible to monitor the emotional state of the delivery person and provide optimal refreshment time, thereby improving work efficiency and customer satisfaction.

[0876] "User" is a term that refers to a user of a food delivery service or a delivery person.

[0877] "Voice commands" is a term that refers to voice commands given by a user to a system.

[0878] "Text data" is a term that refers to data in which voice instructions are converted into text information.

[0879] "Analysis" is a term that refers to the act of evaluating dates, times, conditions, and even emotional states based on text data.

[0880] "Alarm" is a term that refers to a sound or vibration that is activated at a set date and time to notify the user.

[0881] "Emotion engine" is a term used to describe a system that recognizes and evaluates a user's emotional state from text data.

[0882] "Rest time" is a term that refers to the time a delivery person takes to rest.

[0883] "Scheduling" is a term that refers to the act of setting optimal rest times based on various conditions.

[0884] "Smart device" is a term that refers to devices that sense the user's actions and status, such as smartwatches and smartphones.

[0885] "Human presence sensor" is a term that refers to a sensor that detects surrounding movements and actions.

[0886] "Feedback" is a term that refers to the evaluations and opinions that users provide to a system.

[0887] "Food delivery service" is a term that refers to a service that delivers meals or food to a location specified by the customer.

[0888] "Delivery person" is a term used to refer to the staff member in a food delivery service who is responsible for actually delivering the goods.

[0889] The present invention provides a system for managing fatigue of delivery personnel in a food delivery service and efficiently notifying them of refreshment times. An embodiment of the present invention will be described in detail below.

[0890] System Overview

[0891] The present invention consists of a system that accepts a user's voice instructions, converts them into text data, analyzes them using an emotion engine, and schedules appropriate break times.

[0892] 1. Accepting and converting voice commands

[0893] Device: The user (delivery person) issues voice instructions to the system. For example, they might say, "I feel tired" or "I need a break." The device then uses voice recognition technology (e.g., Google Speech Recognition API) to convert the voice instructions into text data.

[0894] 2. Text data analysis and alarm setting

[0895] Server: The converted text data is sent to the server and analyzed using a generative AI model. The emotion engine recognizes the user's emotional state and performs analysis. For example, if the user says "I'm tired," the emotion engine will detect a high stress level.

[0896] 3. Analysis by Emotion Engine

[0897] Server: The server evaluates fatigue and stress levels from text data and schedules breaks. For example, it might suggest a delivery person with a high stress level take a break in 30 minutes.

[0898] 4. Triggering and Continuing Alarms

[0899] Device: When the scheduled break time arrives, the device will activate an alarm. The alarm will notify you with sound and vibration, and the volume and tone will be adjusted based on the analysis results of the emotion engine. The device will then check whether the user has woken up via the smartwatch or motion sensor and stop the alarm.

[0900] Hardware or software used

[0901] Hardware: Smartphones, smartwatches, motion sensors

[0902] Software: Google Speech Recognition API, TextBlob, generative AI model, emotion engine program

[0903] Specific examples

[0904] For example, consider a delivery person saying, "I'm pretty tired this morning. I'd like to take a break." The voice command is converted into text using voice recognition technology. The server then analyzes the text data using a generative AI model to assess the fatigue level. If high fatigue is detected, the system suggests a break in 30 minutes and sets a gentle alarm at an appropriate time. After 30 minutes, the smartphone will sound a gentle alarm, and the delivery person's return from the break will be confirmed on the smartwatch. In this way, the system effectively supports the delivery person's health management.

[0905] Examples of prompt statements

[0906] Please describe your current state in detail. For example, describe your feelings such as "I'm tired" or "I'm sleepy."

[0907] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0908] Step 1:

[0909] Device: The user (delivery person) verbally commands, "I feel tired" or "I need a break." This is the input. The device accepts the voice command. Speech recognition technology (e.g., Google Speech Recognition API) is used here. The voice input is sent to the device as audio data.

[0910] Step 2:

[0911] Terminal: The terminal converts the received voice data into text data using voice recognition technology. Specifically, the voice recognition engine analyzes the voice data and generates the corresponding text data. The input is voice data, and the output is text data.

[0912] Step 3:

[0913] Server: The converted text data is sent to the server. The server uses the generative AI model to analyze the text data. The specific data processing involves extracting emotional information from the text data using natural language processing technology. The input is text data, and the output is emotional information.

[0914] Step 4:

[0915] Server: The server uses an emotion engine to evaluate the emotion information and determine the user's fatigue and stress levels. In this process, the emotion engine analyzes keywords and tones in the text data and scores the emotional state. The input is emotion information, and the output is an emotion score.

[0916] Step 5:

[0917] Server: If the emotion score is high, schedule a break. The break time setting suggests an appropriate break timing, such as the next 30 minutes. The input is the emotion score, and the output is the break schedule. Specific operations include calculating the break time.

[0918] Step 6:

[0919] Server: Sets an alarm when the scheduled break time arrives. The volume and tone of the alarm are adjusted based on the evaluation results of the emotion engine. Specifically, if the emotion score is high, a gentler sound is selected. The input is the break schedule and emotion score, and the output is the adjusted alarm setting.

[0920] Step 7:

[0921] Terminal: When it is time for a break, the terminal will activate an alarm. The specific behavior is to notify the user using an alarm sound or vibration. The input is the alarm setting, and the output is the alarm notification.

[0922] Step 8:

[0923] Device: Checks whether the user has woken up via a smartwatch or motion sensor. Specifically, the sensor detects the user's movement and confirms that the user has woken up. The input is sensor data, and the output is the wake-up confirmation result.

[0924] Step 9:

[0925] Server: Once the wake-up is confirmed, the alarm is stopped. Specifically, the server sends a stop command to the terminal. The input is the wake-up confirmation result, and the output is the alarm stop.

[0926] This completes the entire process and effectively manages fatigue among food delivery personnel.

[0927] 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.

[0928] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0929] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0930] [Third embodiment]

[0931] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0932] 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.

[0933] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0934] 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.

[0935] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0936] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0937] 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.

[0938] 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.

[0939] 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 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.

[0940] 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.

[0941] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0942] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0943] The present invention is a system that improves a user's daily rhythm and assists in waking up efficiently. This system sets an alarm based on the user's voice instruction and continues to operate until the alarm wakes the user up. Furthermore, it has a function that uses a smartwatch or a motion sensor to confirm whether the user is actually awake, and optimizes the system through feedback. A specific embodiment of this system is shown below.

[0944] System Overview

[0945] 1. Accepting and converting voice commands

[0946] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6am tomorrow morning" or "Set the alarm for 7am every Monday morning, except for 8am on public holidays."

[0947] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[0948] 2. Text data analysis and alarm setting

[0949] (Terminal) The converted text data is sent to the server.

[0950] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and conditions.

[0951] For example, it can handle complex settings such as "set the alarm for 6:30 every Monday, and for 7:00 if the previous day is a holiday."

[0952] 3. Triggering and continuing alarms

[0953] (Device) When the set alarm time arrives, the device will activate the alarm, notifying the user with sound, vibration, or both.

[0954] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[0955] 4. Receiving and analyzing feedback

[0956] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm went off at the right time" or "The alarm was too loud" through the app.

[0957] (Server) The server receives this feedback and the generating AI analyzes it, which then optimizes future alarm settings.

[0958] Specific examples

[0959] Specific examples are given below.

[0960] Example 1:

[0961] (User) The user instructs, "Set it to wake me up at 7:00 tomorrow."

[0962] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[0963] (Server) The generation AI analyzes the text data and extracts the information "Set the alarm for 7am the next morning."

[0964] (Device) The alarm will start ringing at 7am the next morning. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[0965] Example 2:

[0966] (User) The user instructs "Wake me up at 6:00 every Monday." He also adds, "However, if it is a public holiday, wake me up at 7:00."

[0967] (Device) The voice recognition function converts voice into text data.

[0968] (Server) The generation AI analyzes the text data and processes the condition "Set the alarm at 6:00 every Monday, but set it to 7:00 on holidays."

[0969] (Device) The alarm is set for 6:00 AM on the following Monday. If a public holiday falls on the same day, the alarm will go off at 7:00 AM.

[0970] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle.

[0971] The processing flow will be explained below.

[0972] Step 1:

[0973] (User) The user issues a voice command to set the alarm, saying, "Set the alarm for 7:00 tomorrow morning."

[0974] Step 2:

[0975] (Device) The device's microphone captures the user's voice instructions, and the internal voice recognition engine converts the voice data into text data.

[0976] Step 3:

[0977] (Terminal) The terminal sends the converted text data to the server.

[0978] Step 4:

[0979] (Server) The server's generated AI receives the text data and analyzes it. During the analysis, it extracts the instruction content ("Set an alarm for 7am tomorrow") and clarifies the specific date and time and setting conditions.

[0980] Step 5:

[0981] (Server) The generation AI generates alarm setting information (date and time: tomorrow at 7:00, repetition: none, special conditions: none) based on the conditions.

[0982] Step 6:

[0983] (Server) Sends the generated alarm setting information to the terminal.

[0984] Step 7:

[0985] (Device) Based on the received alarm setting information, the device registers the alarm in its internal calendar app or alarm function.

[0986] Step 8:

[0987] (Device) When the set alarm time approaches, the device will activate the alarm.

[0988] Step 9:

[0989] (Device) The alarm will start ringing and notify the user with sound and vibration.

[0990] Step 10:

[0991] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[0992] Step 11:

[0993] (Smartwatch / Motion Sensor) If it determines that the user has woken up, it sends a signal to the device to stop the alarm.

[0994] Step 12:

[0995] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[0996] Step 13:

[0997] (User) After waking up, the user provides feedback on the effectiveness of the alarm through the app, such as "The alarm was just right" or "The alarm was too loud."

[0998] Step 14:

[0999] (Device) The device sends the user's feedback to the server.

[1000] Step 15:

[1001] (Server) The server receives the feedback, and the generating AI analyzes it. Based on the feedback, it optimizes future alarm settings.

[1002] Example 1

[1003] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1004] For many people living busy lives in modern society, maintaining a regular rhythm and waking up efficiently is important. However, existing alarm systems lack a means to accurately confirm the user's wake-up status, making it difficult to reliably wake them up. Furthermore, the flexibility of alarm settings is limited, making it difficult to meet individual user needs. Furthermore, there is no well-established mechanism for effectively utilizing feedback to optimize the system, making it difficult to provide optimal alarm settings for each individual user.

