System

Abstract

A system is provided.SOLUTION: A system includes means for collecting voice data of a meeting or a telephone call, converting the voice data into text data, means for analyzing the text data to generate a task, classifying whether the generated task is to be performed by a "person" or by an "artificial intelligence", means for allocating the classified task to an appropriate person in charge, means for registering the allocated task in a project management tool and a personal task management tool, means for managing progress of the task, issuing a notice before deadline, and re-allocating the task as necessary.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In the progress of a project, task management is often not properly carried out, which leads to a problem of overall performance degradation. This problem is particularly noticeable when decisions and tasks made in meetings or calls are not fully understood and not assigned to the appropriate person. Another problem is that due to insufficient management of task progress, necessary reminders and task reassignment before deadlines cannot be carried out. A system that can solve this situation and improve the efficiency and performance of the entire project is needed. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system that includes a means for collecting voice data from meetings and phone calls and converting the voice data into text data, a means for analyzing the text data to generate tasks and classifying the tasks as to whether they will be performed by a "person" or "artificial intelligence," a means for assigning the classified tasks to an appropriate person, a means for registering the assigned tasks in a project management tool and a personal task management tool, and a means for managing the progress of tasks, sending advance notifications, and reassigning tasks as necessary.

[0006] This system uses natural language processing algorithms to analyze text data and generate tasks, efficiently capturing decisions made in meetings and calls, appropriately classifying tasks, and assigning them to responsible parties. It also automatically registers tasks in project management tools and personal task management tools, preventing responsible parties from overlooking them. Furthermore, by managing task progress, notifying people before deadlines and reassigning tasks as necessary, the system supports the efficient progress of projects and improves overall performance.

[0007] "Conference and call audio data" refers to audio information collected from voice communication events such as conferences and telephone calls.

[0008] "Text data" is character information converted from voice data by voice recognition.

[0009] A "task" is a specific work item or activity associated with a project.

[0010] A "human-performed vs. AI-performed classification means" is a method or algorithm for determining whether a generated task should be performed by a human or an AI.

[0011] The "means for assigning to a person in charge" is a method or system for allocating the classified tasks to an appropriate person in charge.

[0012] A "project management tool" is software or a platform that assists in the planning, execution, monitoring, control, and closure of projects.

[0013] A "personal task management tool" is software or a platform that allows individual users to organize, prioritize, and manage their tasks.

[0014] A "task progress management tool" is a method or system for tracking how much of an assigned task has been completed and for facilitating any necessary action.

[0015] "Deadline Notification" is a reminder function that notifies the person in charge that a task deadline is approaching.

[0016] "Task reassignment" is the process of reassigning an already assigned task to a new person in charge. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] System Overview

[0039] This system aims to improve the efficiency of task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[0040] 1. Collecting voice data and converting it to text

[0041] 2. Task Generation and Classification

[0042] 3. Task assignment

[0043] 4. Task progress management and deadline notifications

[0044] Program processing

[0045] Audio data collection and text conversion

[0046] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server then converts the received audio data into text data using a speech recognition API. This text data is later saved as minutes and serves as the basis for analysis.

[0047] Task Generation and Classification

[0048] The server uses natural language processing algorithms to analyze the text data generated from the voice data. This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0049] Task assignment

[0050] The server assigns the classified tasks to the appropriate person in charge. Tasks assigned to users are notified to the users' devices via email or push notifications to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[0051] Task progress management and deadline advance notifications

[0052] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[0053] Specific examples

[0054] Meeting Scenarios

[0055] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[0056] User A: We need to decide on a release plan for a new product.

[0057] User B: Let's complete the market research by next week.

[0058] User A: You should also start preparing your marketing materials.

[0059] The server extracts and classifies the following tasks from this text data:

[0060] User A: Determine release plan

[0061] User B: Market research completed

[0062] Artificial Intelligence: Data collection for marketing materials

[0063] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[0064] This approach streamlines project management, ensures that no tasks are overlooked, and allows users to keep track of task progress, improving overall project performance.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] A user starts a meeting or call. The device records the audio in real time and sends the audio data to the server, where it is converted into a digital format.

[0068] Step 2:

[0069] The server receives the voice data. The server then calls a speech recognition API to convert the received voice data into text data. This process uses natural language processing technology.

[0070] Step 3:

[0071] The server analyzes the generated text data and creates minutes, which are stored in a database and serve as the basis for subsequent task generation processes.

[0072] Step 4:

[0073] The server analyzes the text data of the minutes using natural language processing algorithms, and extracts tasks from important discussions and decisions.

[0074] Step 5:

[0075] The server classifies the extracted tasks into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0076] Step 6:

[0077] The server assigns categorized tasks to appropriate personnel, and this assignment information is recorded in a database.

[0078] Step 7:

[0079] The device will send task notifications to the assignee via email and push notifications, ensuring that the assignee never misses a task.

[0080] Step 8:

[0081] The server automatically registers tasks in project management tools and personal task management tools using API calls.

[0082] Step 9:

[0083] The server periodically monitors the progress of tasks and sends reminders to the person in charge if progress is behind or the deadline is approaching.

[0084] Step 10:

[0085] The server will reassign tasks as needed. This happens if a task is delayed or needs to be reassigned.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] Task management in project management requires efficient progress and appropriate resource allocation, but there are challenges such as information leakage due to numerous meetings and calls, and difficulty in properly allocating tasks. Automation is also required to properly manage progress and send reminders, but traditional manual management takes time and effort and is prone to errors. A system is needed to solve these problems.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes: means for collecting voice data from meetings and calls and converting the voice data into text data; means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, providing advance notices, and reassigning tasks as necessary; a terminal for transmitting voice data to the server in real time; a server for converting voice data into text data using a voice recognition API; a natural language processing algorithm for analyzing the text data and extracting tasks; and means for monitoring the progress of tasks and sending reminder notifications. This improves the efficiency and accuracy of task management and enables appropriate progress management.

[0091] "Conference or call audio data" refers to data that includes all audio information generated during a conference or call.

[0092] "Text data" refers to data obtained by converting voice data into character information.

[0093] A "task" is a task or action item that needs to be done to achieve a specific purpose or goal.

[0094] "People" refers to actual people who use the system to perform tasks.

[0095] "Artificial intelligence" refers to computer programs and algorithms that partially or fully automate human tasks.

[0096] "Classifying" refers to the act of separating objects or information into groups based on specific criteria.

[0097] A "person in charge" is someone who is responsible for carrying out a particular task or work.

[0098] A "project management tool" is software that helps you plan projects, track progress, and communicate with team members.

[0099] A "personal task management tool" is software for managing personal tasks and schedules.

[0100] "Progress" refers to how far a task or project has progressed.

[0101] "Early Deadline Notifications" are reminders sent when a task deadline approaches.

[0102] "Reassignment" refers to the act of reassigning a task that has already been assigned to another person or resource.

[0103] "Terminal" refers to a device (e.g., PC, tablet, smartphone) that a user uses to access the system.

[0104] "Speech recognition API" refers to a program interface for analyzing voice input and converting it into text data.

[0105] "Natural language processing algorithms" refer to algorithms for understanding, analyzing, and generating human language.

[0106] A "reminding notification" is a notification that alerts the user to the progress of a task or a deadline.

[0107] System Overview

[0108] This system aims to streamline task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[0109] 1. Collecting voice data and converting it to text

[0110] 2. Task Generation and Classification

[0111] 3. Task assignment

[0112] 4. Task progress management and deadline notifications

[0113] Audio data collection and text conversion

[0114] When a user starts a meeting or call, the device records the audio and sends the audio data to a server in real time. The server then converts the received audio data into text data using a speech recognition API such as Google® Cloud Speech-to-Text API. This text data is later saved as meeting minutes and serves as the basis for analysis.

[0115] Task Generation and Classification

[0116] The server analyzes the text data generated from the voice data using natural language processing algorithms (e.g., spaCy or NLTK). This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0117] Task assignment

[0118] The server assigns the classified tasks to the appropriate person in charge. The assigned tasks are notified to the user's device via email or push notification to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools (e.g., Trello or Asana) or personal task management tools (e.g., Todoist).

[0119] Task progress management and deadline advance notifications

[0120] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[0121] Adding specific examples

[0122] Meeting Scenarios

[0123] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[0124] User A: We need to decide on a release plan for a new product.

[0125] User B: Let's complete the market research by next week.

[0126] User A: You should also start preparing your marketing materials.

[0127] The server extracts and classifies the following tasks from this text data:

[0128] User A: Determine release plan

[0129] User B: Market research completed

[0130] Artificial Intelligence: Data collection for marketing materials

[0131] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[0132] Example prompts for the generative AI model to use

[0133] Below are some example prompts to input to a generative AI model (e.g., GPT-4®):

[0134] Analyze the text data generated from the following meeting recording, extract tasks from important discussions and decisions, and assign them to the appropriate people.

[0135] User A: We need to decide on a release plan for a new product.

[0136] User B: Let's complete the market research by next week.

[0137] User A: You should also start preparing your marketing materials.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1: Collecting and transmitting audio data in real time

[0140] When a user starts a meeting or call, the device records the audio. The recording is done in real time and the audio data is sent to a server via the Internet. Specifically, a dedicated app on the device captures the user's voice with a microphone and instantly streams it to the server. The input here is the user's voice, and the output is the raw audio data sent to the server.

[0141] Step 2: Convert audio data to text

[0142] The server converts the received voice data into text data using a voice recognition API (for example, Google Cloud Speech-to-Text API). At this time, the voice recognition API analyzes the voice and performs the optimal text conversion using the language model of the voice data. Specifically, the server sends the voice data to the API and receives it as text data. The input is the received voice data, and the output is the converted text data.

