system

Abstract

We provide the system. [Solution] A speech recognition means that acquires audio data in real time and converts the audio data into text, Image recognition means that acquires image data, extracts character information from the image data and converts it into text, A task generation means that analyzes the text data obtained from the speech recognition means and the image recognition means and generates a task, A prioritization means for evaluating the importance and urgency of the generated tasks and prioritizing the tasks, A reminder setting means for setting reminders based on deadlines and priorities for the aforementioned tasks, A system further comprising an autonomous device that operates in a home or business environment and collects information via the voice recognition means and the image recognition means.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern business environment, employees need to manage many tasks simultaneously, and the stress and forgetfulness caused by the complexity have become problems that reduce work efficiency. In particular, for individuals with attention deficit hyperactivity disorder (ADHD), excessive effort is required to manage tasks, resulting in the problem of being unable to concentrate on other tasks. Therefore, there is a need for a system that solves these problems and manages tasks efficiently and effectively.

Means for Solving the Problems

[0005] This invention provides a means for acquiring audio data in real time and converting it into text using speech recognition technology. It also includes a means for acquiring image data and converting character information into text using OCR technology. Furthermore, it proposes a system that automatically generates tasks based on this text data and prioritizes tasks according to their importance and urgency. In addition, it assists in task management by automatically sending reminders based on set deadlines and priorities. Moreover, for users with ADHD, it provides a specially adjusted user interface and assistive tools to reduce the burden of task management and improve work efficiency.

[0006] "Speech recognition means" refers to a technology or device that receives speech data as input and converts it into text data.

[0007] "Image recognition means" refers to a technology or device that acquires image data as input, extracts characters and symbols from it, and converts them into text.

[0008] "Task generation means" refers to a technology or process for analyzing text data obtained by speech recognition means and image recognition means and organizing it into tasks.

[0009] A "prioritization tool" is a technology or process that evaluates the importance and urgency of generated tasks and automatically sets their order.

[0010] A "reminder setting method" is a technology or function that allows users to pre-set notifications for tasks based on deadlines and priorities, and present them to the user at the appropriate time.

[0011] A "module for users with ADHD" is a support tool that provides specialized functions and interfaces for users with Attention Deficit Hyperactivity Disorder (ADHD) to alleviate difficulties in task management. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This system automates task management using speech recognition and image recognition, and is designed to improve work efficiency, particularly for users with Attention Deficit Hyperactivity Disorder (ADHD). A specific implementation is described below.

[0034] First, the device transmits audio data acquired during meetings or work to the server in real time. The server uses speech recognition technology to convert the audio data into text data. This audio data includes the content of the meeting and instructions.

[0035] Next, the device scans images such as whiteboards and handwritten notes through its camera and transfers them to the server. The server uses image recognition technology to extract text information from the images and convert it into text. This information includes notes and descriptions related to tasks.

[0036] These text data are parsed by the server and generated as specific tasks. For example, if a meeting includes the phrase "Submit the report by next Friday," a task to create the report will be automatically generated, and a deadline will be set.

[0037] The server evaluates the importance and urgency of the tasks it generates and automatically sets their priorities. This ensures that new tasks with high urgency are placed higher than other tasks.

[0038] Furthermore, the server sets task reminders according to the user's settings and provides timely notifications for tasks that are approaching deadlines or have high priority. This allows users to efficiently manage the progress of their tasks.

[0039] Furthermore, a specially customized interface is provided for users with ADHD. This is designed to make it easier to check and manage tasks with visual and auditory support.

[0040] As an example, consider a scenario where a user hears deadlines and tasks for multiple projects at once during a meeting. Using this system, the information received can be immediately converted into tasks, allowing the user to focus on them and improve their concentration on other tasks.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The device acquires audio data in real time through the microphone during meetings and work sessions. The acquired audio data is then sent directly to the server.

[0044] Step 2:

[0045] The server inputs the received audio data into a speech recognition engine and converts it into text data. This makes it easier to analyze the instructions and meeting content contained in the audio.

[0046] Step 3:

[0047] The device uses its camera to acquire image data of whiteboards, handwritten notes, and other objects. This image data is also sent to the server.

[0048] Step 4:

[0049] The server processes the received image data using OCR technology, converting the text information within the image into text. The contents of notes on a whiteboard or documents are then extracted.

[0050] Step 5:

[0051] The server integrates text data obtained from speech recognition and image recognition and performs text analysis. This analysis extracts task generation information, deadlines, and priorities.

[0052] Step 6:

[0053] The server generates tasks based on the extracted information and sets appropriate priorities for each task. The tasks are ordered considering importance and urgency.

[0054] Step 7:

[0055] The server schedules reminders for tasks according to user settings. Notifications are prepared based on deadlines and priorities.

[0056] Step 8:

[0057] Users receive task lists and reminder notifications sent from the server to check the progress of their work. They can review and adjust task details as needed.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In recent years, as the demand for improved work efficiency has increased, users with Attention Deficit Hyperactivity Disorder (ADHD) in particular face challenges in appropriately prioritizing tasks and efficiently managing them. Conventional task management systems have limitations in processing audio and visual information, resulting in insufficient support for users with ADHD. Furthermore, the difficulty in real-time information gathering and analysis, which places a heavy burden on users, is also a challenge.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes an information conversion means for acquiring audio information and converting it into text; an information processing means for acquiring visual information, extracting textual information from the visual information and converting it into text; and an instruction generation means for analyzing the textual information obtained by the information conversion means and the information processing means and generating work instructions. This enables real-time information collection and analysis, and in particular makes it possible to provide efficient task management while assisting concentration for users with ADHD.

[0063] "Audio information" refers to information obtained by acquiring audio as digital data, and typically includes audio data such as conversations and instructions.

[0064] "Information conversion means" refers to a device or system that has the function of analyzing audio information and converting it into text format.

[0065] "Visual information" refers to digital data obtained through images and diagrams, and includes textual information and charts.

[0066] "Information processing means" refers to a device or system that has the function of analyzing visual information to extract textual information.

[0067] A "work instruction" is a specific task or instruction generated from analyzed information, and it is a work item with a set schedule and priority.

[0068] "Instruction generation means" refers to a device or system that has the function of analyzing text information obtained from audio and visual information and generating specific work instructions.

[0069] This system efficiently collects audio and visual information and automatically generates tasks based on it, thereby improving work efficiency, especially for users with behavioral disabilities. A specific implementation is described below.

[0070] The terminal uses a microphone to acquire audio information. Audio information obtained during meetings or work sessions is temporarily stored on-site and then transmitted in real time to a multi-function server. HTTPS and similar protocols are used for this transmission to maintain data confidentiality. The terminal also acquires visual information using a built-in or external camera and transmits it to the server. This visual information includes whiteboards and handwritten notes.

[0071] The server applies a speech recognition engine (e.g., an available general-purpose speech recognition API) to the transmitted audio information and converts the audio data into text. Similarly, for visual information, image recognition technology (e.g., a general-purpose image recognition API) is used to extract text information and convert it into text.

[0072] Through the analysis of text information, the server generates specific work instructions. These instructions are automatically prioritized based on their importance and urgency. A reminder function is also included, notifying the user of tasks with approaching deadlines.

[0073] The user interface is customized for ease of use, especially for users with behavioral disabilities, and allows for intuitive operation through both visual and auditory means.

[0074] As an example, suppose a user receives instructions in a meeting that "a report for a specific project is required by next Friday." This system collects and analyzes audio and visual information and automatically generates a "report creation" task instruction and its deadline. In this way, the user can focus on the task, without being burdened by prioritization, and can concentrate more on other tasks.

[0075] A concrete example of a prompt message for a generative AI model might be: "Automate the tasks for this week's meetings. Evaluate their importance and deadlines and output them as a list."

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The terminal acquires voice information using a voice input device. What the user says during meetings or work is input as voice and temporarily stored within the terminal. The voice information is converted into digital data for real-time transmission to the server. The input is analog voice, and this is output as digitized voice data.

[0079] Step 2:

[0080] The server receives audio data from the terminal and converts it into text data using a speech recognition engine. The speech recognition engine extracts phonemes from the input audio data and uses them to construct words and sentences. The output is text data, including instructions and discussions during meetings or work sessions.

[0081] Step 3:

[0082] The device acquires visual information using a camera. Images of whiteboards, handwritten notes, etc., are captured via the camera and immediately sent to the server. The input is analog visual information, which is output as digital image data.

[0083] Step 4:

[0084] The server processes the received image data and extracts text information using image recognition technology. This process identifies characters and shapes from the image data and extracts them as text. The output is text data derived from visual information.

[0085] Step 5:

[0086] The server analyzes text data obtained from speech and visual input. Using natural language processing techniques, it generates specific work instructions based on the analysis. For example, it might generate an instruction such as, "Submit the report by next Friday." The input is text data, and the output is a task instruction.

[0087] Step 6:

[0088] The server applies an algorithm to the generated work orders to evaluate their importance and urgency. Based on the evaluation results, it sets the priority of the work orders. This process organizes the task list according to the task deadlines and content. The output is a prioritized task list.

[0089] Step 7:

[0090] The server sets reminders based on work instructions. It schedules notifications to be sent to users as task deadlines approach. For example, reminders are set for the day before the deadline and for high-priority tasks. The output is the notification schedule for users.

[0091] Step 8:

[0092] Users view the generated task list through a customized interface. Designed with users with behavioral disabilities in mind, it enables visually and audibly intuitive task management. This process provides support to help users easily track task progress and take timely action.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In modern living environments, a large amount of information and tasks arise frequently, making it particularly difficult for individuals with Attention Deficit Hyperactivity Disorder (ADHD) to manage them efficiently. Furthermore, there is a need for systems that allow for efficient task organization, management, and reminder setting in both home and work environments.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for acquiring audio data in real time and converting the audio data into text, means for acquiring image data and extracting character information from the image data and converting it into text, and means for analyzing the text data obtained by the audio recognition means and the image recognition means and generating tasks. This enables users with ADHD to use autonomous devices in their home or work environment and efficiently manage tasks.

[0098] "Speech recognition means" refers to a device or method that acquires speech data in real time and converts that data into text.

[0099] "Image recognition means" refers to a device or method that acquires image data, extracts character information from it, and converts it into text.

[0100] "Task generation means" refers to a device or method that analyzes text data obtained by speech recognition means and image recognition means and generates a specific task based on that analysis.

[0101] A "prioritization means" is a device or method for evaluating the importance and urgency of generated tasks and prioritizing those tasks based on that evaluation.

[0102] A "reminder setting means" is a device or method for setting reminders to notify users based on the deadline or priority of a task.

[0103] An "autonomous device" is a device that collects information via voice recognition and image recognition means in a home or work environment and operates autonomously based on that information.

[0104] An "acoustic data collection device" is a device that is connected to a speech recognition system to collect audio data.

[0105] A "visual information acquisition device" is a device connected to an image recognition system that collects image data.

[0106] An "information terminal" is a device operated by a user to collect data from speech recognition and image recognition.

[0107] This system includes voice recognition means, image recognition means, task generation means, prioritization means, reminder setting means, autonomous devices, sound collection devices, visual information collection devices, and information terminals. The server works in conjunction with these means to automate task management.

[0108] The device is equipped with an acoustic data collection device (microphone) and a visual information collection device (camera) to collect voices emitted by the user during daily activities, as well as visual information such as notes and documents. The voice data is transmitted to the server in real time and converted into text by a speech recognition system. Simultaneously, image data acquired by the camera is extracted as text information through an image recognition system.

[0109] The server analyzes this text data and generates specific tasks using a task generation mechanism. The generated tasks are evaluated by a prioritization mechanism, and priorities are determined based on importance and urgency. Reminders are set for tasks using a reminder setting mechanism and notified to the user in a timely manner.

[0110] This system uses the Google® Cloud Speech-to-Text API for speech recognition and the Google Cloud Vision API for image recognition. Task management utilizes task management tools and APIs such as Trello and Asana to manage schedules.

[0111] For example, if a user tells an autonomous device, "Please complete the presentation materials by this Friday," this voice is transcribed into text and registered as a task. Similarly, by taking a picture of project notes written on a whiteboard with a camera, the project tasks are automatically listed.

[0112] Examples of prompts for using generative AI models include the following:

[0113] "Automatically transcribe the meeting content and convert it into a task."

[0114] "Scan the contents of this memo and create a list. Then, think of solutions for each item."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The terminal uses an acoustic data acquisition device (microphone) to acquire the user's voice data in real time. This voice data is then sent to the server. The input is the user's voice data, and the output is the transmission of voice data to the server.

[0118] Step 2:

[0119] The server converts received audio data into text using the Google Cloud Speech-to-Text API. The input is audio data from the device, and the output is the converted text data. The server analyzes the audio data and converts the phonetic patterns into text.

[0120] Step 3:

[0121] The terminal acquires image data using a visual information collection device (camera) and transfers it to the server. The input is the image data obtained through the camera, and the output is the transmission of the image data to the server.