[1005] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1006] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for confirming the user's wakefulness in cooperation with a smartwatch or a motion sensor, and means for receiving feedback provided by the user and analyzing it using a generative AI model. This allows the system to set an appropriate alarm based on the user's individual needs, helping the user wake up reliably, and enabling system optimization based on the feedback.

[1007] "Means for receiving voice instructions from the user" refers to devices or software that receive voice instructions when a user gives voice instructions to the system in natural language to set alarms or perform other operations.

[1008] The "means for converting voice instructions into text data" refers to a device or software that recognizes received voice instructions and converts the content into text format, such as a voice recognition engine.

[1009] "Means for analyzing text data and setting alarms based on the date, time, and conditions" refers to a device or software that analyzes the converted text data and sets appropriate alarms based on the date, time, and conditions specified by the user.

[1010] "Means for activating an alarm at a set date and time" refers to a device or software that activates an alarm using sound, vibration, or other means at a set date and time.

[1011] "Means for keeping the alarm going until the user wakes up" refers to a device or software that keeps the alarm set so that it does not stop until the user actually wakes up.

[1012] "Means for verifying user alertness in conjunction with a smartwatch or motion sensor" refers to devices or software that use data from a smartwatch or motion sensor to verify the user's physical movement and alertness.

[1013] "Means for receiving and analyzing user-provided feedback using a generative AI model" refers to devices or software that receive user feedback, analyze it using a generative AI model, and optimize system performance or settings.

[1014] This invention is a system for improving a user's daily rhythm and helping them wake up efficiently. The system aims to allow the user to set an alarm by voice and operate until the alarm wakes the user up reliably. Furthermore, it has a function for optimizing the system through feedback.

[1015] System Overview

[1016] 1. Accepting voice commands

[1017] (User) The user gives instructions to the system in natural language to set an alarm, such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[1018] (Device) The device uses voice recognition software (e.g., Google Speech-to-Text API) to convert the user's voice into text data.

[1019] 2. Text Data Analysis

[1020] (Terminal) The converted text data is sent to the server.

[1021] (Server) The generative AI model (e.g., OpenAI GPT-4) deployed on the server analyzes the text data sent and sets alarms based on the user's instructions. This analysis extracts the date, time, and conditions.

[1022] 3. Alarm settings and operation

[1023] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[1024] (Device) The device will activate the alarm with sound or vibration when the set alarm time arrives.

[1025] (Smartwatch / Motion Sensor) In addition, a smartwatch (e.g., Apple Watch) or a motion sensor can be used to monitor the user's waking state and the alarm will continue until the user wakes up.

[1026] 4. Receiving and analyzing feedback

[1027] (User) After the alarm is stopped, the user provides feedback through the smartphone app, such as "The alarm was appropriate" or "The alarm was too loud."

[1028] (Server) The server receives user feedback and the generative AI model analyzes it, allowing for future optimization of alarm settings.

[1029] Specific examples

[1030] A specific example will be given below.

[1031] Example 1:

[1032] (User) The user instructs, "Wake me up at 7 o'clock tomorrow."

[1033] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[1034] (Server) The generating AI analyzes and extracts the information "Set the alarm for 7am the next morning."

[1035] (Device) The alarm will start ringing at 7:00 the next morning. When the user wakes up, the smartwatch detects their movement and sends a signal to the device to stop the alarm, which stops the alarm.

[1036] Example 2:

[1037] (User) The user instructs, "Wake me up at 6:00 every Monday, except on public holidays, at 7:00."

[1038] (Device) The voice recognition function converts voice into text data.

[1039] (Server) The generation AI analyzes and extracts the condition "Set the alarm for 6:00 every Monday, but for holidays, set it for 7:00."

[1040] (Device) The alarm will ring at 6:00 a.m. the following Monday, or 7:00 a.m. if a public holiday falls on the same day.

[1041] As described above, the system of the present invention efficiently supports the user's life rhythm and promotes a healthy lifestyle.

[1042] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1043] Step 1:

[1044] (User) The user issues a voice command to the system, such as "Wake me up at 6am tomorrow morning."

[1045] Input: User's voice command

[1046] Output: Audio data received by the device's microphone

[1047] Specific operation: When the user speaks into the device's microphone, the device picks up the audio.

[1048] Step 2:

[1049] (Device) The device converts the voice into text data using voice recognition software (e.g., Google Speech-to-Text API).

[1050] Input: Audio data

[1051] Output: Text data

[1052] What happens: The speech recognition engine analyzes the audio data and converts it into a corresponding text representation.

[1053] Step 3:

[1054] (Terminal) The terminal sends the converted text data to the server.

[1055] Input: Text data

[1056] Output: Text data sent to the server

[1057] What happens: Text data is sent to a server over an internet connection.

[1058] Step 4:

[1059] (Server) The server analyzes the text data using a generative AI model (e.g., OpenAI GPT-4) to extract date, time, and alarm setting information.

[1060] Input: Text data

[1061] Output: Analyzed alarm setting information (date and time and conditions)

[1062] Specific operation: The generative AI model analyzes the text data and extracts the date, time, and conditions specified by the user.

[1063] Step 5:

[1064] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[1065] Input: Parsed alarm setting information

[1066] Output: A data packet containing configuration information

[1067] Specific operation: The server generates a data packet containing instructions for setting an alarm and sends it to the device.

[1068] Step 6:

[1069] (Device) When the set time arrives, the device will activate an alarm.

[1070] Input: Set alarm information

[1071] Output: Alarm activation (sound, vibration, etc.)

[1072] Specific action: The device will emit an alarm or vibrate at the specified date and time.

[1073] Step 7:

[1074] (Smartwatch / motion sensor) A smartwatch or motion sensor checks whether the user is awake.

[1075] Input: User movement and environmental data

[1076] Output: Awakening confirmation data

[1077] What it does: The smartwatch monitors your movements and notifies your device when movement is detected.

[1078] Step 8:

[1079] (Device) When the user is confirmed awake, the alarm will stop.

[1080] Input: Awakening confirmation data

[1081] Output: Stop alarm

[1082] Specific operation: The device receives data from the smartwatch and stops the alarm.

[1083] Step 9:

[1084] (User) The user provides feedback through the smartphone app, for example, "The alarm was appropriate" or "The alarm was too loud."

[1085] Input: User feedback

[1086] Output: Feedback data entered into the smartphone app

[1087] What happens: A user uses the app's feedback feature to provide a rating.

[1088] Step 10:

[1089] (Server) The server receives the feedback and analyzes it using a generative AI model.

[1090] Input: Feedback data

[1091] Output: Analysis results and optimization information

[1092] What it does: A generative AI model analyzes feedback data and generates information to optimize system settings.

[1093] (Application example 1)

[1094] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1095] Conventional alarm systems only notified users at a time specified by the user, and did not adequately check the user's behavior or optimize the system based on feedback. Furthermore, in physical stores, there was no system in place to ensure that staff were awake and ready to work when it came to shift management. This resulted in staff being late or not performing their shifts, leading to problems with reduced work efficiency.

[1096] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1097] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for using a smartwatch to confirm the user's wakefulness and send a reminder before the user starts work, means for providing alarm setting and reminder functions specialized for store staff shift management, and means for receiving and analyzing feedback provided by the user. This improves the user's lifestyle and enables more efficient and reliable staff shift management in physical stores.

[1098] A "user" is an individual who uses the system to set alarms and receive wake-up and shift management notifications.

[1099] A "means for accepting voice instructions" is a device or system for recognizing and processing voice input from a user.

[1100] The "means for converting voice instructions into text data" is software or algorithms that use voice recognition technology to convert received voice into text data.

[1101] "Means for analyzing text data and setting alarms based on date, time, and conditions" refers to software or a process that extracts necessary information from the analyzed text data and sets the alarm date, time, and conditions based on that information.

[1102] The "means for activating an alarm at a set date and time" refers to software or hardware for triggering an alarm at a specified date and time and issuing a notification.

[1103] "Means for keeping the alarm going until the user wakes up" refers to the mechanism or process for keeping the alarm notification going until the user is sure to wake up.

[1104] "Method for utilizing a smartwatch to detect when a user is awake and send a reminder before the start of a shift" means a system or method for using a sensor in a smartwatch to detect when a user is awake and send a reminder notification before the start of a shift.

[1105] "A means for providing alarm setting and reminder functions specialized for store staff shift management" refers to software or a system for managing the shift schedules of staff working in physical stores and providing alarms and reminders at appropriate times.

[1106] "Means for receiving and analyzing feedback" refers to the mechanisms and processes used to collect feedback provided by users and analyze that data to optimize the system.

[1107] The system for implementing this invention has the ability to accept voice commands, set an alarm based on those commands, and keep the alarm running until the user wakes up. It also uses a smartwatch or motion sensor to check whether the user is awake and optimizes the system based on the feedback.

[1108] System configuration

[1109] 1. Accepting voice commands

[1110] The user issues natural language voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[1111] 2. Speech Recognition and Text Conversion

[1112] The device converts voice instructions received through a voice input device (e.g., a head-mounted display with a microphone) into text data using a voice recognition API. This text data is used as basic information for the entire system.

[1113] 3. Text data analysis and alarm setting

[1114] The converted text data is sent to a server, which uses a generative AI model to analyze the text data and set alarms based on the date, time, and other conditions.

[1115] 4. Alarm triggers and reminders

[1116] At the set time and date, the device will activate an alarm that will notify the user via sound, vibration, or both. Additionally, the smartwatch will be used to check the user's alertness and send reminders before the start of their shift.

[1117] 5. Confirmation of wake-up and alarm stop

[1118] Smartwatches and motion sensors monitor when a user wakes up and continue to ring the alarm until the user confirms they are awake, at which point the alarm automatically stops.

[1119] 6. Receiving and analyzing feedback

[1120] After the alarm is stopped, the user can provide feedback to the system, for example, by sending a comment through the app such as "The alarm was too loud." The server uses a feedback analysis system to analyze this data and optimize future alarm settings.

[1121] Specific examples

[1122] As a specific example of this system, the following case can be given.

[1123] Example 1: A user issues a voice command such as "I want to be woken up at 6:00 AM next Saturday." This command is converted into text data by a speech recognition API, and the generative AI model analyzes it to set an alarm for "6:00 AM next Saturday."