[0143] Step 3: Analyzing text data and extracting tasks

[0144] The server analyzes the converted text data using natural language processing algorithms (e.g., spaCy or NLTK). In this process, important discussions and decisions in the text are identified and extracted as tasks. Specifically, the server begins text analysis and generates tasks based on specific keywords and phrases. The input is the text data, and the output is a list of tasks to be assigned to users or artificial intelligence.

[0145] Step 4: Categorize your tasks

[0146] The extracted tasks are classified by the server into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the task content and keywords. Specifically, the server analyzes the task content and applies an appropriate classification algorithm. The input is a list of extracted tasks, and the output is a classified task list.

[0147] Step 5: Assign tasks

[0148] The server assigns the classified tasks to the appropriate person in charge. The results of the task assignment are notified to the user's device. Specifically, the server calls the API of the task management tool to register the task and sends an email or push notification to the person in charge. The input is the classified task list, and the output is a task assignment notification.

[0149] Step 6: Track your progress and receive reminders

[0150] The server synchronizes data with the project management tool and monitors the progress of tasks. If progress is behind schedule or the deadline is approaching, it sends reminder notifications to the user. Specifically, the server periodically obtains progress data and sends reminder notifications if there is a problem. The input is task progress data, and the output is reminder notifications to the user.

[0151] Each of the above steps will ensure that the overall system functions effectively, improving the efficiency and accuracy of project management.

[0152] (Application example 1)

[0153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0154] In modern factories, maintenance and quality control tasks are becoming increasingly complex, requiring efficient management. In particular, accurate instruction transmission and task assignment are essential for workers to respond quickly on-site. However, manual task assignment and management takes time, potentially resulting in reduced work efficiency and task delays. Furthermore, even when using robots, the lack of a system that can accurately interpret voice instructions and appropriately assign tasks remains an issue.

[0155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0156] In this invention, the server includes: means for collecting voice data from conferences and calls and converting the voice data into text data; means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, notifying users before their deadlines, and reassigning tasks as necessary; and means for providing voice instructions from a worker to a robot in factory maintenance work and quality control, analyzing the instructions, generating tasks, and automatically assigning them to the robot and the worker. This enables efficient task assignment and progress management in factory maintenance work and quality control operations.

[0157] "Voice data" refers to raw voice information collected during meetings, phone calls, etc.

[0158] "Text data" is voice data converted into character information.

[0159] "Analysis" refers to the process of analyzing text data to derive meaning.

[0160] A "task" is a specific item that directs a particular activity or work.

[0161] Tasks performed by "people" are tasks that need to be performed by humans, such as workers or managers.

[0162] Tasks performed by "artificial intelligence" are tasks that can be performed by robots or AI systems.

[0163] "Classification" is the process of determining whether a task extracted from text data will be performed by a "person" or by "artificial intelligence."

[0164] "Responsible Person" refers to a person or system that is responsible for performing a specific task.

[0165] A "project management tool" is software or a system that allows you to centrally manage project progress and tasks.

[0166] A "personal task management tool" is software or a system that allows individual users to manage their own tasks.

[0167] "Progress management" is the process of monitoring whether tasks are progressing as planned and taking necessary actions.

[0168] "Pre-deadline notification" is a notification to inform the person in charge that the deadline for a task is approaching.

[0169] "Reassignment" is the process of changing the person responsible for or the deadline for an originally assigned task.

[0170] "Factory maintenance work" refers to a series of tasks performed to maintain factory facilities and equipment.

[0171] "Quality control" refers to the monitoring and control processes used to ensure the quality of products and services.

[0172] "Voice instructions" refers to verbal instructions given by the worker to the robot.

[0173] "Real-time" means processing immediately without delay.

[0174] System Overview

[0175] The system of the present invention is designed to improve the efficiency of maintenance work and quality control in factories. The main functions of the system are to collect voice data and convert it into text, generate and classify tasks, assign tasks, register tasks in project management tools and personal task management tools, manage task progress, and notify users before deadlines. Specific methods for realizing these functions are described below.

[0176] Program processing

[0177] 1. Collecting voice data and converting it to text

[0178] When performing maintenance or quality control tasks in a factory, workers give voice instructions to the robot. These voice instructions are collected through a microphone installed on the robot. The voice data is sent in real time to a server, which then converts the voice data into text data using the Google Cloud Speech-to-Text API. This text data is then used as the basis for subsequent analysis and task generation.

[0179] 2. Task Generation and Classification

[0180] The server analyzes the text data generated from the voice data using the Google Cloud Natural Language API. Through this process, tasks are automatically extracted from important instructions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0181] 3. Task assignment

[0182] The server automatically assigns the classified tasks to the appropriate person (worker or robot). Tasks assigned to users are notified to the users' devices via email or push notification. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[0183] 4. Task progress management and deadline notifications

[0184] The server periodically monitors the progress of the task. If progress is slow or the deadline is approaching, the server sends a reminder to the user, allowing the user to take appropriate action to complete the task on time. If necessary, the server also reassigns the task's assignee and deadline.

[0185] Specific examples

[0186] Maintenance Scenarios

[0187] Consider a situation where Worker A is performing maintenance work in a factory and needs to give instructions to a robot:

[0188] Worker A: The following line needs to be cleaned.

[0189] Worker B: Let's check all the parts and make sure there are no abnormalities.

[0190] The robot collects this voice data and sends it to the server, which then uses a speech recognition API to generate text data like this:

[0191] Worker A: The following line needs to be cleaned.

[0192] Worker B: Let's check all the parts and make sure there are no abnormalities.

[0193] The server extracts and classifies the following tasks from this text data:

[0194] Worker tasks:

[0195] Worker A: Cleaning the line

[0196] Worker B: Inspection and confirmation of parts

[0197] Robot Task:

[0198] Robot: Collects monitoring data of cleaning operations and sends it to the quality control department

[0199] These tasks are automatically assigned to each worker and robot by the server and registered in project management tools and personal task management tools.

[0200] Prompt Sentence Examples

[0201] Voice recognition result:

[0202] Worker A: The following line needs to be cleaned.

[0203] Worker B: Let's check all the parts and make sure there are no abnormalities.

[0204] Task creation:

[0205] Assign the task of "line cleaning work" to worker A.

[0206] Assign the task of "Inspect and check parts" to worker B.

[0207] The robot is assigned the task of "collecting monitoring data of the cleaning work and sending it to the quality control department."

[0208] This will automate and streamline maintenance and quality control work within factories, enabling workers and robots to work together to smoothly carry out tasks.

[0209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0210] Step 1:

[0211] When a user performs maintenance or quality control work in a factory, the worker gives voice instructions to the robot. A microphone installed on the robot's terminal collects these voice instructions. The input is the worker's voice data, and the output is the voice data collected by the robot's terminal.

[0212] Step 2:

[0213] The device sends the collected voice data to the server in real time, and the server converts the voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is text data.

[0214] Step 3:

[0215] The server analyzes the converted text data using the Google Cloud Natural Language API. This analysis extracts important instructions and decisions from the text. The input is the text data, and the output is the extracted instructions and decisions.

[0216] Step 4:

[0217] The server generates tasks from the analysis results and classifies them into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." The input is the extracted instructions and decisions, and the output is the classified tasks.

[0218] Step 5:

[0219] The server automatically assigns the classified tasks to the appropriate personnel (workers or robots). The input is the classified tasks, and the output is the tasks assigned to each personnel.

[0220] Step 6:

[0221] The server registers the assigned tasks in the project management tool and the personal task management tool. The input is the tasks assigned to the person in charge, and the output is the tasks registered in the management tool.

[0222] Step 7:

[0223] The server periodically monitors the progress of tasks and sends reminder notifications when progress is behind or the deadline is approaching. The input is the progress of tasks registered in the management tool, and the output is reminder notifications.

[0224] Step 8:

[0225] If necessary, the server reassigns task owners and deadlines. The input is tasks that are behind schedule or approaching deadlines, and the output is the reassigned tasks.

[0226] Through the above processing steps, the system is able to efficiently manage and carry out maintenance and quality control work within the factory.

[0227] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0228] System Overview

[0229] This invention aims to improve the efficiency of task management in project management, and by combining it with an emotion engine, it is possible to understand the user's emotions and adjust task priorities and notification timing. The system includes the following main components:

[0230] 1. Collecting voice data and converting it to text

[0231] 2. Task Generation and Classification

[0232] 3. Task assignment

[0233] 4. Task progress management and deadline notifications

[0234] 5. Emotion Recognition Engine and Emotion-Based Adjustments

[0235] Program processing

[0236] Audio data collection and text conversion

[0237] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server converts the audio data into text data using a speech recognition API and generates minutes. The text data is then used for task generation and emotion recognition.

[0238] Task Generation and Classification

[0239] The server analyzes the generated text data using natural language processing algorithms and extracts tasks from key points of discussion and decisions. The extracted tasks are then classified into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on content and keywords.

[0240] Task assignment

[0241] The server assigns the classified tasks to the appropriate person. The assigned tasks are notified to the user via their device. Notification methods include email and push notifications. Tasks are also automatically registered in project management tools and personal task management tools.

[0242] Task progress management and deadline advance notifications

[0243] The server periodically monitors the progress of tasks, and if progress is delayed or the deadline is approaching, it sends reminder notifications to the user, and if necessary, reassigns task owners and deadlines.

[0244] Emotion recognition engine and emotion-based adjustments

[0245] The server is equipped with an emotion engine that recognizes the user's emotions from voice data. The emotion engine identifies the user's emotions by analyzing the tone of the voice and the choice of words. This emotion data is used to adjust task priorities and notification timing.

[0246] For example, if a user is feeling anxious or stressed, the system can lower the priority of the task for that user. Furthermore, based on emotion recognition, the system can send reminders during times when the user is relaxed, promoting efficient task execution.

