system

Abstract

Provide a system. A means for accepting voice input; means for generating text data from the received speech; means for extracting tasks, locations, and deadlines from the text data; A means to generate a to-do list based on the extracted tasks, locations, and due dates; A way to manage the generated to-do list and set reminders, means for generating and tagging a summary of the speech input; a means for storing the generated summary and tagged data; and a means for notifying the user at the time of the reminder.

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] In modern society, individuals lead busy lives and are required to efficiently manage and complete multiple tasks and schedules. However, traditional manual task and schedule management is cumbersome, and people often forget important schedules, leading to issues. Furthermore, the lack of a system that automatically extracts tasks from voice conversations and properly organizes and saves them makes efficient individual task management difficult. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes means for accepting voice input, means for generating text data from the accepted voice, means for extracting tasks, locations, and deadlines from the text data, means for generating a to-do list based on the extracted tasks, locations, and deadlines, means for managing the generated to-do list and setting reminders, means for generating a summary of the voice input and tagging it, means for saving the generated summary and tagged data, and means for notifying at the timing of a reminder.

[0006] "Audio input" is the process of receiving audio as digital data.

[0007] "Text data" is character data generated from speech using speech recognition technology.

[0008] A "task" refers to a specific task or activity that a user must perform.

[0009] "Location" refers to the geographic location or facility where a task is to be performed.

[0010] A "deadline" refers to the date and time by which a task should be completed.

[0011] A "TODO list" is a list of tasks that a user needs to complete in an organized order.

[0012] "Reminder" is a feature that notifies and reminds users of specific tasks or appointments.

[0013] A "summary" is a sentence that briefly summarizes the main topic and important information of the voice input content.

[0014] "Tagging" is the process of attaching relevant keywords and classification information to data.

[0015] "Saving" is the act of writing data to a storage device in order to keep it available for future reference.

[0016] A "notification" is an action that conveys specific information to a user. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention provides a system that accepts voice input and efficiently manages tasks and sends reminders using speech recognition technology and natural language processing (NLP). To implement this system, a server, a terminal, and a user work together.

[0039] Voice input acceptance

[0040] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0041] Voice Recognition

[0042] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[0043] Natural Language Processing

[0044] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[0045] Generate a TODO list

[0046] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, such as Google Calendar or Outlook, where events are directly registered.

[0047] Reminders and notifications

[0048] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[0049] Lifelog storage and tagging

[0050] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Return the book at the library tomorrow at 3 PM" would be generated and tagged with "library," "book," and "return." This data is stored in a database for future search and reference.

[0051] Specific examples

[0052] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "return the book," the location "library," and the due date "tomorrow at 3 PM." The server then uses this information to create a to-do list and adds it to the user's calendar. The server then sets a reminder for the next day at 2:30 PM, and the device notifies the user at the specified time. Finally, the server creates a summary "return the book at the library tomorrow at 3 PM," tags it, and saves it in the database.

[0053] In this way, the present invention provides a specific embodiment of a system that supports a user's daily work by automating task management through voice input and efficiently setting reminders.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[0057] Step 2:

[0058] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[0059] Step 3:

[0060] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[0061] Step 4:

[0062] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[0063] Step 5:

[0064] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[0065] Step 6:

[0066] The server then creates structured data based on the extracted information, specifically JSON format data that includes the task, location, and deadline.

[0067] Step 7:

[0068] The server updates the TODO list based on the generated structured data. The server manages the TODO list and synchronizes it with the user's schedule management tool (e.g., calendar).

[0069] Step 8:

[0070] The server sets a reminder according to the task deadline, and determines the time to notify the user based on the reminder setting time.

[0071] Step 9:

[0072] The server sends a notification to the user's device at the reminder time, and the device displays a notification to the user, such as "You have an appointment to return a book at the library."

[0073] Step 10:

[0074] The server generates a summary of the speech input and stores it as text data. The server also assigns appropriate tags to the summary and stores it in a database.

[0075] Through this step, the specific processing of the system that automates everything from voice input to task management and reminder notifications is realized.

[0076] Example 1

[0077] 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."

[0078] Conventional task management and reminder setting systems require users to manually input tasks and set appropriate reminders, making operation cumbersome and making efficient schedule management difficult. Furthermore, when using voice input, accurate task extraction and appropriate reminder setting are difficult due to insufficient voice recognition accuracy and natural language processing capabilities. The present invention aims to solve these problems and provide a system that allows users to efficiently and accurately manage tasks and set reminders using only voice input.

[0079] 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.

[0080] In this invention, the server includes means for converting received voice data into text data using voice recognition technology, means for analyzing the text data using natural language processing technology to extract tasks, locations, and deadlines, and means for generating a to-do list based on the extracted tasks, locations, and deadlines. This allows the user to accurately register and manage tasks using only voice input, and realizes efficient reminder setting and notifications.

[0081] "User" refers to a person who uses voice input to manage tasks and set reminders.

[0082] "Terminal" refers to a device that accepts and records voice input when a user issues a voice command.

[0083] "Server" refers to a system that receives voice data sent from a terminal, analyzes the data using voice recognition technology and natural language processing technology, and manages tasks and sets reminders.

[0084] "Voice input" refers to voice data such as voice commands, notes, and task instructions that a user issues to a terminal.

[0085] "Recording" refers to the act of the terminal recording the user's voice input.

[0086] "Voice data" refers to digital audio information generated by a terminal recording a user's voice input.

[0087] "Voice recognition technology" refers to the technology that analyzes voice data and converts it into text data.

[0088] "Text data" refers to information of a character string generated from voice data using voice recognition technology.

[0089] "Natural language processing technology" refers to the technology that analyzes text data and extracts information such as tasks, locations, and deadlines.

[0090] A "task" refers to an action or task that a user wants to record.

[0091] "Location" refers to the specific location or facility where the task is performed.

[0092] A "deadline" refers to the date and time by which a task should be performed.

[0093] A "TODO list" is a list that is generated based on extracted tasks, locations, and deadlines and is used to manage a user's schedule.

[0094] "Reminder" refers to a function that is set based on a TODO list and notifies the user.

[0095] A "summary" refers to a short text summary of the main parts of the user's voice input.

[0096] "Tagging" refers to the act of adding relevant keywords or categories to a summary.

[0097] "Storage" refers to the act of storing the generated data in a storage device such as a database.

[0098] "Notification" refers to the act of sending an alert or message to the user at the set reminder time.

[0099] MODE FOR CARRYING OUT THE INVENTION

[0100] The present invention provides a system that efficiently utilizes a user's voice input for task management and reminder setting. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail an embodiment of the present invention.

[0101] Program processing overview

[0102] This system works in cooperation with the device, server, and user. When the user issues a voice command, the device accepts the voice input and sends the recorded voice data to the server. The server analyzes the voice data using speech recognition and natural language processing (NLP) technology to extract information such as tasks, locations, and deadlines. Based on the extracted information, the server generates a to-do list and synchronizes it with the user's schedule management tool. The server then sets reminders and sends notifications to the user's device at the specified time. The server also summarizes and tags the voice input and stores it in a database.

[0103] Hardware and software used

[0104] The following hardware and software are used to implement this system:

[0105] Device: Smartphone, tablet, or computer with voice input

[0106] Server: Cloud or on-premise server

[0107] Speech recognition technology: Google Cloud Speech-to-Text API, etc.

[0108] Natural language processing technology: spaCy, Google Natural Language API, etc.

[0109] Schedule management tools: APIs such as Google Calendar and Microsoft Outlook (registered trademark)

[0110] Database: A database for storing audio data, text data, summarization and tagging data.

[0111] Specific actions and examples

[0112] 1. The user says "Start recording" to the device, which activates the device's built-in microphone and begins recording the voice input.

[0113] 2. The user enters a task, note, etc. by voice and then says "stop recording."

[0114] 3. The device stops recording and sends the recording data to the server.

[0115] 4. The server uses the Google Cloud Speech-to-Text API to perform speech recognition on the received audio data and convert it into text data.

[0116] 5. The server analyzes the text data acquired using spaCy or the Google Natural Language API to extract information about tasks, locations, and deadlines.

[0117] 6. The server generates a to-do list based on the extracted information and synchronizes it with schedule management tools such as Google Calendar and Microsoft Outlook.

[0118] 7. The server sets a reminder based on the information in the TODO list and sends that information to the device.

[0119] 8. At the specified time, the device notifies the user that "You have a book to return at the library."

[0120] 9. The server generates a summary of the speech input, tags it appropriately, and stores it in a database.

[0121] Prompt Sentence Examples

[0122] Here are some example prompts to input to a generative AI model:

[0123] When a user says, "I need to remember to return this book at the library tomorrow at 3 PM," explain the steps to use this voice input for task management and reminder notifications.

[0124] As described above, the present invention provides a system that allows users to manage tasks and set reminders efficiently using only voice input. Detailed processing steps and specific implementations will be described separately. This will greatly support users' daily work.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] The user says "Start recording" to the device. The device receives this voice command as input, activates the built-in microphone, and starts recording. The device displays "Recording." Specifically, the device's microphone begins capturing voice input.

[0128] Input: User's voice command "Start recording"

[0129] Output: Start of recording state

[0130] Step 2:

[0131] The user inputs specific tasks and notes by voice. When recording is finished, the user says "Stop recording." With this input, the device stops recording and temporarily saves the recorded data. The device displays "Stop recording." As a specific operation, the recorded voice data is saved in the device.

[0132] Input: User voice command "stop recording" and voice input for tasks and notes

[0133] Output: Temporarily saved audio data

[0134] Step 3:

[0135] The device sends the temporarily saved audio data to the server using the HTTP or HTTPS protocol. The server receives the audio data and saves it in the specified directory.

[0136] Input: Temporarily saved audio data

[0137] Output: Audio data stored on the server

[0138] Step 4:

[0139] The server calls a speech recognition service such as the Google Cloud Speech-to-Text API and converts the speech data into text data. Specifically, the server sends the speech data to the API and stores the returned text data.

[0140] Input: Audio data stored on the server

[0141] Output: Text data generated by the speech recognition service

[0142] Step 5:

[0143] The server parses the acquired text data using spaCy and the Google Natural Language API, then performs syntax analysis, entity recognition, and intent analysis to extract important information about the task, location, and deadline.

[0144] Input: Text data obtained from the speech recognition service

[0145] Output: Extracted task, location, and deadline information

[0146] Step 6:

[0147] The server generates a to-do list based on the extracted information, and synchronizes the to-do list with the API of schedule management tools such as Google Calendar and Microsoft Outlook.

[0148] Input: Extracted task, location, and due date information

[0149] Output: Generated TODO list and synchronized schedule management tool information

[0150] Step 7:

[0151] The server sets reminders based on the information in the TODO list. Reminders are usually set 30 minutes before the task deadline. The server sends the set reminder information to the device.

[0152] Input: Generated TODO list

[0153] Output: Set reminder information

[0154] Step 8:

[0155] The device will display a reminder at the specified time. Specifically, the device will notify the user via a pop-up notification or alarm, saying, "You have a book to return at the library."

[0156] Input: Set reminder information

[0157] Output: Reminder notification

[0158] Step 9:

[0159] The server generates a summary of the speech input, tags it appropriately, and stores it in a database. Specifically, the server generates a summary and tags and records them in a database.

[0160] Input: Text data obtained through speech recognition and NLP

[0161] Output: Summarized and tagged data stored in a database

[0162] (Application example 1)

[0163] 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."

[0164] Conventional factory task management and reminder setting involve a lot of manual work, resulting in a lack of efficiency. In addition, when work instructions or confirmations are given using voice commands, tasks cannot be managed immediately and reminders must also be set manually, resulting in a significant drop in work efficiency.

[0165] 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.

[0166] In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for extracting tasks, locations, and deadlines from the text data. This enables factory task management using voice instructions to issue and confirm work instructions. Furthermore, the server is equipped with a function for automatically generating a to-do list based on the extracted tasks, locations, and deadlines, and for setting reminders, reducing manual work and enabling efficient task management and reminder setting.

[0167] "Voice input" refers to a method of inputting voice instructions or information into a device.

[0168] "Text data" refers to data obtained by converting voice input into text format.

[0169] A "task" is a specific piece of work or job.

[0170] A "location" is a geographic location or facility where a task is to be performed.

[0171] A "deadline" is the date and time or period by which a task should be completed.

[0172] A "TODO list" is a list of tasks that need to be completed.

[0173] "Reminder" is a function that notifies the user at specific times or under specific conditions.

[0174] A "summary" is text data that briefly summarizes long content.

[0175] "Tagging" is the process of assigning labels to data to make it easier to identify.

[0176] "Factory task management" is a method for managing work content and procedures in a factory.

[0177] This invention is a system for efficiently managing tasks in a factory. A user issues voice instructions to a terminal, and the system has the function of automating task management and reminder setting based on the voice instructions.

[0178] Voice input acceptance

[0179] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs conversations and work instructions as voice, and when completes, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0180] Voice Recognition

[0181] The server then sends the received voice data to a cloud-based speech recognition service, which converts the voice data into text. For example, if a user says, "Please don't forget to do machine maintenance on the main line tomorrow at 9 a.m.", the voice is converted into text data.

[0182] Natural Language Processing

[0183] The server receives the converted text data and analyzes it using a natural language processing (NLP) engine. The analysis includes syntactic analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "Maintain the machine," the location "Mainline," and the deadline "Tomorrow at 9:00 AM" are extracted.

[0184] Generate a TODO list

[0185] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, for example, by registering events directly in a calendar application.

[0186] Reminders and notifications

[0187] The server sets a reminder based on the TODO list. The set reminder sends a notification to the user's device shortly before the deadline (e.g., 30 minutes before). The device then presents the reminder to the user at the set time, informing them that "machine maintenance is scheduled for the main line."

[0188] Lifelog storage and tagging

[0189] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9 AM" would be generated and tagged with "main line," "machine," and "maintenance." This data is stored in a database and can be used for future searches and references.

[0190] Hardware and software used

[0191] The following hardware and software are used to implement this system:

[0192] Device: A device that accepts audio input and makes recordings. Examples: smartphone, smart glasses.

[0193] Server: Processes voice data, manages tasks, and sets reminders. Uses a speech recognition API and natural language processing engine.

[0194] Speech recognition service: A cloud-based API. For example, Google Cloud Speech-to-Text API.

[0195] Natural language processing engine: Analyzes text data. Example: Google Cloud Natural Language API.

[0196] Specific examples

[0197] For example, a user might say: "Please don't forget to perform machine maintenance on the mainline tomorrow at 9 AM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "Maintain machine," the location "Mainline," and the deadline "Tomorrow at 9 AM." The server uses this information to generate a to-do list and adds it to the user's calendar. The server then sets a reminder for 8:30 AM the next day, and the device notifies the user at the specified time. Finally, the server creates a summary "Maintain machine on the mainline tomorrow at 9 AM," tags it, and stores it in the database.

[0198] Example prompts for generative AI models

[0199] Analyze "Please remember to perform maintenance on the machine on the mainline at 9am tomorrow" to extract information about the task, location, and deadline.

[0200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0201] Step 1:

[0202] The device accepts voice input from the user. The user issues the voice command "start recording," and the device begins recording the voice. The user inputs conversations and work instructions as voice, and when complete, says "stop recording." The device stops recording and saves the recorded voice data in memory.

[0203] Step 2:

[0204] The device sends the stored voice data to a server, which then sends the received voice data to a cloud-based voice recognition service for processing, which converts the voice data into text data, which the server receives.

[0205] Step 3:

[0206] The server sends the received text data to a natural language processing (NLP) engine. The NLP engine analyzes the text data and extracts important information through syntactic analysis, entity recognition, and intent analysis. For example, it identifies information such as tasks, locations, and deadlines. The server receives the analysis results and stores the extracted information in a database.

[0207] Step 4:

[0208] The server generates a to-do list based on the extracted task, location, and due date information, and then connects to the user's schedule management tool (e.g., calendar application) and synchronizes the generated to-do list, which adds the corresponding events to the user's calendar.

[0209] Step 5:

[0210] The server sets a reminder based on the TODO list. The reminder is set to a time a little before the due date (e.g. 30 minutes before). The server saves the reminder information in a database and triggers the reminder at the set time.

[0211] Step 6:

[0212] The terminal receives a reminder notification from the server. At the set time, the reminder is displayed on the terminal, and the terminal notifies the user that "machine maintenance is scheduled on the main line."

[0213] Step 7:

[0214] The server generates a summary of the speech input and tags it appropriately. The summary and tagged data are stored in a database for future search and reference. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9:00 AM" would be generated and tagged with "main line," "machine," and "maintenance."

[0215] 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.

[0216] The present invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. In a specific embodiment of this system, a server, a terminal, and a user work together.

[0217] Voice input acceptance

[0218] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the voice. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0219] Voice Recognition

[0220] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[0221] Natural Language Processing

[0222] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[0223] emotion recognition

[0224] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state. The emotion recognition engine determines emotions from, for example, the user's tone of voice and the way they speak. Here, it detects whether the user is nervous, excited, or calm.

[0225] Creating a TODO list and reflecting emotions

[0226] The server combines the extracted task information with the emotion recognition results to generate a to-do list. Task priorities can be adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks of higher importance.

[0227] Reminders and notifications

[0228] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[0229] Lifelog storage and tagging

[0230] A summary of the speech input is generated, including the user's emotional information. The summary is tagged on the server, with tags such as "library," "book," and "return," as well as emotional tags. This data is stored in a database for future use and search.

[0231] Specific examples

[0232] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[0233] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[0234] The processing flow will be explained below.