[0122] Step 4:

[0123] The server uses the Google Cloud Vision API to extract text information from image data and convert it to text. The input is image data from the device, and the output is text data containing the text information. It performs the operation of analyzing and identifying the text within the image.

[0124] Step 5:

[0125] The server analyzes text data obtained through speech recognition and image recognition, and generates specific tasks using a task generation mechanism. The input is the analyzed text data, and the output is the generated tasks. The server then performs an operation to group tasks based on the content of the text data.

[0126] Step 6:

[0127] The server evaluates the importance and urgency of tasks generated by the prioritization mechanism and determines their priority. The input is the generated tasks, and the output is the prioritized tasks. It performs an operation to evaluate task attributes and assign priorities.

[0128] Step 7:

[0129] The server uses a reminder setting mechanism to set reminders for users based on task deadlines and priorities. The input is a prioritized task, and the output is a reminder notification to the user. The server then determines the notification schedule, taking into account the time remaining until the deadline.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This system is an advanced task management system that incorporates emotion recognition, optimizing the user's psychological state and work efficiency. A specific implementation is described below.

[0132] First, the device acquires audio data in real time through the microphone and sends this audio data, collected during meetings and daily tasks, to the server. The server uses speech recognition technology to convert this audio data into text data, preparing it for analysis of conversations and instructions.

[0133] Next, the device uses its camera to acquire image data of a whiteboard, handwritten notes, etc., and sends it to the server. The server uses image recognition technology to analyze the image data and convert the text information within the image into text.

[0134] This text data is integrated and analyzed by the server. This analysis generates structured information as tasks, which are then prioritized based on their deadlines and importance.

[0135] Furthermore, this system is equipped with an emotion engine that analyzes user emotion data acquired from the terminal to evaluate the emotional state in real time. If the user is experiencing stress, the server can adjust the task load and re-evaluate task priorities based on that information.

[0136] The emotion engine optimizes the frequency of reminders and the content of notifications, taking into account the user's psychological state. This allows users to complete tasks more comfortably and efficiently.

[0137] As a concrete example, consider a situation where a user is working on a high-pressure project. In this system, an emotion engine detects the user's stress level and reduces the burden on the user by mitigating task notifications. This allows the user to effectively manage tasks while maintaining focus on other work.

[0138] This configuration allows the system to comprehensively support the user's psychological state and task management, thereby achieving increased efficiency and reduced burden.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The device uses its microphone to acquire audio data during meetings and daily work. The acquired audio data is transmitted to the server in real time.

[0142] Step 2:

[0143] The server feeds the received audio data into a speech recognition engine, which converts the audio into text. This text data includes the spoken words and instructions.

[0144] Step 3:

[0145] The device acquires image data of the whiteboard or handwritten notes through its camera. The acquired image data is then sent to a server.

[0146] Step 4:

[0147] The server uses OCR technology to extract text information from the received image data and converts it into text. This makes the visual information from the meeting available as text.

[0148] Step 5:

[0149] The server analyzes the text data obtained from speech recognition and image recognition and extracts the necessary task information. Deadline and priority information are also analyzed here and generated as tasks.

[0150] Step 6:

[0151] The server prioritizes the generated tasks based on their importance and urgency.

[0152] Step 7:

[0153] The device periodically surveys the user's emotional state using the user's biometric information and behavioral data. This is to provide values ​​to the emotion engine.

[0154] Step 8:

[0155] The server receives user emotion data analyzed by the emotion engine and adjusts the task load based on that state. If the user is stressed, the amount and frequency of task notifications are reduced.

[0156] Step 9:

[0157] The server adjusts reminder and notification settings based on the sentiment analysis results, allowing users to manage tasks in a psychologically optimal state.

[0158] Step 10:

[0159] Users receive a pre-arranged list of tasks and reminder notifications sent from the server. Based on this, they efficiently manage their own tasks.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] Traditional task management systems have difficulty adjusting tasks in accordance with the user's psychological state and emotional changes, making efficient task management difficult when users are experiencing stress. Furthermore, there were no systems that could dynamically adjust task load based on emotions or optimize notification content.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes data recognition means for acquiring audio data in real time and converting the audio data into text, data recognition means for acquiring image data and extracting character information from the image data and converting it into text, and data analysis means for analyzing the text data obtained by the data recognition means and generating tasks. This enables task management and optimization of notification content that dynamically reflects the user's emotional state.

[0165] "Audio data" refers to audio signals acquired via an audio input device.

[0166] "Real-time" means that processing is performed instantly without delay.

[0167] A "data recognition means" is a mechanism that analyzes information from audio or images and converts it into text data.

[0168] "Image data" refers to visual information signals acquired through a visual input device.

[0169] "Textual information" refers to information that can be converted into text, extracted from images or audio.

[0170] A "data analysis tool" is a mechanism that processes acquired text data and organizes the information for a specific purpose.

[0171] A "task" is defined as a unit of work or activity that needs to be managed or performed.

[0172] Prioritization is the process of evaluating tasks based on their importance and urgency, and then determining their order.

[0173] "Adjustment means" refers to methods or mechanisms for optimizing task load and notifications according to the user's situation.

[0174] A "setting mechanism" is a mechanism that reflects the adjusted information and parameters in the system and controls its operation.

[0175] A "user" is someone who operates the system and enjoys its services and functions.

[0176] An "information processing device" is a device that includes an acoustic input device and a visual input device, and that aggregates and processes data.

[0177] This invention relates to a system that enables dynamic task management in accordance with the user's psychological state. This system has the capability to recognize voice and image data, supports diverse data inputs, and adjusts task priorities and optimizes notification content while considering the user's emotional state.

[0178] The terminal uses a microphone as an audio input device to acquire audio data in real time. The collected audio data is converted into a digital signal at the endpoint and sent to the server using a secure communication protocol. The server utilizes speech recognition technology and converts the audio into text data using speech recognition software such as the Google Speech-to-Text API.

[0179] The device also uses a camera as a visual input device to acquire image data of whiteboards and handwritten notes. This image data is analyzed on a server using OCR technology, specifically Tesseract OCR, and converted into text data.

[0180] The text data acquired through these recognition processes is integrated on a server and analyzed using natural language processing techniques. By using generative AI models such as Adobe Sensei, the integrated text data is structured into tasks, and priorities are automatically set based on the required deadlines and priorities.

[0181] Furthermore, the device acquires user emotional data in real time and collects it through sensor devices. This includes voice tone analysis and facial recognition technology. The collected emotional data is analyzed on a server, and the user's psychological state, such as their stress level, is evaluated and reflected in real time.

[0182] For example, if a user is experiencing high pressure on a project, this system can detect their emotional state and flexibly adjust task notifications. This creates an environment where the user can concentrate on other tasks.

[0183] An example of a prompt message that might be input to the generative AI model is: "Please use emotion recognition technology to suggest a task management method tailored to the user's stress level."

[0184] This system comprehensively supports users' psychological state and work efficiency, reducing the burden of work while simultaneously enabling efficient task management.

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The terminal acquires the user's voice data in real time using an acoustic input device. The input here is the user's spoken voice, and the output is a digital acoustic signal. The terminal encodes this acoustic signal and sends it to the server using a secure protocol.

[0188] Step 2:

[0189] The server analyzes the received acoustic signal using speech recognition technology and converts it into text data. Specifically, it uses speech recognition software to process the acoustic signal as input and generate text data as output. The server stores this text data in a database for analysis.

[0190] Step 3:

[0191] The terminal uses a visual input device to acquire image data from sources such as whiteboards and handwritten notes. In this step, the input is image data, and the output is the electronic format of that data. The terminal optimizes and encodes the image before sending it to the server.

[0192] Step 4:

[0193] The server processes the received image data using OCR technology, extracting text information from the image and converting it into text data. The input is image data, and the output is data in which the text from the image has been formatted. The server then integrates this text for analysis.

[0194] Step 5:

[0195] The server analyzes text data obtained from integrated audio and image data using natural language processing techniques. The input for this step is a collection of text data, and the output is a structured task list. A generative AI model is used to set task priorities and associated deadlines.

[0196] Step 6:

[0197] The device uses sensor devices to collect user emotional data in real time. Inputs include the user's voice tone and facial expressions, while output is quantified emotional data. The device quickly transmits this emotional data to a server.

[0198] Step 7:

[0199] The server analyzes emotional data and adjusts task priorities and notification content accordingly. The input is quantified emotional data, and the output is an adjusted task list and notification schedule. The server delivers this in a format optimized for the user's psychological state.

[0200] These steps create a system that enables flexible task management that takes into account the user's psychological state, thereby supporting efficient work execution.

[0201] (Application Example 2)

[0202] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0203] In modern society, users face numerous tasks, leading to increased psychological burden. Furthermore, task management systems often fail to consider the user's emotional state, potentially imposing excessive pressure. In such situations, users cannot achieve their full potential and receive insufficient emotional support. Therefore, there is a need for systems that consider the user's emotional state, alleviate stress, and manage tasks effectively.

[0204] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0205] In this invention, the server includes speech recognition means for acquiring audio data in real time and converting the audio data into text, image recognition means for acquiring image data, extracting character information from the image data and converting it into text, and emotion evaluation means for evaluating the emotional state and re-evaluating task priorities based on that evaluation. This makes it possible to prioritize tasks and adjust notifications while taking into account the emotional state of the user.

[0206] "Audio data" refers to sound information, such as human voices, acquired through a microphone.

[0207] "Converting to text" means analyzing audio or image data and representing it as textual information.

[0208] "Speech recognition means" refers to a technology that analyzes speech data and generates text data as character information.

[0209] "Image data" refers to digital data containing visual information acquired using a camera or similar device.

[0210] "Image recognition means" refers to a technology that extracts and analyzes information such as characters and shapes from image data.

[0211] A "task generation method" is a method for creating a task list that specifies the actions and processes to be performed, based on text data obtained from speech recognition and image recognition methods.

[0212] A "prioritization tool" is a system for efficiently managing generated tasks by prioritizing them based on their importance and urgency.

[0213] An "emotional evaluation tool" is a technological platform that analyzes the emotional state of users and utilizes that information for task management, notifications, and other purposes.

[0214] The "reminder setting method" is a function that schedules task-related notifications based on deadlines and priorities, and adjusts them as needed.

[0215] Modes for carrying out the invention

[0216] In an embodiment of this invention, the system is composed of multiple hardware and software components. A server plays a central role, performing processing related to speech recognition, image recognition, and sentiment evaluation.

[0217] The device is equipped with a microphone to acquire audio data in real time. The Google Cloud Speech-to-Text API is used for speech recognition, converting the audio data into text. The converted text data is then sent to a server for analysis.

[0218] The device is also equipped with a camera to collect image data. This image data is analyzed using the Google Cloud Vision API, and text information is extracted from the images. This information is also sent to the server as text data and used to generate subsequent tasks.

[0219] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of text data obtained from audio and images. Based on this information, it re-evaluates task priorities and adjusts the content and frequency of reminder notifications as needed.

[0220] When a user is working on a long-term project, for example, the system monitors their psychological state and, if their stress level is high, suggests playing relaxing music or taking a break. This helps support the user's motivation to work and efficient task completion.

[0221] A concrete example would be a situation where a user enters a prompt such as, "Analyze today's work and emotions, and provide suggestions for stress reduction." This prompt allows the user to receive specific stress management suggestions based on an emotional assessment through the system.

[0222] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0223] Step 1:

[0224] The device uses a microphone to acquire the user's voice data in real time. This acquired voice data is used as input for speech recognition processing. Speech recognition technology converts this voice data into text data. The resulting text data is sent to a server and used for subsequent processing.

[0225] Step 2:

[0226] The device uses its camera to acquire image data of the user's surroundings. Image recognition technology is used to extract text information from this image data. Image recognition software converts the characters in the image into text data. The converted text data is sent to the server, similar to audio data.

[0227] Step 3:

[0228] The server integrates the text data obtained in steps 1 and 2. This text data is parsed by a task generation algorithm to generate specific tasks. This task data is used for prioritization according to importance and urgency.

[0229] Step 4:

[0230] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of the acquired text data. The input text is analyzed for sentiment evaluation, and the resulting sentiment data is used as an indicator for task management.

[0231] Step 5:

[0232] Based on the sentiment assessment results, the server re-evaluates task priorities. Task reminder settings are adjusted to match the user's current emotional state, and notification content and frequency are changed if necessary. This minimizes the user's psychological burden.

[0233] Step 6:

[0234] The user inputs a prompt message through a generative AI model, such as, "Analyze today's work and emotions, and provide suggestions for stress relief." Based on this prompt, the system creates specific stress management suggestions tailored to the user's emotional state and provides them to the user.

[0235] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0236] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0237] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0238] [Second Embodiment]

[0239] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0240] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0241] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0242] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0243] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0244] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0245] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0246] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0247] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0248] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0249] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0250] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0251] This system automates task management using speech recognition and image recognition, and is designed to improve work efficiency, particularly for users with Attention Deficit Hyperactivity Disorder (ADHD). A specific implementation is described below.