[0247] Specific examples

[0248] Meeting Scenarios

[0249] User A and User B hold an online conference and record the audio data. The device sends the audio data to the server, which then generates the following text data through a speech recognition API:

[0250] User A: We need to decide on a release plan for our new product.

[0251] User B: Let's complete the market research by next week.

[0252] User A: You should also start preparing your marketing materials.

[0253] The server extracts and classifies the following tasks from the generated text data:

[0254] User A: Determine release plan

[0255] User B: Completes market research

[0256] Artificial Intelligence: Data Collection for Marketing Materials

[0257] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reallocate the task of creating marketing materials to an artificial intelligence.

[0258] The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and timely reminders are sent when deadlines approach. This process streamlines project management and ensures that tasks are completed without omission.

[0259] This invention allows users to keep track of task progress and improve overall project performance in an emotionally sensitive manner.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] A user initiates a meeting or call. The device records the conversation in real time and sends the audio data to a server, where it is converted into a digital format and processed.

[0263] Step 2:

[0264] The server converts the received voice data into text data using a voice recognition API. Through this process, text information is automatically generated from the voice.

[0265] Step 3:

[0266] The server analyzes the text data and generates meeting minutes, which are stored in a database and serve as the basis for future task generation and emotion recognition.

[0267] Step 4:

[0268] The server analyzes the stored text data using natural language processing algorithms to extract tasks from key points and decisions during discussions. This analysis includes keyword extraction and contextual analysis.

[0269] Step 5:

[0270] The server classifies the extracted tasks into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on the task content and keywords, and the appropriate person in charge is selected.

[0271] Step 6:

[0272] The emotion engine analyzes the voice data to recognize the user's emotions. The emotion engine analyzes the voice tone and word choice to identify the type of emotion (e.g., stress, anxiety, joy).

[0273] Step 7:

[0274] The server adjusts the priority and placement of tasks based on information from the emotion engine. For example, if the user's emotions indicate stress, it temporarily lowers the priority of urgent tasks.

[0275] Step 8:

[0276] The server assigns the task to the appropriate person, who is then notified of the assigned task via email or push notification.

[0277] Step 9:

[0278] The server automatically registers tasks in project management tools and personal task management tools, allowing the person in charge to check the task content and deadlines.

[0279] Step 10:

[0280] The server periodically monitors the progress of the task and sends reminders when progress is behind or the deadline is approaching. The timing of the reminders is adjusted based on the user's emotional state.

[0281] Step 11:

[0282] The server reassigns tasks as needed. If a task is delayed or needs to be reassigned, a reassignment process is initiated. This process also takes into account the user's emotional state.

[0283] Through this process, the system can understand the user's emotions, improve task management efficiency, and improve overall project performance.

[0284] Example 2

[0285] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0286] Conventional project management systems lack the ability to efficiently manage tasks generated during meetings or phone calls, track progress, and adjust tasks based on user emotions. This can lead to missed tasks and delays in progress, resulting in a decline in overall project performance. There is also the risk that users may feel excessive stress, further reducing productivity. The present invention aims to solve these problems.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0288] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to an appropriate person, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, notifying the user before their deadline, and reassigning tasks as necessary, and means for recognizing the user's emotions from the voice data and adjusting task priorities and notification timings based on the emotion data. This enables efficient management of tasks generated during conferences and calls, understanding the progress, and adjusting tasks based on the user's emotions.

[0289] "Voice data" refers to voice information collected during a conference or call, and is data that is converted into text data.

[0290] "Text data" refers to data that has been converted from voice data into text information using voice recognition technology.

[0291] A "task" refers to a work item or instruction generated during a meeting or call, and is a unit of action to be carried out.

[0292] A "natural language processing algorithm" is a language analysis technology that analyzes text data and generates and classifies tasks.

[0293] A "personnel" is a person or artificial intelligence assigned to carry out the generated task.

[0294] "Project management tool" refers to software or a system for tracking project progress and scheduling tasks.

[0295] "Personal task management tool" refers to software or a system that allows individuals to record, manage, and prioritize their tasks.

[0296] "Progress management" is the process of monitoring the status of task implementation and understanding the degree of progress.

[0297] "Pre-deadline notification" is a notification to remind the person in charge when the deadline for a task is approaching.

[0298] "Emotion recognition" is a technology that analyzes and identifies a user's emotions from voice data.

[0299] "Emotion data" refers to information about a user's emotional state extracted using emotion recognition technology.

[0300] "Priority adjustment" is the process of changing the importance and execution order of tasks based on emotional data.

[0301] "Adjusting notification timing" is the process of determining the optimal timing for sending notifications about a task based on emotion data.

[0302] MODE FOR CARRYING OUT THE INVENTION

[0303] This invention aims to efficiently manage tasks created during meetings and phone calls by converting voice data into text data, analyzing it to create tasks, assigning them to people in charge, and managing their progress. It also includes a function to recognize the user's emotions and adjust task priorities and notification timings based on those emotions.

[0304] The system includes the following major hardware and software components:

[0305] Terminal: Equipped with a microphone for recording audio data and a communication module for transmitting audio data to a server in real time.

[0306] Server: A speech recognition API (e.g., Google Cloud Speech-to-Text API) that converts voice data into text data, and software for converting the data into a different format.

[0307] Natural language processing algorithms (e.g., BERT model): Algorithms that analyze generated text data, generate tasks, and appropriately classify them.

[0308] Emotion recognition engine (e.g., IBM Watson (registered trademark) Tone Analyzer): An engine for recognizing a user's emotions from voice data and generating emotion data.

[0309] Project management tools (e.g., JIRA) and personal task management tools (e.g., Todoist): software for managing tasks and tracking progress.

[0310] When a user starts a meeting or call, the device records the voice data and sends it to the server in real time. The server then uses a speech recognition API to convert the voice data into text data. It then analyzes the text data using a natural language processing algorithm to extract and classify tasks. The server then assigns the generated tasks to the appropriate person and automatically registers them in project management tools and personal task management tools.

[0311] The server periodically monitors task progress and sends reminder notifications if progress is behind or the deadline is approaching. Furthermore, it recognizes the user's emotions from voice data and adjusts task priority and notification timing based on that emotion data. For example, if the user is feeling stressed, it lowers the priority of the task and sends reminder notifications during times when the user is relaxed, promoting efficient task execution.

[0312] Specific examples

[0313] For example, user A and user B hold an online conference and record the audio data. The device sends the audio data to the server, and the server generates the following text data through a speech recognition API:

[0314] User A: We need to decide on a release plan for our new product.

[0315] User B: Let's complete the market research by next week.

[0316] User A: You should also start preparing your marketing materials.

[0317] The server extracts and classifies the following tasks from the generated text data:

[0318] User A: Determine release plan

[0319] User B: Completes market research

[0320] Artificial Intelligence: Data Collection for Marketing Materials

[0321] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reassign the task of creating marketing materials to an artificial intelligence. The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and reminders are sent at the appropriate time when deadlines are approaching. This series of processes streamlines project management and ensures that tasks are completed without any omissions.

[0322] Prompt Sentence Examples

[0323] "Extract tasks from the meeting contents of user A and user B, and adjust the priority of the tasks based on user B's feelings."

[0324] By inputting this prompt into a generative AI model, it can help extract specific tasks and adjust priorities.

[0325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0326] Program processing flow

[0327] Audio data collection and text conversion

[0328] Step 1:

[0329] Terminal: When a user starts a conference, the terminal's audio recording function is activated to capture audio data in real time.

[0330] Input: Voice of the user in the meeting

[0331] Specific operation: Records audio through the device's microphone and saves it as audio data.

[0332] Output: Real-time recorded audio data

[0333] Step 2:

[0334] Terminal: Recorded audio data is sent to the server in real time.

[0335] Input: Recorded audio data

[0336] Specific operation: The device transmits voice data to the server using Wi-Fi or mobile data.

[0337] Output: Audio data sent to the server

[0338] Step 3:

[0339] Server: Convert the received voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text API).

[0340] Input: Audio data

[0341] Specific operation: Calls the speech recognition API and converts the speech data into text format.

[0342] Output: Generated text data

[0343] Task Generation and Classification

[0344] Step 4:

[0345] Server: Analyze the generated text data using a natural language processing algorithm (e.g., the BERT model).

[0346] Input: Text data

[0347] What it does: Runs natural language processing algorithms to analyze text data and extract important keywords and phrases.

[0348] Output: Keywords and phrases from the parsed text data

[0349] Step 5:

[0350] Server: Extracts tasks from the analysis results and classifies them into "tasks to be performed by humans" and "tasks to be performed by AI."

[0351] Input: Keywords and phrases

[0352] Specific actions: Identify tasks based on keywords and phrases and divide them into "tasks to be performed by humans" and "tasks to be performed by AI."

[0353] Output: Categorized tasks

[0354] Task assignment

[0355] Step 6:

[0356] Server: Assigns the extracted tasks to the appropriate person.

[0357] Input: Categorized tasks

[0358] What it does: Assign tasks to the right people based on project progress and their skill sets.

[0359] Output: Tasks assigned to assignees

[0360] Step 7:

[0361] Server: Sends a notification to the task assignee.

[0362] Input: Tasks assigned to assignees

[0363] What it does: Send task details to assignees via email and / or push notification.

[0364] Output: Notification sent to assignee

[0365] Step 8:

[0366] Server: Automatically registers tasks in project management tools and personal task management tools.

[0367] Input: Tasks assigned to assignees

[0368] Specific operation: Register tasks using each tool's API and manage task schedules.

[0369] Output: Tasks registered with the tool

[0370] Task progress management and deadline advance notifications

[0371] Step 9:

[0372] Server: Periodically monitors the progress of the task.

[0373] Input: Progress data of tasks registered in the tool

[0374] Specific operation: Collect progress information entered by the person in charge into the task management tool and analyze it in real time.