[0235] Step 1:

[0236] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[0237] Step 2:

[0238] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[0239] Step 3:

[0240] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[0241] Step 4:

[0242] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[0243] Step 5:

[0244] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[0245] Step 6:

[0246] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state, determining emotions from the tone and vocabulary of the voice.

[0247] Step 7:

[0248] The server integrates the extracted task information with the emotion recognition results to create structured data (e.g., JSON format), including the task, location, deadline, and emotional state.

[0249] Step 8:

[0250] The server updates the TODO list based on the generated structured data. Task priorities are adjusted based on the emotional information. For example, if the user is feeling stressed, tasks with higher importance are displayed first.

[0251] Step 9:

[0252] The server sets reminders based on the to-do list. For example, for a task due at 3:00 PM tomorrow, it sets a reminder for 2:30 PM tomorrow.

[0253] Step 10:

[0254] The server sends a notification to the user's device at the set reminder time, and the device notifies the user that "You have an appointment to return a book at the library."

[0255] Step 11:

[0256] The server generates a summary of the speech input, including emotional information. For example, summary: "Returning the book at the library tomorrow at 3 PM. The user is worried." The server assigns appropriate tags to the summary and stores it in a database.

[0257] Specific examples

[0258] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[0259] Example 2

[0260] 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."

[0261] Efficient task management and reminder setting are crucial for today's busy lifestyles. However, existing systems lack sufficient integration of natural language processing and emotion recognition technologies that utilize voice input, resulting in inadequate task prioritization and reminder setting. Furthermore, task management that takes the user's emotional state into account is inadequate, resulting in a lack of means to reduce the user's mental burden. Therefore, there is a need for a system that can provide appropriate task management and reminder setting that takes the user's emotional state into account based on voice input.

[0262] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for analyzing the voice data and identifying the emotional state. This makes it possible to improve the efficiency of task management using voice input and to prioritize tasks and set reminders taking into account the user's emotional state.

[0263] "Voice input" refers to the means by which a device receives user-uttered speech and processes it as digital data.

[0264] "Text data" is data that is generated by analyzing voice input and expressing it as a string of characters.

[0265] "Work" refers to the tasks or activities that a user must perform.

[0266] "Location" is data about the geographic location or place where work is performed.

[0267] A "deadline" is data that indicates the time or date by which work should be completed.

[0268] A "task list" is a list of multiple task data in an easy-to-manage format.

[0269] "Notifications" are alerts or reminders that inform users based on set times or circumstances.

[0270] A "summary" is a concise summary of speech input or other data.

[0271] "Tagging" is the act of assigning keywords and labels to data to classify and organize it.

[0272] "Emotional state" is information that indicates the user's psychological and emotional state.

[0273] "Priority" refers to the ranking of tasks based on their importance and urgency.

[0274] This invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. This system operates in cooperation with a server, a terminal, and a user.

[0275] Hardware and software used

[0276] The system utilizes the following hardware and software:

[0277] Device: A device that accepts voice input (e.g., smartphone, tablet, voice assistant device).

[0278] Server: Responsible for data processing and management (e.g. cloud server)

[0279] Speech recognition service: A cloud-based API that converts speech to text (e.g., Google Cloud Speech-to-Text API).

[0280] Natural language processing engine: Software that analyzes text data (e.g., spaCy, BERT model)

[0281] Emotion recognition engine: Software that analyzes emotional states from voice data (e.g., IBM Watson (registered trademark) Tone Analyzer)

[0282] Voice input

[0283] The user speaks "Start recording" into the device, and the device starts recording the voice. The user then enters any necessary notes or tasks by voice, and when the recording is complete, speaks "Stop recording." The device then stops recording and sends the voice data to the server.

[0284] Voice Recognition

[0285] The server sends the received voice data to a voice recognition service, converts the voice data into text data, and then receives the text data and proceeds to the next step.

[0286] Natural Language Processing

[0287] The server inputs the acquired text data into a natural language processing engine and performs syntax analysis, entity recognition, and intent analysis. For example, it extracts the task "return the book" from the text data, the location "library," and the deadline "tomorrow at 3:00 PM."

[0288] emotion recognition

[0289] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, for example, determining emotions such as "worried" or "excited" from the tone of the voice and the way the words are used.

[0290] Generate a TODO list

[0291] The server combines the analysis results of the NLP engine and the emotion recognition engine to prioritize tasks and generate a TODO list. For example, if the user is very anxious, the task will be set to high priority.

[0292] Reminders and notifications

[0293] The server sets reminders based on the TODO list and sends notifications to the device. For example, for a task due "tomorrow at 3:00 PM," the server sets a reminder 30 minutes before the task. At the set time, the device notifies the user by voice or pop-up message that "You have an appointment to return a book at the library."

[0294] Lifelog storage and tagging

[0295] The server generates a lifelog that compiles the to-do list and the user's emotional information. The lifelog is tagged with tags such as "library," "book," and "return," as well as emotional tags such as "worried," and is stored in a database. This data can be used for future searches and references.

[0296] Specific examples

[0297] The user says, "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes the text data and extracts the task "return the book," the location "library," and the deadline "tomorrow at 3 PM." At the same time, the emotion recognition engine analyzes the user's emotional state from the voice and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the set reminder time. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[0298] Prompt Sentence Examples

[0299] "Don't forget to take the dog for a walk at 6pm this evening."

[0300] "Remind me that I have a meeting tomorrow morning at 9am"

[0301] "I want to remember to go to my friend's birthday party next Friday."

[0302] The present invention provides specific embodiments of a system that enables efficient task management and reminder setting from voice input and takes into account the emotional state of the user.

[0303] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0304] Step 1:

[0305] Voice input acceptance

[0306] The user speaks "Start recording" into the device. The device receives this voice command, activates the internal microphone, and begins recording audio.

[0307] The user inputs a conversation or task by voice, and when finished, says "stop recording." The device stops recording and temporarily saves the voice data.

[0308] Input: User's voice commands "Start recording" and "Stop recording" and input voice

[0309] Output: Temporarily saved audio data

[0310] Step 2:

[0311] Sending audio data to the server

[0312] The device sends the temporarily saved audio data to the server using HTTP or HTTPS as the communication protocol.

[0313] The device notifies the user that "recorded data will be sent to the server," and data transfer begins. Once the server confirms receipt, it notifies the device that "data has been received."

[0314] Input: Temporarily stored audio data

[0315] Output: Audio data sent to the server

[0316] Step 3:

[0317] Voice Recognition

[0318] The server sends the received voice data to a cloud-based speech recognition service, which converts the voice into text.

[0319] The server processes the voice data and logs "Converting voice data to text." When speech recognition is complete, it logs "Converting voice data to text."

[0320] Input: Audio data stored on the server

[0321] Output: Text data converted from audio

[0322] Step 4:

[0323] Natural Language Processing

[0324] The text data acquired by the server is input into a natural language processing engine, where it performs syntactic analysis, entity recognition, and intent analysis.

[0325] The server logs "Analyzing text data" and passes the data to the NLP engine. After analysis, it logs "Task information extracted." Specifically, it extracts the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM."

[0326] Input: Text data obtained from speech recognition

[0327] Output: Extracted task, location, and due date information

[0328] Step 5:

[0329] emotion recognition

[0330] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state.

[0331] The server logs "Applying emotion recognition engine" and then logs "User's emotional state detected" after analyzing the emotion. For example, it can determine emotions such as anxiety or excitement from the tone of voice and the way the words are used.

[0332] Input: Audio data stored on the server

[0333] Output: Determined emotional state

[0334] Step 6:

[0335] Generate a TODO list

[0336] The server integrates the analysis results of the NLP engine and emotion recognition engine, prioritizes tasks, and generates a TODO list.

[0337] The server logs "Generating a TODO list" and generates a list based on the extracted task information and emotion information. It also logs "TODO list generated." For example, if the user is very worried, it sets the task to high priority.

[0338] Input: Analysis results of the NLP engine and emotion recognition engine

[0339] Output: A prioritized to-do list

[0340] Step 7:

[0341] Set reminders

[0342] The server sets reminders based on the to-do list. For example, for a task due tomorrow at 3:00 PM, it sets a reminder 30 minutes before the task.

[0343] The server logs "Setting reminder" and logs "Reminder set."

[0344] Input: TODO list

[0345] Output: Set reminders

[0346] Step 8:

[0347] Reminder notifications

[0348] The server sends a reminder to the device at the set time. The device logs "Sending reminder notification" and notifies the user by voice or pop-up that "You have an appointment to return a book at the library."

[0349] Input: Set reminder

[0350] Output: Notification displayed on the user's device

[0351] Step 9:

[0352] Lifelog storage and tagging

[0353] The server generates a life log that compiles the to-do list and the user's emotional information and stores it in a database.

[0354] The server logs "Generating a lifelog" and "Lifelog saved." The lifelog is tagged with tags such as "library," "book," and "return," as well as emotion tags such as "worried."

[0355] Input: TODO list and emotional information

[0356] Output: Saved lifelog

[0357] (Application example 2)

[0358] 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."

[0359] Although task management systems that use voice input already exist, they generally only generate text data and extract task information, and do not take into account the user's emotional state when managing tasks or setting reminders. As a result, when workers are stressed or emotionally unstable, effective task management is difficult, which can lead to reduced work efficiency. Furthermore, when considering use in factories and other workplaces, a function that can detect workers' instructions in real time and adjust priorities is required.

[0360] 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.

[0361] In this invention, the server includes means for accepting voice input, means for generating text data from the accepted voice, means for extracting tasks, locations, and deadlines from the text data, means for adjusting task priorities based on emotional information, means for analyzing the emotional state of the worker and detecting stress, and means for presenting task instructions by voice. This enables effective task management that takes into account the emotional state of the worker, and allows for more appropriate reminder settings and task instructions. Furthermore, receiving instructions in real time through voice input and dynamically adjusting priorities is expected to improve work efficiency on the factory floor.

[0362] A "means for accepting voice input" is a device or software that captures the voice uttered by the user as digital data, allowing the system to use the voice for subsequent processing.

[0363] A "means for generating text data" is a software algorithm or service that analyzes audio data and expresses its contents as text information.

[0364] The "means for extracting tasks, locations, and deadlines" refers to a process or technology for identifying the tasks, the locations where the tasks are performed, and the deadlines for the tasks from the generated text data.

[0365] The "means for generating a task list" is a function or application that compiles in list form the tasks that the user needs to perform based on the extracted tasks, locations, and deadlines.

[0366] The "means for managing the task list and setting reminders" refers to a system or program for properly recording the generated task list and sending reminder notifications based on the specified date and time.

[0367] The "means for generating summaries and tagging of speech input" is a process for summarizing text and extracted information generated from speech data and tagging it to make the content understandable at a glance.

[0368] "Means for storing the generated summary and tagged data" refers to a function that records the summarized information and the associated tag data in a database or other storage device, allowing them to be reused and searched later.

[0369] The "means for notifying at the time of the reminder" is a mechanism that sends a notification to the user's device based on the set reminder date and time to notify the user of the scheduled work.

[0370] The "means for adjusting work priorities based on emotional information" is a mechanism for more efficient task management by changing work priorities based on the results of analyzing the emotional state of the worker.

[0371] "Means for analyzing the emotional state of a worker and detecting stress" refers to technologies and algorithms that analyze the emotional state of a worker from voice data, etc., and identify stress or other emotional states.

[0372] A "means for presenting work instructions by voice" is a device or program that transmits instructions or tasks to be performed by a worker by voice.

[0373] The present invention is a system that uses voice input to manage work instructions and adjusts work priorities based on worker emotion analysis. It is particularly intended for use on factory floors, improving work efficiency through real-time voice instructions.

[0374] Hardware and Software Configuration

[0375] The following hardware and software are used to realize this system.

[0376] Hardware: microphone, speaker, factory robot (with control board)

[0377] Software: Speech recognition API (e.g., general cloud-based API), natural language processing engine (e.g., SpaCy or Google Cloud Natural Language), emotion recognition API (e.g., IBM Watson Tone Analyzer), main server, database

[0378] Data processing flow

[0379] 1. Voice input acceptance

[0380] The user says "Start recording" into the microphone. The device receives this voice command and starts recording the voice. Next, the user says, "The next step is to supply material to the conveying line. This is a high priority." When recording is complete, the user says, "Stop recording." The device stops recording and sends the voice data to the server.

[0381] 2. Voice Recognition

[0382] The server sends the received voice data to a voice recognition API and converts it into text data. For example, a voice saying "The next step is to supply materials to the conveyor line. This is a high priority" is converted into text data saying "The next step is to supply materials to the conveyor line. This is a high priority."

[0383] 3. Natural Language Processing

[0384] The server that retrieves the text data uses an NLP engine to analyze the text data. The analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. In the above example, the extracted information is the task "supply materials to the conveyor line," the location "conveyor line," and "high priority."

[0385] 4. Emotion recognition

[0386] The server applies an emotion recognition API to the voice data to analyze the user's emotional state. The emotion recognition API determines the user's emotions from the tone of their voice and the way they speak. It then detects that the user is feeling stressed.

[0387] 5. Task list generation and emotional reflection

[0388] The server integrates the extracted task information with the emotion recognition results to generate a task list. Task priorities are adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks that are of high importance.

[0389] 6. Reminders and notifications

[0390] The server sets reminders based on the task list. The reminders send notifications to the user's terminal shortly before the deadline. The terminal then presents the reminder to the user at the set time, informing them that "The next step is to supply materials to the conveyor line. This is a high priority."

[0391] 7. Summarize and save voice input

[0392] A summary of the speech input is generated, including the user's emotional information. The tagging process is performed on the server, adding tags such as "transport line," "material supply," and "high priority" as well as emotional tags. This data is stored in a database for future use and search.

[0393] Examples and prompts

[0394] For example, a user might say: "The next step is to supply materials to the conveyor line. It's a high priority." The device records this speech and sends it to the server. The server then performs speech recognition and converts it into text data. The NLP engine then analyzes the speech and extracts the task "supply materials to the conveyor line," the location "conveyor line," and the phrase "high priority." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is feeling stressed. The server uses this information to generate a task list and set reminders. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which includes emotional information. All information is stored in a database.

[0395] Call prompt:

[0396] "What is your next task? Please tell me the priority."

[0397] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] The user says "start recording" into the microphone. The device receives this voice command and starts recording the voice. The input is the voice command "start recording" and the output is the start of voice recording. Specifically, the microphone inside the device operates and records the voice as digital data.

[0401] Step 2:

[0402] The user speaks work instructions into the microphone. For example, "The next step is to supply materials to the conveyor line. This is a high priority." The input is the user's work instructions as voice data, and the output is the accumulation of recorded voice data. Specifically, the terminal continuously records the voice and saves it as digital data.

[0403] Step 3:

[0404] The user says "stop recording." The device receives this voice command and stops recording. The input is the voice command "stop recording," and the output is to stop recording and save the voice data. Specifically, the device stops recording and sends the saved voice data to the server.

[0405] Step 4:

[0406] The server sends the received voice data to a voice recognition API and converts it into text data. The input is voice data, and the output is the corresponding text data. Specifically, the server generates an API request and sends it to the voice recognition service. It then receives the text data returned by the voice recognition service.

[0407] Step 5:

[0408] The server analyzes the generated text data using a natural language processing engine to extract tasks, locations, and deadlines. The input is text data, and the output is the extracted task information. Specifically, the server parses the text data, performs entity recognition, and identifies important information through intent analysis.

[0409] Step 6:

[0410] The server sends the voice data to the emotion recognition API and analyzes the emotional state. The input is the voice data and the output is the emotion recognition result. Specifically, the server sends the voice data as an API request and receives the analysis result returned from the emotion recognition service.

[0411] Step 7:

[0412] The server integrates the extracted task information and emotion recognition results to generate a task list. The input is the task information and emotion recognition results, and the output is a task list with adjusted priorities. Specifically, the server compares the task information and emotion recognition results and applies an algorithm to determine the priorities.

[0413] Step 8:

[0414] The server sets a reminder and sends a reminder notification to the user's device at the specified time. The input is a task list and the reminder setting time, and the output is a notification to the device. Specifically, the server sets a timer and sends a notification message to the device when the timer goes off.

[0415] Step 9:

[0416] The device presents the reminder content to the user by voice. The input is the reminder notification from the server, and the output is the voice notification. Specifically, the device's speaker operates and plays the reminder content by voice.

[0417] Step 10:

[0418] The server generates a summary of the speech input, tags it, and stores it in a database. The input is speech data, text data, and emotion recognition results, and the output is a summary and tagged data. Specifically, the server applies a summary generation algorithm, adds relevant tags, and records the data in a database.

[0419] 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.

[0420] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0421] 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.

[0422] [Second embodiment]

[0423] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] In the smart glasses 214, 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.

[0434] 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."

[0435] The present invention provides a system that accepts voice input and efficiently manages tasks and sends reminders using speech recognition technology and natural language processing (NLP). To implement this system, a server, a terminal, and a user work together.

[0436] Voice input acceptance

[0437] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0438] Voice Recognition

[0439] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[0440] Natural Language Processing

[0441] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[0442] Generate a TODO list

[0443] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, for example, by directly registering events in Google Calendar or Outlook.

[0444] Reminders and notifications

[0445] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[0446] Lifelog storage and tagging

[0447] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Return the book at the library tomorrow at 3 PM" would be generated and tagged with "library," "book," and "return." This data is stored in a database for future search and reference.