[0252] First, the device transmits audio data acquired during meetings or work to the server in real time. The server uses speech recognition technology to convert the audio data into text data. This audio data includes the content of the meeting and instructions.

[0253] Next, the device scans images such as whiteboards and handwritten notes through its camera and transfers them to the server. The server uses image recognition technology to extract text information from the images and convert it into text. This information includes notes and descriptions related to tasks.

[0254] These text data are parsed by the server and generated as specific tasks. For example, if a meeting includes the phrase "Submit the report by next Friday," a task to create the report will be automatically generated, and a deadline will be set.

[0255] The server evaluates the importance and urgency of the tasks it generates and automatically sets their priorities. This ensures that new tasks with high urgency are placed higher than other tasks.

[0256] Furthermore, the server sets task reminders according to the user's settings and provides timely notifications for tasks that are approaching deadlines or have high priority. This allows users to efficiently manage the progress of their tasks.

[0257] Furthermore, a specially customized interface is provided for users with ADHD. This is designed to make it easier to check and manage tasks with visual and auditory support.

[0258] As an example, consider a scenario where a user hears deadlines and tasks for multiple projects at once during a meeting. Using this system, the information received can be immediately converted into tasks, allowing the user to focus on them and improve their concentration on other tasks.

[0259] The following describes the processing flow.

[0260] Step 1:

[0261] The device acquires audio data in real time through the microphone during meetings and work sessions. The acquired audio data is then sent directly to the server.

[0262] Step 2:

[0263] The server inputs the received audio data into a speech recognition engine and converts it into text data. This makes it easier to analyze the instructions and meeting content contained in the audio.

[0264] Step 3:

[0265] The device uses its camera to acquire image data of whiteboards, handwritten notes, and other objects. This image data is also sent to the server.

[0266] Step 4:

[0267] The server processes the received image data using OCR technology, converting the text information within the image into text. The contents of notes on a whiteboard or documents are then extracted.

[0268] Step 5:

[0269] The server integrates text data obtained from speech recognition and image recognition and performs text analysis. This analysis extracts task generation information, deadlines, and priorities.

[0270] Step 6:

[0271] The server generates tasks based on the extracted information and sets appropriate priorities for each task. The tasks are ordered considering importance and urgency.

[0272] Step 7:

[0273] The server schedules reminders for tasks according to user settings. Notifications are prepared based on deadlines and priorities.

[0274] Step 8:

[0275] Users receive task lists and reminder notifications sent from the server to check the progress of their work. They can review and adjust task details as needed.

[0276] (Example 1)

[0277] Next, we will describe Example 1. 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."

[0278] In recent years, as the demand for improved work efficiency has increased, users with Attention Deficit Hyperactivity Disorder (ADHD) in particular face challenges in appropriately prioritizing tasks and efficiently managing them. Conventional task management systems have limitations in processing audio and visual information, resulting in insufficient support for users with ADHD. Furthermore, the difficulty in real-time information gathering and analysis, which places a heavy burden on users, is also a challenge.

[0279] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0280] In this invention, the server includes an information conversion means for acquiring audio information and converting it into text; an information processing means for acquiring visual information, extracting textual information from the visual information and converting it into text; and an instruction generation means for analyzing the textual information obtained by the information conversion means and the information processing means and generating work instructions. This enables real-time information collection and analysis, and in particular makes it possible to provide efficient task management while assisting concentration for users with ADHD.

[0281] "Audio information" refers to information obtained by acquiring audio as digital data, and typically includes audio data such as conversations and instructions.

[0282] "Information conversion means" refers to a device or system that has the function of analyzing audio information and converting it into text format.

[0283] "Visual information" refers to digital data obtained through images and graphics, including character information and charts.

[0284] "Information processing means" refers to a device or system that has the function of analyzing character information from visual information and extracting it as text.

[0285] "Work instruction" refers to specific tasks or instructions generated from the analyzed information, which are business items with schedules and priorities set.

[0286] "Instruction generation means" refers to a device or system that has the function of analyzing text information obtained from voice information and visual information and generating specific work instructions.

[0287] This system efficiently collects voice and visual information and automatically generates tasks based on it, thereby improving the work efficiency of users with physical disabilities in particular. The specific embodiments thereof will be described below.

[0288] The terminal uses a microphone to acquire voice information. The voice information obtained during meetings or work is temporarily stored on-site and then transmitted to the multifunctional server in real time. As this transmission protocol, HTTPS or the like is used to maintain the confidentiality of the data. In addition, the terminal uses a built-in or external camera to acquire visual information and transmits it to the server as well. This visual information includes whiteboards, handwritten notes, and the like.

[0289] The server applies a speech recognition engine (e.g., an available general-purpose speech recognition API) to the transmitted voice information to convert the voice data into text. Similarly, for visual information, character information is extracted using image recognition technology (e.g., a general-purpose image recognition API) and converted into text.

[0290] Through the analysis of text information, the server generates specific work instructions. These instructions are automatically prioritized based on their importance and urgency. A reminder function is also included, notifying the user of tasks with approaching deadlines.

[0291] The user interface is customized for ease of use, especially for users with behavioral disabilities, and allows for intuitive operation through both visual and auditory means.

[0292] As an example, suppose a user receives instructions in a meeting that "a report for a specific project is required by next Friday." This system collects and analyzes audio and visual information and automatically generates a "report creation" task instruction and its deadline. In this way, the user can focus on the task, without being burdened by prioritization, and can concentrate more on other tasks.

[0293] A concrete example of a prompt message for a generative AI model might be: "Automate the tasks for this week's meetings. Evaluate their importance and deadlines and output them as a list."

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The terminal acquires voice information using a voice input device. What the user says during meetings or work is input as voice and temporarily stored within the terminal. The voice information is converted into digital data for real-time transmission to the server. The input is analog voice, and this is output as digitized voice data.

[0297] Step 2:

[0298] The server receives the voice data received from the terminal and converts it into text data using a voice recognition engine. The voice recognition engine extracts phonemes from the input voice data and assembles words and sentences based on them. The output is text data including instructions and discussions during meetings and work.

[0299] Step 3:

[0300] The terminal uses a camera to acquire visual information. Images such as whiteboards and handwritten notes are captured through the camera and immediately sent to the server. The input is analog visual information, which is output as digital image data.

[0301] Step 4:

[0302] The server processes the received image data and extracts character information using image recognition technology. In this process, characters and figures are identified from the image data and extracted as text. The output is character data obtained from visual information.

[0303] [[ID=第十九]] Step 5:

[0304] The server analyzes the text data obtained from voice and vision. Using natural language processing technology, specific work instructions are generated through analysis. For example, an instruction such as "Submit the report by Friday next week" is generated. The input is text data, and the output is a work instruction for the task.

[0305] Step 6:

[0306] The server applies an algorithm that evaluates the importance and urgency to the generated work instructions. Based on the evaluation results, the priority of the work instructions is set. In this process, the task list is sorted according to the deadline and content of the task. The output is a task list with priorities assigned.

[0307] Step 7:

[0308] The server sets reminders based on work instructions. It schedules notifications to be sent to users as task deadlines approach. For example, reminders are set for the day before the deadline and for high-priority tasks. The output is the notification schedule for users.

[0309] Step 8:

[0310] Users view the generated task list through a customized interface. Designed with users with behavioral disabilities in mind, it enables visually and audibly intuitive task management. This process provides support to help users easily track task progress and take timely action.

[0311] (Application Example 1)

[0312] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0313] In modern living environments, a large amount of information and tasks arise frequently, making it particularly difficult for individuals with Attention Deficit Hyperactivity Disorder (ADHD) to manage them efficiently. Furthermore, there is a need for systems that allow for efficient task organization, management, and reminder setting in both home and work environments.

[0314] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0315] In this invention, the server includes means for acquiring audio data in real time and converting the audio data into text, means for acquiring image data and extracting character information from the image data and converting it into text, and means for analyzing the text data obtained by the audio recognition means and the image recognition means and generating tasks. This enables users with ADHD to use autonomous devices in their home or work environment and efficiently manage tasks.

[0316] "Speech recognition means" refers to a device or method that acquires speech data in real time and converts that data into text.

[0317] "Image recognition means" refers to a device or method that acquires image data, extracts character information from it, and converts it into text.

[0318] "Task generation means" refers to a device or method that analyzes text data obtained by speech recognition means and image recognition means and generates a specific task based on that analysis.

[0319] A "prioritization means" is a device or method for evaluating the importance and urgency of generated tasks and prioritizing those tasks based on that evaluation.

[0320] A "reminder setting means" is a device or method for setting reminders to notify users based on the deadline or priority of a task.

[0321] An "autonomous device" is a device that collects information via voice recognition and image recognition means in a home or work environment and operates autonomously based on that information.

[0322] An "acoustic data collection device" is a device that is connected to a speech recognition system to collect audio data.

[0323] A "visual information acquisition device" is a device connected to an image recognition system that collects image data.

[0324] An "information terminal" is a device operated by a user to collect data from speech recognition and image recognition.

[0325] This system includes voice recognition means, image recognition means, task generation means, prioritization means, reminder setting means, autonomous devices, sound collection devices, visual information collection devices, and information terminals. The server works in conjunction with these means to automate task management.

[0326] The device is equipped with an acoustic data collection device (microphone) and a visual information collection device (camera) to collect voices emitted by the user during daily activities, as well as visual information such as notes and documents. The voice data is transmitted to the server in real time and converted into text by a speech recognition system. Simultaneously, image data acquired by the camera is extracted as text information through an image recognition system.

[0327] The server analyzes this text data and generates specific tasks using a task generation mechanism. The generated tasks are evaluated by a prioritization mechanism, and priorities are determined based on importance and urgency. Reminders are set for tasks using a reminder setting mechanism and notified to the user in a timely manner.

[0328] This system uses the Google Cloud Speech-to-Text API for speech recognition and the Google Cloud Vision API for image recognition. Task management is handled using task management tools and APIs such as Trello and Asana to manage schedules.

[0329] For example, if a user tells an autonomous device, "Please complete the presentation materials by this Friday," this voice is transcribed into text and registered as a task. Similarly, by taking a picture of project notes written on a whiteboard with a camera, the project tasks are automatically listed.

[0330] Examples of prompts for using generative AI models include the following:

[0331] "Automatically transcribe the meeting content and convert it into a task."

[0332] "Scan the contents of this memo and create a list. Then, think of solutions for each item."

[0333] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0334] Step 1:

[0335] The terminal uses an acoustic data acquisition device (microphone) to acquire the user's voice data in real time. This voice data is then sent to the server. The input is the user's voice data, and the output is the transmission of voice data to the server.

[0336] Step 2:

[0337] The server converts received audio data into text using the Google Cloud Speech-to-Text API. The input is audio data from the device, and the output is the converted text data. The server analyzes the audio data and converts the phonetic patterns into text.

[0338] Step 3:

[0339] The terminal acquires image data using a visual information collection device (camera) and transfers it to the server. The input is the image data obtained through the camera, and the output is the transmission of the image data to the server.

[0340] Step 4:

[0341] The server uses the Google Cloud Vision API to extract text information from image data and convert it to text. The input is image data from the device, and the output is text data containing the text information. It performs the operation of analyzing and identifying the text within the image.

[0342] Step 5:

[0343] The server analyzes text data obtained through speech recognition and image recognition, and generates specific tasks using a task generation mechanism. The input is the analyzed text data, and the output is the generated tasks. The server then performs an operation to group tasks based on the content of the text data.

[0344] Step 6:

[0345] The server evaluates the importance and urgency of tasks generated by the prioritization mechanism and determines their priority. The input is the generated tasks, and the output is the prioritized tasks. It performs an operation to evaluate task attributes and assign priorities.

[0346] Step 7:

[0347] The server uses a reminder setting mechanism to set reminders for users based on task deadlines and priorities. The input is a prioritized task, and the output is a reminder notification to the user. The server then determines the notification schedule, taking into account the time remaining until the deadline.

[0348] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0349] This system is an advanced task management system that incorporates emotion recognition, optimizing the user's psychological state and work efficiency. A specific implementation is described below.

[0350] First, the device acquires audio data in real time through the microphone and sends this audio data, collected during meetings and daily tasks, to the server. The server uses speech recognition technology to convert this audio data into text data, preparing it for analysis of conversations and instructions.

[0351] Next, the device uses its camera to acquire image data of a whiteboard, handwritten notes, etc., and sends it to the server. The server uses image recognition technology to analyze the image data and convert the text information within the image into text.

[0352] This text data is integrated and analyzed by the server. This analysis generates structured information as tasks, which are then prioritized based on their deadlines and importance.

[0353] Furthermore, this system is equipped with an emotion engine that analyzes user emotion data acquired from the terminal to evaluate the emotional state in real time. If the user is experiencing stress, the server can adjust the task load and re-evaluate task priorities based on that information.

[0354] The emotion engine optimizes the frequency of reminders and the content of notifications, taking into account the user's psychological state. This allows users to complete tasks more comfortably and efficiently.