[0375] Output: Progress monitoring results

[0376] Step 10:

[0377] Server: Send reminders when progress is behind or deadlines are approaching.

[0378] Input: Progress monitoring results

[0379] Specific behavior: If progress does not meet certain criteria, a reminder message will be sent to the person in charge via email or push notification.

[0380] Output: Reminder notifications sent

[0381] Step 11:

[0382] Server: Reassign task owners and due dates as needed.

[0383] Input: Progress monitoring results and responses to reminder notifications

[0384] Specific behavior: Change task assignees and adjust deadlines depending on the project situation.

[0385] Output: Reassigned tasks

[0386] Emotion recognition engine and emotion-based adjustments

[0387] Step 12:

[0388] Server: Uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize user emotions from voice data.

[0389] Input: Audio data

[0390] What it does: It uses an emotion recognition engine to analyze voice data and identify the user's emotional state.

[0391] Output: User emotion data

[0392] Step 13:

[0393] Server: Adjust task priorities and notification timing based on emotional data.

[0394] Input: User emotion data

[0395] Specific operation: Optimize task execution order and notification timing based on emotional data. For example, lower the priority of tasks for users who are feeling stressed and notify them during times when they are relaxed.

[0396] Output: Adjusted task priority and notification timing

[0397] (Application example 2)

[0398] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0399] Autonomous vehicle operation managers must efficiently manage a variety of tasks, particularly the content of meetings and phone calls, and assign them appropriately. Furthermore, systems are needed to optimize task priorities and facilitate smooth operation management by taking into account the emotions and stress levels of operation managers. However, current systems have difficulty meeting these requirements, resulting in inefficient task management and assignment, and a consequent decline in the overall efficiency of operation management.

[0400] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0401] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to appropriate personnel, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, providing advance notices of deadlines, and reassigning tasks as necessary, means for recognizing emotions from the voice data and adjusting task priorities based on the emotions, and means for adjusting the timing of task reminder notifications based on the emotion recognition. This enables operations managers to efficiently manage tasks while taking emotions and stress levels into consideration, thereby enabling smooth operation of autonomous vehicles.

[0402] "Audio data" is digital or analog data that records sound waves generated during meetings, telephone calls, etc.

[0403] "Text data" is character information converted from voice data, and is data that expresses the content of a speech as a string of characters.

[0404] A "task" is a set of tasks or activities that must be performed to achieve a specific goal, and can be performed by a human or artificial intelligence.

[0405] A "natural language processing algorithm" is an algorithm that analyzes text data and understands its meaning and context, and is a technology used to generate tasks.

[0406] "Emotion recognition" is a technology that identifies and identifies a person's emotional state from voice data, facial expressions, etc.

[0407] "Priority" refers to the criteria for evaluating and sorting the order and importance of tasks or work.

[0408] "Reminder notification" is a feature that notifies users again when a specific task or deadline is approaching.

[0409] A "project management tool" refers to software or a system that helps effectively manage multiple tasks or projects.

[0410] "Personal task management tool" refers to software or systems used by individuals to manage their daily tasks and schedules.

[0411] "Artificial intelligence" refers to the technology and systems that allow computers to perform intellectual tasks that humans perform.

[0412] The present invention provides a system for enabling an autonomous vehicle operation manager to efficiently manage tasks. The system includes multiple means, including voice data collection and text conversion, task generation and classification, and emotion recognition. Specific embodiments will be described below.

[0413] Hardware and Software Use

[0414] Hardware

[0415] Smartphones: Used to collect and record audio data.

[0416] Server: Performs the main processing of voice-to-text conversion, emotion recognition, and task management.

[0417] software

[0418] Google Cloud Speech-to-Text API: Used to convert audio data into text data.

[0419] Natural language processing algorithms (e.g., NLTK): Analyze text data and generate tasks.

[0420] Emotion Recognition API: Used to recognize emotions from audio data.

[0421] Project management tool and personal task management tool: Register tasks and track progress.

[0422] Data processing and calculation

[0423] 1. Audio data collection and text conversion:

[0424] Users can record audio data from meetings or phone calls using the microphone on their smartphone, and the recorded audio data is immediately sent to the server.

[0425] The server uses the Google Cloud Speech-to-Text API to convert voice data into text data in real time.

[0426] 2. Task generation and classification:

[0427] The server uses natural language processing algorithms to analyze the generated text data and extract tasks from key information and decisions.

[0428] The extracted tasks are classified into tasks performed by "people" and tasks performed by "artificial intelligence."

[0429] For example, if the text data contains the phrase "Complete market research," the task will be classified as being performed by a human.

[0430] 3. Priority adjustment through emotion recognition:

[0431] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data. If the user is feeling stressed, the priority of the task for that user will be lowered.

[0432] For example, if emotions such as "anxiety" or "stress" are detected, the task's priority will be set low and the timing of reminder notifications for other tasks will be adjusted.

[0433] Example scenario

[0434] User A and User B hold an online conference and record the audio data. The device (smartphone) sends the audio data to the server, which then generates the following text data via the Google Cloud Speech-to-Text API:

[0435] User A: We need to decide on a release plan for our new product.

[0436] User B: Let's complete our market research.

[0437] User A: You should also start preparing your marketing materials.

[0438] The server extracts and classifies the following tasks from this text data:

[0439] User A: Determine release plan

[0440] User B: Completes market research

[0441] Artificial Intelligence: Data Collection for Marketing Materials

[0442] Furthermore, if the emotion engine senses stress from User B's voice, it will adjust task priorities and reallocate the task of creating marketing materials to the AI. Through this series of processes, the operation manager can efficiently manage tasks while taking into account emotions and stress levels, ensuring the smooth operation of autonomous vehicles.

[0443] Prompt Sentence Examples

[0444] "Generate tasks for the user based on the following audio data and notify them based on that. If possible, recognize the user's emotions and adjust the priority of the tasks."

[0445] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0446] Step 1:

[0447] Collection and transmission of voice data

[0448] The user uses the microphone on their smartphone to record audio data from a meeting or call. Once the recording is complete, the device transmits the audio data to a server in real time.

[0449] Input: Audio data from meetings and calls

[0450] Data processing: Digital conversion and streaming of audio data

[0451] Output: Audio data sent to the server

[0452] Step 2:

[0453] Converting audio data to text data

[0454] The server converts the audio data into text using the Google Cloud Speech-to-Text API, which parses the audio data and generates a string of output.

[0455] Input: Audio data sent to the server

[0456] Data Calculation: Speech Recognition and Text Conversion

[0457] Output: Text data

[0458] Step 3:

[0459] Analyzing text data and extracting tasks

[0460] The server uses natural language processing algorithms (e.g., NLTK) to analyze the text data and automatically extract tasks based on key information and decisions.

[0461] Input: Text data

[0462] Data Computing: Information Extraction through Natural Language Processing

[0463] Output: Extracted tasks

[0464] Step 4:

[0465] Task Classification

[0466] The extracted tasks are classified as either performed by a human or by an artificial intelligence. For example, a task such as "Complete market research" is classified as a task performed by a human.

[0467] Input: Extracted tasks

[0468] Data calculation: Task classification (keyword matching, etc.)

[0469] Output: Categorized tasks

[0470] Step 5:

[0471] Emotion recognition

[0472] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data, and the recognized emotion data is used for subsequent task management.

[0473] Input: Audio data

[0474] Data arithmetic: Analysis by emotion recognition algorithms

[0475] Output: Emotion data

[0476] Step 6:

[0477] Adjusting task priorities

[0478] The server adjusts task priorities based on the perceived user emotion, for example, if the user is feeling stressed, it lowers the priority of the tasks for that user.

[0479] Input: Emotion data, classification task

[0480] Data arithmetic: Priority adjustment based on emotional data

[0481] Output: Tasks with adjusted priorities

[0482] Step 7:

[0483] Task assignment and notifications

[0484] The server assigns the prioritized tasks to the appropriate person, automatically registers them in project management tools and personal task management tools, and notifies the user via email and push notifications.

[0485] Input: Priority adjusted tasks

[0486] Data calculation: task allocation and registration with tools, notification generation

[0487] Output: Assigned tasks and notifications

[0488] Step 8:

[0489] Progress management and reminders

[0490] The server periodically monitors the progress of tasks, sending reminders if progress is falling behind or deadlines are approaching, and reassigning tasks as necessary.

[0491] Input: Assigned Tasks

[0492] Data calculation: Progress management, reassignment of deadlines, and generation of reminder notifications

[0493] Output: Reminders and reassigned tasks

[0494] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0495] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search<url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0496] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0497] [Second embodiment]

[0498] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0499] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0500] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0501] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0502] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0504] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0505] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0506] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0507] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0508] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0509] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0510] System Overview

[0511] This system aims to improve the efficiency of task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[0512] 1. Collecting voice data and converting it to text

[0513] 2. Task Generation and Classification

[0514] 3. Task assignment

[0515] 4. Task progress management and deadline notifications

[0516] Program processing

[0517] Audio data collection and text conversion

[0518] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server then converts the received audio data into text data using a speech recognition API. This text data is later saved as minutes and serves as the basis for analysis.

[0519] Task Generation and Classification

[0520] The server uses natural language processing algorithms to analyze the text data generated from the voice data. This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0521] Task assignment

[0522] The server assigns the classified tasks to the appropriate person in charge. Tasks assigned to users are notified to the users' devices via email or push notifications to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[0523] Task progress management and deadline advance notifications

[0524] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[0525] Specific examples

[0526] Meeting Scenarios

[0527] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[0528] User A: We need to decide on a release plan for a new product.

[0529] User B: Let's complete the market research by next week.

[0530] User A: You should also start preparing your marketing materials.