[0448] Specific examples

[0449] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "return the book," the location "library," and the due date "tomorrow at 3 PM." The server then uses this information to create a to-do list and adds it to the user's calendar. The server then sets a reminder for the next day at 2:30 PM, and the device notifies the user at the specified time. Finally, the server creates a summary "return the book at the library tomorrow at 3 PM," tags it, and saves it in the database.

[0450] In this way, the present invention provides a specific embodiment of a system that supports a user's daily work by automating task management through voice input and efficiently setting reminders.

[0451] The processing flow will be explained below.

[0452] Step 1:

[0453] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[0454] Step 2:

[0455] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[0456] Step 3:

[0457] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[0458] Step 4:

[0459] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[0460] Step 5:

[0461] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[0462] Step 6:

[0463] The server then creates structured data based on the extracted information, specifically JSON format data that includes the task, location, and deadline.

[0464] Step 7:

[0465] The server updates the TODO list based on the generated structured data. The server manages the TODO list and synchronizes it with the user's schedule management tool (e.g., calendar).

[0466] Step 8:

[0467] The server sets a reminder according to the task deadline, and determines the time to notify the user based on the reminder setting time.

[0468] Step 9:

[0469] The server sends a notification to the user's device at the reminder time, and the device displays a notification to the user, such as "You have an appointment to return a book at the library."

[0470] Step 10:

[0471] The server generates a summary of the speech input and stores it as text data. The server also assigns appropriate tags to the summary and stores it in a database.

[0472] Through this step, the specific processing of the system that automates everything from voice input to task management and reminder notifications is realized.

[0473] Example 1

[0474] 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."

[0475] Conventional task management and reminder setting systems require users to manually input tasks and set appropriate reminders, making operation cumbersome and making efficient schedule management difficult. Furthermore, when using voice input, accurate task extraction and appropriate reminder setting are difficult due to insufficient voice recognition accuracy and natural language processing capabilities. The present invention aims to solve these problems and provide a system that allows users to efficiently and accurately manage tasks and set reminders using only voice input.

[0476] 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.

[0477] In this invention, the server includes means for converting received voice data into text data using voice recognition technology, means for analyzing the text data using natural language processing technology to extract tasks, locations, and deadlines, and means for generating a to-do list based on the extracted tasks, locations, and deadlines. This allows the user to accurately register and manage tasks using only voice input, and realizes efficient reminder setting and notifications.

[0478] "User" refers to a person who uses voice input to manage tasks and set reminders.

[0479] "Terminal" refers to a device that accepts and records voice input when a user issues a voice command.

[0480] "Server" refers to a system that receives voice data sent from a terminal, analyzes the data using voice recognition technology and natural language processing technology, and manages tasks and sets reminders.

[0481] "Voice input" refers to voice data such as voice commands, notes, and task instructions that a user issues to a terminal.

[0482] "Recording" refers to the act of the terminal recording the user's voice input.

[0483] "Voice data" refers to digital audio information generated by a terminal recording a user's voice input.

[0484] "Voice recognition technology" refers to the technology that analyzes voice data and converts it into text data.

[0485] "Text data" refers to information of a character string generated from voice data using voice recognition technology.

[0486] "Natural language processing technology" refers to the technology that analyzes text data and extracts information such as tasks, locations, and deadlines.

[0487] A "task" refers to an action or task that a user wants to record.

[0488] "Location" refers to the specific location or facility where the task is performed.

[0489] A "deadline" refers to the date and time by which a task should be performed.

[0490] A "TODO list" is a list that is generated based on extracted tasks, locations, and deadlines and is used to manage a user's schedule.

[0491] "Reminder" refers to a function that is set based on a TODO list and notifies the user.

[0492] A "summary" refers to a short text summary of the main parts of the user's voice input.

[0493] "Tagging" refers to the act of adding relevant keywords or categories to a summary.

[0494] "Storage" refers to the act of storing the generated data in a storage device such as a database.

[0495] "Notification" refers to the act of sending an alert or message to the user at the set reminder time.

[0496] MODE FOR CARRYING OUT THE INVENTION

[0497] The present invention provides a system that efficiently utilizes a user's voice input for task management and reminder setting. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail an embodiment of the present invention.

[0498] Program processing overview

[0499] This system works in cooperation with the device, server, and user. When the user issues a voice command, the device accepts the voice input and sends the recorded voice data to the server. The server analyzes the voice data using speech recognition and natural language processing (NLP) technology to extract information such as tasks, locations, and deadlines. Based on the extracted information, the server generates a to-do list and synchronizes it with the user's schedule management tool. The server then sets reminders and sends notifications to the user's device at the specified time. The server also summarizes and tags the voice input and stores it in a database.

[0500] Hardware and software used

[0501] The following hardware and software are used to implement this system:

[0502] Device: Smartphone, tablet, or computer with voice input

[0503] Server: Cloud or on-premise server

[0504] Speech recognition technology: Google Cloud Speech-to-Text API, etc.

[0505] Natural language processing technology: spaCy, Google Natural Language API, etc.

[0506] Schedule management tools: APIs for Google Calendar, Microsoft Outlook, etc.

[0507] Database: A database for storing audio data, text data, summarization and tagging data.

[0508] Specific actions and examples

[0509] 1. The user says "Start recording" to the device, which activates the device's built-in microphone and begins recording the voice input.

[0510] 2. The user enters a task, note, etc. by voice and then says "stop recording."

[0511] 3. The device stops recording and sends the recording data to the server.

[0512] 4. The server uses the Google Cloud Speech-to-Text API to perform speech recognition on the received audio data and convert it into text data.

[0513] 5. The server analyzes the text data acquired using spaCy or the Google Natural Language API to extract information about tasks, locations, and deadlines.

[0514] 6. The server generates a to-do list based on the extracted information and synchronizes it with schedule management tools such as Google Calendar and Microsoft Outlook.

[0515] 7. The server sets a reminder based on the information in the TODO list and sends that information to the device.

[0516] 8. At the specified time, the device notifies the user that "You have a book to return at the library."

[0517] 9. The server generates a summary of the speech input, tags it appropriately, and stores it in a database.

[0518] Prompt Sentence Examples

[0519] Here are some example prompts to input to a generative AI model:

[0520] When a user says, "I need to remember to return this book at the library tomorrow at 3 PM," explain the steps to use this voice input for task management and reminder notifications.

[0521] As described above, the present invention provides a system that allows users to manage tasks and set reminders efficiently using only voice input. Detailed processing steps and specific implementations will be described separately. This will greatly support users' daily work.

[0522] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0523] Step 1:

[0524] The user says "Start recording" to the device. The device receives this voice command as input, activates the built-in microphone, and starts recording. The device displays "Recording." Specifically, the device's microphone begins capturing voice input.

[0525] Input: User's voice command "Start recording"

[0526] Output: Start of recording state

[0527] Step 2:

[0528] The user inputs specific tasks and notes by voice. When recording is finished, the user says "Stop recording." With this input, the device stops recording and temporarily saves the recorded data. The device displays "Stop recording." As a specific operation, the recorded voice data is saved in the device.

[0529] Input: User voice command "stop recording" and voice input for tasks and notes

[0530] Output: Temporarily saved audio data

[0531] Step 3:

[0532] The device sends the temporarily saved audio data to the server using the HTTP or HTTPS protocol. The server receives the audio data and saves it in the specified directory.

[0533] Input: Temporarily saved audio data

[0534] Output: Audio data stored on the server

[0535] Step 4:

[0536] The server calls a speech recognition service such as the Google Cloud Speech-to-Text API and converts the speech data into text data. Specifically, the server sends the speech data to the API and stores the returned text data.

[0537] Input: Audio data stored on the server

[0538] Output: Text data generated by the speech recognition service

[0539] Step 5:

[0540] The server parses the acquired text data using spaCy and the Google Natural Language API, then performs syntax analysis, entity recognition, and intent analysis to extract important information about the task, location, and deadline.

[0541] Input: Text data obtained from the speech recognition service

[0542] Output: Extracted task, location, and deadline information

[0543] Step 6:

[0544] The server generates a to-do list based on the extracted information, and synchronizes the to-do list with the API of schedule management tools such as Google Calendar and Microsoft Outlook.

[0545] Input: Extracted task, location, and due date information

[0546] Output: Generated TODO list and synchronized schedule management tool information

[0547] Step 7:

[0548] The server sets reminders based on the information in the TODO list. Reminders are usually set 30 minutes before the task deadline. The server sends the set reminder information to the device.

[0549] Input: Generated TODO list

[0550] Output: Set reminder information

[0551] Step 8:

[0552] The device will display a reminder at the specified time. Specifically, the device will notify the user via a pop-up notification or alarm, saying, "You have a book to return at the library."

[0553] Input: Set reminder information

[0554] Output: Reminder notification

[0555] Step 9:

[0556] The server generates a summary of the speech input, tags it appropriately, and stores it in a database. Specifically, the server generates a summary and tags and records them in a database.

[0557] Input: Text data obtained through speech recognition and NLP

[0558] Output: Summarized and tagged data stored in a database

[0559] (Application example 1)

[0560] 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."

[0561] Conventional factory task management and reminder setting involve a lot of manual work, resulting in a lack of efficiency. In addition, when work instructions or confirmations are given using voice commands, tasks cannot be managed immediately and reminders must also be set manually, resulting in a significant drop in work efficiency.

[0562] 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.

[0563] In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for extracting tasks, locations, and deadlines from the text data. This enables factory task management using voice instructions to issue and confirm work instructions. Furthermore, the server is equipped with a function for automatically generating a to-do list based on the extracted tasks, locations, and deadlines, and for setting reminders, reducing manual work and enabling efficient task management and reminder setting.

[0564] "Voice input" refers to a method of inputting voice instructions or information into a device.

[0565] "Text data" refers to data obtained by converting voice input into text format.

[0566] A "task" is a specific piece of work or job.

[0567] A "location" is a geographic location or facility where a task is to be performed.

[0568] A "deadline" is the date and time or period by which a task should be completed.

[0569] A "TODO list" is a list of tasks that need to be completed.

[0570] "Reminder" is a function that notifies the user at specific times or under specific conditions.

[0571] A "summary" is text data that briefly summarizes long content.

[0572] "Tagging" is the process of assigning labels to data to make it easier to identify.

[0573] "Factory task management" is a method for managing work content and procedures in a factory.

[0574] This invention is a system for efficiently managing tasks in a factory. A user issues voice instructions to a terminal, and the system has the function of automating task management and reminder setting based on the voice instructions.

[0575] Voice input acceptance

[0576] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs conversations and work instructions as voice, and when completes, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0577] Voice Recognition

[0578] The server then sends the received voice data to a cloud-based speech recognition service, which converts the voice data into text. For example, if a user says, "Please don't forget to do machine maintenance on the main line tomorrow at 9 a.m.", the voice is converted into text data.

[0579] Natural Language Processing

[0580] The server receives the converted text data and analyzes it using a natural language processing (NLP) engine. The analysis includes syntactic analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "Maintain the machine," the location "Mainline," and the deadline "Tomorrow at 9:00 AM" are extracted.

[0581] Generate a TODO list

[0582] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, for example, by registering events directly in a calendar application.

[0583] Reminders and notifications

[0584] The server sets a reminder based on the TODO list. The set reminder sends a notification to the user's device shortly before the deadline (e.g., 30 minutes before). The device then presents the reminder to the user at the set time, informing them that "machine maintenance is scheduled for the main line."

[0585] Lifelog storage and tagging

[0586] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9 AM" would be generated and tagged with "main line," "machine," and "maintenance." This data is stored in a database and can be used for future searches and references.

[0587] Hardware and software used

[0588] The following hardware and software are used to implement this system:

[0589] Device: A device that accepts audio input and makes recordings. Examples: smartphone, smart glasses.

[0590] Server: Processes voice data, manages tasks, and sets reminders. Uses a speech recognition API and natural language processing engine.

[0591] Speech recognition service: A cloud-based API. For example, Google Cloud Speech-to-Text API.

[0592] Natural language processing engine: Analyzes text data. Example: Google Cloud Natural Language API.

[0593] Specific examples

[0594] For example, a user might say: "Please don't forget to perform machine maintenance on the mainline tomorrow at 9 AM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "Maintain machine," the location "Mainline," and the deadline "Tomorrow at 9 AM." The server uses this information to generate a to-do list and adds it to the user's calendar. The server then sets a reminder for 8:30 AM the next day, and the device notifies the user at the specified time. Finally, the server creates a summary "Maintain machine on the mainline tomorrow at 9 AM," tags it, and stores it in the database.

[0595] Example prompts for generative AI models

[0596] Analyze "Please remember to perform maintenance on the machine on the mainline at 9am tomorrow" to extract information about the task, location, and deadline.

[0597] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0598] Step 1:

[0599] The device accepts voice input from the user. The user issues the voice command "start recording," and the device begins recording the voice. The user inputs conversations and work instructions as voice, and when complete, says "stop recording." The device stops recording and saves the recorded voice data in memory.

[0600] Step 2:

[0601] The device sends the stored voice data to a server, which then sends the received voice data to a cloud-based voice recognition service for processing, which converts the voice data into text data, which the server receives.

[0602] Step 3:

[0603] The server sends the received text data to a natural language processing (NLP) engine. The NLP engine analyzes the text data and extracts important information through syntactic analysis, entity recognition, and intent analysis. For example, it identifies information such as tasks, locations, and deadlines. The server receives the analysis results and stores the extracted information in a database.

[0604] Step 4:

[0605] The server generates a to-do list based on the extracted task, location, and due date information, and then connects to the user's schedule management tool (e.g., calendar application) and synchronizes the generated to-do list, which adds the corresponding events to the user's calendar.

[0606] Step 5:

[0607] The server sets a reminder based on the TODO list. The reminder is set to a time a little before the due date (e.g. 30 minutes before). The server saves the reminder information in a database and triggers the reminder at the set time.

[0608] Step 6:

[0609] The terminal receives a reminder notification from the server. At the set time, the reminder is displayed on the terminal, and the terminal notifies the user that "machine maintenance is scheduled on the main line."

[0610] Step 7:

[0611] The server generates a summary of the speech input and tags it appropriately. The summary and tagged data are stored in a database for future search and reference. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9:00 AM" would be generated and tagged with "main line," "machine," and "maintenance."

[0612] 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.

[0613] The present invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. In a specific embodiment of this system, a server, a terminal, and a user work together.

[0614] Voice input acceptance

[0615] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the voice. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0616] Voice Recognition

[0617] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[0618] Natural Language Processing

[0619] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[0620] emotion recognition

[0621] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state. The emotion recognition engine determines emotions from, for example, the user's tone of voice and the way they speak. Here, it detects whether the user is nervous, excited, or calm.

[0622] Creating a TODO list and reflecting emotions

[0623] The server combines the extracted task information with the emotion recognition results to generate a to-do list. Task priorities can be adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks of higher importance.

[0624] Reminders and notifications

[0625] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[0626] Lifelog storage and tagging

[0627] A summary of the speech input is generated, including the user's emotional information. The summary is tagged on the server, with tags such as "library," "book," and "return," as well as emotional tags. This data is stored in a database for future use and search.

[0628] Specific examples

[0629] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[0630] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[0631] The processing flow will be explained below.

[0632] Step 1:

[0633] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[0634] Step 2:

[0635] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[0636] Step 3:

[0637] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[0638] Step 4:

[0639] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[0640] Step 5:

[0641] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[0642] Step 6:

[0643] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state, determining emotions from the tone and vocabulary of the voice.

[0644] Step 7:

[0645] The server integrates the extracted task information with the emotion recognition results to create structured data (e.g., JSON format), including the task, location, deadline, and emotional state.

[0646] Step 8:

[0647] The server updates the TODO list based on the generated structured data. Task priorities are adjusted based on the emotional information. For example, if the user is feeling stressed, tasks with higher importance are displayed first.

[0648] Step 9:

[0649] The server sets reminders based on the to-do list. For example, for a task due at 3:00 PM tomorrow, it sets a reminder for 2:30 PM tomorrow.

[0650] Step 10:

[0651] The server sends a notification to the user's device at the set reminder time, and the device notifies the user that "You have an appointment to return a book at the library."

[0652] Step 11:

[0653] The server generates a summary of the speech input, including emotional information. For example, summary: "Returning the book at the library tomorrow at 3 PM. The user is worried." The server assigns appropriate tags to the summary and stores it in a database.

[0654] Specific examples

[0655] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[0656] Example 2

[0657] 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."

[0658] Efficient task management and reminder setting are crucial for today's busy lifestyles. However, existing systems lack sufficient integration of natural language processing and emotion recognition technologies that utilize voice input, resulting in inadequate task prioritization and reminder setting. Furthermore, task management that takes the user's emotional state into account is inadequate, resulting in a lack of means to reduce the user's mental burden. Therefore, there is a need for a system that can provide appropriate task management and reminder setting that takes the user's emotional state into account based on voice input.

[0659] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for analyzing the voice data and identifying the emotional state. This makes it possible to improve the efficiency of task management using voice input and to prioritize tasks and set reminders taking into account the user's emotional state.

[0660] "Voice input" refers to the means by which a device receives user-uttered speech and processes it as digital data.

[0661] "Text data" is data that is generated by analyzing voice input and expressing it as a string of characters.

[0662] "Work" refers to the tasks or activities that a user must perform.

[0663] "Location" is data about the geographic location or place where work is performed.

[0664] A "deadline" is data that indicates the time or date by which work should be completed.

[0665] A "task list" is a list of multiple task data in an easy-to-manage format.

[0666] "Notifications" are alerts or reminders that inform users based on set times or circumstances.

[0667] A "summary" is a concise summary of speech input or other data.