[0355] As a concrete example, consider a situation where a user is working on a high-pressure project. In this system, an emotion engine detects the user's stress level and reduces the burden on the user by mitigating task notifications. This allows the user to effectively manage tasks while maintaining focus on other work.

[0356] This configuration allows the system to comprehensively support the user's psychological state and task management, thereby achieving increased efficiency and reduced burden.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The device uses its microphone to acquire audio data during meetings and daily work. The acquired audio data is transmitted to the server in real time.

[0360] Step 2:

[0361] The server feeds the received audio data into a speech recognition engine, which converts the audio into text. This text data includes the spoken words and instructions.

[0362] Step 3:

[0363] The device acquires image data of the whiteboard or handwritten notes through its camera. The acquired image data is then sent to a server.

[0364] Step 4:

[0365] The server uses OCR technology to extract text information from the received image data and converts it into text. This makes the visual information from the meeting available as text.

[0366] Step 5:

[0367] The server analyzes the text data obtained from speech recognition and image recognition and extracts the necessary task information. Deadline and priority information are also analyzed here and generated as tasks.

[0368] Step 6:

[0369] The server prioritizes the generated tasks based on their importance and urgency.

[0370] Step 7:

[0371] The device periodically surveys the user's emotional state using the user's biometric information and behavioral data. This is to provide values ​​to the emotion engine.

[0372] Step 8:

[0373] The server receives user emotion data analyzed by the emotion engine and adjusts the task load based on that state. If the user is stressed, the amount and frequency of task notifications are reduced.

[0374] Step 9:

[0375] The server adjusts reminder and notification settings based on the sentiment analysis results, allowing users to manage tasks in a psychologically optimal state.

[0376] Step 10:

[0377] Users receive a pre-arranged list of tasks and reminder notifications sent from the server. Based on this, they efficiently manage their own tasks.

[0378] (Example 2)

[0379] Next, we will describe Example 2. 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".

[0380] Traditional task management systems have difficulty adjusting tasks in accordance with the user's psychological state and emotional changes, making efficient task management difficult when users are experiencing stress. Furthermore, there were no systems that could dynamically adjust task load based on emotions or optimize notification content.

[0381] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0382] In this invention, the server includes data recognition means for acquiring audio data in real time and converting the audio data into text, data recognition means for acquiring image data and extracting character information from the image data and converting it into text, and data analysis means for analyzing the text data obtained by the data recognition means and generating tasks. This enables task management and optimization of notification content that dynamically reflects the user's emotional state.

[0383] "Audio data" refers to audio signals acquired via an audio input device.

[0384] "Real-time" means that processing is performed instantly without delay.

[0385] A "data recognition means" is a mechanism that analyzes information from audio or images and converts it into text data.

[0386] "Image data" refers to visual information signals acquired through a visual input device.

[0387] "Textual information" refers to information that can be converted into text, extracted from images or audio.

[0388] A "data analysis tool" is a mechanism that processes acquired text data and organizes the information for a specific purpose.

[0389] A "task" is defined as a unit of work or activity that needs to be managed or performed.

[0390] Prioritization is the process of evaluating tasks based on their importance and urgency, and then determining their order.

[0391] "Adjustment means" refers to methods or mechanisms for optimizing task load and notifications according to the user's situation.

[0392] A "setting mechanism" is a mechanism that reflects the adjusted information and parameters in the system and controls its operation.

[0393] A "user" is someone who operates the system and enjoys its services and functions.

[0394] An "information processing device" is a device that includes an acoustic input device and a visual input device, and that aggregates and processes data.

[0395] This invention relates to a system that enables dynamic task management in accordance with the user's psychological state. This system has the capability to recognize voice and image data, supports diverse data inputs, and adjusts task priorities and optimizes notification content while considering the user's emotional state.

[0396] The terminal uses a microphone as an audio input device to acquire audio data in real time. The collected audio data is converted into a digital signal at the endpoint and sent to the server using a secure communication protocol. The server utilizes speech recognition technology and converts the audio into text data using speech recognition software such as the Google Speech-to-Text API.

[0397] The device also uses a camera as a visual input device to acquire image data of whiteboards and handwritten notes. This image data is analyzed on a server using OCR technology, specifically Tesseract OCR, and converted into text data.

[0398] The text data acquired through these recognition processes is integrated on a server and analyzed using natural language processing techniques. By using generative AI models such as Adobe Sensei, the integrated text data is structured into tasks, and priorities are automatically set based on the required deadlines and priorities.

[0399] Furthermore, the device acquires user emotional data in real time and collects it through sensor devices. This includes voice tone analysis and facial recognition technology. The collected emotional data is analyzed on a server, and the user's psychological state, such as their stress level, is evaluated and reflected in real time.

[0400] For example, if a user is experiencing high pressure on a project, this system can detect their emotional state and flexibly adjust task notifications. This creates an environment where the user can concentrate on other tasks.

[0401] An example of a prompt message that might be input to the generative AI model is: "Please use emotion recognition technology to suggest a task management method tailored to the user's stress level."

[0402] This system comprehensively supports users' psychological state and work efficiency, reducing the burden of work while simultaneously enabling efficient task management.

[0403] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0404] Step 1:

[0405] The terminal acquires the user's voice data in real time using an acoustic input device. The input here is the user's spoken voice, and the output is a digital acoustic signal. The terminal encodes this acoustic signal and sends it to the server using a secure protocol.

[0406] Step 2:

[0407] The server analyzes the received acoustic signal using speech recognition technology and converts it into text data. Specifically, it uses speech recognition software to process the acoustic signal as input and generate text data as output. The server stores this text data in a database for analysis.

[0408] Step 3:

[0409] The terminal uses a visual input device to acquire image data from sources such as whiteboards and handwritten notes. In this step, the input is image data, and the output is the electronic format of that data. The terminal optimizes and encodes the image before sending it to the server.

[0410] Step 4:

[0411] The server processes the received image data using OCR technology, extracting text information from the image and converting it into text data. The input is image data, and the output is data in which the text from the image has been formatted. The server then integrates this text for analysis.

[0412] Step 5:

[0413] The server analyzes text data obtained from integrated audio and image data using natural language processing techniques. The input for this step is a collection of text data, and the output is a structured task list. A generative AI model is used to set task priorities and associated deadlines.

[0414] Step 6:

[0415] The device uses sensor devices to collect user emotional data in real time. Inputs include the user's voice tone and facial expressions, while output is quantified emotional data. The device quickly transmits this emotional data to a server.

[0416] Step 7:

[0417] The server analyzes emotional data and adjusts task priorities and notification content accordingly. The input is quantified emotional data, and the output is an adjusted task list and notification schedule. The server delivers this in a format optimized for the user's psychological state.

[0418] These steps create a system that enables flexible task management that takes into account the user's psychological state, thereby supporting efficient work execution.

[0419] (Application Example 2)

[0420] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0421] In modern society, users face numerous tasks, leading to increased psychological burden. Furthermore, task management systems often fail to consider the user's emotional state, potentially imposing excessive pressure. In such situations, users cannot achieve their full potential and receive insufficient emotional support. Therefore, there is a need for systems that consider the user's emotional state, alleviate stress, and manage tasks effectively.

[0422] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0423] In this invention, the server includes speech recognition means for acquiring audio data in real time and converting the audio data into text, image recognition means for acquiring image data, extracting character information from the image data and converting it into text, and emotion evaluation means for evaluating the emotional state and re-evaluating task priorities based on that evaluation. This makes it possible to prioritize tasks and adjust notifications while taking into account the emotional state of the user.

[0424] "Audio data" refers to sound information, such as human voices, acquired through a microphone.

[0425] "Converting to text" means analyzing audio or image data and representing it as textual information.

[0426] "Speech recognition means" refers to a technology that analyzes speech data and generates text data as character information.

[0427] "Image data" refers to digital data containing visual information acquired using a camera or similar device.

[0428] "Image recognition means" refers to a technology that extracts and analyzes information such as characters and shapes from image data.

[0429] A "task generation method" is a method for creating a task list that specifies the actions and processes to be performed, based on text data obtained from speech recognition and image recognition methods.

[0430] A "prioritization tool" is a system for efficiently managing generated tasks by prioritizing them based on their importance and urgency.

[0431] An "emotional evaluation tool" is a technological platform that analyzes the emotional state of users and utilizes that information for task management, notifications, and other purposes.

[0432] The "reminder setting method" is a function that schedules task-related notifications based on deadlines and priorities, and adjusts them as needed.

[0433] Modes for carrying out the invention

[0434] In an embodiment of this invention, the system is composed of multiple hardware and software components. A server plays a central role, performing processing related to speech recognition, image recognition, and sentiment evaluation.

[0435] The device is equipped with a microphone to acquire audio data in real time. The Google Cloud Speech-to-Text API is used for speech recognition, converting the audio data into text. The converted text data is then sent to a server for analysis.

[0436] The device is also equipped with a camera to collect image data. This image data is analyzed using the Google Cloud Vision API, and text information is extracted from the images. This information is also sent to the server as text data and used to generate subsequent tasks.

[0437] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of text data obtained from audio and images. Based on this information, it re-evaluates task priorities and adjusts the content and frequency of reminder notifications as needed.

[0438] When a user is working on a long-term project, for example, the system monitors their psychological state and, if their stress level is high, suggests playing relaxing music or taking a break. This helps support the user's motivation to work and efficient task completion.

[0439] A concrete example would be a situation where a user enters a prompt such as, "Analyze today's work and emotions, and provide suggestions for stress reduction." This prompt allows the user to receive specific stress management suggestions based on an emotional assessment through the system.

[0440] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0441] Step 1:

[0442] The device uses a microphone to acquire the user's voice data in real time. This acquired voice data is used as input for speech recognition processing. Speech recognition technology converts this voice data into text data. The resulting text data is sent to a server and used for subsequent processing.

[0443] Step 2:

[0444] The device uses its camera to acquire image data of the user's surroundings. Image recognition technology is used to extract text information from this image data. Image recognition software converts the characters in the image into text data. The converted text data is sent to the server, similar to audio data.

[0445] Step 3:

[0446] The server integrates the text data obtained in steps 1 and 2. This text data is parsed by a task generation algorithm to generate specific tasks. This task data is used for prioritization according to importance and urgency.

[0447] Step 4:

[0448] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of the acquired text data. The input text is analyzed for sentiment evaluation, and the resulting sentiment data is used as an indicator for task management.

[0449] Step 5:

[0450] Based on the sentiment assessment results, the server re-evaluates task priorities. Task reminder settings are adjusted to match the user's current emotional state, and notification content and frequency are changed if necessary. This minimizes the user's psychological burden.

[0451] Step 6:

[0452] The user inputs a prompt message through a generative AI model, such as, "Analyze today's work and emotions, and provide suggestions for stress relief." Based on this prompt, the system creates specific stress management suggestions tailored to the user's emotional state and provides them to the user.

[0453] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0454] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0455] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0456] [Third Embodiment]

[0457] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0458] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0459] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0460] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0461] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0462] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0463] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0464] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0465] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0466] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0467] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0468] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0469] This system automates task management using speech recognition and image recognition, and is designed to improve work efficiency, particularly for users with Attention Deficit Hyperactivity Disorder (ADHD). A specific implementation is described below.

[0470] First, the device transmits audio data acquired during meetings or work to the server in real time. The server uses speech recognition technology to convert the audio data into text data. This audio data includes the content of the meeting and instructions.

[0471] Next, the device scans images such as whiteboards and handwritten notes through its camera and transfers them to the server. The server uses image recognition technology to extract text information from the images and convert it into text. This information includes notes and descriptions related to tasks.

[0472] These text data are parsed by the server and generated as specific tasks. For example, if a meeting includes the phrase "Submit the report by next Friday," a task to create the report will be automatically generated, and a deadline will be set.

[0473] The server evaluates the importance and urgency of the tasks it generates and automatically sets their priorities. This ensures that new tasks with high urgency are placed higher than other tasks.

[0474] Furthermore, the server sets task reminders according to the user's settings and provides timely notifications for tasks that are approaching deadlines or have high priority. This allows users to efficiently manage the progress of their tasks.

[0475] Furthermore, a specially customized interface is provided for users with ADHD. This is designed to make it easier to check and manage tasks with visual and auditory support.

[0476] As an example, consider a scenario where a user hears deadlines and tasks for multiple projects at once during a meeting. Using this system, the information received can be immediately converted into tasks, allowing the user to focus on them and improve their concentration on other tasks.

[0477] The following describes the processing flow.

[0478] Step 1:

[0479] The device acquires audio data in real time through the microphone during meetings and work sessions. The acquired audio data is then sent directly to the server.

[0480] Step 2:

[0481] The server inputs the received audio data into a speech recognition engine and converts it into text data. This makes it easier to analyze the instructions and meeting content contained in the audio.

[0482] Step 3:

[0483] The device uses its camera to acquire image data of whiteboards, handwritten notes, and other objects. This image data is also sent to the server.