[0531] The server extracts and classifies the following tasks from this text data:

[0532] User A: Determine release plan

[0533] User B: Market research completed

[0534] Artificial Intelligence: Data collection for marketing materials

[0535] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[0536] This approach streamlines project management, ensures that no tasks are overlooked, and allows users to keep track of task progress, improving overall project performance.

[0537] The processing flow will be explained below.

[0538] Step 1:

[0539] A user starts a meeting or call. The device records the audio in real time and sends the audio data to the server, where it is converted into a digital format.

[0540] Step 2:

[0541] The server receives the voice data. The server then calls a speech recognition API to convert the received voice data into text data. This process uses natural language processing technology.

[0542] Step 3:

[0543] The server analyzes the generated text data and creates minutes, which are stored in a database and serve as the basis for subsequent task generation processes.

[0544] Step 4:

[0545] The server analyzes the text data of the minutes using natural language processing algorithms, and extracts tasks from important discussions and decisions.

[0546] Step 5:

[0547] The server classifies the extracted tasks into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0548] Step 6:

[0549] The server assigns categorized tasks to appropriate personnel, and this assignment information is recorded in a database.

[0550] Step 7:

[0551] The device will send task notifications to the assignee via email and push notifications, ensuring that the assignee never misses a task.

[0552] Step 8:

[0553] The server automatically registers tasks in project management tools and personal task management tools using API calls.

[0554] Step 9:

[0555] The server periodically monitors the progress of tasks and sends reminders to the person in charge if progress is behind or the deadline is approaching.

[0556] Step 10:

[0557] The server will reassign tasks as needed. This happens if a task is delayed or needs to be reassigned.

[0558] Example 1

[0559] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0560] Task management in project management requires efficient progress and appropriate resource allocation, but there are challenges such as information leakage due to numerous meetings and calls, and difficulty in properly allocating tasks. Automation is also required to properly manage progress and send reminders, but traditional manual management takes time and effort and is prone to errors. A system is needed to solve these problems.

[0561] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0562] In this invention, the server includes: means for collecting voice data from meetings and calls and converting the voice data into text data; means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, providing advance notices, and reassigning tasks as necessary; a terminal for transmitting voice data to the server in real time; a server for converting voice data into text data using a voice recognition API; a natural language processing algorithm for analyzing the text data and extracting tasks; and means for monitoring the progress of tasks and sending reminder notifications. This improves the efficiency and accuracy of task management and enables appropriate progress management.

[0563] "Conference or call audio data" refers to data that includes all audio information generated during a conference or call.

[0564] "Text data" refers to data obtained by converting voice data into character information.

[0565] A "task" is a task or action item that needs to be done to achieve a specific purpose or goal.

[0566] "People" refers to actual people who use the system to perform tasks.

[0567] "Artificial intelligence" refers to computer programs and algorithms that partially or fully automate human tasks.

[0568] "Classifying" refers to the act of separating objects or information into groups based on specific criteria.

[0569] A "person in charge" is someone who is responsible for carrying out a particular task or work.

[0570] A "project management tool" is software that helps you plan projects, track progress, and communicate with team members.

[0571] A "personal task management tool" is software for managing personal tasks and schedules.

[0572] "Progress" refers to how far a task or project has progressed.

[0573] "Early Deadline Notifications" are reminders sent when a task deadline approaches.

[0574] "Reassignment" refers to the act of reassigning a task that has already been assigned to another person or resource.

[0575] "Terminal" refers to a device (e.g., PC, tablet, smartphone) that a user uses to access the system.

[0576] "Speech recognition API" refers to a program interface for analyzing voice input and converting it into text data.

[0577] "Natural language processing algorithms" refer to algorithms for understanding, analyzing, and generating human language.

[0578] A "reminding notification" is a notification that alerts the user to the progress of a task or a deadline.

[0579] System Overview

[0580] This system aims to streamline task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[0581] 1. Collecting voice data and converting it to text

[0582] 2. Task Generation and Classification

[0583] 3. Task assignment

[0584] 4. Task progress management and deadline notifications

[0585] Audio data collection and text conversion

[0586] When a user starts a meeting or call, the device records the audio and sends the audio data to a server in real time. The server then converts the received audio data into text using a speech recognition API such as Google Cloud Speech-to-Text API. This text data is later saved as meeting minutes and serves as the basis for analysis.

[0587] Task Generation and Classification

[0588] The server analyzes the text data generated from the voice data using natural language processing algorithms (e.g., spaCy or NLTK). This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0589] Task assignment

[0590] The server assigns the classified tasks to the appropriate person in charge. The assigned tasks are notified to the user's device via email or push notification to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools (e.g., Trello or Asana) or personal task management tools (e.g., Todoist).

[0591] Task progress management and deadline advance notifications

[0592] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[0593] Adding specific examples

[0594] Meeting Scenarios

[0595] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[0596] User A: We need to decide on a release plan for a new product.

[0597] User B: Let's complete the market research by next week.

[0598] User A: You should also start preparing your marketing materials.

[0599] The server extracts and classifies the following tasks from this text data:

[0600] User A: Determine release plan

[0601] User B: Market research completed

[0602] Artificial Intelligence: Data collection for marketing materials

[0603] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[0604] Example prompts for the generative AI model to use

[0605] Below are some example prompts to input to a generative AI model (e.g., GPT-4):

[0606] Analyze the text data generated from the following meeting recording, extract tasks from important discussions and decisions, and assign them to the appropriate people.

[0607] User A: We need to decide on a release plan for a new product.

[0608] User B: Let's complete the market research by next week.

[0609] User A: You should also start preparing your marketing materials.

[0610] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0611] Step 1: Collecting and transmitting audio data in real time

[0612] When a user starts a meeting or call, the device records the audio. The recording is done in real time and the audio data is sent to a server via the Internet. Specifically, a dedicated app on the device captures the user's voice with a microphone and instantly streams it to the server. The input here is the user's voice, and the output is the raw audio data sent to the server.

[0613] Step 2: Convert audio data to text

[0614] The server converts the received voice data into text data using a voice recognition API (for example, Google Cloud Speech-to-Text API). At this time, the voice recognition API analyzes the voice and performs the optimal text conversion using the language model of the voice data. Specifically, the server sends the voice data to the API and receives it as text data. The input is the received voice data, and the output is the converted text data.

[0615] Step 3: Analyzing text data and extracting tasks

[0616] The server analyzes the converted text data using natural language processing algorithms (e.g., spaCy or NLTK). In this process, important discussions and decisions in the text are identified and extracted as tasks. Specifically, the server begins text analysis and generates tasks based on specific keywords and phrases. The input is the text data, and the output is a list of tasks to be assigned to users or artificial intelligence.

[0617] Step 4: Categorize your tasks

[0618] The extracted tasks are classified by the server into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the task content and keywords. Specifically, the server analyzes the task content and applies an appropriate classification algorithm. The input is a list of extracted tasks, and the output is a classified task list.

[0619] Step 5: Assign tasks

[0620] The server assigns the classified tasks to the appropriate person in charge. The results of the task assignment are notified to the user's device. Specifically, the server calls the API of the task management tool to register the task and sends an email or push notification to the person in charge. The input is the classified task list, and the output is a task assignment notification.

[0621] Step 6: Track your progress and receive reminders

[0622] The server synchronizes data with the project management tool and monitors the progress of tasks. If progress is behind schedule or the deadline is approaching, it sends reminder notifications to the user. Specifically, the server periodically obtains progress data and sends reminder notifications if there is a problem. The input is task progress data, and the output is reminder notifications to the user.

[0623] Each of the above steps will ensure that the overall system functions effectively, improving the efficiency and accuracy of project management.

[0624] (Application example 1)

[0625] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0626] In modern factories, maintenance and quality control tasks are becoming increasingly complex, requiring efficient management. In particular, accurate instruction transmission and task assignment are essential for workers to respond quickly on-site. However, manual task assignment and management takes time, potentially resulting in reduced work efficiency and task delays. Furthermore, even when using robots, the lack of a system that can accurately interpret voice instructions and appropriately assign tasks remains an issue.

[0627] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0628] In this invention, the server includes: means for collecting voice data from conferences and calls and converting the voice data into text data; means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, notifying users before their deadlines, and reassigning tasks as necessary; and means for providing voice instructions from a worker to a robot in factory maintenance work and quality control, analyzing the instructions, generating tasks, and automatically assigning them to the robot and the worker. This enables efficient task assignment and progress management in factory maintenance work and quality control operations.

[0629] "Voice data" refers to raw voice information collected during meetings, phone calls, etc.

[0630] "Text data" is voice data converted into character information.

[0631] "Analysis" refers to the process of analyzing text data to derive meaning.

[0632] A "task" is a specific item that directs a particular activity or work.

[0633] Tasks performed by "people" are tasks that need to be performed by humans, such as workers or managers.

[0634] Tasks performed by "artificial intelligence" are tasks that can be performed by robots or AI systems.

[0635] "Classification" is the process of determining whether a task extracted from text data will be performed by a "person" or by "artificial intelligence."

[0636] "Responsible Person" refers to a person or system that is responsible for performing a specific task.

[0637] A "project management tool" is software or a system that allows you to centrally manage project progress and tasks.

[0638] A "personal task management tool" is software or a system that allows individual users to manage their own tasks.

[0639] "Progress management" is the process of monitoring whether tasks are progressing as planned and taking necessary actions.

[0640] "Pre-deadline notification" is a notification to inform the person in charge that the deadline for a task is approaching.

[0641] "Reassignment" is the process of changing the person responsible for or the deadline for an originally assigned task.

[0642] "Factory maintenance work" refers to a series of tasks performed to maintain factory facilities and equipment.

[0643] "Quality control" refers to the monitoring and control processes used to ensure the quality of products and services.

[0644] "Voice instructions" refers to verbal instructions given by the worker to the robot.

[0645] "Real-time" means processing immediately without delay.