[1124] Example 2: As an application example of staff shift management in a brick-and-mortar store, a smartwatch is used to send wake-up reminders to staff before they start their shift. Shift schedules are set through voice commands, and wake-up confirmation is performed on the smartwatch.

[1125] Prompt Sentence Examples

[1126] If a user requests "I want to be woken up at 6 AM next Saturday," the voice recognition API converts this into text data and sets an alarm for "6 AM next Saturday." The alarm will ring at the specified time, and the smartwatch will confirm that the user has woken up. The alarm will continue until the user has woken up, and feedback will be collected.

[1127] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1128] Step 1:

[1129] The user issues voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[1130] Input: User's voice command

[1131] Output: Audio data (analog signal)

[1132] Step 2:

[1133] The device collects the received voice data through a voice input device (a head-mounted display with a microphone) and converts the voice data into text data using a voice recognition API.

[1134] Input: Audio data (analog signal)

[1135] Output: Text data (digital format)

[1136] Step 3:

[1137] The converted text data is sent from the device to a server, which then analyzes the text data using a generative AI model to extract the necessary date, time, and condition information from the instructions.

[1138] Input: Text data (digital format)

[1139] Output: Analysis results (date and time, conditions)

[1140] Step 4:

[1141] The server generates an alarm schedule based on the extracted date and time and conditions, and transmits the information to the terminal.

[1142] Input: Analysis results (date and time, conditions)

[1143] Output: Alarm schedule

[1144] Step 5:

[1145] At the set date and time, the device will activate an alarm, which will notify the user by sound, vibration, or both.

[1146] Input: Alarm Schedule

[1147] Output: Alarm notification (sound, vibration)

[1148] Step 6:

[1149] At the same time as the alarm goes off, the smartwatch activates sensors to detect the user's movement and monitors their state of wakefulness.

[1150] Input: alarm notification, user movement data

[1151] Output: Awakening state information

[1152] Step 7:

[1153] If the user is awake, the smartwatch sends the information to the device, which then stops the alarm. If the user does not wake up, the alarm continues to ring.

[1154] Input: Awakening state information

[1155] Output: Alarm stop signal

[1156] Step 8:

[1157] After the alarm is stopped, the user provides feedback to the system, for example, by sending a comment such as "The alarm was too loud" through the app.

[1158] Input: User feedback

[1159] Output: Feedback data

[1160] Step 9:

[1161] The server analyzes the collected feedback data using a feedback analysis system to find improvements to optimize the system's performance.

[1162] Input: Feedback data

[1163] Output: Analysis results (improvement points)

[1164] This will improve users' daily routines and also make staff shift management in physical stores more efficient and reliable.

[1165] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1166] The present invention is a system that provides a user with sleep management and effective wake-up support, and further combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on the emotions. Specific embodiments of the present invention are described in detail below.

[1167] System Overview

[1168] 1. Accepting and converting voice commands

[1169] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[1170] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[1171] 2. Text data analysis and alarm setting

[1172] (Terminal) The converted text data is sent to the server.

[1173] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and other conditions. This makes it possible to set alarms based on complex conditions.

[1174] 3. Emotion analysis using an emotion engine

[1175] (Server) The generation AI recognizes the user's emotions from the text data, and the emotion engine analyzes it to understand the user's stress level and emotional state based on the user's tone and the words used.

[1176] For example, feedback such as "I want to wake you up again at 6 tomorrow morning, but the volume was too loud last time" can help us recognize that the user was dissatisfied with the previous alarm.

[1177] 4. Triggering and Continuing Alarms

[1178] (Device) When the set alarm time arrives, the device will activate the alarm. The alarm will notify the user by sound, vibration, or both. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[1179] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[1180] 5. Receiving and analyzing feedback

[1181] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm was just right" or "The alarm was too loud" through the app.

[1182] (Server) The server receives this feedback and the emotion engine analyzes it. Evaluations and improvements based on the user's emotions are extracted, and future alarm settings are optimized.

[1183] Specific examples

[1184] Specific examples are given below.

[1185] Example 1:

[1186] (User) The user instructs, "I want to be woken up at 7:00 tomorrow. However, the previous alarm sound was too loud and annoying."

[1187] (Device) The voice recognition function converts voice into text data.

[1188] (Server) The generation AI analyzes the text data and extracts the information, such as "set the alarm for 7am the next day and lower the volume," and the emotion engine recognizes the user's discomfort.

[1189] (Device) The next morning, the alarm will start ringing at 7:00 AM, with the volume set to an appropriate level based on the emotion engine analysis. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[1190] Example 2:

[1191] (User) The user instructs, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[1192] (Device) The voice recognition function converts voice into text data.

[1193] (Server) The generation AI analyzes the text data, and the emotion engine analyzes the user's gloomy emotions to understand setting information such as "Set the alarm for 6:00 every Monday, but notify gently."

[1194] (Device) The alarm will ring at 6am next Monday morning, but the notification method will be set to a soft, pleasant sound or vibration.

[1195] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle through emotion-based optimization.

[1196] The processing flow will be explained below.

[1197] Step 1:

[1198] (User) The user verbally instructs, "Set the alarm for 7:00 tomorrow morning, but the volume was too loud last time."

[1199] Step 2:

[1200] (Device) The device's microphone captures the user's voice commands and sends them to the internal voice recognition engine.

[1201] Step 3:

[1202] (Terminal) The voice recognition engine converts the voice data into text data and sends the text data to the server.

[1203] Step 4:

[1204] (Server) The generation AI installed on the server analyzes the received text data and extracts the instructions ("Set the alarm for 7am tomorrow morning" or "The volume was too loud last time").

[1205] Step 5:

[1206] (Server) The emotion engine analyzes the user's emotions from their instructions. For example, from the part "The volume was too loud last time," it recognizes that the user is dissatisfied with the previous alarm setting.

[1207] Step 6:

[1208] (Server) The generation AI takes into account the analysis results of the emotion engine and generates optimal alarm setting information, such as "Date and time: 7:00 the next day" and "Volume: Low."

[1209] Step 7:

[1210] (Server) Sends the generated alarm setting information to the terminal.

[1211] Step 8:

[1212] (Device) Based on the setting information received by the device, an alarm is registered in the internal calendar app or alarm function.

[1213] Step 9:

[1214] (Device) When the set alarm time approaches, the device will activate the alarm.

[1215] Step 10:

[1216] (Device) The alarm will start ringing and notify the user with sound and vibration. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[1217] Step 11:

[1218] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[1219] Step 12:

[1220] (Smartwatch) When it determines that the user has woken up, the smartwatch sends a signal to the device to stop the alarm.

[1221] Step 13:

[1222] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[1223] Step 14:

[1224] (User) After waking up, the user provides feedback through the app about the effectiveness of the alarm and areas for improvement, such as "The alarm volume this time was just right."

[1225] Step 15:

[1226] (Device) The device sends the user's feedback to the server.

[1227] Step 16:

[1228] (Server) The server receives the feedback, analyzes it with an emotion engine, evaluates it based on the user's emotions, and generates data to be reflected in future alarm settings.

[1229] Example 2

[1230] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1231] Conventional alarm systems often provide alarms in a uniform manner without considering the user's emotions or feedback, resulting in low user satisfaction. Furthermore, they lack a means to properly monitor whether the user is actually awake, making it difficult to provide effective sleep management and wake-up support. Therefore, it is necessary to provide a system that recognizes the user's emotions and sets alarms that reflect their feedback.

[1232] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1233] In this invention, the server includes means for recognizing and analyzing user emotions, means for optimizing alarm settings based on said emotions, and means for receiving and analyzing feedback provided by the user, thereby enabling optimal alarm settings based on individual user emotions and feedback.

[1234] "User" refers to an individual who uses this system to receive sleep management and wake-up support.

[1235] "Voice instructions" refers to instructions or commands given by a user to a system through voice.

[1236] "Text data" refers to character string information converted from voice instructions using voice recognition technology.

[1237] "Analysis" refers to the process of analyzing received text data and feedback data to understand its content.

[1238] "Alarm" refers to a notification method set by the system to help the user wake up.

[1239] "Emotion" refers to the psychological state or feelings that users express through their speech and feedback.

[1240] An "emotion engine" refers to an analysis system that recognizes emotions from users' text data and optimizes settings based on that information.

[1241] "Smart devices" refers to electronic devices with internet connectivity and sensors, such as smartwatches and smartphones.

[1242] "Motion sensor" refers to a sensor unit that detects human movement and provides that information to the system.

[1243] The present invention is a system for providing users with sleep management and effective wake-up support, which combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on those emotions.

[1244] System configuration

[1245] 1. Hardware Configuration

[1246] (Terminal) This system uses a terminal (e.g., smartphone, smart speaker) to receive user voice commands. The terminal has a microphone for voice recognition and Internet connectivity.

[1247] (Smart devices / motion sensors) Furthermore, it works in conjunction with smart devices (e.g., smartwatches) and motion sensors (e.g., human sensors) to detect user movements.

[1248] 2. Software Configuration

[1249] (Voice recognition software) The device is installed with voice recognition software (e.g., Google Assistant, Amazon Alexa). This software converts the user's voice into text data in real time.

[1250] (Generative AI model) The server is equipped with a generative AI model (e.g., GPT-4) that analyzes text data and optimizes alarm settings based on date, time, and other conditions.

[1251] (Emotion engine) An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) is installed on the server, which recognizes and analyzes user emotions from text data.

[1252] Data processing and calculation

[1253] (Terminal) The terminal receives voice instructions from the user, converts them into text data using voice recognition software, and sends it to the server.

[1254] (Server) The server uses a generative AI model to analyze the text data and extract alarm setting information based on the date, time, and conditions. It also uses an emotion engine to analyze the user's emotions and optimize the alarm settings.

[1255] (Feedback Analysis) The server also receives feedback from users and analyzes it with the emotion engine. The results of this feedback analysis are used to further optimize future alarm settings.

[1256] Specific examples

[1257] Example 1:

[1258] (User) says, "I want to be woken up at 7:00 tomorrow. However, the previous alarm was too loud and annoying."

[1259] (Device) Use the voice recognition function to convert voice into text.

[1260] (Server) The generative AI model analyzes the text and extracts the information, "Set the alarm for 7am the next day and lower the volume." The emotion engine recognizes the user's discomfort.