[0668] "Tagging" is the act of assigning keywords and labels to data to classify and organize it.

[0669] "Emotional state" is information that indicates the user's psychological and emotional state.

[0670] "Priority" refers to the ranking of tasks based on their importance and urgency.

[0671] This invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. This system operates in cooperation with a server, a terminal, and a user.

[0672] Hardware and software used

[0673] The system utilizes the following hardware and software:

[0674] Device: A device that accepts voice input (e.g., smartphone, tablet, voice assistant device).

[0675] Server: Responsible for data processing and management (e.g. cloud server)

[0676] Speech recognition service: A cloud-based API that converts speech to text (e.g., Google Cloud Speech-to-Text API).

[0677] Natural language processing engine: Software that analyzes text data (e.g., spaCy, BERT model)

[0678] Emotion recognition engine: Software that analyzes emotional states from voice data (e.g., IBM Watson Tone Analyzer)

[0679] Voice input

[0680] The user speaks "Start recording" into the device, and the device starts recording the voice. The user then enters any necessary notes or tasks by voice, and when the recording is complete, speaks "Stop recording." The device then stops recording and sends the voice data to the server.

[0681] Voice Recognition

[0682] The server sends the received voice data to a voice recognition service, converts the voice data into text data, and then receives the text data and proceeds to the next step.

[0683] Natural Language Processing

[0684] The server inputs the acquired text data into a natural language processing engine and performs syntax analysis, entity recognition, and intent analysis. For example, it extracts the task "return the book" from the text data, the location "library," and the deadline "tomorrow at 3:00 PM."

[0685] emotion recognition

[0686] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, for example, determining emotions such as "worried" or "excited" from the tone of the voice and the way the words are used.

[0687] Generate a TODO list

[0688] The server combines the analysis results of the NLP engine and the emotion recognition engine to prioritize tasks and generate a TODO list. For example, if the user is very anxious, the task will be set to high priority.

[0689] Reminders and notifications

[0690] The server sets reminders based on the TODO list and sends notifications to the device. For example, for a task due "tomorrow at 3:00 PM," the server sets a reminder 30 minutes before the task. At the set time, the device notifies the user by voice or pop-up message that "You have an appointment to return a book at the library."

[0691] Lifelog storage and tagging

[0692] The server generates a lifelog that compiles the to-do list and the user's emotional information. The lifelog is tagged with tags such as "library," "book," and "return," as well as emotional tags such as "worried," and is stored in a database. This data can be used for future searches and references.

[0693] Specific examples

[0694] The user says, "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes the text data and extracts the task "return the book," the location "library," and the deadline "tomorrow at 3 PM." At the same time, the emotion recognition engine analyzes the user's emotional state from the voice and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the set reminder time. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[0695] Prompt Sentence Examples

[0696] "Don't forget to take the dog for a walk at 6pm this evening."

[0697] "Remind me that I have a meeting tomorrow morning at 9am"

[0698] "I want to remember to go to my friend's birthday party next Friday."

[0699] The present invention provides specific embodiments of a system that enables efficient task management and reminder setting from voice input and takes into account the emotional state of the user.

[0700] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0701] Step 1:

[0702] Voice input acceptance

[0703] The user speaks "Start recording" into the device. The device receives this voice command, activates the internal microphone, and begins recording audio.

[0704] The user inputs a conversation or task by voice, and when finished, says "stop recording." The device stops recording and temporarily saves the voice data.

[0705] Input: User's voice commands "Start recording" and "Stop recording" and input voice

[0706] Output: Temporarily saved audio data

[0707] Step 2:

[0708] Sending audio data to the server

[0709] The device sends the temporarily saved audio data to the server using HTTP or HTTPS as the communication protocol.

[0710] The device notifies the user that "recorded data will be sent to the server," and data transfer begins. Once the server confirms receipt, it notifies the device that "data has been received."

[0711] Input: Temporarily stored audio data

[0712] Output: Audio data sent to the server

[0713] Step 3:

[0714] Voice Recognition

[0715] The server sends the received voice data to a cloud-based speech recognition service, which converts the voice into text.

[0716] The server processes the voice data and logs "Converting voice data to text." When speech recognition is complete, it logs "Converting voice data to text."

[0717] Input: Audio data stored on the server

[0718] Output: Text data converted from audio

[0719] Step 4:

[0720] Natural Language Processing

[0721] The text data acquired by the server is input into a natural language processing engine, where it performs syntactic analysis, entity recognition, and intent analysis.

[0722] The server logs "Analyzing text data" and passes the data to the NLP engine. After analysis, it logs "Task information extracted." Specifically, it extracts the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM."

[0723] Input: Text data obtained from speech recognition

[0724] Output: Extracted task, location, and due date information

[0725] Step 5:

[0726] emotion recognition

[0727] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state.

[0728] The server logs "Applying emotion recognition engine" and then logs "User's emotional state detected" after analyzing the emotion. For example, it can determine emotions such as anxiety or excitement from the tone of voice and the way the words are used.

[0729] Input: Audio data stored on the server

[0730] Output: Determined emotional state

[0731] Step 6:

[0732] Generate a TODO list

[0733] The server integrates the analysis results of the NLP engine and emotion recognition engine, prioritizes tasks, and generates a TODO list.

[0734] The server logs "Generating a TODO list" and generates a list based on the extracted task information and emotion information. It also logs "TODO list generated." For example, if the user is very worried, it sets the task to high priority.

[0735] Input: Analysis results of the NLP engine and emotion recognition engine

[0736] Output: A prioritized to-do list

[0737] Step 7:

[0738] Set reminders

[0739] The server sets reminders based on the to-do list. For example, for a task due tomorrow at 3:00 PM, it sets a reminder 30 minutes before the task.

[0740] The server logs "Setting reminder" and logs "Reminder set."

[0741] Input: TODO list

[0742] Output: Set reminders

[0743] Step 8:

[0744] Reminder notifications

[0745] The server sends a reminder to the device at the set time. The device logs "Sending reminder notification" and notifies the user by voice or pop-up that "You have an appointment to return a book at the library."

[0746] Input: Set reminder

[0747] Output: Notification displayed on the user's device

[0748] Step 9:

[0749] Lifelog storage and tagging

[0750] The server generates a life log that compiles the to-do list and the user's emotional information and stores it in a database.

[0751] The server logs "Generating a lifelog" and "Lifelog saved." The lifelog is tagged with tags such as "library," "book," and "return," as well as emotion tags such as "worried."

[0752] Input: TODO list and emotional information

[0753] Output: Saved lifelog

[0754] (Application example 2)

[0755] 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."

[0756] Although task management systems that use voice input already exist, they generally only generate text data and extract task information, and do not take into account the user's emotional state when managing tasks or setting reminders. As a result, when workers are stressed or emotionally unstable, effective task management is difficult, which can lead to reduced work efficiency. Furthermore, when considering use in factories and other workplaces, a function that can detect workers' instructions in real time and adjust priorities is required.

[0757] 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.

[0758] In this invention, the server includes means for accepting voice input, means for generating text data from the accepted voice, means for extracting tasks, locations, and deadlines from the text data, means for adjusting task priorities based on emotional information, means for analyzing the emotional state of the worker and detecting stress, and means for presenting task instructions by voice. This enables effective task management that takes into account the emotional state of the worker, and allows for more appropriate reminder settings and task instructions. Furthermore, receiving instructions in real time through voice input and dynamically adjusting priorities is expected to improve work efficiency on the factory floor.

[0759] A "means for accepting voice input" is a device or software that captures the voice uttered by the user as digital data, allowing the system to use the voice for subsequent processing.

[0760] A "means for generating text data" is a software algorithm or service that analyzes audio data and expresses its contents as text information.

[0761] The "means for extracting tasks, locations, and deadlines" refers to a process or technology for identifying the tasks, the locations where the tasks are performed, and the deadlines for the tasks from the generated text data.

[0762] The "means for generating a task list" is a function or application that compiles in list form the tasks that the user needs to perform based on the extracted tasks, locations, and deadlines.

[0763] The "means for managing the task list and setting reminders" refers to a system or program for properly recording the generated task list and sending reminder notifications based on the specified date and time.

[0764] The "means for generating summaries and tagging of speech input" is a process for summarizing text and extracted information generated from speech data and tagging it to make the content understandable at a glance.

[0765] "Means for storing the generated summary and tagged data" refers to a function that records the summarized information and the associated tag data in a database or other storage device, allowing them to be reused and searched later.

[0766] The "means for notifying at the time of the reminder" is a mechanism that sends a notification to the user's device based on the set reminder date and time to notify the user of the scheduled work.

[0767] The "means for adjusting work priorities based on emotional information" is a mechanism for more efficient task management by changing work priorities based on the results of analyzing the emotional state of the worker.

[0768] "Means for analyzing the emotional state of a worker and detecting stress" refers to technologies and algorithms that analyze the emotional state of a worker from voice data, etc., and identify stress or other emotional states.

[0769] A "means for presenting work instructions by voice" is a device or program that transmits instructions or tasks to be performed by a worker by voice.

[0770] The present invention is a system that uses voice input to manage work instructions and adjusts work priorities based on worker emotion analysis. It is particularly intended for use on factory floors, improving work efficiency through real-time voice instructions.

[0771] Hardware and Software Configuration

[0772] The following hardware and software are used to realize this system.

[0773] Hardware: microphone, speaker, factory robot (with control board)

[0774] Software: Speech recognition API (e.g., general cloud-based API), natural language processing engine (e.g., SpaCy or Google Cloud Natural Language), emotion recognition API (e.g., IBM Watson Tone Analyzer), main server, database

[0775] Data processing flow

[0776] 1. Voice input acceptance

[0777] The user says "Start recording" into the microphone. The device receives this voice command and starts recording the voice. Next, the user says, "The next step is to supply material to the conveying line. This is a high priority." When recording is complete, the user says, "Stop recording." The device stops recording and sends the voice data to the server.

[0778] 2. Voice Recognition

[0779] The server sends the received voice data to a voice recognition API and converts it into text data. For example, a voice saying "The next step is to supply materials to the conveyor line. This is a high priority" is converted into text data saying "The next step is to supply materials to the conveyor line. This is a high priority."

[0780] 3. Natural Language Processing

[0781] The server that retrieves the text data uses an NLP engine to analyze the text data. The analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. In the above example, the extracted information is the task "supply materials to the conveyor line," the location "conveyor line," and "high priority."

[0782] 4. Emotion recognition

[0783] The server applies an emotion recognition API to the voice data to analyze the user's emotional state. The emotion recognition API determines the user's emotions from the tone of their voice and the way they speak. It then detects that the user is feeling stressed.

[0784] 5. Task list generation and emotional reflection

[0785] The server integrates the extracted task information with the emotion recognition results to generate a task list. Task priorities are adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks that are of high importance.

[0786] 6. Reminders and notifications

[0787] The server sets reminders based on the task list. The reminders send notifications to the user's terminal shortly before the deadline. The terminal then presents the reminder to the user at the set time, informing them that "The next step is to supply materials to the conveyor line. This is a high priority."

[0788] 7. Summarize and save voice input

[0789] A summary of the speech input is generated, including the user's emotional information. The tagging process is performed on the server, adding tags such as "transport line," "material supply," and "high priority" as well as emotional tags. This data is stored in a database for future use and search.

[0790] Examples and prompts

[0791] For example, a user might say: "The next step is to supply materials to the conveyor line. It's a high priority." The device records this speech and sends it to the server. The server then performs speech recognition and converts it into text data. The NLP engine then analyzes the speech and extracts the task "supply materials to the conveyor line," the location "conveyor line," and the phrase "high priority." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is feeling stressed. The server uses this information to generate a task list and set reminders. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which includes emotional information. All information is stored in a database.

[0792] Call prompt:

[0793] "What is your next task? Please tell me the priority."

[0794] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[0795] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0796] Step 1:

[0797] The user says "start recording" into the microphone. The device receives this voice command and starts recording the voice. The input is the voice command "start recording" and the output is the start of voice recording. Specifically, the microphone inside the device operates and records the voice as digital data.

[0798] Step 2:

[0799] The user speaks work instructions into the microphone. For example, "The next step is to supply materials to the conveyor line. This is a high priority." The input is the user's work instructions as voice data, and the output is the accumulation of recorded voice data. Specifically, the terminal continuously records the voice and saves it as digital data.

[0800] Step 3:

[0801] The user says "stop recording." The device receives this voice command and stops recording. The input is the voice command "stop recording," and the output is to stop recording and save the voice data. Specifically, the device stops recording and sends the saved voice data to the server.

[0802] Step 4:

[0803] The server sends the received voice data to a voice recognition API and converts it into text data. The input is voice data, and the output is the corresponding text data. Specifically, the server generates an API request and sends it to the voice recognition service. It then receives the text data returned by the voice recognition service.

[0804] Step 5:

[0805] The server analyzes the generated text data using a natural language processing engine to extract tasks, locations, and deadlines. The input is text data, and the output is the extracted task information. Specifically, the server parses the text data, performs entity recognition, and identifies important information through intent analysis.

[0806] Step 6:

[0807] The server sends the voice data to the emotion recognition API and analyzes the emotional state. The input is the voice data and the output is the emotion recognition result. Specifically, the server sends the voice data as an API request and receives the analysis result returned from the emotion recognition service.

[0808] Step 7:

[0809] The server integrates the extracted task information and emotion recognition results to generate a task list. The input is the task information and emotion recognition results, and the output is a task list with adjusted priorities. Specifically, the server compares the task information and emotion recognition results and applies an algorithm to determine the priorities.

[0810] Step 8:

[0811] The server sets a reminder and sends a reminder notification to the user's device at the specified time. The input is a task list and the reminder setting time, and the output is a notification to the device. Specifically, the server sets a timer and sends a notification message to the device when the timer goes off.

[0812] Step 9:

[0813] The device presents the reminder content to the user by voice. The input is the reminder notification from the server, and the output is the voice notification. Specifically, the device's speaker operates and plays the reminder content by voice.

[0814] Step 10:

[0815] The server generates a summary of the speech input, tags it, and stores it in a database. The input is speech data, text data, and emotion recognition results, and the output is a summary and tagged data. Specifically, the server applies a summary generation algorithm, adds relevant tags, and records the data in a database.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] [Third embodiment]

[0820] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0821] 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.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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).

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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."

[0832] The present invention provides a system that accepts voice input and efficiently manages tasks and sends reminders using speech recognition technology and natural language processing (NLP). To implement this system, a server, a terminal, and a user work together.

[0833] Voice input acceptance

[0834] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0835] Voice Recognition

[0836] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[0837] Natural Language Processing

[0838] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[0839] Generate a TODO list

[0840] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, for example, by directly registering events in Google Calendar or Outlook.

[0841] Reminders and notifications

[0842] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[0843] Lifelog storage and tagging

[0844] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Return the book at the library tomorrow at 3 PM" would be generated and tagged with "library," "book," and "return." This data is stored in a database for future search and reference.

[0845] Specific examples

[0846] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "return the book," the location "library," and the due date "tomorrow at 3 PM." The server then uses this information to create a to-do list and adds it to the user's calendar. The server then sets a reminder for the next day at 2:30 PM, and the device notifies the user at the specified time. Finally, the server creates a summary "return the book at the library tomorrow at 3 PM," tags it, and saves it in the database.

[0847] In this way, the present invention provides a specific embodiment of a system that supports a user's daily work by automating task management through voice input and efficiently setting reminders.

[0848] The processing flow will be explained below.

[0849] Step 1:

[0850] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[0851] Step 2:

[0852] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[0853] Step 3:

[0854] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[0855] Step 4:

[0856] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[0857] Step 5:

[0858] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[0859] Step 6:

[0860] The server then creates structured data based on the extracted information, specifically JSON format data that includes the task, location, and deadline.

[0861] Step 7:

[0862] The server updates the TODO list based on the generated structured data. The server manages the TODO list and synchronizes it with the user's schedule management tool (e.g., calendar).

[0863] Step 8:

[0864] The server sets a reminder according to the task deadline, and determines the time to notify the user based on the reminder setting time.

[0865] Step 9:

[0866] The server sends a notification to the user's device at the reminder time, and the device displays a notification to the user, such as "You have an appointment to return a book at the library."

[0867] Step 10:

[0868] The server generates a summary of the speech input and stores it as text data. The server also assigns appropriate tags to the summary and stores it in a database.

[0869] Through this step, the specific processing of the system that automates everything from voice input to task management and reminder notifications is realized.

[0870] Example 1

[0871] 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."

[0872] Conventional task management and reminder setting systems require users to manually input tasks and set appropriate reminders, making operation cumbersome and making efficient schedule management difficult. Furthermore, when using voice input, accurate task extraction and appropriate reminder setting are difficult due to insufficient voice recognition accuracy and natural language processing capabilities. The present invention aims to solve these problems and provide a system that allows users to efficiently and accurately manage tasks and set reminders using only voice input.

[0873] 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.

[0874] In this invention, the server includes means for converting received voice data into text data using voice recognition technology, means for analyzing the text data using natural language processing technology to extract tasks, locations, and deadlines, and means for generating a to-do list based on the extracted tasks, locations, and deadlines. This allows the user to accurately register and manage tasks using only voice input, and realizes efficient reminder setting and notifications.

[0875] "User" refers to a person who uses voice input to manage tasks and set reminders.

[0876] "Terminal" refers to a device that accepts and records voice input when a user issues a voice command.

[0877] "Server" refers to a system that receives voice data sent from a terminal, analyzes the data using voice recognition technology and natural language processing technology, and manages tasks and sets reminders.