[0484] Step 4:

[0485] The server processes the received image data using OCR technology, converting the text information within the image into text. The contents of notes on a whiteboard or documents are then extracted.

[0486] Step 5:

[0487] The server integrates text data obtained from speech recognition and image recognition and performs text analysis. This analysis extracts task generation information, deadlines, and priorities.

[0488] Step 6:

[0489] The server generates tasks based on the extracted information and sets appropriate priorities for each task. The tasks are ordered considering importance and urgency.

[0490] Step 7:

[0491] The server schedules reminders for tasks according to user settings. Notifications are prepared based on deadlines and priorities.

[0492] Step 8:

[0493] Users receive task lists and reminder notifications sent from the server to check the progress of their work. They can review and adjust task details as needed.

[0494] (Example 1)

[0495] Next, we will describe Example 1. 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."

[0496] In recent years, as the demand for improved work efficiency has increased, users with Attention Deficit Hyperactivity Disorder (ADHD) in particular face challenges in appropriately prioritizing tasks and efficiently managing them. Conventional task management systems have limitations in processing audio and visual information, resulting in insufficient support for users with ADHD. Furthermore, the difficulty in real-time information gathering and analysis, which places a heavy burden on users, is also a challenge.

[0497] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0498] In this invention, the server includes an information conversion means for acquiring audio information and converting it into text; an information processing means for acquiring visual information, extracting textual information from the visual information and converting it into text; and an instruction generation means for analyzing the textual information obtained by the information conversion means and the information processing means and generating work instructions. This enables real-time information collection and analysis, and in particular makes it possible to provide efficient task management while assisting concentration for users with ADHD.

[0499] "Audio information" refers to information obtained by acquiring audio as digital data, and typically includes audio data such as conversations and instructions.

[0500] "Information conversion means" refers to a device or system that has the function of analyzing audio information and converting it into text format.

[0501] "Visual information" refers to digital data obtained through images and diagrams, and includes textual information and charts.

[0502] "Information processing means" refers to a device or system that has the function of analyzing visual information to extract textual information.

[0503] A "work instruction" is a specific task or instruction generated from analyzed information, and it is a work item with a set schedule and priority.

[0504] "Instruction generation means" refers to a device or system that has the function of analyzing text information obtained from audio and visual information and generating specific work instructions.

[0505] This system efficiently collects audio and visual information and automatically generates tasks based on it, thereby improving work efficiency, especially for users with behavioral disabilities. A specific implementation is described below.

[0506] The terminal uses a microphone to acquire audio information. Audio information obtained during meetings or work sessions is temporarily stored on-site and then transmitted in real time to a multi-function server. HTTPS and similar protocols are used for this transmission to maintain data confidentiality. The terminal also acquires visual information using a built-in or external camera and transmits it to the server. This visual information includes whiteboards and handwritten notes.

[0507] The server applies a speech recognition engine (e.g., an available general-purpose speech recognition API) to the transmitted audio information and converts the audio data into text. Similarly, for visual information, image recognition technology (e.g., a general-purpose image recognition API) is used to extract text information and convert it into text.

[0508] Through the analysis of text information, the server generates specific work instructions. These instructions are automatically prioritized based on their importance and urgency. A reminder function is also included, notifying the user of tasks with approaching deadlines.

[0509] The user interface is customized for ease of use, especially for users with behavioral disabilities, and allows for intuitive operation through both visual and auditory means.

[0510] As an example, suppose a user receives instructions in a meeting that "a report for a specific project is required by next Friday." This system collects and analyzes audio and visual information and automatically generates a "report creation" task instruction and its deadline. In this way, the user can focus on the task, without being burdened by prioritization, and can concentrate more on other tasks.

[0511] A concrete example of a prompt message for a generative AI model might be: "Automate the tasks for this week's meetings. Evaluate their importance and deadlines and output them as a list."

[0512] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0513] Step 1:

[0514] The terminal acquires voice information using a voice input device. What the user says during meetings or work is input as voice and temporarily stored within the terminal. The voice information is converted into digital data for real-time transmission to the server. The input is analog voice, and this is output as digitized voice data.

[0515] Step 2:

[0516] The server receives audio data from the terminal and converts it into text data using a speech recognition engine. The speech recognition engine extracts phonemes from the input audio data and uses them to construct words and sentences. The output is text data, including instructions and discussions during meetings or work sessions.

[0517] Step 3:

[0518] The device acquires visual information using a camera. Images of whiteboards, handwritten notes, etc., are captured via the camera and immediately sent to the server. The input is analog visual information, which is output as digital image data.

[0519] Step 4:

[0520] The server processes the received image data and extracts text information using image recognition technology. This process identifies characters and shapes from the image data and extracts them as text. The output is text data derived from visual information.

[0521] Step 5:

[0522] The server analyzes text data obtained from speech and visual input. Using natural language processing techniques, it generates specific work instructions based on the analysis. For example, it might generate an instruction such as, "Submit the report by next Friday." The input is text data, and the output is a task instruction.

[0523] Step 6:

[0524] The server applies an algorithm to the generated work orders to evaluate their importance and urgency. Based on the evaluation results, it sets the priority of the work orders. This process organizes the task list according to the task deadlines and content. The output is a prioritized task list.

[0525] Step 7:

[0526] The server sets reminders based on work instructions. It schedules notifications to be sent to users as task deadlines approach. For example, reminders are set for the day before the deadline and for high-priority tasks. The output is the notification schedule for users.

[0527] Step 8:

[0528] Users view the generated task list through a customized interface. Designed with users with behavioral disabilities in mind, it enables visually and audibly intuitive task management. This process provides support to help users easily track task progress and take timely action.

[0529] (Application Example 1)

[0530] Next, we will explain Application Example 1. In the following explanation, 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."

[0531] In modern living environments, a large amount of information and tasks arise frequently, making it particularly difficult for individuals with Attention Deficit Hyperactivity Disorder (ADHD) to manage them efficiently. Furthermore, there is a need for systems that allow for efficient task organization, management, and reminder setting in both home and work environments.

[0532] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0533] In this invention, the server includes means for acquiring audio data in real time and converting the audio data into text, means for acquiring image data and extracting character information from the image data and converting it into text, and means for analyzing the text data obtained by the audio recognition means and the image recognition means and generating tasks. This enables users with ADHD to use autonomous devices in their home or work environment and efficiently manage tasks.

[0534] "Speech recognition means" refers to a device or method that acquires speech data in real time and converts that data into text.

[0535] "Image recognition means" refers to a device or method that acquires image data, extracts character information from it, and converts it into text.

[0536] "Task generation means" refers to a device or method that analyzes text data obtained by speech recognition means and image recognition means and generates a specific task based on that analysis.

[0537] A "prioritization means" is a device or method for evaluating the importance and urgency of generated tasks and prioritizing those tasks based on that evaluation.

[0538] A "reminder setting means" is a device or method for setting reminders to notify users based on the deadline or priority of a task.

[0539] An "autonomous device" is a device that collects information via voice recognition and image recognition means in a home or work environment and operates autonomously based on that information.

[0540] An "acoustic data collection device" is a device that is connected to a speech recognition system to collect audio data.

[0541] A "visual information acquisition device" is a device connected to an image recognition system that collects image data.

[0542] An "information terminal" is a device operated by a user to collect data from speech recognition and image recognition.

[0543] This system includes voice recognition means, image recognition means, task generation means, prioritization means, reminder setting means, autonomous devices, sound collection devices, visual information collection devices, and information terminals. The server works in conjunction with these means to automate task management.

[0544] The device is equipped with an acoustic data collection device (microphone) and a visual information collection device (camera) to collect voices emitted by the user during daily activities, as well as visual information such as notes and documents. The voice data is transmitted to the server in real time and converted into text by a speech recognition system. Simultaneously, image data acquired by the camera is extracted as text information through an image recognition system.

[0545] The server analyzes this text data and generates specific tasks using a task generation mechanism. The generated tasks are evaluated by a prioritization mechanism, and priorities are determined based on importance and urgency. Reminders are set for tasks using a reminder setting mechanism and notified to the user in a timely manner.

[0546] This system uses the Google Cloud Speech-to-Text API for speech recognition and the Google Cloud Vision API for image recognition. Task management is handled using task management tools and APIs such as Trello and Asana to manage schedules.

[0547] For example, if a user tells an autonomous device, "Please complete the presentation materials by this Friday," this voice is transcribed into text and registered as a task. Similarly, by taking a picture of project notes written on a whiteboard with a camera, the project tasks are automatically listed.

[0548] Examples of prompts for using generative AI models include the following:

[0549] "Automatically transcribe the meeting content and convert it into a task."

[0550] "Scan the contents of this memo and create a list. Then, think of solutions for each item."

[0551] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0552] Step 1:

[0553] The terminal uses an acoustic data acquisition device (microphone) to acquire the user's voice data in real time. This voice data is then sent to the server. The input is the user's voice data, and the output is the transmission of voice data to the server.

[0554] Step 2:

[0555] The server converts received audio data into text using the Google Cloud Speech-to-Text API. The input is audio data from the device, and the output is the converted text data. The server analyzes the audio data and converts the phonetic patterns into text.

[0556] Step 3:

[0557] The terminal acquires image data using a visual information collection device (camera) and transfers it to the server. The input is the image data obtained through the camera, and the output is the transmission of the image data to the server.

[0558] Step 4:

[0559] The server uses the Google Cloud Vision API to extract text information from image data and convert it to text. The input is image data from the device, and the output is text data containing the text information. It performs the operation of analyzing and identifying the text within the image.

[0560] Step 5:

[0561] The server analyzes text data obtained through speech recognition and image recognition, and generates specific tasks using a task generation mechanism. The input is the analyzed text data, and the output is the generated tasks. The server then performs an operation to group tasks based on the content of the text data.

[0562] Step 6:

[0563] The server evaluates the importance and urgency of tasks generated by the prioritization mechanism and determines their priority. The input is the generated tasks, and the output is the prioritized tasks. It performs an operation to evaluate task attributes and assign priorities.

[0564] Step 7:

[0565] The server uses a reminder setting mechanism to set reminders for users based on task deadlines and priorities. The input is a prioritized task, and the output is a reminder notification to the user. The server then determines the notification schedule, taking into account the time remaining until the deadline.

[0566] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0567] This system is an advanced task management system that incorporates emotion recognition, optimizing the user's psychological state and work efficiency. A specific implementation is described below.

[0568] First, the device acquires audio data in real time through the microphone and sends this audio data, collected during meetings and daily tasks, to the server. The server uses speech recognition technology to convert this audio data into text data, preparing it for analysis of conversations and instructions.

[0569] Next, the device uses its camera to acquire image data of a whiteboard, handwritten notes, etc., and sends it to the server. The server uses image recognition technology to analyze the image data and convert the text information within the image into text.

[0570] This text data is integrated and analyzed by the server. This analysis generates structured information as tasks, which are then prioritized based on their deadlines and importance.

[0571] Furthermore, this system is equipped with an emotion engine that analyzes user emotion data acquired from the terminal to evaluate the emotional state in real time. If the user is experiencing stress, the server can adjust the task load and re-evaluate task priorities based on that information.

[0572] The emotion engine optimizes the frequency of reminders and the content of notifications, taking into account the user's psychological state. This allows users to complete tasks more comfortably and efficiently.

[0573] As a concrete example, consider a situation where a user is working on a high-pressure project. In this system, an emotion engine detects the user's stress level and reduces the burden on the user by mitigating task notifications. This allows the user to effectively manage tasks while maintaining focus on other work.

[0574] This configuration allows the system to comprehensively support the user's psychological state and task management, thereby achieving increased efficiency and reduced burden.

[0575] The following describes the processing flow.

[0576] Step 1:

[0577] The device uses its microphone to acquire audio data during meetings and daily work. The acquired audio data is transmitted to the server in real time.

[0578] Step 2:

[0579] The server feeds the received audio data into a speech recognition engine, which converts the audio into text. This text data includes the spoken words and instructions.

[0580] Step 3:

[0581] The device acquires image data of the whiteboard or handwritten notes through its camera. The acquired image data is then sent to a server.

[0582] Step 4:

[0583] The server uses OCR technology to extract text information from the received image data and converts it into text. This makes the visual information from the meeting available as text.

[0584] Step 5:

[0585] The server analyzes the text data obtained from speech recognition and image recognition and extracts the necessary task information. Deadline and priority information are also analyzed here and generated as tasks.

[0586] Step 6:

[0587] The server prioritizes the generated tasks based on their importance and urgency.

[0588] Step 7:

[0589] The device periodically surveys the user's emotional state using the user's biometric information and behavioral data. This is to provide values ​​to the emotion engine.

[0590] Step 8:

[0591] The server receives user emotion data analyzed by the emotion engine and adjusts the task load based on that state. If the user is stressed, the amount and frequency of task notifications are reduced.

[0592] Step 9:

[0593] The server adjusts reminder and notification settings based on the sentiment analysis results, allowing users to manage tasks in a psychologically optimal state.

[0594] Step 10:

[0595] Users receive a pre-arranged list of tasks and reminder notifications sent from the server. Based on this, they efficiently manage their own tasks.