[1261] (Device) The alarm will start ringing at 7am the next morning, with the volume set to an appropriate adjusted level.

[1262] Example 2:

[1263] (User) gives the command, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[1264] (Device) Use the voice recognition function to convert voice into text.

[1265] (Server) The generative AI model analyzes the text and determines, "Set an alarm for 6:00 every Monday, but gently." The emotion engine recognizes the user's depressed emotion.

[1266] (Device) At 6:00 AM the following Monday morning, the alarm will sound and vibrate to gently wake the user.

[1267] The above is an embodiment of the invention. This system realizes flexible and effective wake-up support that reflects the user's emotions and feedback.

[1268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1269] Step 1:

[1270] (User) The user gives instructions to set the alarm by voice.

[1271] Specific operation: The user speaks into the device, "Please wake me up at 6am tomorrow morning."

[1272] Input: User's voice command.

[1273] Output: Audio data.

[1274] Step 2:

[1275] (Terminal) The terminal uses voice recognition software to convert the voice data into text data.

[1276] What it does: Speech recognition software (e.g., Google Assistant) converts the user's speech into text, such as "Wake me up at 6am tomorrow morning."

[1277] Input: Audio data.

[1278] Output: Text data.

[1279] Step 3:

[1280] (Terminal) The converted text data is sent to the server.

[1281] Specific operation: Send text data to the server using an HTTP request.

[1282] Input: Text data.

[1283] Output: Text data is sent.

[1284] Step 4:

[1285] (Server) Analyzes text data using a generative AI model to extract dates, times, and conditions.

[1286] Specific operation: A generative AI model (e.g., GPT-4) analyzes the date and time "6:00 AM tomorrow" and the instruction "Wake me up."

[1287] Input: Text data.

[1288] Output: Alarm setting condition.

[1289] Step 5:

[1290] (Server) Analyze user emotions using an emotion engine.

[1291] Specific operation: An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) analyzes the user's emotions from text data and understands the user's psychological state.

[1292] Input: Text data.

[1293] Output: The user's emotional state.

[1294] Step 6:

[1295] (Server) Optimize alarm settings based on analysis results.

[1296] Specific behavior: Adjust the alarm volume and notification method based on the results of the emotion engine.

[1297] Input: Alarm setting conditions, user's emotional state.

[1298] Output: Optimized alarm settings.

[1299] Step 7:

[1300] (Server) Sends optimized alarm settings to the device.

[1301] Specific operation: Alarm setting information is returned to the terminal as an HTTP response.

[1302] Input: Optimized alarm settings.

[1303] Output: Alarm setting information.

[1304] Step 8:

[1305] (Device) The alarm will start when the set alarm time arrives.

[1306] Specific operation: An alarm sound or vibration will be generated at the specified time.

[1307] Input: Alarm setting information.

[1308] Output: Triggering an alarm.

[1309] Step 9:

[1310] (Smart device / motion sensor) Monitors whether the user is awake.

[1311] Specific operation: The smartwatch or motion sensor detects the user's movements and confirms that they have woken up.

[1312] Input: User behavior data.

[1313] Output: The user's wake-up status.

[1314] Step 10:

[1315] (User) Provide feedback after the alarm stops.

[1316] Specific behavior: The user enters feedback through the app, such as "The alarm was too loud."

[1317] Input: User feedback.

[1318] Output: Feedback data.

[1319] Step 11:

[1320] (Server) Analyze the feedback data and optimize future alarm settings.

[1321] Specific operation: The emotion engine analyzes the feedback and reflects it in the next alarm setting.

[1322] Input: Feedback data.

[1323] Output: Optimized alarm setting information.

[1324] (Application example 2)

[1325] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1326] In conventional food delivery services, there was a lack of adequate management of fatigue and stress among delivery personnel, which led to a decline in work efficiency and customer satisfaction.In addition, there was no system in place to effectively schedule delivery personnel's refreshment time and encourage them to take breaks at the optimal timing.

[1327] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1328] In this invention, the server includes means for receiving voice instructions from the user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on the date, time, and conditions, means including an emotion engine for analyzing the emotional state of the delivery person and detecting fatigue or stress, means for scheduling break times, means for activating the alarm at the set date and time, and means for continuing the alarm until the user wakes up. This makes it possible to monitor the emotional state of the delivery person and provide optimal refreshment time, thereby improving work efficiency and customer satisfaction.

[1329] "User" is a term that refers to a user of a food delivery service or a delivery person.

[1330] "Voice commands" is a term that refers to voice commands given by a user to a system.

[1331] "Text data" is a term that refers to data in which voice instructions are converted into text information.

[1332] "Analysis" is a term that refers to the act of evaluating dates, times, conditions, and even emotional states based on text data.

[1333] "Alarm" is a term that refers to a sound or vibration that is activated at a set date and time to notify the user.

[1334] "Emotion engine" is a term used to describe a system that recognizes and evaluates a user's emotional state from text data.

[1335] "Rest time" is a term that refers to the time a delivery person takes to rest.

[1336] "Scheduling" is a term that refers to the act of setting optimal rest times based on various conditions.

[1337] "Smart device" is a term that refers to devices that sense the user's actions and status, such as smartwatches and smartphones.

[1338] "Human presence sensor" is a term that refers to a sensor that detects surrounding movements and actions.

[1339] "Feedback" is a term that refers to the evaluations and opinions that users provide to a system.

[1340] "Food delivery service" is a term that refers to a service that delivers meals or food to a location specified by the customer.

[1341] "Delivery person" is a term used to refer to the staff member in a food delivery service who is responsible for actually delivering the goods.

[1342] The present invention provides a system for managing fatigue of delivery personnel in a food delivery service and efficiently notifying them of refreshment times. An embodiment of the present invention will be described in detail below.

[1343] System Overview

[1344] The present invention consists of a system that accepts a user's voice instructions, converts them into text data, analyzes them using an emotion engine, and schedules appropriate break times.

[1345] 1. Accepting and converting voice commands

[1346] Device: The user (delivery person) issues voice instructions to the system. For example, they might say, "I feel tired" or "I need a break." The device then uses voice recognition technology (e.g., Google Speech Recognition API) to convert the voice instructions into text data.

[1347] 2. Text data analysis and alarm setting

[1348] Server: The converted text data is sent to the server and analyzed using a generative AI model. The emotion engine recognizes the user's emotional state and performs analysis. For example, if the user says "I'm tired," the emotion engine will detect a high stress level.

[1349] 3. Analysis by Emotion Engine

[1350] Server: The server evaluates fatigue and stress levels from text data and schedules breaks. For example, it might suggest a delivery person with a high stress level take a break in 30 minutes.

[1351] 4. Triggering and Continuing Alarms

[1352] Device: When the scheduled break time arrives, the device will activate an alarm. The alarm will notify you with sound and vibration, and the volume and tone will be adjusted based on the analysis results of the emotion engine. The device will then check whether the user has woken up via the smartwatch or motion sensor and stop the alarm.

[1353] Hardware or software used

[1354] Hardware: Smartphones, smartwatches, motion sensors

[1355] Software: Google Speech Recognition API, TextBlob, generative AI model, emotion engine program

[1356] Specific examples

[1357] For example, consider a delivery person saying, "I'm pretty tired this morning. I'd like to take a break." The voice command is converted into text using voice recognition technology. The server then analyzes the text data using a generative AI model to assess the fatigue level. If high fatigue is detected, the system suggests a break in 30 minutes and sets a gentle alarm at an appropriate time. After 30 minutes, the smartphone will sound a gentle alarm, and the delivery person's return from the break will be confirmed on the smartwatch. In this way, the system effectively supports the delivery person's health management.

[1358] Examples of prompt statements

[1359] Please describe your current state in detail. For example, describe your feelings such as "I'm tired" or "I'm sleepy."

[1360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1361] Step 1:

[1362] Device: The user (delivery person) verbally commands, "I feel tired" or "I need a break." This is the input. The device accepts the voice command. Speech recognition technology (e.g., Google Speech Recognition API) is used here. The voice input is sent to the device as audio data.

[1363] Step 2:

[1364] Terminal: The terminal converts the received voice data into text data using voice recognition technology. Specifically, the voice recognition engine analyzes the voice data and generates the corresponding text data. The input is voice data, and the output is text data.

[1365] Step 3:

[1366] Server: The converted text data is sent to the server. The server uses the generative AI model to analyze the text data. The specific data processing involves extracting emotional information from the text data using natural language processing technology. The input is text data, and the output is emotional information.

[1367] Step 4:

[1368] Server: The server uses an emotion engine to evaluate the emotion information and determine the user's fatigue and stress levels. In this process, the emotion engine analyzes keywords and tones in the text data and scores the emotional state. The input is emotion information, and the output is an emotion score.

[1369] Step 5:

[1370] Server: If the emotion score is high, schedule a break. The break time setting suggests an appropriate break timing, such as the next 30 minutes. The input is the emotion score, and the output is the break schedule. Specific operations include calculating the break time.

[1371] Step 6:

[1372] Server: Sets an alarm when the scheduled break time arrives. The volume and tone of the alarm are adjusted based on the evaluation results of the emotion engine. Specifically, if the emotion score is high, a gentler sound is selected. The input is the break schedule and emotion score, and the output is the adjusted alarm setting.

[1373] Step 7:

[1374] Terminal: When it is time for a break, the terminal will activate an alarm. The specific behavior is to notify the user using an alarm sound or vibration. The input is the alarm setting, and the output is the alarm notification.

[1375] Step 8:

[1376] Device: Checks whether the user has woken up via a smartwatch or motion sensor. Specifically, the sensor detects the user's movement and confirms that the user has woken up. The input is sensor data, and the output is the wake-up confirmation result.

[1377] Step 9:

[1378] Server: Once the wake-up is confirmed, the alarm is stopped. Specifically, the server sends a stop command to the terminal. The input is the wake-up confirmation result, and the output is the alarm stop.

[1379] This completes the entire process and effectively manages fatigue among food delivery personnel.

[1380] 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.

[1381] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1382] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1383] [Fourth embodiment]

[1384] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1385] 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.

[1386] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[1387] 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.

[1388] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1389] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1390] 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.

[1391] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1392] 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.

[1393] 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 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.

[1394] 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.