[0878] "Voice input" refers to voice data such as voice commands, notes, and task instructions that a user issues to a terminal.

[0879] "Recording" refers to the act of the terminal recording the user's voice input.

[0880] "Voice data" refers to digital audio information generated by a terminal recording a user's voice input.

[0881] "Voice recognition technology" refers to the technology that analyzes voice data and converts it into text data.

[0882] "Text data" refers to information of a character string generated from voice data using voice recognition technology.

[0883] "Natural language processing technology" refers to the technology that analyzes text data and extracts information such as tasks, locations, and deadlines.

[0884] A "task" refers to an action or task that a user wants to record.

[0885] "Location" refers to the specific location or facility where the task is performed.

[0886] A "deadline" refers to the date and time by which a task should be performed.

[0887] A "TODO list" is a list that is generated based on extracted tasks, locations, and deadlines and is used to manage a user's schedule.

[0888] "Reminder" refers to a function that is set based on a TODO list and notifies the user.

[0889] A "summary" refers to a short text summary of the main parts of the user's voice input.

[0890] "Tagging" refers to the act of adding relevant keywords or categories to a summary.

[0891] "Storage" refers to the act of storing the generated data in a storage device such as a database.

[0892] "Notification" refers to the act of sending an alert or message to the user at the set reminder time.

[0893] MODE FOR CARRYING OUT THE INVENTION

[0894] The present invention provides a system that efficiently utilizes a user's voice input for task management and reminder setting. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail an embodiment of the present invention.

[0895] Program processing overview

[0896] This system works in cooperation with the device, server, and user. When the user issues a voice command, the device accepts the voice input and sends the recorded voice data to the server. The server analyzes the voice data using speech recognition and natural language processing (NLP) technology to extract information such as tasks, locations, and deadlines. Based on the extracted information, the server generates a to-do list and synchronizes it with the user's schedule management tool. The server then sets reminders and sends notifications to the user's device at the specified time. The server also summarizes and tags the voice input and stores it in a database.

[0897] Hardware and software used

[0898] The following hardware and software are used to implement this system:

[0899] Device: Smartphone, tablet, or computer with voice input

[0900] Server: Cloud or on-premise server

[0901] Speech recognition technology: Google Cloud Speech-to-Text API, etc.

[0902] Natural language processing technology: spaCy, Google Natural Language API, etc.

[0903] Schedule management tools: APIs for Google Calendar, Microsoft Outlook, etc.

[0904] Database: A database for storing audio data, text data, summarization and tagging data.

[0905] Specific actions and examples

[0906] 1. The user says "Start recording" to the device, which activates the device's built-in microphone and begins recording the voice input.

[0907] 2. The user enters a task, note, etc. by voice and then says "stop recording."

[0908] 3. The device stops recording and sends the recording data to the server.

[0909] 4. The server uses the Google Cloud Speech-to-Text API to perform speech recognition on the received audio data and convert it into text data.

[0910] 5. The server analyzes the text data acquired using spaCy or the Google Natural Language API to extract information about tasks, locations, and deadlines.

[0911] 6. The server generates a to-do list based on the extracted information and synchronizes it with schedule management tools such as Google Calendar and Microsoft Outlook.

[0912] 7. The server sets a reminder based on the information in the TODO list and sends that information to the device.

[0913] 8. At the specified time, the device notifies the user that "You have a book to return at the library."

[0914] 9. The server generates a summary of the speech input, tags it appropriately, and stores it in a database.

[0915] Prompt Sentence Examples

[0916] Here are some example prompts to input to a generative AI model:

[0917] When a user says, "I need to remember to return this book at the library tomorrow at 3 PM," explain the steps to use this voice input for task management and reminder notifications.

[0918] As described above, the present invention provides a system that allows users to manage tasks and set reminders efficiently using only voice input. Detailed processing steps and specific implementations will be described separately. This will greatly support users' daily work.

[0919] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0920] Step 1:

[0921] The user says "Start recording" to the device. The device receives this voice command as input, activates the built-in microphone, and starts recording. The device displays "Recording." Specifically, the device's microphone begins capturing voice input.

[0922] Input: User's voice command "Start recording"

[0923] Output: Start of recording state

[0924] Step 2:

[0925] The user inputs specific tasks and notes by voice. When recording is finished, the user says "Stop recording." With this input, the device stops recording and temporarily saves the recorded data. The device displays "Stop recording." As a specific operation, the recorded voice data is saved in the device.

[0926] Input: User voice command "stop recording" and voice input for tasks and notes

[0927] Output: Temporarily saved audio data

[0928] Step 3:

[0929] The device sends the temporarily saved audio data to the server using the HTTP or HTTPS protocol. The server receives the audio data and saves it in the specified directory.

[0930] Input: Temporarily saved audio data

[0931] Output: Audio data stored on the server

[0932] Step 4:

[0933] The server calls a speech recognition service such as the Google Cloud Speech-to-Text API and converts the speech data into text data. Specifically, the server sends the speech data to the API and stores the returned text data.

[0934] Input: Audio data stored on the server

[0935] Output: Text data generated by the speech recognition service

[0936] Step 5:

[0937] The server parses the acquired text data using spaCy and the Google Natural Language API, then performs syntax analysis, entity recognition, and intent analysis to extract important information about the task, location, and deadline.

[0938] Input: Text data obtained from the speech recognition service

[0939] Output: Extracted task, location, and deadline information

[0940] Step 6:

[0941] The server generates a to-do list based on the extracted information, and synchronizes the to-do list with the API of schedule management tools such as Google Calendar and Microsoft Outlook.

[0942] Input: Extracted task, location, and due date information

[0943] Output: Generated TODO list and synchronized schedule management tool information

[0944] Step 7:

[0945] The server sets reminders based on the information in the TODO list. Reminders are usually set 30 minutes before the task deadline. The server sends the set reminder information to the device.

[0946] Input: Generated TODO list

[0947] Output: Set reminder information

[0948] Step 8:

[0949] The device will display a reminder at the specified time. Specifically, the device will notify the user via a pop-up notification or alarm, saying, "You have a book to return at the library."

[0950] Input: Set reminder information

[0951] Output: Reminder notification

[0952] Step 9:

[0953] The server generates a summary of the speech input, tags it appropriately, and stores it in a database. Specifically, the server generates a summary and tags and records them in a database.

[0954] Input: Text data obtained through speech recognition and NLP

[0955] Output: Summarized and tagged data stored in a database

[0956] (Application example 1)

[0957] 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."

[0958] Conventional factory task management and reminder setting involve a lot of manual work, resulting in a lack of efficiency. In addition, when work instructions or confirmations are given using voice commands, tasks cannot be managed immediately and reminders must also be set manually, resulting in a significant drop in work efficiency.

[0959] 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.

[0960] In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for extracting tasks, locations, and deadlines from the text data. This enables factory task management using voice instructions to issue and confirm work instructions. Furthermore, the server is equipped with a function for automatically generating a to-do list based on the extracted tasks, locations, and deadlines, and for setting reminders, reducing manual work and enabling efficient task management and reminder setting.

[0961] "Voice input" refers to a method of inputting voice instructions or information into a device.

[0962] "Text data" refers to data obtained by converting voice input into text format.

[0963] A "task" is a specific piece of work or job.

[0964] A "location" is a geographic location or facility where a task is to be performed.

[0965] A "deadline" is the date and time or period by which a task should be completed.

[0966] A "TODO list" is a list of tasks that need to be completed.

[0967] "Reminder" is a function that notifies the user at specific times or under specific conditions.

[0968] A "summary" is text data that briefly summarizes long content.

[0969] "Tagging" is the process of assigning labels to data to make it easier to identify.

[0970] "Factory task management" is a method for managing work content and procedures in a factory.

[0971] This invention is a system for efficiently managing tasks in a factory. A user issues voice instructions to a terminal, and the system has the function of automating task management and reminder setting based on the voice instructions.

[0972] Voice input acceptance

[0973] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs conversations and work instructions as voice, and when completes, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[0974] Voice Recognition

[0975] The server then sends the received voice data to a cloud-based speech recognition service, which converts the voice data into text. For example, if a user says, "Please don't forget to do machine maintenance on the main line tomorrow at 9 a.m.", the voice is converted into text data.

[0976] Natural Language Processing

[0977] The server receives the converted text data and analyzes it using a natural language processing (NLP) engine. The analysis includes syntactic analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "Maintain the machine," the location "Mainline," and the deadline "Tomorrow at 9:00 AM" are extracted.

[0978] Generate a TODO list

[0979] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, for example, by registering events directly in a calendar application.

[0980] Reminders and notifications

[0981] The server sets a reminder based on the TODO list. The set reminder sends a notification to the user's device shortly before the deadline (e.g., 30 minutes before). The device then presents the reminder to the user at the set time, informing them that "machine maintenance is scheduled for the main line."

[0982] Lifelog storage and tagging

[0983] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9 AM" would be generated and tagged with "main line," "machine," and "maintenance." This data is stored in a database and can be used for future searches and references.

[0984] Hardware and software used

[0985] The following hardware and software are used to implement this system:

[0986] Device: A device that accepts audio input and makes recordings. Examples: smartphone, smart glasses.

[0987] Server: Processes voice data, manages tasks, and sets reminders. Uses a speech recognition API and natural language processing engine.

[0988] Speech recognition service: A cloud-based API. For example, Google Cloud Speech-to-Text API.

[0989] Natural language processing engine: Analyzes text data. Example: Google Cloud Natural Language API.

[0990] Specific examples

[0991] For example, a user might say: "Please don't forget to perform machine maintenance on the mainline tomorrow at 9 AM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "Maintain machine," the location "Mainline," and the deadline "Tomorrow at 9 AM." The server uses this information to generate a to-do list and adds it to the user's calendar. The server then sets a reminder for 8:30 AM the next day, and the device notifies the user at the specified time. Finally, the server creates a summary "Maintain machine on the mainline tomorrow at 9 AM," tags it, and stores it in the database.

[0992] Example prompts for generative AI models

[0993] Analyze "Please remember to perform maintenance on the machine on the mainline at 9am tomorrow" to extract information about the task, location, and deadline.

[0994] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0995] Step 1:

[0996] The device accepts voice input from the user. The user issues the voice command "start recording," and the device begins recording the voice. The user inputs conversations and work instructions as voice, and when complete, says "stop recording." The device stops recording and saves the recorded voice data in memory.

[0997] Step 2:

[0998] The device sends the stored voice data to a server, which then sends the received voice data to a cloud-based voice recognition service for processing, which converts the voice data into text data, which the server receives.

[0999] Step 3:

[1000] The server sends the received text data to a natural language processing (NLP) engine. The NLP engine analyzes the text data and extracts important information through syntactic analysis, entity recognition, and intent analysis. For example, it identifies information such as tasks, locations, and deadlines. The server receives the analysis results and stores the extracted information in a database.

[1001] Step 4:

[1002] The server generates a to-do list based on the extracted task, location, and due date information, and then connects to the user's schedule management tool (e.g., calendar application) and synchronizes the generated to-do list, which adds the corresponding events to the user's calendar.

[1003] Step 5:

[1004] The server sets a reminder based on the TODO list. The reminder is set to a time a little before the due date (e.g. 30 minutes before). The server saves the reminder information in a database and triggers the reminder at the set time.

[1005] Step 6:

[1006] The terminal receives a reminder notification from the server. At the set time, the reminder is displayed on the terminal, and the terminal notifies the user that "machine maintenance is scheduled on the main line."

[1007] Step 7:

[1008] The server generates a summary of the speech input and tags it appropriately. The summary and tagged data are stored in a database for future search and reference. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9:00 AM" would be generated and tagged with "main line," "machine," and "maintenance."

[1009] 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.

[1010] The present invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. In a specific embodiment of this system, a server, a terminal, and a user work together.

[1011] Voice input acceptance

[1012] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the voice. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[1013] Voice Recognition

[1014] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[1015] Natural Language Processing

[1016] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[1017] emotion recognition

[1018] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state. The emotion recognition engine determines emotions from, for example, the user's tone of voice and the way they speak. Here, it detects whether the user is nervous, excited, or calm.

[1019] Creating a TODO list and reflecting emotions

[1020] The server combines the extracted task information with the emotion recognition results to generate a to-do list. Task priorities can be adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks of higher importance.

[1021] Reminders and notifications

[1022] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[1023] Lifelog storage and tagging

[1024] A summary of the speech input is generated, including the user's emotional information. The summary is tagged on the server, with tags such as "library," "book," and "return," as well as emotional tags. This data is stored in a database for future use and search.

[1025] Specific examples

[1026] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[1027] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[1028] The processing flow will be explained below.

[1029] Step 1:

[1030] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[1031] Step 2:

[1032] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[1033] Step 3:

[1034] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[1035] Step 4:

[1036] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[1037] Step 5:

[1038] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[1039] Step 6:

[1040] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state, determining emotions from the tone and vocabulary of the voice.

[1041] Step 7:

[1042] The server integrates the extracted task information with the emotion recognition results to create structured data (e.g., JSON format), including the task, location, deadline, and emotional state.

[1043] Step 8:

[1044] The server updates the TODO list based on the generated structured data. Task priorities are adjusted based on the emotional information. For example, if the user is feeling stressed, tasks with higher importance are displayed first.

[1045] Step 9:

[1046] The server sets reminders based on the to-do list. For example, for a task due at 3:00 PM tomorrow, it sets a reminder for 2:30 PM tomorrow.

[1047] Step 10:

[1048] The server sends a notification to the user's device at the set reminder time, and the device notifies the user that "You have an appointment to return a book at the library."

[1049] Step 11:

[1050] The server generates a summary of the speech input, including emotional information. For example, summary: "Returning the book at the library tomorrow at 3 PM. The user is worried." The server assigns appropriate tags to the summary and stores it in a database.

[1051] Specific examples

[1052] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[1053] Example 2

[1054] 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."

[1055] Efficient task management and reminder setting are crucial for today's busy lifestyles. However, existing systems lack sufficient integration of natural language processing and emotion recognition technologies that utilize voice input, resulting in inadequate task prioritization and reminder setting. Furthermore, task management that takes the user's emotional state into account is inadequate, resulting in a lack of means to reduce the user's mental burden. Therefore, there is a need for a system that can provide appropriate task management and reminder setting that takes the user's emotional state into account based on voice input.

[1056] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for analyzing the voice data and identifying the emotional state. This makes it possible to improve the efficiency of task management using voice input and to prioritize tasks and set reminders taking into account the user's emotional state.

[1057] "Voice input" refers to the means by which a device receives user-uttered speech and processes it as digital data.

[1058] "Text data" is data that is generated by analyzing voice input and expressing it as a string of characters.

[1059] "Work" refers to the tasks or activities that a user must perform.

[1060] "Location" is data about the geographic location or place where work is performed.

[1061] A "deadline" is data that indicates the time or date by which work should be completed.

[1062] A "task list" is a list of multiple task data in an easy-to-manage format.

[1063] "Notifications" are alerts or reminders that inform users based on set times or circumstances.

[1064] A "summary" is a concise summary of speech input or other data.

[1065] "Tagging" is the act of assigning keywords and labels to data to classify and organize it.

[1066] "Emotional state" is information that indicates the user's psychological and emotional state.

[1067] "Priority" refers to the ranking of tasks based on their importance and urgency.

[1068] This invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. This system operates in cooperation with a server, a terminal, and a user.

[1069] Hardware and software used

[1070] The system utilizes the following hardware and software:

[1071] Device: A device that accepts voice input (e.g., smartphone, tablet, voice assistant device).

[1072] Server: Responsible for data processing and management (e.g. cloud server)

[1073] Speech recognition service: A cloud-based API that converts speech to text (e.g., Google Cloud Speech-to-Text API).

[1074] Natural language processing engine: Software that analyzes text data (e.g., spaCy, BERT model)

[1075] Emotion recognition engine: Software that analyzes emotional states from voice data (e.g., IBM Watson Tone Analyzer)

[1076] Voice input

[1077] The user speaks "Start recording" into the device, and the device starts recording the voice. The user then enters any necessary notes or tasks by voice, and when the recording is complete, speaks "Stop recording." The device then stops recording and sends the voice data to the server.

[1078] Voice Recognition

[1079] The server sends the received voice data to a voice recognition service, converts the voice data into text data, and then receives the text data and proceeds to the next step.

[1080] Natural Language Processing

[1081] The server inputs the acquired text data into a natural language processing engine and performs syntax analysis, entity recognition, and intent analysis. For example, it extracts the task "return the book" from the text data, the location "library," and the deadline "tomorrow at 3:00 PM."

[1082] emotion recognition

[1083] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, for example, determining emotions such as "worried" or "excited" from the tone of the voice and the way the words are used.

[1084] Generate a TODO list

[1085] The server combines the analysis results of the NLP engine and the emotion recognition engine to prioritize tasks and generate a TODO list. For example, if the user is very anxious, the task will be set to high priority.

[1086] Reminders and notifications

[1087] The server sets reminders based on the TODO list and sends notifications to the device. For example, for a task due "tomorrow at 3:00 PM," the server sets a reminder 30 minutes before the task. At the set time, the device notifies the user by voice or pop-up message that "You have an appointment to return a book at the library."

[1088] Lifelog storage and tagging

[1089] The server generates a lifelog that compiles the to-do list and the user's emotional information. The lifelog is tagged with tags such as "library," "book," and "return," as well as emotional tags such as "worried," and is stored in a database. This data can be used for future searches and references.