[0596] (Example 2)

[0597] Next, we will describe Example 2. 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."

[0598] Traditional task management systems have difficulty adjusting tasks in accordance with the user's psychological state and emotional changes, making efficient task management difficult when users are experiencing stress. Furthermore, there were no systems that could dynamically adjust task load based on emotions or optimize notification content.

[0599] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0600] In this invention, the server includes data recognition means for acquiring audio data in real time and converting the audio data into text, data recognition means for acquiring image data and extracting character information from the image data and converting it into text, and data analysis means for analyzing the text data obtained by the data recognition means and generating tasks. This enables task management and optimization of notification content that dynamically reflects the user's emotional state.

[0601] "Audio data" refers to audio signals acquired via an audio input device.

[0602] "Real-time" means that processing is performed instantly without delay.

[0603] A "data recognition means" is a mechanism that analyzes information from audio or images and converts it into text data.

[0604] "Image data" refers to visual information signals acquired through a visual input device.

[0605] "Textual information" refers to information that can be converted into text, extracted from images or audio.

[0606] A "data analysis tool" is a mechanism that processes acquired text data and organizes the information for a specific purpose.

[0607] A "task" is defined as a unit of work or activity that needs to be managed or performed.

[0608] Prioritization is the process of evaluating tasks based on their importance and urgency, and then determining their order.

[0609] "Adjustment means" refers to methods or mechanisms for optimizing task load and notifications according to the user's situation.

[0610] A "setting mechanism" is a mechanism that reflects the adjusted information and parameters in the system and controls its operation.

[0611] A "user" is someone who operates the system and enjoys its services and functions.

[0612] An "information processing device" is a device that includes an acoustic input device and a visual input device, and that aggregates and processes data.

[0613] This invention relates to a system that enables dynamic task management in accordance with the user's psychological state. This system has the capability to recognize voice and image data, supports diverse data inputs, and adjusts task priorities and optimizes notification content while considering the user's emotional state.

[0614] The terminal uses a microphone as an audio input device to acquire audio data in real time. The collected audio data is converted into a digital signal at the endpoint and sent to the server using a secure communication protocol. The server utilizes speech recognition technology and converts the audio into text data using speech recognition software such as the Google Speech-to-Text API.

[0615] The device also uses a camera as a visual input device to acquire image data of whiteboards and handwritten notes. This image data is analyzed on a server using OCR technology, specifically Tesseract OCR, and converted into text data.

[0616] The text data acquired through these recognition processes is integrated on a server and analyzed using natural language processing techniques. By using generative AI models such as Adobe Sensei, the integrated text data is structured into tasks, and priorities are automatically set based on the required deadlines and priorities.

[0617] Furthermore, the device acquires user emotional data in real time and collects it through sensor devices. This includes voice tone analysis and facial recognition technology. The collected emotional data is analyzed on a server, and the user's psychological state, such as their stress level, is evaluated and reflected in real time.

[0618] For example, if a user is experiencing high pressure on a project, this system can detect their emotional state and flexibly adjust task notifications. This creates an environment where the user can concentrate on other tasks.

[0619] An example of a prompt message that might be input to the generative AI model is: "Please use emotion recognition technology to suggest a task management method tailored to the user's stress level."

[0620] This system comprehensively supports users' psychological state and work efficiency, reducing the burden of work while simultaneously enabling efficient task management.

[0621] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0622] Step 1:

[0623] The terminal acquires the user's voice data in real time using an acoustic input device. The input here is the user's spoken voice, and the output is a digital acoustic signal. The terminal encodes this acoustic signal and sends it to the server using a secure protocol.

[0624] Step 2:

[0625] The server analyzes the received acoustic signal using speech recognition technology and converts it into text data. Specifically, it uses speech recognition software to process the acoustic signal as input and generate text data as output. The server stores this text data in a database for analysis.

[0626] Step 3:

[0627] The terminal uses a visual input device to acquire image data from sources such as whiteboards and handwritten notes. In this step, the input is image data, and the output is the electronic format of that data. The terminal optimizes and encodes the image before sending it to the server.

[0628] Step 4:

[0629] The server processes the received image data using OCR technology, extracting text information from the image and converting it into text data. The input is image data, and the output is data in which the text from the image has been formatted. The server then integrates this text for analysis.

[0630] Step 5:

[0631] The server analyzes text data obtained from integrated audio and image data using natural language processing techniques. The input for this step is a collection of text data, and the output is a structured task list. A generative AI model is used to set task priorities and associated deadlines.

[0632] Step 6:

[0633] The device uses sensor devices to collect user emotional data in real time. Inputs include the user's voice tone and facial expressions, while output is quantified emotional data. The device quickly transmits this emotional data to a server.

[0634] Step 7:

[0635] The server analyzes emotional data and adjusts task priorities and notification content accordingly. The input is quantified emotional data, and the output is an adjusted task list and notification schedule. The server delivers this in a format optimized for the user's psychological state.

[0636] These steps create a system that enables flexible task management that takes into account the user's psychological state, thereby supporting efficient work execution.

[0637] (Application Example 2)

[0638] Next, we will explain application example 2. In the following explanation, 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."

[0639] In modern society, users face numerous tasks, leading to increased psychological burden. Furthermore, task management systems often fail to consider the user's emotional state, potentially imposing excessive pressure. In such situations, users cannot achieve their full potential and receive insufficient emotional support. Therefore, there is a need for systems that consider the user's emotional state, alleviate stress, and manage tasks effectively.

[0640] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0641] In this invention, the server includes speech recognition means for acquiring audio data in real time and converting the audio data into text, image recognition means for acquiring image data, extracting character information from the image data and converting it into text, and emotion evaluation means for evaluating the emotional state and re-evaluating task priorities based on that evaluation. This makes it possible to prioritize tasks and adjust notifications while taking into account the emotional state of the user.

[0642] "Audio data" refers to sound information, such as human voices, acquired through a microphone.

[0643] "Converting to text" means analyzing audio or image data and representing it as textual information.

[0644] "Speech recognition means" refers to a technology that analyzes speech data and generates text data as character information.

[0645] "Image data" refers to digital data containing visual information acquired using a camera or similar device.

[0646] "Image recognition means" refers to a technology that extracts and analyzes information such as characters and shapes from image data.

[0647] A "task generation method" is a method for creating a task list that specifies the actions and processes to be performed, based on text data obtained from speech recognition and image recognition methods.

[0648] A "prioritization tool" is a system for efficiently managing generated tasks by prioritizing them based on their importance and urgency.

[0649] An "emotional evaluation tool" is a technological platform that analyzes the emotional state of users and utilizes that information for task management, notifications, and other purposes.

[0650] The "reminder setting method" is a function that schedules task-related notifications based on deadlines and priorities, and adjusts them as needed.

[0651] Modes for carrying out the invention

[0652] In an embodiment of this invention, the system is composed of multiple hardware and software components. A server plays a central role, performing processing related to speech recognition, image recognition, and sentiment evaluation.

[0653] The device is equipped with a microphone to acquire audio data in real time. The Google Cloud Speech-to-Text API is used for speech recognition, converting the audio data into text. The converted text data is then sent to a server for analysis.

[0654] The device is also equipped with a camera to collect image data. This image data is analyzed using the Google Cloud Vision API, and text information is extracted from the images. This information is also sent to the server as text data and used to generate subsequent tasks.

[0655] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of text data obtained from audio and images. Based on this information, it re-evaluates task priorities and adjusts the content and frequency of reminder notifications as needed.

[0656] When a user is working on a long-term project, for example, the system monitors their psychological state and, if their stress level is high, suggests playing relaxing music or taking a break. This helps support the user's motivation to work and efficient task completion.

[0657] A concrete example would be a situation where a user enters a prompt such as, "Analyze today's work and emotions, and provide suggestions for stress reduction." This prompt allows the user to receive specific stress management suggestions based on an emotional assessment through the system.

[0658] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0659] Step 1:

[0660] The device uses a microphone to acquire the user's voice data in real time. This acquired voice data is used as input for speech recognition processing. Speech recognition technology converts this voice data into text data. The resulting text data is sent to a server and used for subsequent processing.

[0661] Step 2:

[0662] The device uses its camera to acquire image data of the user's surroundings. Image recognition technology is used to extract text information from this image data. Image recognition software converts the characters in the image into text data. The converted text data is sent to the server, similar to audio data.

[0663] Step 3:

[0664] The server integrates the text data obtained in steps 1 and 2. This text data is parsed by a task generation algorithm to generate specific tasks. This task data is used for prioritization according to importance and urgency.

[0665] Step 4:

[0666] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of the acquired text data. The input text is analyzed for sentiment evaluation, and the resulting sentiment data is used as an indicator for task management.

[0667] Step 5:

[0668] Based on the sentiment assessment results, the server re-evaluates task priorities. Task reminder settings are adjusted to match the user's current emotional state, and notification content and frequency are changed if necessary. This minimizes the user's psychological burden.

[0669] Step 6:

[0670] The user inputs a prompt message through a generative AI model, such as, "Analyze today's work and emotions, and provide suggestions for stress relief." Based on this prompt, the system creates specific stress management suggestions tailored to the user's emotional state and provides them to the user.

[0671] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0672] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0673] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0674] [Fourth Embodiment]

[0675] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0676] As shown in Figure 7, the 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.

[0677] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0678] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0679] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0680] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0681] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0682] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0683] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0684] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0685] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0686] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0687] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0688] This system automates task management using speech recognition and image recognition, and is designed to improve work efficiency, particularly for users with Attention Deficit Hyperactivity Disorder (ADHD). A specific implementation is described below.

[0689] First, the device transmits audio data acquired during meetings or work to the server in real time. The server uses speech recognition technology to convert the audio data into text data. This audio data includes the content of the meeting and instructions.

[0690] Next, the device scans images such as whiteboards and handwritten notes through its camera and transfers them to the server. The server uses image recognition technology to extract text information from the images and convert it into text. This information includes notes and descriptions related to tasks.

[0691] These text data are parsed by the server and generated as specific tasks. For example, if a meeting includes the phrase "Submit the report by next Friday," a task to create the report will be automatically generated, and a deadline will be set.

[0692] The server evaluates the importance and urgency of the tasks it generates and automatically sets their priorities. This ensures that new tasks with high urgency are placed higher than other tasks.

[0693] Furthermore, the server sets task reminders according to the user's settings and provides timely notifications for tasks that are approaching deadlines or have high priority. This allows users to efficiently manage the progress of their tasks.

[0694] Furthermore, a specially customized interface is provided for users with ADHD. This is designed to make it easier to check and manage tasks with visual and auditory support.

[0695] As an example, consider a scenario where a user hears deadlines and tasks for multiple projects at once during a meeting. Using this system, the information received can be immediately converted into tasks, allowing the user to focus on them and improve their concentration on other tasks.

[0696] The following describes the processing flow.

[0697] Step 1:

[0698] The device acquires audio data in real time through the microphone during meetings and work sessions. The acquired audio data is then sent directly to the server.

[0699] Step 2:

[0700] The server inputs the received audio data into a speech recognition engine and converts it into text data. This makes it easier to analyze the instructions and meeting content contained in the audio.

[0701] Step 3:

[0702] The device uses its camera to acquire image data of whiteboards, handwritten notes, and other objects. This image data is also sent to the server.

[0703] Step 4:

[0704] The server processes the received image data using OCR technology, converting the text information within the image into text. The contents of notes on a whiteboard or documents are then extracted.

[0705] Step 5:

[0706] The server integrates text data obtained from speech recognition and image recognition and performs text analysis. This analysis extracts task generation information, deadlines, and priorities.

[0707] Step 6:

[0708] The server generates tasks based on the extracted information and sets appropriate priorities for each task. The tasks are ordered considering importance and urgency.

[0709] Step 7:

[0710] The server schedules reminders for tasks according to user settings. Notifications are prepared based on deadlines and priorities.

[0711] Step 8:

[0712] Users receive task lists and reminder notifications sent from the server to check the progress of their work. They can review and adjust task details as needed.

[0713] (Example 1)

[0714] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0715] In recent years, as the demand for improved work efficiency has increased, users with Attention Deficit Hyperactivity Disorder (ADHD) in particular face challenges in appropriately prioritizing tasks and efficiently managing them. Conventional task management systems have limitations in processing audio and visual information, resulting in insufficient support for users with ADHD. Furthermore, the difficulty in real-time information gathering and analysis, which places a heavy burden on users, is also a challenge.

[0716] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0717] In this invention, the server includes an information conversion means for acquiring audio information and converting it into text; an information processing means for acquiring visual information, extracting textual information from the visual information and converting it into text; and an instruction generation means for analyzing the textual information obtained by the information conversion means and the information processing means and generating work instructions. This enables real-time information collection and analysis, and in particular makes it possible to provide efficient task management while assisting concentration for users with ADHD.

[0718] "Audio information" refers to information obtained by acquiring audio as digital data, and typically includes audio data such as conversations and instructions.