[0646] System Overview

[0647] The system of the present invention is designed to improve the efficiency of maintenance work and quality control in factories. The main functions of the system are to collect voice data and convert it into text, generate and classify tasks, assign tasks, register tasks in project management tools and personal task management tools, manage task progress, and notify users before deadlines. Specific methods for realizing these functions are described below.

[0648] Program processing

[0649] 1. Collecting voice data and converting it to text

[0650] When performing maintenance or quality control tasks in a factory, workers give voice instructions to the robot. These voice instructions are collected through a microphone installed on the robot. The voice data is sent in real time to a server, which then converts the voice data into text data using the Google Cloud Speech-to-Text API. This text data is then used as the basis for subsequent analysis and task generation.

[0651] 2. Task Generation and Classification

[0652] The server analyzes the text data generated from the voice data using the Google Cloud Natural Language API. Through this process, tasks are automatically extracted from important instructions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0653] 3. Task assignment

[0654] The server automatically assigns the classified tasks to the appropriate person (worker or robot). Tasks assigned to users are notified to the users' devices via email or push notification. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[0655] 4. Task progress management and deadline notifications

[0656] The server periodically monitors the progress of the task. If progress is slow or the deadline is approaching, the server sends a reminder to the user, allowing the user to take appropriate action to complete the task on time. If necessary, the server also reassigns the task's assignee and deadline.

[0657] Specific examples

[0658] Maintenance Scenarios

[0659] Consider a situation where Worker A is performing maintenance work in a factory and needs to give instructions to a robot:

[0660] Worker A: The following line needs to be cleaned.

[0661] Worker B: Let's check all the parts and make sure there are no abnormalities.

[0662] The robot collects this voice data and sends it to the server, which then uses a speech recognition API to generate text data like this:

[0663] Worker A: The following line needs to be cleaned.

[0664] Worker B: Let's check all the parts and make sure there are no abnormalities.

[0665] The server extracts and classifies the following tasks from this text data:

[0666] Worker tasks:

[0667] Worker A: Cleaning the line

[0668] Worker B: Inspection and confirmation of parts

[0669] Robot Task:

[0670] Robot: Collects monitoring data of cleaning operations and sends it to the quality control department

[0671] These tasks are automatically assigned to each worker and robot by the server and registered in project management tools and personal task management tools.

[0672] Prompt Sentence Examples

[0673] Voice recognition result:

[0674] Worker A: The following line needs to be cleaned.

[0675] Worker B: Let's check all the parts and make sure there are no abnormalities.

[0676] Task creation:

[0677] Assign the task of "line cleaning work" to worker A.

[0678] Assign the task of "Inspect and check parts" to worker B.

[0679] The robot is assigned the task of "collecting monitoring data of the cleaning work and sending it to the quality control department."

[0680] This will automate and streamline maintenance and quality control work within factories, enabling workers and robots to work together to smoothly carry out tasks.

[0681] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0682] Step 1:

[0683] When a user performs maintenance or quality control work in a factory, the worker gives voice instructions to the robot. A microphone installed on the robot's terminal collects these voice instructions. The input is the worker's voice data, and the output is the voice data collected by the robot's terminal.

[0684] Step 2:

[0685] The device sends the collected voice data to the server in real time, and the server converts the voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is text data.

[0686] Step 3:

[0687] The server analyzes the converted text data using the Google Cloud Natural Language API. This analysis extracts important instructions and decisions from the text. The input is the text data, and the output is the extracted instructions and decisions.

[0688] Step 4:

[0689] The server generates tasks from the analysis results and classifies them into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." The input is the extracted instructions and decisions, and the output is the classified tasks.

[0690] Step 5:

[0691] The server automatically assigns the classified tasks to the appropriate personnel (workers or robots). The input is the classified tasks, and the output is the tasks assigned to each personnel.

[0692] Step 6:

[0693] The server registers the assigned tasks in the project management tool and the personal task management tool. The input is the tasks assigned to the person in charge, and the output is the tasks registered in the management tool.

[0694] Step 7:

[0695] The server periodically monitors the progress of tasks and sends reminder notifications when progress is behind or the deadline is approaching. The input is the progress of tasks registered in the management tool, and the output is reminder notifications.

[0696] Step 8:

[0697] If necessary, the server reassigns task owners and deadlines. The input is tasks that are behind schedule or approaching deadlines, and the output is the reassigned tasks.

[0698] Through the above processing steps, the system is able to efficiently manage and carry out maintenance and quality control work within the factory.

[0699] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0700] System Overview

[0701] This invention aims to improve the efficiency of task management in project management, and by combining it with an emotion engine, it is possible to understand the user's emotions and adjust task priorities and notification timing. The system includes the following main components:

[0702] 1. Collecting voice data and converting it to text

[0703] 2. Task Generation and Classification

[0704] 3. Task assignment

[0705] 4. Task progress management and deadline notifications

[0706] 5. Emotion Recognition Engine and Emotion-Based Adjustments

[0707] Program processing

[0708] Audio data collection and text conversion

[0709] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server converts the audio data into text data using a speech recognition API and generates minutes. The text data is then used for task generation and emotion recognition.

[0710] Task Generation and Classification

[0711] The server analyzes the generated text data using natural language processing algorithms and extracts tasks from key points of discussion and decisions. The extracted tasks are then classified into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on content and keywords.

[0712] Task assignment

[0713] The server assigns the classified tasks to the appropriate person. The assigned tasks are notified to the user via their device. Notification methods include email and push notifications. Tasks are also automatically registered in project management tools and personal task management tools.

[0714] Task progress management and deadline advance notifications

[0715] The server periodically monitors the progress of tasks, and if progress is delayed or the deadline is approaching, it sends reminder notifications to the user, and if necessary, reassigns task owners and deadlines.

[0716] Emotion recognition engine and emotion-based adjustments

[0717] The server is equipped with an emotion engine that recognizes the user's emotions from voice data. The emotion engine identifies the user's emotions by analyzing the tone of the voice and the choice of words. This emotion data is used to adjust task priorities and notification timing.

[0718] For example, if a user is feeling anxious or stressed, the system can lower the priority of the task for that user. Furthermore, based on emotion recognition, the system can send reminders during times when the user is relaxed, promoting efficient task execution.

[0719] Specific examples

[0720] Meeting Scenarios

[0721] User A and User B hold an online conference and record the audio data. The device sends the audio data to the server, which then generates the following text data through a speech recognition API:

[0722] User A: We need to decide on a release plan for our new product.

[0723] User B: Let's complete the market research by next week.

[0724] User A: You should also start preparing your marketing materials.

[0725] The server extracts and classifies the following tasks from the generated text data:

[0726] User A: Determine release plan

[0727] User B: Completes market research

[0728] Artificial Intelligence: Data Collection for Marketing Materials

[0729] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reallocate the task of creating marketing materials to an artificial intelligence.

[0730] The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and timely reminders are sent when deadlines approach. This process streamlines project management and ensures that tasks are completed without omission.

[0731] This invention allows users to keep track of task progress and improve overall project performance in an emotionally sensitive manner.

[0732] The processing flow will be explained below.

[0733] Step 1:

[0734] A user initiates a meeting or call. The device records the conversation in real time and sends the audio data to a server, where it is converted into a digital format and processed.

[0735] Step 2:

[0736] The server converts the received voice data into text data using a voice recognition API. Through this process, text information is automatically generated from the voice.

[0737] Step 3:

[0738] The server analyzes the text data and generates meeting minutes, which are stored in a database and serve as the basis for future task generation and emotion recognition.

[0739] Step 4:

[0740] The server analyzes the stored text data using natural language processing algorithms to extract tasks from key points and decisions during discussions. This analysis includes keyword extraction and contextual analysis.

[0741] Step 5:

[0742] The server classifies the extracted tasks into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on the task content and keywords, and the appropriate person in charge is selected.

[0743] Step 6:

[0744] The emotion engine analyzes the voice data to recognize the user's emotions. The emotion engine analyzes the voice tone and word choice to identify the type of emotion (e.g., stress, anxiety, joy).

[0745] Step 7:

[0746] The server adjusts the priority and placement of tasks based on information from the emotion engine. For example, if the user's emotions indicate stress, it temporarily lowers the priority of urgent tasks.

[0747] Step 8:

[0748] The server assigns the task to the appropriate person, who is then notified of the assigned task via email or push notification.

[0749] Step 9:

[0750] The server automatically registers tasks in project management tools and personal task management tools, allowing the person in charge to check the task content and deadlines.

[0751] Step 10:

[0752] The server periodically monitors the progress of the task and sends reminders when progress is behind or the deadline is approaching. The timing of the reminders is adjusted based on the user's emotional state.

[0753] Step 11:

[0754] The server reassigns tasks as needed. If a task is delayed or needs to be reassigned, a reassignment process is initiated. This process also takes into account the user's emotional state.

[0755] Through this process, the system can understand the user's emotions, improve task management efficiency, and improve overall project performance.

[0756] Example 2

[0757] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0758] Conventional project management systems lack the ability to efficiently manage tasks generated during meetings or phone calls, track progress, and adjust tasks based on user emotions. This can lead to missed tasks and delays in progress, resulting in a decline in overall project performance. There is also the risk that users may feel excessive stress, further reducing productivity. The present invention aims to solve these problems.

[0759] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0760] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to an appropriate person, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, notifying the user before their deadline, and reassigning tasks as necessary, and means for recognizing the user's emotions from the voice data and adjusting task priorities and notification timings based on the emotion data. This enables efficient management of tasks generated during conferences and calls, understanding the progress, and adjusting tasks based on the user's emotions.

[0761] "Voice data" refers to voice information collected during a conference or call, and is data that is converted into text data.

[0762] "Text data" refers to data that has been converted from voice data into text information using voice recognition technology.

[0763] A "task" refers to a work item or instruction generated during a meeting or call, and is a unit of action to be carried out.