[1090] Specific examples

[1091] The user says, "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes the text data and extracts the task "return the book," the location "library," and the deadline "tomorrow at 3 PM." At the same time, the emotion recognition engine analyzes the user's emotional state from the voice and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the set reminder time. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[1092] Prompt Sentence Examples

[1093] "Don't forget to take the dog for a walk at 6pm this evening."

[1094] "Remind me that I have a meeting tomorrow morning at 9am"

[1095] "I want to remember to go to my friend's birthday party next Friday."

[1096] The present invention provides specific embodiments of a system that enables efficient task management and reminder setting from voice input and takes into account the emotional state of the user.

[1097] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1098] Step 1:

[1099] Voice input acceptance

[1100] The user speaks "Start recording" into the device. The device receives this voice command, activates the internal microphone, and begins recording audio.

[1101] The user inputs a conversation or task by voice, and when finished, says "stop recording." The device stops recording and temporarily saves the voice data.

[1102] Input: User's voice commands "Start recording" and "Stop recording" and input voice

[1103] Output: Temporarily saved audio data

[1104] Step 2:

[1105] Sending audio data to the server

[1106] The device sends the temporarily saved audio data to the server using HTTP or HTTPS as the communication protocol.

[1107] The device notifies the user that "recorded data will be sent to the server," and data transfer begins. Once the server confirms receipt, it notifies the device that "data has been received."

[1108] Input: Temporarily stored audio data

[1109] Output: Audio data sent to the server

[1110] Step 3:

[1111] Voice Recognition

[1112] The server sends the received voice data to a cloud-based speech recognition service, which converts the voice into text.

[1113] The server processes the voice data and logs "Converting voice data to text." When speech recognition is complete, it logs "Converting voice data to text."

[1114] Input: Audio data stored on the server

[1115] Output: Text data converted from audio

[1116] Step 4:

[1117] Natural Language Processing

[1118] The text data acquired by the server is input into a natural language processing engine, where it performs syntactic analysis, entity recognition, and intent analysis.

[1119] The server logs "Analyzing text data" and passes the data to the NLP engine. After analysis, it logs "Task information extracted." Specifically, it extracts the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM."

[1120] Input: Text data obtained from speech recognition

[1121] Output: Extracted task, location, and due date information

[1122] Step 5:

[1123] emotion recognition

[1124] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state.

[1125] The server logs "Applying emotion recognition engine" and then logs "User's emotional state detected" after analyzing the emotion. For example, it can determine emotions such as anxiety or excitement from the tone of voice and the way the words are used.

[1126] Input: Audio data stored on the server

[1127] Output: Determined emotional state

[1128] Step 6:

[1129] Generate a TODO list

[1130] The server integrates the analysis results of the NLP engine and emotion recognition engine, prioritizes tasks, and generates a TODO list.

[1131] The server logs "Generating a TODO list" and generates a list based on the extracted task information and emotion information. It also logs "TODO list generated." For example, if the user is very worried, it sets the task to high priority.

[1132] Input: Analysis results of the NLP engine and emotion recognition engine

[1133] Output: A prioritized to-do list

[1134] Step 7:

[1135] Set reminders

[1136] The server sets reminders based on the to-do list. For example, for a task due tomorrow at 3:00 PM, it sets a reminder 30 minutes before the task.

[1137] The server logs "Setting reminder" and logs "Reminder set."

[1138] Input: TODO list

[1139] Output: Set reminders

[1140] Step 8:

[1141] Reminder notifications

[1142] The server sends a reminder to the device at the set time. The device logs "Sending reminder notification" and notifies the user by voice or pop-up that "You have an appointment to return a book at the library."

[1143] Input: Set reminder

[1144] Output: Notification displayed on the user's device

[1145] Step 9:

[1146] Lifelog storage and tagging

[1147] The server generates a life log that compiles the to-do list and the user's emotional information and stores it in a database.

[1148] The server logs "Generating a lifelog" and "Lifelog saved." The lifelog is tagged with tags such as "library," "book," and "return," as well as emotion tags such as "worried."

[1149] Input: TODO list and emotional information

[1150] Output: Saved lifelog

[1151] (Application example 2)

[1152] 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."

[1153] Although task management systems that use voice input already exist, they generally only generate text data and extract task information, and do not take into account the user's emotional state when managing tasks or setting reminders. As a result, when workers are stressed or emotionally unstable, effective task management is difficult, which can lead to reduced work efficiency. Furthermore, when considering use in factories and other workplaces, a function that can detect workers' instructions in real time and adjust priorities is required.

[1154] 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.

[1155] In this invention, the server includes means for accepting voice input, means for generating text data from the accepted voice, means for extracting tasks, locations, and deadlines from the text data, means for adjusting task priorities based on emotional information, means for analyzing the emotional state of the worker and detecting stress, and means for presenting task instructions by voice. This enables effective task management that takes into account the emotional state of the worker, and allows for more appropriate reminder settings and task instructions. Furthermore, receiving instructions in real time through voice input and dynamically adjusting priorities is expected to improve work efficiency on the factory floor.

[1156] A "means for accepting voice input" is a device or software that captures the voice uttered by the user as digital data, allowing the system to use the voice for subsequent processing.

[1157] A "means for generating text data" is a software algorithm or service that analyzes audio data and expresses its contents as text information.

[1158] The "means for extracting tasks, locations, and deadlines" refers to a process or technology for identifying the tasks, the locations where the tasks are performed, and the deadlines for the tasks from the generated text data.

[1159] The "means for generating a task list" is a function or application that compiles in list form the tasks that the user needs to perform based on the extracted tasks, locations, and deadlines.

[1160] The "means for managing the task list and setting reminders" refers to a system or program for properly recording the generated task list and sending reminder notifications based on the specified date and time.

[1161] The "means for generating summaries and tagging of speech input" is a process for summarizing text and extracted information generated from speech data and tagging it to make the content understandable at a glance.

[1162] "Means for storing the generated summary and tagged data" refers to a function that records the summarized information and the associated tag data in a database or other storage device, allowing them to be reused and searched later.

[1163] The "means for notifying at the time of the reminder" is a mechanism that sends a notification to the user's device based on the set reminder date and time to notify the user of the scheduled work.

[1164] The "means for adjusting work priorities based on emotional information" is a mechanism for more efficient task management by changing work priorities based on the results of analyzing the emotional state of the worker.

[1165] "Means for analyzing the emotional state of a worker and detecting stress" refers to technologies and algorithms that analyze the emotional state of a worker from voice data, etc., and identify stress or other emotional states.

[1166] A "means for presenting work instructions by voice" is a device or program that transmits instructions or tasks to be performed by a worker by voice.

[1167] The present invention is a system that uses voice input to manage work instructions and adjusts work priorities based on worker emotion analysis. It is particularly intended for use on factory floors, improving work efficiency through real-time voice instructions.

[1168] Hardware and Software Configuration

[1169] The following hardware and software are used to realize this system.

[1170] Hardware: microphone, speaker, factory robot (with control board)

[1171] Software: Speech recognition API (e.g., general cloud-based API), natural language processing engine (e.g., SpaCy or Google Cloud Natural Language), emotion recognition API (e.g., IBM Watson Tone Analyzer), main server, database

[1172] Data processing flow

[1173] 1. Voice input acceptance

[1174] The user says "Start recording" into the microphone. The device receives this voice command and starts recording the voice. Next, the user says, "The next step is to supply material to the conveying line. This is a high priority." When recording is complete, the user says, "Stop recording." The device stops recording and sends the voice data to the server.

[1175] 2. Voice Recognition

[1176] The server sends the received voice data to a voice recognition API and converts it into text data. For example, a voice saying "The next step is to supply materials to the conveyor line. This is a high priority" is converted into text data saying "The next step is to supply materials to the conveyor line. This is a high priority."

[1177] 3. Natural Language Processing

[1178] The server that retrieves the text data uses an NLP engine to analyze the text data. The analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. In the above example, the extracted information is the task "supply materials to the conveyor line," the location "conveyor line," and "high priority."

[1179] 4. Emotion recognition

[1180] The server applies an emotion recognition API to the voice data to analyze the user's emotional state. The emotion recognition API determines the user's emotions from the tone of their voice and the way they speak. It then detects that the user is feeling stressed.

[1181] 5. Task list generation and emotional reflection

[1182] The server integrates the extracted task information with the emotion recognition results to generate a task list. Task priorities are adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks that are of high importance.

[1183] 6. Reminders and notifications

[1184] The server sets reminders based on the task list. The reminders send notifications to the user's terminal shortly before the deadline. The terminal then presents the reminder to the user at the set time, informing them that "The next step is to supply materials to the conveyor line. This is a high priority."

[1185] 7. Summarize and save voice input

[1186] A summary of the speech input is generated, including the user's emotional information. The tagging process is performed on the server, adding tags such as "transport line," "material supply," and "high priority" as well as emotional tags. This data is stored in a database for future use and search.

[1187] Examples and prompts

[1188] For example, a user might say: "The next step is to supply materials to the conveyor line. It's a high priority." The device records this speech and sends it to the server. The server then performs speech recognition and converts it into text data. The NLP engine then analyzes the speech and extracts the task "supply materials to the conveyor line," the location "conveyor line," and the phrase "high priority." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is feeling stressed. The server uses this information to generate a task list and set reminders. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which includes emotional information. All information is stored in a database.

[1189] Call prompt:

[1190] "What is your next task? Please tell me the priority."

[1191] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[1192] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1193] Step 1:

[1194] The user says "start recording" into the microphone. The device receives this voice command and starts recording the voice. The input is the voice command "start recording" and the output is the start of voice recording. Specifically, the microphone inside the device operates and records the voice as digital data.

[1195] Step 2:

[1196] The user speaks work instructions into the microphone. For example, "The next step is to supply materials to the conveyor line. This is a high priority." The input is the user's work instructions as voice data, and the output is the accumulation of recorded voice data. Specifically, the terminal continuously records the voice and saves it as digital data.

[1197] Step 3:

[1198] The user says "stop recording." The device receives this voice command and stops recording. The input is the voice command "stop recording," and the output is to stop recording and save the voice data. Specifically, the device stops recording and sends the saved voice data to the server.

[1199] Step 4:

[1200] The server sends the received voice data to a voice recognition API and converts it into text data. The input is voice data, and the output is the corresponding text data. Specifically, the server generates an API request and sends it to the voice recognition service. It then receives the text data returned by the voice recognition service.

[1201] Step 5:

[1202] The server analyzes the generated text data using a natural language processing engine to extract tasks, locations, and deadlines. The input is text data, and the output is the extracted task information. Specifically, the server parses the text data, performs entity recognition, and identifies important information through intent analysis.

[1203] Step 6:

[1204] The server sends the voice data to the emotion recognition API and analyzes the emotional state. The input is the voice data and the output is the emotion recognition result. Specifically, the server sends the voice data as an API request and receives the analysis result returned from the emotion recognition service.

[1205] Step 7:

[1206] The server integrates the extracted task information and emotion recognition results to generate a task list. The input is the task information and emotion recognition results, and the output is a task list with adjusted priorities. Specifically, the server compares the task information and emotion recognition results and applies an algorithm to determine the priorities.

[1207] Step 8:

[1208] The server sets a reminder and sends a reminder notification to the user's device at the specified time. The input is a task list and the reminder setting time, and the output is a notification to the device. Specifically, the server sets a timer and sends a notification message to the device when the timer goes off.

[1209] Step 9:

[1210] The device presents the reminder content to the user by voice. The input is the reminder notification from the server, and the output is the voice notification. Specifically, the device's speaker operates and plays the reminder content by voice.

[1211] Step 10:

[1212] The server generates a summary of the speech input, tags it, and stores it in a database. The input is speech data, text data, and emotion recognition results, and the output is a summary and tagged data. Specifically, the server applies a summary generation algorithm, adds relevant tags, and records the data in a database.

[1213] 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.

[1214] 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.

[1215] 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.

[1216] [Fourth embodiment]

[1217] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1218] 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.

[1219] 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).

[1220] 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.

[1221] 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.

[1222] 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).

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] 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.

[1229] 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."

[1230] The present invention provides a system that accepts voice input and efficiently manages tasks and sends reminders using speech recognition technology and natural language processing (NLP). To implement this system, a server, a terminal, and a user work together.

[1231] Voice input acceptance

[1232] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[1233] Voice Recognition

[1234] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[1235] Natural Language Processing

[1236] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[1237] Generate a TODO list

[1238] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, for example, by directly registering events in Google Calendar or Outlook.

[1239] Reminders and notifications

[1240] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[1241] Lifelog storage and tagging

[1242] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Return the book at the library tomorrow at 3 PM" would be generated and tagged with "library," "book," and "return." This data is stored in a database for future search and reference.

[1243] Specific examples

[1244] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "return the book," the location "library," and the due date "tomorrow at 3 PM." The server then uses this information to create a to-do list and adds it to the user's calendar. The server then sets a reminder for the next day at 2:30 PM, and the device notifies the user at the specified time. Finally, the server creates a summary "return the book at the library tomorrow at 3 PM," tags it, and saves it in the database.

[1245] In this way, the present invention provides a specific embodiment of a system that supports a user's daily work by automating task management through voice input and efficiently setting reminders.

[1246] The processing flow will be explained below.

[1247] Step 1:

[1248] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[1249] Step 2:

[1250] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[1251] Step 3:

[1252] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[1253] Step 4:

[1254] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[1255] Step 5:

[1256] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[1257] Step 6:

[1258] The server then creates structured data based on the extracted information, specifically JSON format data that includes the task, location, and deadline.

[1259] Step 7:

[1260] The server updates the TODO list based on the generated structured data. The server manages the TODO list and synchronizes it with the user's schedule management tool (e.g., calendar).

[1261] Step 8:

[1262] The server sets a reminder according to the task deadline, and determines the time to notify the user based on the reminder setting time.

[1263] Step 9:

[1264] The server sends a notification to the user's device at the reminder time, and the device displays a notification to the user, such as "You have an appointment to return a book at the library."

[1265] Step 10:

[1266] The server generates a summary of the speech input and stores it as text data. The server also assigns appropriate tags to the summary and stores it in a database.

[1267] Through this step, the specific processing of the system that automates everything from voice input to task management and reminder notifications is realized.

[1268] Example 1

[1269] 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."

[1270] Conventional task management and reminder setting systems require users to manually input tasks and set appropriate reminders, making operation cumbersome and making efficient schedule management difficult. Furthermore, when using voice input, accurate task extraction and appropriate reminder setting are difficult due to insufficient voice recognition accuracy and natural language processing capabilities. The present invention aims to solve these problems and provide a system that allows users to efficiently and accurately manage tasks and set reminders using only voice input.

[1271] 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.

[1272] In this invention, the server includes means for converting received voice data into text data using voice recognition technology, means for analyzing the text data using natural language processing technology to extract tasks, locations, and deadlines, and means for generating a to-do list based on the extracted tasks, locations, and deadlines. This allows the user to accurately register and manage tasks using only voice input, and realizes efficient reminder setting and notifications.

[1273] "User" refers to a person who uses voice input to manage tasks and set reminders.

[1274] "Terminal" refers to a device that accepts and records voice input when a user issues a voice command.

[1275] "Server" refers to a system that receives voice data sent from a terminal, analyzes the data using voice recognition technology and natural language processing technology, and manages tasks and sets reminders.

[1276] "Voice input" refers to voice data such as voice commands, notes, and task instructions that a user issues to a terminal.

[1277] "Recording" refers to the act of the terminal recording the user's voice input.

[1278] "Voice data" refers to digital audio information generated by a terminal recording a user's voice input.

[1279] "Voice recognition technology" refers to the technology that analyzes voice data and converts it into text data.

[1280] "Text data" refers to information of a character string generated from voice data using voice recognition technology.

[1281] "Natural language processing technology" refers to the technology that analyzes text data and extracts information such as tasks, locations, and deadlines.

[1282] A "task" refers to an action or task that a user wants to record.

[1283] "Location" refers to the specific location or facility where the task is performed.

[1284] A "deadline" refers to the date and time by which a task should be performed.

[1285] A "TODO list" is a list that is generated based on extracted tasks, locations, and deadlines and is used to manage a user's schedule.

[1286] "Reminder" refers to a function that is set based on a TODO list and notifies the user.

[1287] A "summary" refers to a short text summary of the main parts of the user's voice input.

[1288] "Tagging" refers to the act of adding relevant keywords or categories to a summary.

[1289] "Storage" refers to the act of storing the generated data in a storage device such as a database.

[1290] "Notification" refers to the act of sending an alert or message to the user at the set reminder time.

[1291] MODE FOR CARRYING OUT THE INVENTION

[1292] The present invention provides a system that efficiently utilizes a user's voice input for task management and reminder setting. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail an embodiment of the present invention.

[1293] Program processing overview

[1294] This system works in cooperation with the device, server, and user. When the user issues a voice command, the device accepts the voice input and sends the recorded voice data to the server. The server analyzes the voice data using speech recognition and natural language processing (NLP) technology to extract information such as tasks, locations, and deadlines. Based on the extracted information, the server generates a to-do list and synchronizes it with the user's schedule management tool. The server then sets reminders and sends notifications to the user's device at the specified time. The server also summarizes and tags the voice input and stores it in a database.

[1295] Hardware and software used

[1296] The following hardware and software are used to implement this system:

[1297] Device: Smartphone, tablet, or computer with voice input

[1298] Server: Cloud or on-premise server

[1299] Speech recognition technology: Google Cloud Speech-to-Text API, etc.

[1300] Natural language processing technology: spaCy, Google Natural Language API, etc.

[1301] Schedule management tools: APIs for Google Calendar, Microsoft Outlook, etc.