[0719] "Information conversion means" refers to a device or system that has the function of analyzing audio information and converting it into text format.

[0720] "Visual information" refers to digital data obtained through images and diagrams, and includes textual information and charts.

[0721] "Information processing means" refers to a device or system that has the function of analyzing visual information to extract textual information.

[0722] A "work instruction" is a specific task or instruction generated from analyzed information, and it is a work item with a set schedule and priority.

[0723] "Instruction generation means" refers to a device or system that has the function of analyzing text information obtained from audio and visual information and generating specific work instructions.

[0724] This system efficiently collects audio and visual information and automatically generates tasks based on it, thereby improving work efficiency, especially for users with behavioral disabilities. A specific implementation is described below.

[0725] The terminal uses a microphone to acquire audio information. Audio information obtained during meetings or work sessions is temporarily stored on-site and then transmitted in real time to a multi-function server. HTTPS and similar protocols are used for this transmission to maintain data confidentiality. The terminal also acquires visual information using a built-in or external camera and transmits it to the server. This visual information includes whiteboards and handwritten notes.

[0726] The server applies a speech recognition engine (e.g., an available general-purpose speech recognition API) to the transmitted audio information and converts the audio data into text. Similarly, for visual information, image recognition technology (e.g., a general-purpose image recognition API) is used to extract text information and convert it into text.

[0727] Through the analysis of text information, the server generates specific work instructions. These instructions are automatically prioritized based on their importance and urgency. A reminder function is also included, notifying the user of tasks with approaching deadlines.

[0728] The user interface is customized for ease of use, especially for users with behavioral disabilities, and allows for intuitive operation through both visual and auditory means.

[0729] As an example, suppose a user receives instructions in a meeting that "a report for a specific project is required by next Friday." This system collects and analyzes audio and visual information and automatically generates a "report creation" task instruction and its deadline. In this way, the user can focus on the task, without being burdened by prioritization, and can concentrate more on other tasks.

[0730] A concrete example of a prompt message for a generative AI model might be: "Automate the tasks for this week's meetings. Evaluate their importance and deadlines and output them as a list."

[0731] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0732] Step 1:

[0733] The terminal acquires voice information using a voice input device. What the user says during meetings or work is input as voice and temporarily stored within the terminal. The voice information is converted into digital data for real-time transmission to the server. The input is analog voice, and this is output as digitized voice data.

[0734] Step 2:

[0735] The server receives audio data from the terminal and converts it into text data using a speech recognition engine. The speech recognition engine extracts phonemes from the input audio data and uses them to construct words and sentences. The output is text data, including instructions and discussions during meetings or work sessions.

[0736] Step 3:

[0737] The device acquires visual information using a camera. Images of whiteboards, handwritten notes, etc., are captured via the camera and immediately sent to the server. The input is analog visual information, which is output as digital image data.

[0738] Step 4:

[0739] The server processes the received image data and extracts text information using image recognition technology. This process identifies characters and shapes from the image data and extracts them as text. The output is text data derived from visual information.

[0740] Step 5:

[0741] The server analyzes text data obtained from speech and visual input. Using natural language processing techniques, it generates specific work instructions based on the analysis. For example, it might generate an instruction such as, "Submit the report by next Friday." The input is text data, and the output is a task instruction.

[0742] Step 6:

[0743] The server applies an algorithm to the generated work orders to evaluate their importance and urgency. Based on the evaluation results, it sets the priority of the work orders. This process organizes the task list according to the task deadlines and content. The output is a prioritized task list.

[0744] Step 7:

[0745] The server sets reminders based on work instructions. It schedules notifications to be sent to users as task deadlines approach. For example, reminders are set for the day before the deadline and for high-priority tasks. The output is the notification schedule for users.

[0746] Step 8:

[0747] Users view the generated task list through a customized interface. Designed with users with behavioral disabilities in mind, it enables visually and audibly intuitive task management. This process provides support to help users easily track task progress and take timely action.

[0748] (Application Example 1)

[0749] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0750] In modern living environments, a large amount of information and tasks arise frequently, making it particularly difficult for individuals with Attention Deficit Hyperactivity Disorder (ADHD) to manage them efficiently. Furthermore, there is a need for systems that allow for efficient task organization, management, and reminder setting in both home and work environments.

[0751] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0752] In this invention, the server includes means for acquiring audio data in real time and converting the audio data into text, means for acquiring image data and extracting character information from the image data and converting it into text, and means for analyzing the text data obtained by the audio recognition means and the image recognition means and generating tasks. This enables users with ADHD to use autonomous devices in their home or work environment and efficiently manage tasks.

[0753] "Speech recognition means" refers to a device or method that acquires speech data in real time and converts that data into text.

[0754] "Image recognition means" refers to a device or method that acquires image data, extracts character information from it, and converts it into text.

[0755] "Task generation means" refers to a device or method that analyzes text data obtained by speech recognition means and image recognition means and generates a specific task based on that analysis.

[0756] A "prioritization means" is a device or method for evaluating the importance and urgency of generated tasks and prioritizing those tasks based on that evaluation.

[0757] A "reminder setting means" is a device or method for setting reminders to notify users based on the deadline or priority of a task.

[0758] An "autonomous device" is a device that collects information via voice recognition and image recognition means in a home or work environment and operates autonomously based on that information.

[0759] An "acoustic data collection device" is a device that is connected to a speech recognition system to collect audio data.

[0760] A "visual information acquisition device" is a device connected to an image recognition system that collects image data.

[0761] An "information terminal" is a device operated by a user to collect data from speech recognition and image recognition.

[0762] This system includes voice recognition means, image recognition means, task generation means, prioritization means, reminder setting means, autonomous devices, sound collection devices, visual information collection devices, and information terminals. The server works in conjunction with these means to automate task management.

[0763] The device is equipped with an acoustic data collection device (microphone) and a visual information collection device (camera) to collect voices emitted by the user during daily activities, as well as visual information such as notes and documents. The voice data is transmitted to the server in real time and converted into text by a speech recognition system. Simultaneously, image data acquired by the camera is extracted as text information through an image recognition system.

[0764] The server analyzes this text data and generates specific tasks using a task generation mechanism. The generated tasks are evaluated by a prioritization mechanism, and priorities are determined based on importance and urgency. Reminders are set for tasks using a reminder setting mechanism and notified to the user in a timely manner.

[0765] This system uses the Google Cloud Speech-to-Text API for speech recognition and the Google Cloud Vision API for image recognition. Task management is handled using task management tools and APIs such as Trello and Asana to manage schedules.

[0766] For example, if a user tells an autonomous device, "Please complete the presentation materials by this Friday," this voice is transcribed into text and registered as a task. Similarly, by taking a picture of project notes written on a whiteboard with a camera, the project tasks are automatically listed.

[0767] Examples of prompts for using generative AI models include the following:

[0768] "Automatically transcribe the meeting content and convert it into a task."

[0769] "Scan the contents of this memo and create a list. Then, think of solutions for each item."

[0770] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0771] Step 1:

[0772] The terminal uses an acoustic data acquisition device (microphone) to acquire the user's voice data in real time. This voice data is then sent to the server. The input is the user's voice data, and the output is the transmission of voice data to the server.

[0773] Step 2:

[0774] The server converts received audio data into text using the Google Cloud Speech-to-Text API. The input is audio data from the device, and the output is the converted text data. The server analyzes the audio data and converts the phonetic patterns into text.

[0775] Step 3:

[0776] The terminal acquires image data using a visual information collection device (camera) and transfers it to the server. The input is the image data obtained through the camera, and the output is the transmission of the image data to the server.

[0777] Step 4:

[0778] The server uses the Google Cloud Vision API to extract text information from image data and convert it to text. The input is image data from the device, and the output is text data containing the text information. It performs the operation of analyzing and identifying the text within the image.

[0779] Step 5:

[0780] The server analyzes text data obtained through speech recognition and image recognition, and generates specific tasks using a task generation mechanism. The input is the analyzed text data, and the output is the generated tasks. The server then performs an operation to group tasks based on the content of the text data.

[0781] Step 6:

[0782] The server evaluates the importance and urgency of tasks generated by the prioritization mechanism and determines their priority. The input is the generated tasks, and the output is the prioritized tasks. It performs an operation to evaluate task attributes and assign priorities.

[0783] Step 7:

[0784] The server uses a reminder setting mechanism to set reminders for users based on task deadlines and priorities. The input is a prioritized task, and the output is a reminder notification to the user. The server then determines the notification schedule, taking into account the time remaining until the deadline.

[0785] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0786] This system is an advanced task management system that incorporates emotion recognition, optimizing the user's psychological state and work efficiency. A specific implementation is described below.

[0787] First, the device acquires audio data in real time through the microphone and sends this audio data, collected during meetings and daily tasks, to the server. The server uses speech recognition technology to convert this audio data into text data, preparing it for analysis of conversations and instructions.

[0788] Next, the device uses its camera to acquire image data of a whiteboard, handwritten notes, etc., and sends it to the server. The server uses image recognition technology to analyze the image data and convert the text information within the image into text.

[0789] This text data is integrated and analyzed by the server. This analysis generates structured information as tasks, which are then prioritized based on their deadlines and importance.

[0790] Furthermore, this system is equipped with an emotion engine that analyzes user emotion data acquired from the terminal to evaluate the emotional state in real time. If the user is experiencing stress, the server can adjust the task load and re-evaluate task priorities based on that information.

[0791] The emotion engine optimizes the frequency of reminders and the content of notifications, taking into account the user's psychological state. This allows users to complete tasks more comfortably and efficiently.

[0792] As a concrete example, consider a situation where a user is working on a high-pressure project. In this system, an emotion engine detects the user's stress level and reduces the burden on the user by mitigating task notifications. This allows the user to effectively manage tasks while maintaining focus on other work.

[0793] This configuration allows the system to comprehensively support the user's psychological state and task management, thereby achieving increased efficiency and reduced burden.

[0794] The following describes the processing flow.

[0795] Step 1:

[0796] The device uses its microphone to acquire audio data during meetings and daily work. The acquired audio data is transmitted to the server in real time.

[0797] Step 2:

[0798] The server feeds the received audio data into a speech recognition engine, which converts the audio into text. This text data includes the spoken words and instructions.

[0799] Step 3:

[0800] The device acquires image data of the whiteboard or handwritten notes through its camera. The acquired image data is then sent to a server.

[0801] Step 4:

[0802] The server uses OCR technology to extract text information from the received image data and converts it into text. This makes the visual information from the meeting available as text.

[0803] Step 5:

[0804] The server analyzes the text data obtained from speech recognition and image recognition and extracts the necessary task information. Deadline and priority information are also analyzed here and generated as tasks.

[0805] Step 6:

[0806] The server prioritizes the generated tasks based on their importance and urgency.

[0807] Step 7:

[0808] The device periodically surveys the user's emotional state using the user's biometric information and behavioral data. This is to provide values ​​to the emotion engine.

[0809] Step 8:

[0810] The server receives user emotion data analyzed by the emotion engine and adjusts the task load based on that state. If the user is stressed, the amount and frequency of task notifications are reduced.

[0811] Step 9:

[0812] The server adjusts reminder and notification settings based on the sentiment analysis results, allowing users to manage tasks in a psychologically optimal state.

[0813] Step 10:

[0814] Users receive a pre-arranged list of tasks and reminder notifications sent from the server. Based on this, they efficiently manage their own tasks.

[0815] (Example 2)

[0816] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0817] Traditional task management systems have difficulty adjusting tasks in accordance with the user's psychological state and emotional changes, making efficient task management difficult when users are experiencing stress. Furthermore, there were no systems that could dynamically adjust task load based on emotions or optimize notification content.

[0818] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0819] In this invention, the server includes data recognition means for acquiring audio data in real time and converting the audio data into text, data recognition means for acquiring image data and extracting character information from the image data and converting it into text, and data analysis means for analyzing the text data obtained by the data recognition means and generating tasks. This enables task management and optimization of notification content that dynamically reflects the user's emotional state.

[0820] "Audio data" refers to audio signals acquired via an audio input device.

[0821] "Real-time" means that processing is performed instantly without delay.

[0822] A "data recognition means" is a mechanism that analyzes information from audio or images and converts it into text data.

[0823] "Image data" refers to visual information signals acquired through a visual input device.

[0824] "Textual information" refers to information that can be converted into text, extracted from images or audio.

[0825] A "data analysis tool" is a mechanism that processes acquired text data and organizes the information for a specific purpose.

[0826] A "task" is defined as a unit of work or activity that needs to be managed or performed.

[0827] Prioritization is the process of evaluating tasks based on their importance and urgency, and then determining their order.

[0828] "Adjustment means" refers to methods or mechanisms for optimizing task load and notifications according to the user's situation.

[0829] A "setting mechanism" is a mechanism that reflects the adjusted information and parameters in the system and controls its operation.

[0830] A "user" is someone who operates the system and enjoys its services and functions.

[0831] An "information processing device" is a device that includes an acoustic input device and a visual input device, and that aggregates and processes data.