[1395] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1396] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1397] The present invention is a system that improves a user's daily rhythm and assists in waking up efficiently. This system sets an alarm based on the user's voice instruction and continues to operate until the alarm wakes the user up. Furthermore, it has a function that uses a smartwatch or a motion sensor to confirm whether the user is actually awake, and optimizes the system through feedback. A specific embodiment of this system is shown below.

[1398] System Overview

[1399] 1. Accepting and converting voice commands

[1400] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6am tomorrow morning" or "Set the alarm for 7am every Monday morning, except for 8am on public holidays."

[1401] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[1402] 2. Text data analysis and alarm setting

[1403] (Terminal) The converted text data is sent to the server.

[1404] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and conditions.

[1405] For example, it can handle complex settings such as "set the alarm for 6:30 every Monday, and for 7:00 if the previous day is a holiday."

[1406] 3. Triggering and continuing alarms

[1407] (Device) When the set alarm time arrives, the device will activate the alarm, notifying the user with sound, vibration, or both.

[1408] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[1409] 4. Receiving and analyzing feedback

[1410] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm went off at the right time" or "The alarm was too loud" through the app.

[1411] (Server) The server receives this feedback and the generating AI analyzes it, which then optimizes future alarm settings.

[1412] Specific examples

[1413] Specific examples are given below.

[1414] Example 1:

[1415] (User) The user instructs, "Set it to wake me up at 7:00 tomorrow."

[1416] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[1417] (Server) The generation AI analyzes the text data and extracts the information "Set the alarm for 7am the next morning."

[1418] (Device) The alarm will start ringing at 7am the next morning. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[1419] Example 2:

[1420] (User) The user instructs "Wake me up at 6:00 every Monday." He also adds, "However, if it is a public holiday, wake me up at 7:00."

[1421] (Device) The voice recognition function converts voice into text data.

[1422] (Server) The generation AI analyzes the text data and processes the condition "Set the alarm at 6:00 every Monday, but set it to 7:00 on holidays."

[1423] (Device) The alarm is set for 6:00 AM on the following Monday. If a public holiday falls on the same day, the alarm will go off at 7:00 AM.

[1424] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle.

[1425] The processing flow will be explained below.

[1426] Step 1:

[1427] (User) The user issues a voice command to set the alarm, saying, "Set the alarm for 7:00 tomorrow morning."

[1428] Step 2:

[1429] (Device) The device's microphone captures the user's voice instructions, and the internal voice recognition engine converts the voice data into text data.

[1430] Step 3:

[1431] (Terminal) The terminal sends the converted text data to the server.

[1432] Step 4:

[1433] (Server) The server's generated AI receives the text data and analyzes it. During the analysis, it extracts the instruction content ("Set an alarm for 7am tomorrow") and clarifies the specific date and time and setting conditions.

[1434] Step 5:

[1435] (Server) The generation AI generates alarm setting information (date and time: tomorrow at 7:00, repetition: none, special conditions: none) based on the conditions.

[1436] Step 6:

[1437] (Server) Sends the generated alarm setting information to the terminal.

[1438] Step 7:

[1439] (Device) Based on the received alarm setting information, the device registers the alarm in its internal calendar app or alarm function.

[1440] Step 8:

[1441] (Device) When the set alarm time approaches, the device will activate the alarm.

[1442] Step 9:

[1443] (Device) The alarm will start ringing and notify the user with sound and vibration.

[1444] Step 10:

[1445] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[1446] Step 11:

[1447] (Smartwatch / Motion Sensor) If it determines that the user has woken up, it sends a signal to the device to stop the alarm.

[1448] Step 12:

[1449] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[1450] Step 13:

[1451] (User) After waking up, the user provides feedback on the effectiveness of the alarm through the app, such as "The alarm was just right" or "The alarm was too loud."

[1452] Step 14:

[1453] (Device) The device sends the user's feedback to the server.

[1454] Step 15:

[1455] (Server) The server receives the feedback, and the generating AI analyzes it. Based on the feedback, it optimizes future alarm settings.

[1456] Example 1

[1457] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1458] For many people living busy lives in modern society, maintaining a regular rhythm and waking up efficiently is important. However, existing alarm systems lack a means to accurately confirm the user's wake-up status, making it difficult to reliably wake them up. Furthermore, the flexibility of alarm settings is limited, making it difficult to meet individual user needs. Furthermore, there is no well-established mechanism for effectively utilizing feedback to optimize the system, making it difficult to provide optimal alarm settings for each individual user.

[1459] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1460] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for confirming the user's wakefulness in cooperation with a smartwatch or a motion sensor, and means for receiving feedback provided by the user and analyzing it using a generative AI model. This allows the system to set an appropriate alarm based on the user's individual needs, helping the user wake up reliably, and enabling system optimization based on the feedback.

[1461] "Means for receiving voice instructions from the user" refers to devices or software that receive voice instructions when a user gives voice instructions to the system in natural language to set alarms or perform other operations.

[1462] The "means for converting voice instructions into text data" refers to a device or software that recognizes received voice instructions and converts the content into text format, such as a voice recognition engine.

[1463] "Means for analyzing text data and setting alarms based on the date, time, and conditions" refers to a device or software that analyzes the converted text data and sets appropriate alarms based on the date, time, and conditions specified by the user.

[1464] "Means for activating an alarm at a set date and time" refers to a device or software that activates an alarm using sound, vibration, or other means at a set date and time.

[1465] "Means for keeping the alarm going until the user wakes up" refers to a device or software that keeps the alarm set so that it does not stop until the user actually wakes up.

[1466] "Means for verifying user alertness in conjunction with a smartwatch or motion sensor" refers to devices or software that use data from a smartwatch or motion sensor to verify the user's physical movement and alertness.

[1467] "Means for receiving and analyzing user-provided feedback using a generative AI model" refers to devices or software that receive user feedback, analyze it using a generative AI model, and optimize system performance or settings.

[1468] This invention is a system for improving a user's daily rhythm and helping them wake up efficiently. The system aims to allow the user to set an alarm by voice and operate until the alarm wakes the user up reliably. Furthermore, it has a function for optimizing the system through feedback.

[1469] System Overview

[1470] 1. Accepting voice commands

[1471] (User) The user gives instructions to the system in natural language to set an alarm, such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[1472] (Device) The device uses voice recognition software (e.g., Google Speech-to-Text API) to convert the user's voice into text data.

[1473] 2. Text Data Analysis

[1474] (Terminal) The converted text data is sent to the server.

[1475] (Server) The generative AI model (e.g., OpenAI GPT-4) deployed on the server analyzes the text data sent and sets alarms based on the user's instructions. This analysis extracts the date, time, and conditions.

[1476] 3. Alarm settings and operation

[1477] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[1478] (Device) The device will activate the alarm with sound or vibration when the set alarm time arrives.

[1479] (Smartwatch / Motion Sensor) In addition, a smartwatch (e.g., Apple Watch) or a motion sensor can be used to monitor the user's waking state and the alarm will continue until the user wakes up.

[1480] 4. Receiving and analyzing feedback

[1481] (User) After the alarm is stopped, the user provides feedback through the smartphone app, such as "The alarm was appropriate" or "The alarm was too loud."

[1482] (Server) The server receives user feedback and the generative AI model analyzes it, allowing for future optimization of alarm settings.

[1483] Specific examples

[1484] A specific example will be given below.

[1485] Example 1:

[1486] (User) The user instructs, "Wake me up at 7 o'clock tomorrow."

[1487] (Device) The voice recognition function converts the voice into text data such as "Wake me up at 7 o'clock tomorrow."

[1488] (Server) The generating AI analyzes and extracts the information "Set the alarm for 7am the next morning."

[1489] (Device) The alarm will start ringing at 7:00 the next morning. When the user wakes up, the smartwatch detects their movement and sends a signal to the device to stop the alarm, which stops the alarm.

[1490] Example 2:

[1491] (User) The user instructs, "Wake me up at 6:00 every Monday, except on public holidays, at 7:00."

[1492] (Device) The voice recognition function converts voice into text data.

[1493] (Server) The generation AI analyzes and extracts the condition "Set the alarm for 6:00 every Monday, but for holidays, set it for 7:00."

[1494] (Device) The alarm will ring at 6:00 a.m. the following Monday, or 7:00 a.m. if a public holiday falls on the same day.

[1495] As described above, the system of the present invention efficiently supports the user's life rhythm and promotes a healthy lifestyle.

[1496] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1497] Step 1:

[1498] (User) The user issues a voice command to the system, such as "Wake me up at 6am tomorrow morning."

[1499] Input: User's voice command

[1500] Output: Audio data received by the device's microphone

[1501] Specific operation: When the user speaks into the device's microphone, the device picks up the audio.

[1502] Step 2:

[1503] (Device) The device converts the voice into text data using voice recognition software (e.g., Google Speech-to-Text API).

[1504] Input: Audio data

[1505] Output: Text data

[1506] What happens: The speech recognition engine analyzes the audio data and converts it into a corresponding text representation.

[1507] Step 3:

[1508] (Terminal) The terminal sends the converted text data to the server.

[1509] Input: Text data

[1510] Output: Text data sent to the server

[1511] What happens: Text data is sent to a server over an internet connection.

[1512] Step 4:

[1513] (Server) The server analyzes the text data using a generative AI model (e.g., OpenAI GPT-4) to extract date, time, and alarm setting information.

[1514] Input: Text data

[1515] Output: Analyzed alarm setting information (date and time and conditions)

[1516] Specific operation: The generative AI model analyzes the text data and extracts the date, time, and conditions specified by the user.

[1517] Step 5:

[1518] (Server) Based on the analysis results of the generation AI model, alarm setting information is created and sent to the terminal.

[1519] Input: Parsed alarm setting information

[1520] Output: A data packet containing configuration information

[1521] Specific operation: The server generates a data packet containing instructions for setting an alarm and sends it to the device.

[1522] Step 6:

[1523] (Device) When the set time arrives, the device will activate an alarm.

[1524] Input: Set alarm information

[1525] Output: Alarm activation (sound, vibration, etc.)

[1526] Specific action: The device will emit an alarm or vibrate at the specified date and time.

[1527] Step 7:

[1528] (Smartwatch / motion sensor) A smartwatch or motion sensor checks whether the user is awake.

[1529] Input: User movement and environmental data

[1530] Output: Awakening confirmation data

[1531] What it does: The smartwatch monitors your movements and notifies your device when movement is detected.