[1302] Database: A database for storing audio data, text data, summarization and tagging data.

[1303] Specific actions and examples

[1304] 1. The user says "Start recording" to the device, which activates the device's built-in microphone and begins recording the voice input.

[1305] 2. The user enters a task, note, etc. by voice and then says "stop recording."

[1306] 3. The device stops recording and sends the recording data to the server.

[1307] 4. The server uses the Google Cloud Speech-to-Text API to perform speech recognition on the received audio data and convert it into text data.

[1308] 5. The server analyzes the text data acquired using spaCy or the Google Natural Language API to extract information about tasks, locations, and deadlines.

[1309] 6. The server generates a to-do list based on the extracted information and synchronizes it with schedule management tools such as Google Calendar and Microsoft Outlook.

[1310] 7. The server sets a reminder based on the information in the TODO list and sends that information to the device.

[1311] 8. At the specified time, the device notifies the user that "You have a book to return at the library."

[1312] 9. The server generates a summary of the speech input, tags it appropriately, and stores it in a database.

[1313] Prompt Sentence Examples

[1314] Here are some example prompts to input to a generative AI model:

[1315] When a user says, "I need to remember to return this book at the library tomorrow at 3 PM," explain the steps to use this voice input for task management and reminder notifications.

[1316] As described above, the present invention provides a system that allows users to manage tasks and set reminders efficiently using only voice input. Detailed processing steps and specific implementations will be described separately. This will greatly support users' daily work.

[1317] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] The user says "Start recording" to the device. The device receives this voice command as input, activates the built-in microphone, and starts recording. The device displays "Recording." Specifically, the device's microphone begins capturing voice input.

[1320] Input: User's voice command "Start recording"

[1321] Output: Start of recording state

[1322] Step 2:

[1323] The user inputs specific tasks and notes by voice. When recording is finished, the user says "Stop recording." With this input, the device stops recording and temporarily saves the recorded data. The device displays "Stop recording." As a specific operation, the recorded voice data is saved in the device.

[1324] Input: User voice command "stop recording" and voice input for tasks and notes

[1325] Output: Temporarily saved audio data

[1326] Step 3:

[1327] The device sends the temporarily saved audio data to the server using the HTTP or HTTPS protocol. The server receives the audio data and saves it in the specified directory.

[1328] Input: Temporarily saved audio data

[1329] Output: Audio data stored on the server

[1330] Step 4:

[1331] The server calls a speech recognition service such as the Google Cloud Speech-to-Text API and converts the speech data into text data. Specifically, the server sends the speech data to the API and stores the returned text data.

[1332] Input: Audio data stored on the server

[1333] Output: Text data generated by the speech recognition service

[1334] Step 5:

[1335] The server parses the acquired text data using spaCy and the Google Natural Language API, then performs syntax analysis, entity recognition, and intent analysis to extract important information about the task, location, and deadline.

[1336] Input: Text data obtained from the speech recognition service

[1337] Output: Extracted task, location, and deadline information

[1338] Step 6:

[1339] The server generates a to-do list based on the extracted information, and synchronizes the to-do list with the API of schedule management tools such as Google Calendar and Microsoft Outlook.

[1340] Input: Extracted task, location, and due date information

[1341] Output: Generated TODO list and synchronized schedule management tool information

[1342] Step 7:

[1343] The server sets reminders based on the information in the TODO list. Reminders are usually set 30 minutes before the task deadline. The server sends the set reminder information to the device.

[1344] Input: Generated TODO list

[1345] Output: Set reminder information

[1346] Step 8:

[1347] The device will display a reminder at the specified time. Specifically, the device will notify the user via a pop-up notification or alarm, saying, "You have a book to return at the library."

[1348] Input: Set reminder information

[1349] Output: Reminder notification

[1350] Step 9:

[1351] The server generates a summary of the speech input, tags it appropriately, and stores it in a database. Specifically, the server generates a summary and tags and records them in a database.

[1352] Input: Text data obtained through speech recognition and NLP

[1353] Output: Summarized and tagged data stored in a database

[1354] (Application example 1)

[1355] 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."

[1356] Conventional factory task management and reminder setting involve a lot of manual work, resulting in a lack of efficiency. In addition, when work instructions or confirmations are given using voice commands, tasks cannot be managed immediately and reminders must also be set manually, resulting in a significant drop in work efficiency.

[1357] 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.

[1358] In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for extracting tasks, locations, and deadlines from the text data. This enables factory task management using voice instructions to issue and confirm work instructions. Furthermore, the server is equipped with a function for automatically generating a to-do list based on the extracted tasks, locations, and deadlines, and for setting reminders, reducing manual work and enabling efficient task management and reminder setting.

[1359] "Voice input" refers to a method of inputting voice instructions or information into a device.

[1360] "Text data" refers to data obtained by converting voice input into text format.

[1361] A "task" is a specific piece of work or job.

[1362] A "location" is a geographic location or facility where a task is to be performed.

[1363] A "deadline" is the date and time or period by which a task should be completed.

[1364] A "TODO list" is a list of tasks that need to be completed.

[1365] "Reminder" is a function that notifies the user at specific times or under specific conditions.

[1366] A "summary" is text data that briefly summarizes long content.

[1367] "Tagging" is the process of assigning labels to data to make it easier to identify.

[1368] "Factory task management" is a method for managing work content and procedures in a factory.

[1369] This invention is a system for efficiently managing tasks in a factory. A user issues voice instructions to a terminal, and the system has the function of automating task management and reminder setting based on the voice instructions.

[1370] Voice input acceptance

[1371] The user issues a voice command to the device saying "Start recording." The device receives this command and starts recording. The user inputs conversations and work instructions as voice, and when completes, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[1372] Voice Recognition

[1373] The server then sends the received voice data to a cloud-based speech recognition service, which converts the voice data into text. For example, if a user says, "Please don't forget to do machine maintenance on the main line tomorrow at 9 a.m.", the voice is converted into text data.

[1374] Natural Language Processing

[1375] The server receives the converted text data and analyzes it using a natural language processing (NLP) engine. The analysis includes syntactic analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "Maintain the machine," the location "Mainline," and the deadline "Tomorrow at 9:00 AM" are extracted.

[1376] Generate a TODO list

[1377] The server generates a to-do list based on the extracted task, location, and due date information, and the to-do list is synchronized with the user's schedule management tool, for example, by registering events directly in a calendar application.

[1378] Reminders and notifications

[1379] The server sets a reminder based on the TODO list. The set reminder sends a notification to the user's device shortly before the deadline (e.g., 30 minutes before). The device then presents the reminder to the user at the set time, informing them that "machine maintenance is scheduled for the main line."

[1380] Lifelog storage and tagging

[1381] A summary of the speech input is generated and tagged on the server. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9 AM" would be generated and tagged with "main line," "machine," and "maintenance." This data is stored in a database and can be used for future searches and references.

[1382] Hardware and software used

[1383] The following hardware and software are used to implement this system:

[1384] Device: A device that accepts audio input and makes recordings. Examples: smartphone, smart glasses.

[1385] Server: Processes voice data, manages tasks, and sets reminders. Uses a speech recognition API and natural language processing engine.

[1386] Speech recognition service: A cloud-based API. For example, Google Cloud Speech-to-Text API.

[1387] Natural language processing engine: Analyzes text data. Example: Google Cloud Natural Language API.

[1388] Specific examples

[1389] For example, a user might say: "Please don't forget to perform machine maintenance on the mainline tomorrow at 9 AM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The text data is then analyzed using an NLP engine to extract the task "Maintain machine," the location "Mainline," and the deadline "Tomorrow at 9 AM." The server uses this information to generate a to-do list and adds it to the user's calendar. The server then sets a reminder for 8:30 AM the next day, and the device notifies the user at the specified time. Finally, the server creates a summary "Maintain machine on the mainline tomorrow at 9 AM," tags it, and stores it in the database.

[1390] Example prompts for generative AI models

[1391] Analyze "Please remember to perform maintenance on the machine on the mainline at 9am tomorrow" to extract information about the task, location, and deadline.

[1392] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1393] Step 1:

[1394] The device accepts voice input from the user. The user issues the voice command "start recording," and the device begins recording the voice. The user inputs conversations and work instructions as voice, and when complete, says "stop recording." The device stops recording and saves the recorded voice data in memory.

[1395] Step 2:

[1396] The device sends the stored voice data to a server, which then sends the received voice data to a cloud-based voice recognition service for processing, which converts the voice data into text data, which the server receives.

[1397] Step 3:

[1398] The server sends the received text data to a natural language processing (NLP) engine. The NLP engine analyzes the text data and extracts important information through syntactic analysis, entity recognition, and intent analysis. For example, it identifies information such as tasks, locations, and deadlines. The server receives the analysis results and stores the extracted information in a database.

[1399] Step 4:

[1400] The server generates a to-do list based on the extracted task, location, and due date information, and then connects to the user's schedule management tool (e.g., calendar application) and synchronizes the generated to-do list, which adds the corresponding events to the user's calendar.

[1401] Step 5:

[1402] The server sets a reminder based on the TODO list. The reminder is set to a time a little before the due date (e.g. 30 minutes before). The server saves the reminder information in a database and triggers the reminder at the set time.

[1403] Step 6:

[1404] The terminal receives a reminder notification from the server. At the set time, the reminder is displayed on the terminal, and the terminal notifies the user that "machine maintenance is scheduled on the main line."

[1405] Step 7:

[1406] The server generates a summary of the speech input and tags it appropriately. The summary and tagged data are stored in a database for future search and reference. For example, a summary such as "Maintenance on the machine on the main line tomorrow at 9:00 AM" would be generated and tagged with "main line," "machine," and "maintenance."

[1407] 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.

[1408] The present invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. In a specific embodiment of this system, a server, a terminal, and a user work together.

[1409] Voice input acceptance

[1410] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the voice. The user inputs the conversation or notes as voice, and when finished, says "Stop recording." The device stops recording and sends the recorded voice data to the server.

[1411] Voice Recognition

[1412] The server sends the received voice data to a voice recognition service, which converts the voice data into text. For example, a common cloud-based API can be used as the voice recognition service. Speech such as "I have to remember to return the book at the library tomorrow at 3 PM" is converted into text data such as "I have to remember to return the book at the library tomorrow at 3 PM."

[1413] Natural Language Processing

[1414] The server then uses an NLP engine to analyze the text data. This analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. For example, in the above example, the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM" are extracted.

[1415] emotion recognition

[1416] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state. The emotion recognition engine determines emotions from, for example, the user's tone of voice and the way they speak. Here, it detects whether the user is nervous, excited, or calm.

[1417] Creating a TODO list and reflecting emotions

[1418] The server combines the extracted task information with the emotion recognition results to generate a to-do list. Task priorities can be adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks of higher importance.

[1419] Reminders and notifications

[1420] The server sets a reminder based on the TODO list. The reminder is sent to the user's device shortly before the due date (e.g., 30 minutes before). The device then displays the reminder to the user at the set time, informing them that "You have an appointment to return a book at the library."

[1421] Lifelog storage and tagging

[1422] A summary of the speech input is generated, including the user's emotional information. The summary is tagged on the server, with tags such as "library," "book," and "return," as well as emotional tags. This data is stored in a database for future use and search.

[1423] Specific examples

[1424] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[1425] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[1426] The processing flow will be explained below.

[1427] Step 1:

[1428] The user issues a voice command to the device saying "Start recording." The device receives this voice command and starts recording the audio.

[1429] Step 2:

[1430] The user enters a conversation or note as voice. When finished, the user says "stop recording." The device stops recording and temporarily saves the recorded voice data.

[1431] Step 3:

[1432] The device sends the recorded voice data to the server, which receives and stores the voice data and prepares it for voice recognition processing.

[1433] Step 4:

[1434] The server sends the voice data to a speech recognition service. The server retrieves the text data from the speech recognition service (e.g., a cloud-based API).

[1435] Step 5:

[1436] The server sends the retrieved text data to a natural language processing (NLP) engine, which parses the text data and extracts information about the task, location, and deadline.

[1437] Step 6:

[1438] The server applies an emotion recognition engine to the voice data to analyze the user's emotional state, determining emotions from the tone and vocabulary of the voice.

[1439] Step 7:

[1440] The server integrates the extracted task information with the emotion recognition results to create structured data (e.g., JSON format), including the task, location, deadline, and emotional state.

[1441] Step 8:

[1442] The server updates the TODO list based on the generated structured data. Task priorities are adjusted based on the emotional information. For example, if the user is feeling stressed, tasks with higher importance are displayed first.

[1443] Step 9:

[1444] The server sets reminders based on the to-do list. For example, for a task due at 3:00 PM tomorrow, it sets a reminder for 2:30 PM tomorrow.

[1445] Step 10:

[1446] The server sends a notification to the user's device at the set reminder time, and the device notifies the user that "You have an appointment to return a book at the library."

[1447] Step 11:

[1448] The server generates a summary of the speech input, including emotional information. For example, summary: "Returning the book at the library tomorrow at 3 PM. The user is worried." The server assigns appropriate tags to the summary and stores it in a database.

[1449] Specific examples

[1450] For example, a user might say: "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes it and extracts the task of "returning the book," the location of "library," and the deadline of "tomorrow at 3 PM." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[1451] Example 2

[1452] 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."

[1453] Efficient task management and reminder setting are crucial for today's busy lifestyles. However, existing systems lack sufficient integration of natural language processing and emotion recognition technologies that utilize voice input, resulting in inadequate task prioritization and reminder setting. Furthermore, task management that takes the user's emotional state into account is inadequate, resulting in a lack of means to reduce the user's mental burden. Therefore, there is a need for a system that can provide appropriate task management and reminder setting that takes the user's emotional state into account based on voice input.

[1454] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accepting voice input, a means for generating text data from the accepted voice, and a means for analyzing the voice data and identifying the emotional state. This makes it possible to improve the efficiency of task management using voice input and to prioritize tasks and set reminders taking into account the user's emotional state.

[1455] "Voice input" refers to the means by which a device receives user-uttered speech and processes it as digital data.

[1456] "Text data" is data that is generated by analyzing voice input and expressing it as a string of characters.

[1457] "Work" refers to the tasks or activities that a user must perform.

[1458] "Location" is data about the geographic location or place where work is performed.

[1459] A "deadline" is data that indicates the time or date by which work should be completed.

[1460] A "task list" is a list of multiple task data in an easy-to-manage format.

[1461] "Notifications" are alerts or reminders that inform users based on set times or circumstances.

[1462] A "summary" is a concise summary of speech input or other data.

[1463] "Tagging" is the act of assigning keywords and labels to data to classify and organize it.

[1464] "Emotional state" is information that indicates the user's psychological and emotional state.

[1465] "Priority" refers to the ranking of tasks based on their importance and urgency.

[1466] This invention is a system that efficiently manages tasks and sends reminders by accepting voice input and utilizing speech recognition technology, natural language processing (NLP), and an emotion recognition engine. This system operates in cooperation with a server, a terminal, and a user.

[1467] Hardware and software used

[1468] The system utilizes the following hardware and software:

[1469] Device: A device that accepts voice input (e.g., smartphone, tablet, voice assistant device).

[1470] Server: Responsible for data processing and management (e.g. cloud server)

[1471] Speech recognition service: A cloud-based API that converts speech to text (e.g., Google Cloud Speech-to-Text API).

[1472] Natural language processing engine: Software that analyzes text data (e.g., spaCy, BERT model)

[1473] Emotion recognition engine: Software that analyzes emotional states from voice data (e.g., IBM Watson Tone Analyzer)

[1474] Voice input

[1475] The user speaks "Start recording" into the device, and the device starts recording the voice. The user then enters any necessary notes or tasks by voice, and when the recording is complete, speaks "Stop recording." The device then stops recording and sends the voice data to the server.

[1476] Voice Recognition

[1477] The server sends the received voice data to a voice recognition service, converts the voice data into text data, and then receives the text data and proceeds to the next step.

[1478] Natural Language Processing

[1479] The server inputs the acquired text data into a natural language processing engine and performs syntax analysis, entity recognition, and intent analysis. For example, it extracts the task "return the book" from the text data, the location "library," and the deadline "tomorrow at 3:00 PM."

[1480] emotion recognition

[1481] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state, for example, determining emotions such as "worried" or "excited" from the tone of the voice and the way the words are used.

[1482] Generate a TODO list

[1483] The server combines the analysis results of the NLP engine and the emotion recognition engine to prioritize tasks and generate a TODO list. For example, if the user is very anxious, the task will be set to high priority.

[1484] Reminders and notifications

[1485] The server sets reminders based on the TODO list and sends notifications to the device. For example, for a task due "tomorrow at 3:00 PM," the server sets a reminder 30 minutes before the task. At the set time, the device notifies the user by voice or pop-up message that "You have an appointment to return a book at the library."

[1486] Lifelog storage and tagging

[1487] The server generates a lifelog that compiles the to-do list and the user's emotional information. The lifelog is tagged with tags such as "library," "book," and "return," as well as emotional tags such as "worried," and is stored in a database. This data can be used for future searches and references.

[1488] Specific examples

[1489] The user says, "I have to remember to return the book at the library tomorrow at 3 PM." The device records this speech and sends it to the server. The server performs speech recognition and converts it into text data. The NLP engine then analyzes the text data and extracts the task "return the book," the location "library," and the deadline "tomorrow at 3 PM." At the same time, the emotion recognition engine analyzes the user's emotional state from the voice and detects, for example, that the user is worried. The server uses this information to generate a to-do list and set a reminder. A notification is sent to the user's device at the set reminder time. The server also generates a summary, which also includes emotional information. All information is stored in a database.