[0832] This invention relates to a system that enables dynamic task management in accordance with the user's psychological state. This system has the capability to recognize voice and image data, supports diverse data inputs, and adjusts task priorities and optimizes notification content while considering the user's emotional state.

[0833] The terminal uses a microphone as an audio input device to acquire audio data in real time. The collected audio data is converted into a digital signal at the endpoint and sent to the server using a secure communication protocol. The server utilizes speech recognition technology and converts the audio into text data using speech recognition software such as the Google Speech-to-Text API.

[0834] The device also uses a camera as a visual input device to acquire image data of whiteboards and handwritten notes. This image data is analyzed on a server using OCR technology, specifically Tesseract OCR, and converted into text data.

[0835] The text data acquired through these recognition processes is integrated on a server and analyzed using natural language processing techniques. By using generative AI models such as Adobe Sensei, the integrated text data is structured into tasks, and priorities are automatically set based on the required deadlines and priorities.

[0836] Furthermore, the device acquires user emotional data in real time and collects it through sensor devices. This includes voice tone analysis and facial recognition technology. The collected emotional data is analyzed on a server, and the user's psychological state, such as their stress level, is evaluated and reflected in real time.

[0837] For example, if a user is experiencing high pressure on a project, this system can detect their emotional state and flexibly adjust task notifications. This creates an environment where the user can concentrate on other tasks.

[0838] An example of a prompt message that might be input to the generative AI model is: "Please use emotion recognition technology to suggest a task management method tailored to the user's stress level."

[0839] This system comprehensively supports users' psychological state and work efficiency, reducing the burden of work while simultaneously enabling efficient task management.

[0840] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0841] Step 1:

[0842] The terminal acquires the user's voice data in real time using an acoustic input device. The input here is the user's spoken voice, and the output is a digital acoustic signal. The terminal encodes this acoustic signal and sends it to the server using a secure protocol.

[0843] Step 2:

[0844] The server analyzes the received acoustic signal using speech recognition technology and converts it into text data. Specifically, it uses speech recognition software to process the acoustic signal as input and generate text data as output. The server stores this text data in a database for analysis.

[0845] Step 3:

[0846] The terminal uses a visual input device to acquire image data from sources such as whiteboards and handwritten notes. In this step, the input is image data, and the output is the electronic format of that data. The terminal optimizes and encodes the image before sending it to the server.

[0847] Step 4:

[0848] The server processes the received image data using OCR technology, extracting text information from the image and converting it into text data. The input is image data, and the output is data in which the text from the image has been formatted. The server then integrates this text for analysis.

[0849] Step 5:

[0850] The server analyzes text data obtained from integrated audio and image data using natural language processing techniques. The input for this step is a collection of text data, and the output is a structured task list. A generative AI model is used to set task priorities and associated deadlines.

[0851] Step 6:

[0852] The device uses sensor devices to collect user emotional data in real time. Inputs include the user's voice tone and facial expressions, while output is quantified emotional data. The device quickly transmits this emotional data to a server.

[0853] Step 7:

[0854] The server analyzes emotional data and adjusts task priorities and notification content accordingly. The input is quantified emotional data, and the output is an adjusted task list and notification schedule. The server delivers this in a format optimized for the user's psychological state.

[0855] These steps create a system that enables flexible task management that takes into account the user's psychological state, thereby supporting efficient work execution.

[0856] (Application Example 2)

[0857] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0858] In modern society, users face numerous tasks, leading to increased psychological burden. Furthermore, task management systems often fail to consider the user's emotional state, potentially imposing excessive pressure. In such situations, users cannot achieve their full potential and receive insufficient emotional support. Therefore, there is a need for systems that consider the user's emotional state, alleviate stress, and manage tasks effectively.

[0859] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0860] In this invention, the server includes speech recognition means for acquiring audio data in real time and converting the audio data into text, image recognition means for acquiring image data, extracting character information from the image data and converting it into text, and emotion evaluation means for evaluating the emotional state and re-evaluating task priorities based on that evaluation. This makes it possible to prioritize tasks and adjust notifications while taking into account the emotional state of the user.

[0861] "Audio data" refers to sound information, such as human voices, acquired through a microphone.

[0862] "Converting to text" means analyzing audio or image data and representing it as textual information.

[0863] "Speech recognition means" refers to a technology that analyzes speech data and generates text data as character information.

[0864] "Image data" refers to digital data containing visual information acquired using a camera or similar device.

[0865] "Image recognition means" refers to a technology that extracts and analyzes information such as characters and shapes from image data.

[0866] A "task generation method" is a method for creating a task list that specifies the actions and processes to be performed, based on text data obtained from speech recognition and image recognition methods.

[0867] A "prioritization tool" is a system for efficiently managing generated tasks by prioritizing them based on their importance and urgency.

[0868] An "emotional evaluation tool" is a technological platform that analyzes the emotional state of users and utilizes that information for task management, notifications, and other purposes.

[0869] The "reminder setting method" is a function that schedules task-related notifications based on deadlines and priorities, and adjusts them as needed.

[0870] Modes for carrying out the invention

[0871] In an embodiment of this invention, the system is composed of multiple hardware and software components. A server plays a central role, performing processing related to speech recognition, image recognition, and sentiment evaluation.

[0872] The device is equipped with a microphone to acquire audio data in real time. The Google Cloud Speech-to-Text API is used for speech recognition, converting the audio data into text. The converted text data is then sent to a server for analysis.

[0873] The device is also equipped with a camera to collect image data. This image data is analyzed using the Google Cloud Vision API, and text information is extracted from the images. This information is also sent to the server as text data and used to generate subsequent tasks.

[0874] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of text data obtained from audio and images. Based on this information, it re-evaluates task priorities and adjusts the content and frequency of reminder notifications as needed.

[0875] When a user is working on a long-term project, for example, the system monitors their psychological state and, if their stress level is high, suggests playing relaxing music or taking a break. This helps support the user's motivation to work and efficient task completion.

[0876] A concrete example would be a situation where a user enters a prompt such as, "Analyze today's work and emotions, and provide suggestions for stress reduction." This prompt allows the user to receive specific stress management suggestions based on an emotional assessment through the system.

[0877] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0878] Step 1:

[0879] The device uses a microphone to acquire the user's voice data in real time. This acquired voice data is used as input for speech recognition processing. Speech recognition technology converts this voice data into text data. The resulting text data is sent to a server and used for subsequent processing.

[0880] Step 2:

[0881] The device uses its camera to acquire image data of the user's surroundings. Image recognition technology is used to extract text information from this image data. Image recognition software converts the characters in the image into text data. The converted text data is sent to the server, similar to audio data.

[0882] Step 3:

[0883] The server integrates the text data obtained in steps 1 and 2. This text data is parsed by a task generation algorithm to generate specific tasks. This task data is used for prioritization according to importance and urgency.

[0884] Step 4:

[0885] The server uses sentiment analysis libraries such as DeepMoji to evaluate the emotional state of the acquired text data. The input text is analyzed for sentiment evaluation, and the resulting sentiment data is used as an indicator for task management.

[0886] Step 5:

[0887] Based on the sentiment assessment results, the server re-evaluates task priorities. Task reminder settings are adjusted to match the user's current emotional state, and notification content and frequency are changed if necessary. This minimizes the user's psychological burden.

[0888] Step 6:

[0889] The user inputs a prompt message through a generative AI model, such as, "Analyze today's work and emotions, and provide suggestions for stress relief." Based on this prompt, the system creates specific stress management suggestions tailored to the user's emotional state and provides them to the user.

[0890] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0891] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0892] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0893] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0894] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0895] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0896] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0897] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0898] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0899] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0900] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0901] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0902] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0903] 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.

[0904] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0905] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0906] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0907] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0908] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0909] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0910] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0911] The following is further disclosed regarding the embodiments described above.

[0912] (Claim 1)

[0913] A speech recognition means that acquires audio data in real time and converts the audio data into text,

[0914] Image recognition means that acquires image data, extracts character information from the image data and converts it into text,

[0915] A task generation means that analyzes the text data obtained from the speech recognition means and the image recognition means and generates a task,

[0916] A prioritization means for evaluating the importance and urgency of the generated tasks and prioritizing the tasks,

[0917] A reminder setting means for setting reminders based on deadlines and priorities for the aforementioned tasks,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, further comprising a module that provides a customized interface for users with ADHD and assists concentration.

[0921] (Claim 3)

[0922] The system according to claim 1, further comprising a terminal operated by a user, having a microphone connected to the voice recognition means and a camera connected to the image recognition means.

[0923] "Example 1"

[0924] (Claim 1)

[0925] An information conversion means that acquires audio information and converts the audio information into text,

[0926] An information processing means that acquires visual information, extracts textual information from the visual information, and converts it into text,

[0927] An instruction generation means that analyzes the text information obtained by the information conversion means and the information processing means and generates work instructions,

[0928] A prioritization means for evaluating the importance and urgency of the generated work instructions and prioritizing the said work instructions,

[0929] A notification management means for setting notifications based on deadlines and priorities for the aforementioned work instructions,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, further comprising a user interface customized for users with behavioral disorders and a function to assist concentration.

[0933] (Claim 3)

[0934] The system according to claim 1, further comprising a device operated by a user, which has an audio input device connected to the information conversion means and an image input device connected to the information processing means.

[0935] "Application Example 1"

[0936] (Claim 1)

[0937] A speech recognition means that acquires audio data in real time and converts the audio data into text,

[0938] Image recognition means that acquires image data, extracts character information from the image data and converts it into text,

[0939] A task generation means that analyzes the text data obtained from the speech recognition means and the image recognition means and generates a task,

[0940] A prioritization means for evaluating the importance and urgency of the generated tasks and prioritizing the tasks,

[0941] A reminder setting means for setting reminders based on deadlines and priorities for the aforementioned tasks,

[0942] A system further comprising an autonomous device that operates in a home or business environment and collects information via the voice recognition means and the image recognition means.

[0943] (Claim 2)

[0944] The system according to claim 1, further comprising a module that provides a customized interface for users with ADHD and assists concentration.

[0945] (Claim 3)

[0946] The system according to claim 1, further comprising an information terminal operated by a user, having an acoustic collection device connected to the speech recognition means and a visual information collection device connected to the image recognition means.

[0947] "Example 2 of combining an emotion engine"

[0948] (Claim 1)

[0949] A data recognition means that acquires audio data in real time and converts the audio data into text,

[0950] A data recognition means that acquires image data, extracts character information from the image data and converts it into text,

[0951] A data analysis means that analyzes the text data obtained by the data recognition means and generates a task,

[0952] An evaluation means for evaluating the importance and urgency of the generated tasks and prioritizing the tasks,

[0953] An adjustment means that analyzes emotional data acquired from the terminal and adjusts the workload of the task based on the user's psychological state,

[0954] A setting means for optimizing the reminder based on the results of the adjustment means,

[0955] A system that includes this.

[0956] (Claim 2)

[0957] The system according to claim 1, comprising a program that dynamically adjusts notification content according to the user's emotional state.

[0958] (Claim 3)

[0959] The system according to claim 1, further comprising an information processing device operated by a user, having an acoustic input device and a visual input device connected to the data recognition means.

[0960] "Application example 2 when combining with an emotional engine"

[0961] (Claim 1)

[0962] A speech recognition means that acquires audio data in real time and converts the audio data into text,

[0963] Image recognition means that acquires image data, extracts character information from the image data and converts it into text,

[0964] A task generation means that analyzes the text data obtained from the speech recognition means and the image recognition means and generates a task,

[0965] A prioritization means for evaluating the importance and urgency of the generated tasks and prioritizing the tasks,

[0966] An emotional assessment tool that evaluates emotional states and re-evaluates task priorities based on that evaluation,

[0967] A reminder setting means for the aforementioned task, which sets reminders based on deadlines and priorities and adjusts notifications based on emotional state,

[0968] A system that includes this.

[0969] (Claim 2)

[0970] The system according to claim 1, further comprising a module that evaluates emotional states in the living environment and makes suggestions to promote relaxation.

[0971] (Claim 3)

[0972] The system according to claim 1, further comprising a terminal that is operated by an object, having a microphone connected to the voice recognition means and a camera connected to the image recognition means. [Explanation of Symbols]

[0973] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A speech recognition means that acquires audio data in real time and converts the audio data into text, Image recognition means that acquires image data, extracts character information from the image data and converts it into text, A task generation means that analyzes the text data obtained from the speech recognition means and the image recognition means and generates a task, A prioritization means for evaluating the importance and urgency of the generated tasks and prioritizing the tasks, A reminder setting means for setting reminders based on deadlines and priorities for the aforementioned tasks, A system further comprising an autonomous device that operates in a home or business environment and collects information via the voice recognition means and the image recognition means.

2. The system according to claim 1, further comprising a module that provides a customized interface for the user and assists concentration.

3. The system according to claim 1, further comprising an information terminal operated by a user, having an acoustic collection device connected to the speech recognition means and a visual information collection device connected to the image recognition means.

Images