[0764] A "natural language processing algorithm" is a language analysis technology that analyzes text data and generates and classifies tasks.

[0765] A "personnel" is a person or artificial intelligence assigned to carry out the generated task.

[0766] "Project management tool" refers to software or a system for tracking project progress and scheduling tasks.

[0767] "Personal task management tool" refers to software or a system that allows individuals to record, manage, and prioritize their tasks.

[0768] "Progress management" is the process of monitoring the status of task implementation and understanding the degree of progress.

[0769] "Pre-deadline notification" is a notification to remind the person in charge when the deadline for a task is approaching.

[0770] "Emotion recognition" is a technology that analyzes and identifies a user's emotions from voice data.

[0771] "Emotion data" refers to information about a user's emotional state extracted using emotion recognition technology.

[0772] "Priority adjustment" is the process of changing the importance and execution order of tasks based on emotional data.

[0773] "Adjusting notification timing" is the process of determining the optimal timing for sending notifications about a task based on emotion data.

[0774] MODE FOR CARRYING OUT THE INVENTION

[0775] This invention aims to efficiently manage tasks created during meetings and phone calls by converting voice data into text data, analyzing it to create tasks, assigning them to people in charge, and managing their progress. It also includes a function to recognize the user's emotions and adjust task priorities and notification timings based on those emotions.

[0776] The system includes the following major hardware and software components:

[0777] Terminal: Equipped with a microphone for recording audio data and a communication module for transmitting audio data to a server in real time.

[0778] Server: A speech recognition API (e.g., Google Cloud Speech-to-Text API) that converts voice data into text data, and software for converting the data into a different format.

[0779] Natural language processing algorithms (e.g., BERT model): Algorithms that analyze generated text data, generate tasks, and appropriately classify them.

[0780] Emotion recognition engine (e.g., IBM Watson Tone Analyzer): An engine for recognizing user emotions from voice data and generating emotion data.

[0781] Project management tools (e.g., JIRA) and personal task management tools (e.g., Todoist): software for managing tasks and tracking progress.

[0782] When a user starts a meeting or call, the device records the voice data and sends it to the server in real time. The server then uses a speech recognition API to convert the voice data into text data. It then analyzes the text data using a natural language processing algorithm to extract and classify tasks. The server then assigns the generated tasks to the appropriate person and automatically registers them in project management tools and personal task management tools.

[0783] The server periodically monitors task progress and sends reminder notifications if progress is behind or the deadline is approaching. Furthermore, it recognizes the user's emotions from voice data and adjusts task priority and notification timing based on that emotion data. For example, if the user is feeling stressed, it lowers the priority of the task and sends reminder notifications during times when the user is relaxed, promoting efficient task execution.

[0784] Specific examples

[0785] For example, user A and user B hold an online conference and record the audio data. The device sends the audio data to the server, and the server generates the following text data through a speech recognition API:

[0786] User A: We need to decide on a release plan for our new product.

[0787] User B: Let's complete the market research by next week.

[0788] User A: You should also start preparing your marketing materials.

[0789] The server extracts and classifies the following tasks from the generated text data:

[0790] User A: Determine release plan

[0791] User B: Completes market research

[0792] Artificial Intelligence: Data Collection for Marketing Materials

[0793] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reassign the task of creating marketing materials to an artificial intelligence. The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and reminders are sent at the appropriate time when deadlines are approaching. This series of processes streamlines project management and ensures that tasks are completed without any omissions.

[0794] Prompt Sentence Examples

[0795] "Extract tasks from the meeting contents of user A and user B, and adjust the priority of the tasks based on user B's feelings."

[0796] By inputting this prompt into a generative AI model, it can help extract specific tasks and adjust priorities.

[0797] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0798] Program processing flow

[0799] Audio data collection and text conversion

[0800] Step 1:

[0801] Terminal: When a user starts a conference, the terminal's audio recording function is activated to capture audio data in real time.

[0802] Input: Voice of the user in the meeting

[0803] Specific operation: Records audio through the device's microphone and saves it as audio data.

[0804] Output: Real-time recorded audio data

[0805] Step 2:

[0806] Terminal: Recorded audio data is sent to the server in real time.

[0807] Input: Recorded audio data

[0808] Specific operation: The device transmits voice data to the server using Wi-Fi or mobile data.

[0809] Output: Audio data sent to the server

[0810] Step 3:

[0811] Server: Convert the received voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text API).

[0812] Input: Audio data

[0813] Specific operation: Calls the speech recognition API and converts the speech data into text format.

[0814] Output: Generated text data

[0815] Task Generation and Classification

[0816] Step 4:

[0817] Server: Analyze the generated text data using a natural language processing algorithm (e.g., the BERT model).

[0818] Input: Text data

[0819] What it does: Runs natural language processing algorithms to analyze text data and extract important keywords and phrases.

[0820] Output: Keywords and phrases from the parsed text data

[0821] Step 5:

[0822] Server: Extracts tasks from the analysis results and classifies them into "tasks to be performed by humans" and "tasks to be performed by AI."

[0823] Input: Keywords and phrases

[0824] Specific actions: Identify tasks based on keywords and phrases and divide them into "tasks to be performed by humans" and "tasks to be performed by AI."

[0825] Output: Categorized tasks

[0826] Task assignment

[0827] Step 6:

[0828] Server: Assigns the extracted tasks to the appropriate person.

[0829] Input: Categorized tasks

[0830] What it does: Assign tasks to the right people based on project progress and their skill sets.

[0831] Output: Tasks assigned to assignees

[0832] Step 7:

[0833] Server: Sends a notification to the task assignee.

[0834] Input: Tasks assigned to assignees

[0835] What it does: Send task details to assignees via email and / or push notification.

[0836] Output: Notification sent to assignee

[0837] Step 8:

[0838] Server: Automatically registers tasks in project management tools and personal task management tools.

[0839] Input: Tasks assigned to assignees

[0840] Specific operation: Register tasks using each tool's API and manage task schedules.

[0841] Output: Tasks registered with the tool

[0842] Task progress management and deadline advance notifications

[0843] Step 9:

[0844] Server: Periodically monitors the progress of the task.

[0845] Input: Progress data of tasks registered in the tool

[0846] Specific operation: Collect progress information entered by the person in charge into the task management tool and analyze it in real time.

[0847] Output: Progress monitoring results

[0848] Step 10:

[0849] Server: Send reminders when progress is behind or deadlines are approaching.

[0850] Input: Progress monitoring results

[0851] Specific behavior: If progress does not meet certain criteria, a reminder message will be sent to the person in charge via email or push notification.

[0852] Output: Reminder notifications sent

[0853] Step 11:

[0854] Server: Reassign task owners and due dates as needed.

[0855] Input: Progress monitoring results and responses to reminder notifications

[0856] Specific behavior: Change task assignees and adjust deadlines depending on the project situation.

[0857] Output: Reassigned tasks

[0858] Emotion recognition engine and emotion-based adjustments

[0859] Step 12:

[0860] Server: Uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize user emotions from voice data.

[0861] Input: Audio data

[0862] What it does: It uses an emotion recognition engine to analyze voice data and identify the user's emotional state.

[0863] Output: User emotion data

[0864] Step 13:

[0865] Server: Adjust task priorities and notification timing based on emotional data.

[0866] Input: User emotion data

[0867] Specific operation: Optimize task execution order and notification timing based on emotional data. For example, lower the priority of tasks for users who are feeling stressed and notify them during times when they are relaxed.

[0868] Output: Adjusted task priority and notification timing

[0869] (Application example 2)

[0870] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0871] Autonomous vehicle operation managers must efficiently manage a variety of tasks, particularly the content of meetings and phone calls, and assign them appropriately. Furthermore, systems are needed to optimize task priorities and facilitate smooth operation management by taking into account the emotions and stress levels of operation managers. However, current systems have difficulty meeting these requirements, resulting in inefficient task management and assignment, and a consequent decline in the overall efficiency of operation management.

[0872] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0873] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to appropriate personnel, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, providing advance notices of deadlines, and reassigning tasks as necessary, means for recognizing emotions from the voice data and adjusting task priorities based on the emotions, and means for adjusting the timing of task reminder notifications based on the emotion recognition. This enables operations managers to efficiently manage tasks while taking emotions and stress levels into consideration, thereby enabling smooth operation of autonomous vehicles.

[0874] "Audio data" is digital or analog data that records sound waves generated during meetings, telephone calls, etc.

[0875] "Text data" is character information converted from voice data, and is data that expresses the content of a speech as a string of characters.

[0876] A "task" is a set of tasks or activities that must be performed to achieve a specific goal, and can be performed by a human or artificial intelligence.

[0877] A "natural language processing algorithm" is an algorithm that analyzes text data and understands its meaning and context, and is a technology used to generate tasks.

[0878] "Emotion recognition" is a technology that identifies and identifies a person's emotional state from voice data, facial expressions, etc.

[0879] "Priority" refers to the criteria for evaluating and sorting the order and importance of tasks or work.

[0880] "Reminder notification" is a feature that notifies users again when a specific task or deadline is approaching.

[0881] A "project management tool" refers to software or a system that helps effectively manage multiple tasks or projects.

[0882] "Personal task management tool" refers to software or systems used by individuals to manage their daily tasks and schedules.

[0883] "Artificial intelligence" refers to the technology and systems that allow computers to perform intellectual tasks that humans perform.

[0884] The present invention provides a system for enabling an autonomous vehicle operation manager to efficiently manage tasks. The system includes multiple means, including voice data collection and text conversion, task generation and classification, and emotion recognition. Specific embodiments will be described below.

[0885] Hardware and Software Use

[0886] Hardware

[0887] Smartphones: Used to collect and record audio data.

[0888] Server: Performs the main processing of voice-to-text conversion, emotion recognition, and task management.