[1490] Prompt Sentence Examples

[1491] "Don't forget to take the dog for a walk at 6pm this evening."

[1492] "Remind me that I have a meeting tomorrow morning at 9am"

[1493] "I want to remember to go to my friend's birthday party next Friday."

[1494] The present invention provides specific embodiments of a system that enables efficient task management and reminder setting from voice input and takes into account the emotional state of the user.

[1495] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1496] Step 1:

[1497] Voice input acceptance

[1498] The user speaks "Start recording" into the device. The device receives this voice command, activates the internal microphone, and begins recording audio.

[1499] The user inputs a conversation or task by voice, and when finished, says "stop recording." The device stops recording and temporarily saves the voice data.

[1500] Input: User's voice commands "Start recording" and "Stop recording" and input voice

[1501] Output: Temporarily saved audio data

[1502] Step 2:

[1503] Sending audio data to the server

[1504] The device sends the temporarily saved audio data to the server using HTTP or HTTPS as the communication protocol.

[1505] The device notifies the user that "recorded data will be sent to the server," and data transfer begins. Once the server confirms receipt, it notifies the device that "data has been received."

[1506] Input: Temporarily stored audio data

[1507] Output: Audio data sent to the server

[1508] Step 3:

[1509] Voice Recognition

[1510] The server sends the received voice data to a cloud-based speech recognition service, which converts the voice into text.

[1511] The server processes the voice data and logs "Converting voice data to text." When speech recognition is complete, it logs "Converting voice data to text."

[1512] Input: Audio data stored on the server

[1513] Output: Text data converted from audio

[1514] Step 4:

[1515] Natural Language Processing

[1516] The text data acquired by the server is input into a natural language processing engine, where it performs syntactic analysis, entity recognition, and intent analysis.

[1517] The server logs "Analyzing text data" and passes the data to the NLP engine. After analysis, it logs "Task information extracted." Specifically, it extracts the task "return the book," the location "library," and the deadline "tomorrow at 3:00 PM."

[1518] Input: Text data obtained from speech recognition

[1519] Output: Extracted task, location, and due date information

[1520] Step 5:

[1521] emotion recognition

[1522] The server inputs the voice data into an emotion recognition engine to analyze the user's emotional state.

[1523] The server logs "Applying emotion recognition engine" and then logs "User's emotional state detected" after analyzing the emotion. For example, it can determine emotions such as anxiety or excitement from the tone of voice and the way the words are used.

[1524] Input: Audio data stored on the server

[1525] Output: Determined emotional state

[1526] Step 6:

[1527] Generate a TODO list

[1528] The server integrates the analysis results of the NLP engine and emotion recognition engine, prioritizes tasks, and generates a TODO list.

[1529] The server logs "Generating a TODO list" and generates a list based on the extracted task information and emotion information. It also logs "TODO list generated." For example, if the user is very worried, it sets the task to high priority.

[1530] Input: Analysis results of the NLP engine and emotion recognition engine

[1531] Output: A prioritized to-do list

[1532] Step 7:

[1533] Set reminders

[1534] The server sets reminders based on the to-do list. For example, for a task due tomorrow at 3:00 PM, it sets a reminder 30 minutes before the task.

[1535] The server logs "Setting reminder" and logs "Reminder set."

[1536] Input: TODO list

[1537] Output: Set reminders

[1538] Step 8:

[1539] Reminder notifications

[1540] The server sends a reminder to the device at the set time. The device logs "Sending reminder notification" and notifies the user by voice or pop-up that "You have an appointment to return a book at the library."

[1541] Input: Set reminder

[1542] Output: Notification displayed on the user's device

[1543] Step 9:

[1544] Lifelog storage and tagging

[1545] The server generates a life log that compiles the to-do list and the user's emotional information and stores it in a database.

[1546] The server logs "Generating a lifelog" and "Lifelog saved." The lifelog is tagged with tags such as "library," "book," and "return," as well as emotion tags such as "worried."

[1547] Input: TODO list and emotional information

[1548] Output: Saved lifelog

[1549] (Application example 2)

[1550] 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."

[1551] Although task management systems that use voice input already exist, they generally only generate text data and extract task information, and do not take into account the user's emotional state when managing tasks or setting reminders. As a result, when workers are stressed or emotionally unstable, effective task management is difficult, which can lead to reduced work efficiency. Furthermore, when considering use in factories and other workplaces, a function that can detect workers' instructions in real time and adjust priorities is required.

[1552] 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.

[1553] In this invention, the server includes means for accepting voice input, means for generating text data from the accepted voice, means for extracting tasks, locations, and deadlines from the text data, means for adjusting task priorities based on emotional information, means for analyzing the emotional state of the worker and detecting stress, and means for presenting task instructions by voice. This enables effective task management that takes into account the emotional state of the worker, and allows for more appropriate reminder settings and task instructions. Furthermore, receiving instructions in real time through voice input and dynamically adjusting priorities is expected to improve work efficiency on the factory floor.

[1554] A "means for accepting voice input" is a device or software that captures the voice uttered by the user as digital data, allowing the system to use the voice for subsequent processing.

[1555] A "means for generating text data" is a software algorithm or service that analyzes audio data and expresses its contents as text information.

[1556] The "means for extracting tasks, locations, and deadlines" refers to a process or technology for identifying the tasks, the locations where the tasks are performed, and the deadlines for the tasks from the generated text data.

[1557] The "means for generating a task list" is a function or application that compiles in list form the tasks that the user needs to perform based on the extracted tasks, locations, and deadlines.

[1558] The "means for managing the task list and setting reminders" refers to a system or program for properly recording the generated task list and sending reminder notifications based on the specified date and time.

[1559] The "means for generating summaries and tagging of speech input" is a process for summarizing text and extracted information generated from speech data and tagging it to make the content understandable at a glance.

[1560] "Means for storing the generated summary and tagged data" refers to a function that records the summarized information and the associated tag data in a database or other storage device, allowing them to be reused and searched later.

[1561] The "means for notifying at the time of the reminder" is a mechanism that sends a notification to the user's device based on the set reminder date and time to notify the user of the scheduled work.

[1562] The "means for adjusting work priorities based on emotional information" is a mechanism for more efficient task management by changing work priorities based on the results of analyzing the emotional state of the worker.

[1563] "Means for analyzing the emotional state of a worker and detecting stress" refers to technologies and algorithms that analyze the emotional state of a worker from voice data, etc., and identify stress or other emotional states.

[1564] A "means for presenting work instructions by voice" is a device or program that transmits instructions or tasks to be performed by a worker by voice.

[1565] The present invention is a system that uses voice input to manage work instructions and adjusts work priorities based on worker emotion analysis. It is particularly intended for use on factory floors, improving work efficiency through real-time voice instructions.

[1566] Hardware and Software Configuration

[1567] The following hardware and software are used to realize this system.

[1568] Hardware: microphone, speaker, factory robot (with control board)

[1569] Software: Speech recognition API (e.g., general cloud-based API), natural language processing engine (e.g., SpaCy or Google Cloud Natural Language), emotion recognition API (e.g., IBM Watson Tone Analyzer), main server, database

[1570] Data processing flow

[1571] 1. Voice input acceptance

[1572] The user says "Start recording" into the microphone. The device receives this voice command and starts recording the voice. Next, the user says, "The next step is to supply material to the conveying line. This is a high priority." When recording is complete, the user says, "Stop recording." The device stops recording and sends the voice data to the server.

[1573] 2. Voice Recognition

[1574] The server sends the received voice data to a voice recognition API and converts it into text data. For example, a voice saying "The next step is to supply materials to the conveyor line. This is a high priority" is converted into text data saying "The next step is to supply materials to the conveyor line. This is a high priority."

[1575] 3. Natural Language Processing

[1576] The server that retrieves the text data uses an NLP engine to analyze the text data. The analysis includes syntax analysis, entity recognition, and intent analysis. During this process, important information such as the task, location, and deadline is extracted. In the above example, the extracted information is the task "supply materials to the conveyor line," the location "conveyor line," and "high priority."

[1577] 4. Emotion recognition

[1578] The server applies an emotion recognition API to the voice data to analyze the user's emotional state. The emotion recognition API determines the user's emotions from the tone of their voice and the way they speak. It then detects that the user is feeling stressed.

[1579] 5. Task list generation and emotional reflection

[1580] The server integrates the extracted task information with the emotion recognition results to generate a task list. Task priorities are adjusted based on the emotion information. For example, if the user is feeling stressed, the system will prioritize tasks that are of high importance.

[1581] 6. Reminders and notifications

[1582] The server sets reminders based on the task list. The reminders send notifications to the user's terminal shortly before the deadline. The terminal then presents the reminder to the user at the set time, informing them that "The next step is to supply materials to the conveyor line. This is a high priority."

[1583] 7. Summarize and save voice input

[1584] A summary of the speech input is generated, including the user's emotional information. The tagging process is performed on the server, adding tags such as "transport line," "material supply," and "high priority" as well as emotional tags. This data is stored in a database for future use and search.

[1585] Examples and prompts

[1586] For example, a user might say: "The next step is to supply materials to the conveyor line. It's a high priority." The device records this speech and sends it to the server. The server then performs speech recognition and converts it into text data. The NLP engine then analyzes the speech and extracts the task "supply materials to the conveyor line," the location "conveyor line," and the phrase "high priority." At the same time, an emotion recognition engine analyzes the user's emotional state from the speech and detects, for example, that the user is feeling stressed. The server uses this information to generate a task list and set reminders. A notification is sent to the user's device at the time of the reminder. The server also generates a summary, which includes emotional information. All information is stored in a database.

[1587] Call prompt:

[1588] "What is your next task? Please tell me the priority."

[1589] In this way, the present invention provides a specific embodiment of a system that automates task management from voice input and performs task management and reminder notifications taking into account the user's emotions.

[1590] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1591] Step 1:

[1592] The user says "start recording" into the microphone. The device receives this voice command and starts recording the voice. The input is the voice command "start recording" and the output is the start of voice recording. Specifically, the microphone inside the device operates and records the voice as digital data.

[1593] Step 2:

[1594] The user speaks work instructions into the microphone. For example, "The next step is to supply materials to the conveyor line. This is a high priority." The input is the user's work instructions as voice data, and the output is the accumulation of recorded voice data. Specifically, the terminal continuously records the voice and saves it as digital data.

[1595] Step 3:

[1596] The user says "stop recording." The device receives this voice command and stops recording. The input is the voice command "stop recording," and the output is to stop recording and save the voice data. Specifically, the device stops recording and sends the saved voice data to the server.

[1597] Step 4:

[1598] The server sends the received voice data to a voice recognition API and converts it into text data. The input is voice data, and the output is the corresponding text data. Specifically, the server generates an API request and sends it to the voice recognition service. It then receives the text data returned by the voice recognition service.

[1599] Step 5:

[1600] The server analyzes the generated text data using a natural language processing engine to extract tasks, locations, and deadlines. The input is text data, and the output is the extracted task information. Specifically, the server parses the text data, performs entity recognition, and identifies important information through intent analysis.

[1601] Step 6:

[1602] The server sends the voice data to the emotion recognition API and analyzes the emotional state. The input is the voice data and the output is the emotion recognition result. Specifically, the server sends the voice data as an API request and receives the analysis result returned from the emotion recognition service.

[1603] Step 7:

[1604] The server integrates the extracted task information and emotion recognition results to generate a task list. The input is the task information and emotion recognition results, and the output is a task list with adjusted priorities. Specifically, the server compares the task information and emotion recognition results and applies an algorithm to determine the priorities.

[1605] Step 8:

[1606] The server sets a reminder and sends a reminder notification to the user's device at the specified time. The input is a task list and the reminder setting time, and the output is a notification to the device. Specifically, the server sets a timer and sends a notification message to the device when the timer goes off.

[1607] Step 9:

[1608] The device presents the reminder content to the user by voice. The input is the reminder notification from the server, and the output is the voice notification. Specifically, the device's speaker operates and plays the reminder content by voice.

[1609] Step 10:

[1610] The server generates a summary of the speech input, tags it, and stores it in a database. The input is speech data, text data, and emotion recognition results, and the output is a summary and tagged data. Specifically, the server applies a summary generation algorithm, adds relevant tags, and records the data in a database.

[1611] 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.

[1612] 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.

[1613] 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 robot 414.

[1614] 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.

[1615] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion 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.

[1616] 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.

[1617] 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).

[1618] 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.

[1619] 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."

[1620] 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.

[1621] 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).

[1622] 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.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] 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.

[1627] 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.

[1628] 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.

[1629] 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.

[1630] 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.

[1631] 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.

[1632] The following is further disclosed regarding the above embodiment.

[1633] (Claim 1)

[1634] means for accepting voice input;

[1635] means for generating text data from the received speech;

[1636] means for extracting tasks, locations, and deadlines from the text data;

[1637] A means to generate a to-do list based on the extracted tasks, locations, and due dates;

[1638] A way to manage the generated to-do list and set reminders,

[1639] means for generating and tagging a summary of the speech input;

[1640] a means for storing the generated summary and tagged data;

[1641] The system includes a means for notifying users when a reminder is due.

[1642] (Claim 2)

[1643] 10. The system of claim 1, further comprising: means for transmitting the received speech to a speech recognition API.

[1644] (Claim 3)

[1645] 10. The system of claim 1, further comprising means for analyzing the text data with a natural language processing engine.

[1646] "Example 1"

[1647] (Claim 1)

[1648] means for accepting voice input by a user issuing a voice command;

[1649] means for recording the received audio;

[1650] means for transmitting the recorded voice data to a server;

[1651] A means for converting the received voice data into text data using voice recognition technology;

[1652] A means for analyzing the text data using natural language processing technology and extracting the task, location, and deadline;

[1653] means for generating a to-do list based on the extracted tasks, locations, and deadlines;

[1654] A means for managing the generated TODO list and setting reminders;

[1655] A means of notifying the user at the time of the reminder,

[1656] means for generating a summary and tagging of the speech input;

[1657] The system includes means for storing said generated summary and tagging data.

[1658] (Claim 2)

[1659] 10. The system of claim 1, further comprising means for transmitting the received voice data to a voice recognition service.

[1660] (Claim 3)

[1661] 10. The system of claim 1, further comprising means for analyzing the text data with a natural language processing engine.

[1662] "Application Example 1"

[1663] (Claim 1)

[1664] means for accepting voice input;

[1665] means for generating text data from the received speech;

[1666] means for extracting tasks, locations, and deadlines from the text data;

[1667] A means to generate a to-do list based on the extracted tasks, locations, and due dates;

[1668] A way to manage the generated to-do list and set reminders,

[1669] means for generating and tagging a summary of the speech input;

[1670] a means for storing the generated summary and tagged data;

[1671] A way to notify you at the time of reminder,

[1672] A factory task management means for issuing and confirming work instructions using voice instructions;

[1673] A factory system that automatically manages tasks and sets reminders based on voice commands.

[1674] (Claim 2)

[1675] 10. The system of claim 1, further comprising: means for transmitting the received speech to a speech recognition API.

[1676] (Claim 3)

[1677] 10. The system of claim 1, further comprising means for analyzing the text data with a natural language processing engine.

[1678] "Example 2: Combining Emotion Engines"

[1679] (Claim 1)

[1680] means for accepting voice input;

[1681] means for generating text data from the received speech;

[1682] means for extracting tasks, locations, and deadlines from the text data;

[1683] a means for generating a task list based on the extracted tasks, locations, and deadlines;

[1684] A way to manage your to-do list and set notifications;

[1685] means for generating and tagging a summary of the speech input;

[1686] a means for storing the generated summary and tagged data;

[1687] means for transmitting a notification to a user terminal at the timing of the notification;

[1688] means for analyzing the audio data to identify an emotional state;

[1689] A system including a means for adjusting task priorities based on emotional state.

[1690] (Claim 2)

[1691] 10. The system of claim 1, further comprising: means for transmitting the received speech to a speech recognition service.

[1692] (Claim 3)

[1693] 10. The system of claim 1, further comprising means for analyzing the text data with a natural language processing engine.

[1694] "Application example 2 when combining emotion engines"

[1695] (Claim 1)

[1696] means for accepting voice input;

[1697] means for generating text data from the received speech;

[1698] means for extracting tasks, locations, and deadlines from the text data;

[1699] means for generating a task list based on the extracted tasks, locations, and deadlines;

[1700] a means for managing the generated task list and setting reminders;

[1701] means for generating and tagging a summary of the speech input;

[1702] a means for storing the generated summary and tagged data;

[1703] A way to notify you at the time of reminder,

[1704] A means for adjusting task priorities based on emotional information;

[1705] means for analyzing the emotional state of a worker and detecting stress;

[1706] A system including means for audibly presenting work instructions.

[1707] (Claim 2)

[1708] 10. The system of claim 1, further comprising: means for transmitting the received speech to a speech recognition API.

[1709] (Claim 3)

[1710] 10. The system of claim 1, further comprising means for analyzing the text data with a natural language processing engine. [Explanation of symbols]

[1711] 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 input; means for generating text data from the received speech; means for extracting tasks, locations, and deadlines from the text data; A means to generate a to-do list based on the extracted tasks, locations, and due dates; A way to manage the generated to-do list and set reminders, means for generating and tagging a summary of the speech input; a means for storing the generated summary and tagged data; and a means for notifying the user at the time of the reminder.

2. The system of claim 1 further comprising means for transmitting the received speech to a speech recognition API.

3. The system of claim 1 , further comprising means for analyzing the text data with a natural language processing engine.

Images