[1532] Step 8:

[1533] (Device) When the user is confirmed awake, the alarm will stop.

[1534] Input: Awakening confirmation data

[1535] Output: Stop alarm

[1536] Specific operation: The device receives data from the smartwatch and stops the alarm.

[1537] Step 9:

[1538] (User) The user provides feedback through the smartphone app, for example, "The alarm was appropriate" or "The alarm was too loud."

[1539] Input: User feedback

[1540] Output: Feedback data entered into the smartphone app

[1541] What happens: A user uses the app's feedback feature to provide a rating.

[1542] Step 10:

[1543] (Server) The server receives the feedback and analyzes it using a generative AI model.

[1544] Input: Feedback data

[1545] Output: Analysis results and optimization information

[1546] What it does: A generative AI model analyzes feedback data and generates information to optimize system settings.

[1547] (Application example 1)

[1548] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1549] Conventional alarm systems only notified users at a time specified by the user, and did not adequately check the user's behavior or optimize the system based on feedback. Furthermore, in physical stores, there was no system in place to ensure that staff were awake and ready to work when it came to shift management. This resulted in staff being late or not performing their shifts, leading to problems with reduced work efficiency.

[1550] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1551] In this invention, the server includes means for receiving voice instructions from a user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on a date, time, and conditions, means for activating the alarm at the set date and time, means for continuing the alarm until the user wakes up, means for using a smartwatch to confirm the user's wakefulness and send a reminder before the user starts work, means for providing alarm setting and reminder functions specialized for store staff shift management, and means for receiving and analyzing feedback provided by the user. This improves the user's lifestyle and enables more efficient and reliable staff shift management in physical stores.

[1552] A "user" is an individual who uses the system to set alarms and receive wake-up and shift management notifications.

[1553] A "means for accepting voice instructions" is a device or system for recognizing and processing voice input from a user.

[1554] The "means for converting voice instructions into text data" is software or algorithms that use voice recognition technology to convert received voice into text data.

[1555] "Means for analyzing text data and setting alarms based on date, time, and conditions" refers to software or a process that extracts necessary information from the analyzed text data and sets the alarm date, time, and conditions based on that information.

[1556] The "means for activating an alarm at a set date and time" refers to software or hardware for triggering an alarm at a specified date and time and issuing a notification.

[1557] "Means for keeping the alarm going until the user wakes up" refers to the mechanism or process for keeping the alarm notification going until the user is sure to wake up.

[1558] "Method for utilizing a smartwatch to detect when a user is awake and send a reminder before the start of a shift" means a system or method for using a sensor in a smartwatch to detect when a user is awake and send a reminder notification before the start of a shift.

[1559] "A means for providing alarm setting and reminder functions specialized for store staff shift management" refers to software or a system for managing the shift schedules of staff working in physical stores and providing alarms and reminders at appropriate times.

[1560] "Means for receiving and analyzing feedback" refers to the mechanisms and processes used to collect feedback provided by users and analyze that data to optimize the system.

[1561] The system for implementing this invention has the ability to accept voice commands, set an alarm based on those commands, and keep the alarm running until the user wakes up. It also uses a smartwatch or motion sensor to check whether the user is awake and optimizes the system based on the feedback.

[1562] System configuration

[1563] 1. Accepting voice commands

[1564] The user issues natural language voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[1565] 2. Speech Recognition and Text Conversion

[1566] The device converts voice instructions received through a voice input device (e.g., a head-mounted display with a microphone) into text data using a voice recognition API. This text data is used as basic information for the entire system.

[1567] 3. Text data analysis and alarm setting

[1568] The converted text data is sent to a server, which uses a generative AI model to analyze the text data and set alarms based on the date, time, and other conditions.

[1569] 4. Alarm triggers and reminders

[1570] At the set time and date, the device will activate an alarm that will notify the user via sound, vibration, or both. Additionally, the smartwatch will be used to check the user's alertness and send reminders before the start of their shift.

[1571] 5. Confirmation of wake-up and alarm stop

[1572] Smartwatches and motion sensors monitor when a user wakes up and continue to ring the alarm until the user confirms they are awake, at which point the alarm automatically stops.

[1573] 6. Receiving and analyzing feedback

[1574] After the alarm is stopped, the user can provide feedback to the system, for example, by sending a comment through the app such as "The alarm was too loud." The server uses a feedback analysis system to analyze this data and optimize future alarm settings.

[1575] Specific examples

[1576] As a specific example of this system, the following case can be given.

[1577] Example 1: A user issues a voice command such as "I want to be woken up at 6:00 AM next Saturday." This command is converted into text data by a speech recognition API, and the generative AI model analyzes it to set an alarm for "6:00 AM next Saturday."

[1578] Example 2: As an application example of staff shift management in a brick-and-mortar store, a smartwatch is used to send wake-up reminders to staff before they start their shift. Shift schedules are set through voice commands, and wake-up confirmation is performed on the smartwatch.

[1579] Prompt Sentence Examples

[1580] If a user requests "I want to be woken up at 6 AM next Saturday," the voice recognition API converts this into text data and sets an alarm for "6 AM next Saturday." The alarm will ring at the specified time, and the smartwatch will confirm that the user has woken up. The alarm will continue until the user has woken up, and feedback will be collected.

[1581] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1582] Step 1:

[1583] The user issues voice commands to the device, such as "Wake me up at 6:00 AM next Saturday."

[1584] Input: User's voice command

[1585] Output: Audio data (analog signal)

[1586] Step 2:

[1587] The device collects the received voice data through a voice input device (a head-mounted display with a microphone) and converts the voice data into text data using a voice recognition API.

[1588] Input: Audio data (analog signal)

[1589] Output: Text data (digital format)

[1590] Step 3:

[1591] The converted text data is sent from the device to a server, which then analyzes the text data using a generative AI model to extract the necessary date, time, and condition information from the instructions.

[1592] Input: Text data (digital format)

[1593] Output: Analysis results (date and time, conditions)

[1594] Step 4:

[1595] The server generates an alarm schedule based on the extracted date and time and conditions, and transmits the information to the terminal.

[1596] Input: Analysis results (date and time, conditions)

[1597] Output: Alarm schedule

[1598] Step 5:

[1599] At the set date and time, the device will activate an alarm, which will notify the user by sound, vibration, or both.

[1600] Input: Alarm Schedule

[1601] Output: Alarm notification (sound, vibration)

[1602] Step 6:

[1603] At the same time as the alarm goes off, the smartwatch activates sensors to detect the user's movement and monitors their state of wakefulness.

[1604] Input: alarm notification, user movement data

[1605] Output: Awakening state information

[1606] Step 7:

[1607] If the user is awake, the smartwatch sends the information to the device, which then stops the alarm. If the user does not wake up, the alarm continues to ring.

[1608] Input: Awakening state information

[1609] Output: Alarm stop signal

[1610] Step 8:

[1611] After the alarm is stopped, the user provides feedback to the system, for example, by sending a comment such as "The alarm was too loud" through the app.

[1612] Input: User feedback

[1613] Output: Feedback data

[1614] Step 9:

[1615] The server analyzes the collected feedback data using a feedback analysis system to find improvements to optimize the system's performance.

[1616] Input: Feedback data

[1617] Output: Analysis results (improvement points)

[1618] This will improve users' daily routines and also make staff shift management in physical stores more efficient and reliable.

[1619] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1620] The present invention is a system that provides a user with sleep management and effective wake-up support, and further combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on the emotions. Specific embodiments of the present invention are described in detail below.

[1621] System Overview

[1622] 1. Accepting and converting voice commands

[1623] (User) The user issues alarm setting instructions to the system in natural language, including complex requests such as "Wake me up at 6:00 tomorrow morning" or "Set the alarm for 7:00 every Monday morning, except for 8:00 on public holidays."

[1624] (Terminal) The terminal recognizes the user's voice and converts the voice input into text data.

[1625] 2. Text data analysis and alarm setting

[1626] (Terminal) The converted text data is sent to the server.

[1627] (Server) The server's generated AI analyzes the text data sent and sets alarms based on the date, time, and other conditions. This makes it possible to set alarms based on complex conditions.

[1628] 3. Emotion analysis using an emotion engine

[1629] (Server) The generation AI recognizes the user's emotions from the text data, and the emotion engine analyzes it to understand the user's stress level and emotional state based on the user's tone and the words used.

[1630] For example, feedback such as "I want to wake you up again at 6 tomorrow morning, but the volume was too loud last time" can help us recognize that the user was dissatisfied with the previous alarm.

[1631] 4. Triggering and Continuing Alarms

[1632] (Device) When the set alarm time arrives, the device will activate the alarm. The alarm will notify the user by sound, vibration, or both. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[1633] (Smartwatch / Motion Sensor) Furthermore, it works in conjunction with a smartwatch or motion sensor to monitor whether the user has actually woken up, and the alarm will continue to ring until the user wakes up.

[1634] 5. Receiving and analyzing feedback

[1635] (User) After the alarm stops, the user can provide feedback to the system, such as "The alarm was just right" or "The alarm was too loud" through the app.

[1636] (Server) The server receives this feedback and the emotion engine analyzes it. Evaluations and improvements based on the user's emotions are extracted, and future alarm settings are optimized.

[1637] Specific examples

[1638] Specific examples are given below.

[1639] Example 1:

[1640] (User) The user instructs, "I want to be woken up at 7:00 tomorrow. However, the previous alarm sound was too loud and annoying."

[1641] (Device) The voice recognition function converts voice into text data.

[1642] (Server) The generation AI analyzes the text data and extracts the information, such as "set the alarm for 7am the next day and lower the volume," and the emotion engine recognizes the user's discomfort.

[1643] (Device) The next morning, the alarm will start ringing at 7:00 AM, with the volume set to an appropriate level based on the emotion engine analysis. When the user wakes up, the smartwatch will detect their movement and stop the alarm.

[1644] Example 2:

[1645] (User) The user instructs, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[1646] (Device) The voice recognition function converts voice into text data.

[1647] (Server) The generation AI analyzes the text data, and the emotion engine analyzes the user's gloomy emotions to understand setting information such as "Set the alarm for 6:00 every Monday, but notify gently."

[1648] (Device) The alarm will ring at 6am next Monday morning, but the notification method will be set to a soft, pleasant sound or vibration.

[1649] Through these examples, the system of the present invention effectively supports the user's daily rhythm and promotes a healthy lifestyle through emotion-based optimization.

[1650] The processing flow will be explained below.

[1651] Step 1:

[1652] (User) The user verbally instructs, "Set the alarm for 7:00 tomorrow morning, but the volume was too loud last time."

[1653] Step 2:

[1654] (Device) The device's microphone captures the user's voice commands and sends them to the internal voice recognition engine.

[1655] Step 3:

[1656] (Terminal) The voice recognition engine converts the voice data into text data and sends the text data to the server.

[1657] Step 4:

[1658] (Server) The generation AI installed on the server analyzes the received text data and extracts the instructions ("Set the alarm for 7am tomorrow morning" or "The volume was too loud last time").

[1659] Step 5:

[1660] (Server) The emotion engine analyzes the user's emotions from their instructions. For example, from the part "The volume was too loud last time," it recognizes that the user is dissatisfied with the previous alarm setting.

[1661] Step 6:

[1662] (Server) The generation AI takes into account the analysis results of the emotion engine and generates optimal alarm setting information, such as "Date and time: 7:00 the next day" and "Volume: Low."

[1663] Step 7:

[1664] (Server) Sends the generated alarm setting information to the terminal.

[1665] Step 8:

[1666] (Device) Based on the setting information received by the device, an alarm is registered in the internal calendar app or alarm function.

[1667] Step 9:

[1668] (Device) When the set alarm time approaches, the device will activate the alarm.

[1669] Step 10:

[1670] (Device) The alarm will start ringing and notify the user with sound and vibration. The volume and notification method will be adjusted based on the analysis results of the emotion engine.

[1671] Step 11:

[1672] (Smartwatch / Motion Sensor) A smartwatch or motion sensor monitors the user's movements and heart rate to determine whether the user has woken up.

[1673] Step 12:

[1674] (Smartwatch) When it determines that the user has woken up, the smartwatch sends a signal to the device to stop the alarm.

[1675] Step 13:

[1676] (Terminal) The terminal receives the alarm stop signal and stops the alarm.

[1677] Step 14:

[1678] (User) After waking up, the user provides feedback through the app about the effectiveness of the alarm and areas for improvement, such as "The alarm volume this time was just right."

[1679] Step 15:

[1680] (Device) The device sends the user's feedback to the server.

[1681] Step 16:

[1682] (Server) The server receives the feedback, analyzes it with an emotion engine, evaluates it based on the user's emotions, and generates data to be reflected in future alarm settings.

[1683] Example 2

[1684] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1685] Conventional alarm systems often provide alarms in a uniform manner without considering the user's emotions or feedback, resulting in low user satisfaction. Furthermore, they lack a means to properly monitor whether the user is actually awake, making it difficult to provide effective sleep management and wake-up support. Therefore, it is necessary to provide a system that recognizes the user's emotions and sets alarms that reflect their feedback.

[1686] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1687] In this invention, the server includes means for recognizing and analyzing user emotions, means for optimizing alarm settings based on said emotions, and means for receiving and analyzing feedback provided by the user, thereby enabling optimal alarm settings based on individual user emotions and feedback.

[1688] "User" refers to an individual who uses this system to receive sleep management and wake-up support.

[1689] "Voice instructions" refers to instructions or commands given by a user to a system through voice.

[1690] "Text data" refers to character string information converted from voice instructions using voice recognition technology.

[1691] "Analysis" refers to the process of analyzing received text data and feedback data to understand its content.

[1692] "Alarm" refers to a notification method set by the system to help the user wake up.

[1693] "Emotion" refers to the psychological state or feelings that users express through their speech and feedback.

[1694] An "emotion engine" refers to an analysis system that recognizes emotions from users' text data and optimizes settings based on that information.

[1695] "Smart devices" refers to electronic devices with internet connectivity and sensors, such as smartwatches and smartphones.

[1696] "Motion sensor" refers to a sensor unit that detects human movement and provides that information to the system.

[1697] The present invention is a system for providing users with sleep management and effective wake-up support, which combines an emotion engine that recognizes the user's emotions and optimizes alarm settings and feedback responses based on those emotions.

[1698] System configuration

[1699] 1. Hardware Configuration

[1700] (Terminal) This system uses a terminal (e.g., smartphone, smart speaker) to receive user voice commands. The terminal has a microphone for voice recognition and Internet connectivity.

[1701] (Smart devices / motion sensors) Furthermore, it works in conjunction with smart devices (e.g., smartwatches) and motion sensors (e.g., human sensors) to detect user movements.

[1702] 2. Software Configuration

[1703] (Voice recognition software) The device is installed with voice recognition software (e.g., Google Assistant, Amazon Alexa). This software converts the user's voice into text data in real time.

[1704] (Generative AI model) The server is equipped with a generative AI model (e.g., GPT-4) that analyzes text data and optimizes alarm settings based on date, time, and other conditions.

[1705] (Emotion engine) An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) is installed on the server, which recognizes and analyzes user emotions from text data.

[1706] Data processing and calculation

[1707] (Terminal) The terminal receives voice instructions from the user, converts them into text data using voice recognition software, and sends it to the server.

[1708] (Server) The server uses a generative AI model to analyze the text data and extract alarm setting information based on the date, time, and conditions. It also uses an emotion engine to analyze the user's emotions and optimize the alarm settings.

[1709] (Feedback Analysis) The server also receives feedback from users and analyzes it with the emotion engine. The results of this feedback analysis are used to further optimize future alarm settings.

[1710] Specific examples

[1711] Example 1:

[1712] (User) says, "I want to be woken up at 7:00 tomorrow. However, the previous alarm was too loud and annoying."

[1713] (Device) Use the voice recognition function to convert voice into text.

[1714] (Server) The generative AI model analyzes the text and extracts the information, "Set the alarm for 7am the next day and lower the volume." The emotion engine recognizes the user's discomfort.

[1715] (Device) The alarm will start ringing at 7am the next morning, with the volume set to an appropriate adjusted level.

[1716] Example 2:

[1717] (User) gives the command, "Wake me up at 6:00 every Monday. Lately, Monday mornings have been particularly depressing, so please wake me up gently."

[1718] (Device) Use the voice recognition function to convert voice into text.

[1719] (Server) The generative AI model analyzes the text and determines, "Set an alarm for 6:00 every Monday, but gently." The emotion engine recognizes the user's depressed emotion.

[1720] (Device) At 6:00 AM the following Monday morning, the alarm will sound and vibrate to gently wake the user.

[1721] The above is an embodiment of the invention. This system realizes flexible and effective wake-up support that reflects the user's emotions and feedback.

[1722] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1723] Step 1:

[1724] (User) The user gives instructions to set the alarm by voice.

[1725] Specific operation: The user speaks into the device, "Please wake me up at 6am tomorrow morning."

[1726] Input: User's voice command.

[1727] Output: Audio data.

[1728] Step 2:

[1729] (Terminal) The terminal uses voice recognition software to convert the voice data into text data.

[1730] What it does: Speech recognition software (e.g., Google Assistant) converts the user's speech into text, such as "Wake me up at 6am tomorrow morning."

[1731] Input: Audio data.

[1732] Output: Text data.

[1733] Step 3:

[1734] (Terminal) The converted text data is sent to the server.

[1735] Specific operation: Send text data to the server using an HTTP request.

[1736] Input: Text data.

[1737] Output: Text data is sent.

[1738] Step 4:

[1739] (Server) Analyzes text data using a generative AI model to extract dates, times, and conditions.

[1740] Specific operation: A generative AI model (e.g., GPT-4) analyzes the date and time "6:00 AM tomorrow" and the instruction "Wake me up."

[1741] Input: Text data.

[1742] Output: Alarm setting condition.

[1743] Step 5:

[1744] (Server) Analyze user emotions using an emotion engine.

[1745] Specific operation: An emotion engine (e.g., Microsoft Azure's Text Analytics for Sentiment Analysis) analyzes the user's emotions from text data and understands the user's psychological state.

[1746] Input: Text data.

[1747] Output: The user's emotional state.

[1748] Step 6:

[1749] (Server) Optimize alarm settings based on analysis results.

[1750] Specific behavior: Adjust the alarm volume and notification method based on the results of the emotion engine.

[1751] Input: Alarm setting conditions, user's emotional state.

[1752] Output: Optimized alarm settings.

[1753] Step 7:

[1754] (Server) Sends optimized alarm settings to the device.

[1755] Specific operation: Alarm setting information is returned to the terminal as an HTTP response.

[1756] Input: Optimized alarm settings.

[1757] Output: Alarm setting information.

[1758] Step 8:

[1759] (Device) The alarm will start when the set alarm time arrives.

[1760] Specific operation: An alarm sound or vibration will be generated at the specified time.

[1761] Input: Alarm setting information.

[1762] Output: Triggering an alarm.

[1763] Step 9:

[1764] (Smart device / motion sensor) Monitors whether the user is awake.

[1765] Specific operation: The smartwatch or motion sensor detects the user's movements and confirms that they have woken up.

[1766] Input: User behavior data.

[1767] Output: The user's wake-up status.

[1768] Step 10:

[1769] (User) Provide feedback after the alarm stops.

[1770] Specific behavior: The user enters feedback through the app, such as "The alarm was too loud."

[1771] Input: User feedback.

[1772] Output: Feedback data.

[1773] Step 11:

[1774] (Server) Analyze the feedback data and optimize future alarm settings.

[1775] Specific operation: The emotion engine analyzes the feedback and reflects it in the next alarm setting.

[1776] Input: Feedback data.

[1777] Output: Optimized alarm setting information.

[1778] (Application example 2)

[1779] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1780] In conventional food delivery services, there was a lack of adequate management of fatigue and stress among delivery personnel, which led to a decline in work efficiency and customer satisfaction.In addition, there was no system in place to effectively schedule delivery personnel's refreshment time and encourage them to take breaks at the optimal timing.

[1781] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1782] In this invention, the server includes means for receiving voice instructions from the user, means for converting the voice instructions into text data, means for analyzing the text data and setting an alarm based on the date, time, and conditions, means including an emotion engine for analyzing the emotional state of the delivery person and detecting fatigue or stress, means for scheduling break times, means for activating the alarm at the set date and time, and means for continuing the alarm until the user wakes up. This makes it possible to monitor the emotional state of the delivery person and provide optimal refreshment time, thereby improving work efficiency and customer satisfaction.

[1783] "User" is a term that refers to a user of a food delivery service or a delivery person.

[1784] "Voice commands" is a term that refers to voice commands given by a user to a system.

[1785] "Text data" is a term that refers to data in which voice instructions are converted into text information.

[1786] "Analysis" is a term that refers to the act of evaluating dates, times, conditions, and even emotional states based on text data.

[1787] "Alarm" is a term that refers to a sound or vibration that is activated at a set date and time to notify the user.

[1788] "Emotion engine" is a term used to describe a system that recognizes and evaluates a user's emotional state from text data.

[1789] "Rest time" is a term that refers to the time a delivery person takes to rest.

[1790] "Scheduling" is a term that refers to the act of setting optimal rest times based on various conditions.

[1791] "Smart device" is a term that refers to devices that sense the user's actions and status, such as smartwatches and smartphones.

[1792] "Human presence sensor" is a term that refers to a sensor that detects surrounding movements and actions.

[1793] "Feedback" is a term that refers to the evaluations and opinions that users provide to a system.

[1794] "Food delivery service" is a term that refers to a service that delivers meals or food to a location specified by the customer.

[1795] "Delivery person" is a term used to refer to the staff member in a food delivery service who is responsible for actually delivering the goods.

[1796] The present invention provides a system for managing fatigue of delivery personnel in a food delivery service and efficiently notifying them of refreshment times. An embodiment of the present invention will be described in detail below.

[1797] System Overview

[1798] The present invention consists of a system that accepts a user's voice instructions, converts them into text data, analyzes them using an emotion engine, and schedules appropriate break times.

[1799] 1. Accepting and converting voice commands

[1800] Device: The user (delivery person) issues voice instructions to the system. For example, they might say, "I feel tired" or "I need a break." The device then uses voice recognition technology (e.g., Google Speech Recognition API) to convert the voice instructions into text data.

[1801] 2. Text data analysis and alarm setting

[1802] Server: The converted text data is sent to the server and analyzed using a generative AI model. The emotion engine recognizes the user's emotional state and performs analysis. For example, if the user says "I'm tired," the emotion engine will detect a high stress level.

[1803] 3. Analysis by Emotion Engine

[1804] Server: The server evaluates fatigue and stress levels from text data and schedules breaks. For example, it might suggest a delivery person with a high stress level take a break in 30 minutes.

[1805] 4. Triggering and Continuing Alarms

[1806] Device: When the scheduled break time arrives, the device will activate an alarm. The alarm will notify you with sound and vibration, and the volume and tone will be adjusted based on the analysis results of the emotion engine. The device will then check whether the user has woken up via the smartwatch or motion sensor and stop the alarm.

[1807] Hardware or software used

[1808] Hardware: Smartphones, smartwatches, motion sensors

[1809] Software: Google Speech Recognition API, TextBlob, generative AI model, emotion engine program

[1810] Specific examples

[1811] For example, consider a delivery person saying, "I'm pretty tired this morning. I'd like to take a break." The voice command is converted into text using voice recognition technology. The server then analyzes the text data using a generative AI model to assess the fatigue level. If high fatigue is detected, the system suggests a break in 30 minutes and sets a gentle alarm at an appropriate time. After 30 minutes, the smartphone will sound a gentle alarm, and the delivery person's return from the break will be confirmed on the smartwatch. In this way, the system effectively supports the delivery person's health management.

[1812] Examples of prompt statements

[1813] Please describe your current state in detail. For example, describe your feelings such as "I'm tired" or "I'm sleepy."

[1814] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1815] Step 1:

[1816] Device: The user (delivery person) verbally commands, "I feel tired" or "I need a break." This is the input. The device accepts the voice command. Speech recognition technology (e.g., Google Speech Recognition API) is used here. The voice input is sent to the device as audio data.

[1817] Step 2:

[1818] Terminal: The terminal converts the received voice data into text data using voice recognition technology. Specifically, the voice recognition engine analyzes the voice data and generates the corresponding text data. The input is voice data, and the output is text data.

[1819] Step 3:

[1820] Server: The converted text data is sent to the server. The server uses the generative AI model to analyze the text data. The specific data processing involves extracting emotional information from the text data using natural language processing technology. The input is text data, and the output is emotional information.

[1821] Step 4:

[1822] Server: The server uses an emotion engine to evaluate the emotion information and determine the user's fatigue and stress levels. In this process, the emotion engine analyzes keywords and tones in the text data and scores the emotional state. The input is emotion information, and the output is an emotion score.

[1823] Step 5:

[1824] Server: If the emotion score is high, schedule a break. The break time setting suggests an appropriate break timing, such as the next 30 minutes. The input is the emotion score, and the output is the break schedule. Specific operations include calculating the break time.

[1825] Step 6:

[1826] Server: Sets an alarm when the scheduled break time arrives. The volume and tone of the alarm are adjusted based on the evaluation results of the emotion engine. Specifically, if the emotion score is high, a gentler sound is selected. The input is the break schedule and emotion score, and the output is the adjusted alarm setting.

[1827] Step 7:

[1828] Terminal: When it is time for a break, the terminal will activate an alarm. The specific behavior is to notify the user using an alarm sound or vibration. The input is the alarm setting, and the output is the alarm notification.

[1829] Step 8:

[1830] Device: Checks whether the user has woken up via a smartwatch or motion sensor. Specifically, the sensor detects the user's movement and confirms that the user has woken up. The input is sensor data, and the output is the wake-up confirmation result.

[1831] Step 9:

[1832] Server: Once the wake-up is confirmed, the alarm is stopped. Specifically, the server sends a stop command to the terminal. The input is the wake-up confirmation result, and the output is the alarm stop.

[1833] This completes the entire process and effectively manages fatigue among food delivery personnel.

[1834] 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.

[1835] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1836] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1837] 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.

[1838] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1839] 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.

[1840] 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).

[1841] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1842] 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."

[1843] 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.

[1844] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1845] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1846] 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.

[1847] 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.

[1848] 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.

[1849] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1850] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1851] 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.

[1852] 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.

[1853] 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.

[1854] 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.

[1855] The following is further disclosed regarding the above embodiment.

[1856] (Claim 1)

[1857] means for accepting voice instructions from a user;

[1858] means for converting the voice instruction into text data;

[1859] means for analyzing the text data and setting an alarm based on the date, time and conditions;

[1860] means for activating the alarm at a set date and time;

[1861] The system includes a means for causing the alarm to continue until the user wakes up.

[1862] (Claim 2)

[1863] 10. The system of claim 1, further comprising means for receiving and analyzing user-provided feedback.

[1864] (Claim 3)

[1865] 10. The system of claim 1, further comprising means for verifying user wakefulness in conjunction with a smartwatch or a motion sensor.

[1866] "Example 1"

[1867] (Claim 1)

[1868] means for accepting voice instructions from a user;

[1869] means for converting the voice instruction into text data;

[1870] means for analyzing the text data and setting an alarm based on the date, time and conditions;

[1871] means for activating the alarm at a set date and time;

[1872] a means for causing the alarm to continue until the user wakes up;

[1873] A means to check whether the user is awake by linking with a smartwatch or motion sensor, and

[1874] A system that includes a means for receiving user-provided feedback and analyzing it using a generative AI model.

[1875] (Claim 2)

[1876] 10. The system of claim 1, further comprising: means for generating a prompt sentence based on the user's voice instruction and the analysis result.

[1877] (Claim 3)

[1878] 10. The system of claim 1, further comprising means for optimizing future alarm settings based on the analyzed feedback.

[1879] "Application Example 1"

[1880] (Claim 1)

[1881] means for accepting voice instructions from a user;

[1882] means for converting the voice instruction into text data;

[1883] means for analyzing the text data and setting an alarm based on the date, time and conditions;

[1884] means for activating the alarm at a set date and time;

[1885] a means for causing the alarm to continue until the user wakes up;

[1886] The system uses a smartwatch to check that the user is awake and includes a means to send a reminder before the start of work.

[1887] (Claim 2)

[1888] 10. The system of claim 1, further comprising means for receiving and analyzing user-provided feedback.

[1889] (Claim 3)

[1890] A means to check whether the user is awake by linking with a smartwatch or motion sensor, and

[1891] 10. The system of claim 1, further comprising means for providing alarm setting and reminder functions specific to store staff shift management.

[1892] "Example 2: Combining Emotion Engines"

[1893] (Claim 1)

[1894] means for accepting voice instructions from a user;

[1895] means for converting the voice instruction into text data;

[1896] means for analyzing the text data and setting an alarm based on the date, time and conditions;

[1897] A means of recognizing and analyzing user emotions;

[1898] means for optimizing alarm settings based on said emotion;

[1899] means for activating the alarm at a set date and time;

[1900] The system includes a means for causing the alarm to continue until the user wakes up.

[1901] (Claim 2)

[1902] 10. The system of claim 1, further comprising means for receiving and analyzing user-provided feedback.

[1903] (Claim 3)

[1904] 10. The system of claim 1, further comprising means for verifying user wakefulness in conjunction with a smart device or motion sensor.

[1905] "Application example 2 when combining emotion engines"

[1906] (Claim 1)

[1907] means for accepting voice instructions from a user;

[1908] means for converting the voice instruction into text data;

[1909] means for analyzing the text data and setting an alarm based on the date, time and conditions;

[1910] means for analyzing an emotional state of the delivery person and detecting fatigue or stress, the emotional state including an emotion engine;

[1911] A means of scheduling breaks;

[1912] means for activating the alarm at a set date and time;

[1913] a means for causing the alarm to continue until the user wakes up;

[1914] A system including:

[1915] (Claim 2)

[1916] 10. The system of claim 1, further comprising means for receiving and analyzing user-provided feedback.

[1917] (Claim 3)

[1918] 10. The system of claim 1, further comprising means for verifying user wakefulness in conjunction with a smart device or a motion sensor. [Explanation of symbols]

[1919] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for accepting voice instructions from a user; means for converting the voice instruction into text data; means for analyzing the text data and setting an alarm based on the date, time and conditions; means for activating the alarm at a set date and time; The system includes a means for causing the alarm to continue until the user wakes up.

2. The system of claim 1 , further comprising means for receiving and analyzing user-provided feedback.

3. The system of claim 1 further comprising means for verifying user wakefulness in conjunction with a smartwatch or a motion sensor.

Images