[0889] software

[0890] Google Cloud Speech-to-Text API: Used to convert audio data into text data.

[0891] Natural language processing algorithms (e.g., NLTK): Analyze text data and generate tasks.

[0892] Emotion Recognition API: Used to recognize emotions from audio data.

[0893] Project management tool and personal task management tool: Register tasks and track progress.

[0894] Data processing and calculation

[0895] 1. Audio data collection and text conversion:

[0896] Users can record audio data from meetings or phone calls using the microphone on their smartphone, and the recorded audio data is immediately sent to the server.

[0897] The server uses the Google Cloud Speech-to-Text API to convert voice data into text data in real time.

[0898] 2. Task generation and classification:

[0899] The server uses natural language processing algorithms to analyze the generated text data and extract tasks from key information and decisions.

[0900] The extracted tasks are classified into tasks performed by "people" and tasks performed by "artificial intelligence."

[0901] For example, if the text data contains the phrase "Complete market research," the task will be classified as being performed by a human.

[0902] 3. Priority adjustment through emotion recognition:

[0903] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data. If the user is feeling stressed, the priority of the task for that user will be lowered.

[0904] For example, if emotions such as "anxiety" or "stress" are detected, the task's priority will be set low and the timing of reminder notifications for other tasks will be adjusted.

[0905] Example scenario

[0906] User A and User B hold an online conference and record the audio data. The device (smartphone) sends the audio data to the server, which then generates the following text data via the Google Cloud Speech-to-Text API:

[0907] User A: We need to decide on a release plan for our new product.

[0908] User B: Let's complete our market research.

[0909] User A: You should also start preparing your marketing materials.

[0910] The server extracts and classifies the following tasks from this text data:

[0911] User A: Determine release plan

[0912] User B: Completes market research

[0913] Artificial Intelligence: Data Collection for Marketing Materials

[0914] Furthermore, if the emotion engine senses stress from User B's voice, it will adjust task priorities and reallocate the task of creating marketing materials to the AI. Through this series of processes, the operation manager can efficiently manage tasks while taking into account emotions and stress levels, ensuring the smooth operation of autonomous vehicles.

[0915] Prompt Sentence Examples

[0916] "Generate tasks for the user based on the following audio data and notify them based on that. If possible, recognize the user's emotions and adjust the priority of the tasks."

[0917] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0918] Step 1:

[0919] Collection and transmission of voice data

[0920] The user uses the microphone on their smartphone to record audio data from a meeting or call. Once the recording is complete, the device transmits the audio data to a server in real time.

[0921] Input: Audio data from meetings and calls

[0922] Data processing: Digital conversion and streaming of audio data

[0923] Output: Audio data sent to the server

[0924] Step 2:

[0925] Converting audio data to text data

[0926] The server converts the audio data into text using the Google Cloud Speech-to-Text API, which parses the audio data and generates a string of output.

[0927] Input: Audio data sent to the server

[0928] Data Calculation: Speech Recognition and Text Conversion

[0929] Output: Text data

[0930] Step 3:

[0931] Analyzing text data and extracting tasks

[0932] The server uses natural language processing algorithms (e.g., NLTK) to analyze the text data and automatically extract tasks based on key information and decisions.

[0933] Input: Text data

[0934] Data Computing: Information Extraction through Natural Language Processing

[0935] Output: Extracted tasks

[0936] Step 4:

[0937] Task Classification

[0938] The extracted tasks are classified as either performed by a human or by an artificial intelligence. For example, a task such as "Complete market research" is classified as a task performed by a human.

[0939] Input: Extracted tasks

[0940] Data calculation: Task classification (keyword matching, etc.)

[0941] Output: Categorized tasks

[0942] Step 5:

[0943] Emotion recognition

[0944] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data, and the recognized emotion data is used for subsequent task management.

[0945] Input: Audio data

[0946] Data arithmetic: Analysis by emotion recognition algorithms

[0947] Output: Emotion data

[0948] Step 6:

[0949] Adjusting task priorities

[0950] The server adjusts task priorities based on the perceived user emotion, for example, if the user is feeling stressed, it lowers the priority of the tasks for that user.

[0951] Input: Emotion data, classification task

[0952] Data arithmetic: Priority adjustment based on emotional data

[0953] Output: Tasks with adjusted priorities

[0954] Step 7:

[0955] Task assignment and notifications

[0956] The server assigns the prioritized tasks to the appropriate person, automatically registers them in project management tools and personal task management tools, and notifies the user via email and push notifications.

[0957] Input: Priority adjusted tasks

[0958] Data calculation: task allocation and registration with tools, notification generation

[0959] Output: Assigned tasks and notifications

[0960] Step 8:

[0961] Progress management and reminders

[0962] The server periodically monitors the progress of tasks, sending reminders if progress is falling behind or deadlines are approaching, and reassigning tasks as necessary.

[0963] Input: Assigned Tasks

[0964] Data calculation: Progress management, reassignment of deadlines, and generation of reminder notifications

[0965] Output: Reminders and reassigned tasks

[0966] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0967] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0968] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0969] [Third embodiment]

[0970] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0971] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0972] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0973] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0974] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0975] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0976] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0977] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0978] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0979] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0980] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0981] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0982] System Overview

[0983] This system aims to improve the efficiency of task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[0984] 1. Collecting voice data and converting it to text

[0985] 2. Task Generation and Classification

[0986] 3. Task assignment

[0987] 4. Task progress management and deadline notifications

[0988] Program processing

[0989] Audio data collection and text conversion

[0990] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server then converts the received audio data into text data using a speech recognition API. This text data is later saved as minutes and serves as the basis for analysis.

[0991] Task Generation and Classification

[0992] The server uses natural language processing algorithms to analyze the text data generated from the voice data. This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[0993] Task assignment

[0994] The server assigns the classified tasks to the appropriate person in charge. Tasks assigned to users are notified to the users' devices via email or push notifications to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[0995] Task progress management and deadline advance notifications

[0996] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[0997] Specific examples

[0998] Meeting Scenarios

[0999] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[1000] User A: We need to decide on a release plan for a new product.

[1001] User B: Let's complete the market research by next week.

[1002] User A: You should also start preparing your marketing materials.

[1003] The server extracts and classifies the following tasks from this text data:

[1004] User A: Determine release plan

[1005] User B: Market research completed

[1006] Artificial Intelligence: Data collection for marketing materials

[1007] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[1008] This approach streamlines project management, ensures that no tasks are overlooked, and allows users to keep track of task progress, improving overall project performance.

[1009] The processing flow will be explained below.

[1010] Step 1:

[1011] A user starts a meeting or call. The device records the audio in real time and sends the audio data to the server, where it is converted into a digital format.

[1012] Step 2:

[1013] The server receives the voice data. The server then calls a speech recognition API to convert the received voice data into text data. This process uses natural language processing technology.

[1014] Step 3:

[1015] The server analyzes the generated text data and creates minutes, which are stored in a database and serve as the basis for subsequent task generation processes.

[1016] Step 4:

[1017] The server analyzes the text data of the minutes using natural language processing algorithms, and extracts tasks from important discussions and decisions.

[1018] Step 5:

[1019] The server classifies the extracted tasks into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[1020] Step 6:

[1021] The server assigns categorized tasks to appropriate personnel, and this assignment information is recorded in a database.

[1022] Step 7:

[1023] The device will send task notifications to the assignee via email and push notifications, ensuring that the assignee never misses a task.

[1024] Step 8:

[1025] The server automatically registers tasks in project management tools and personal task management tools using API calls.

[1026] Step 9:

[1027] The server periodically monitors the progress of tasks and sends reminders to the person in charge if progress is behind or the deadline is approaching.

[1028] Step 10:

[1029] The server will reassign tasks as needed. This happens if a task is delayed or needs to be reassigned.

[1030] Example 1

[1031] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1032] Task management in project management requires efficient progress and appropriate resource allocation, but there are challenges such as information leakage due to numerous meetings and calls, and difficulty in properly allocating tasks. Automation is also required to properly manage progress and send reminders, but traditional manual management takes time and effort and is prone to errors. A system is needed to solve these problems.

[1033] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1034] In this invention, the server includes: means for collecting voice data from meetings and calls and converting the voice data into text data; means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, providing advance notices, and reassigning tasks as necessary; a terminal for transmitting voice data to the server in real time; a server for converting voice data into text data using a voice recognition API; a natural language processing algorithm for analyzing the text data and extracting tasks; and means for monitoring the progress of tasks and sending reminder notifications. This improves the efficiency and accuracy of task management and enables appropriate progress management.

[1035] "Conference or call audio data" refers to data that includes all audio information generated during a conference or call.

[1036] "Text data" refers to data obtained by converting voice data into character information.

[1037] A "task" is a task or action item that needs to be done to achieve a specific purpose or goal.

[1038] "People" refers to actual people who use the system to perform tasks.

[1039] "Artificial intelligence" refers to computer programs and algorithms that partially or fully automate human tasks.

[1040] "Classifying" refers to the act of separating objects or information into groups based on specific criteria.

[1041] A "person in charge" is someone who is responsible for carrying out a particular task or work.

[1042] A "project management tool" is software that helps you plan projects, track progress, and communicate with team members.

[1043] A "personal task management tool" is software for managing personal tasks and schedules.

[1044] "Progress" refers to how far a task or project has progressed.

[1045] "Early Deadline Notifications" are reminders sent when a task deadline approaches.

[1046] "Reassignment" refers to the act of reassigning a task that has already been assigned to another person or resource.

[1047] "Terminal" refers to a device (e.g., PC, tablet, smartphone) that a user uses to access the system.

[1048] "Speech recognition API" refers to a program interface for analyzing voice input and converting it into text data.

[1049] "Natural language processing algorithms" refer to algorithms for understanding, analyzing, and generating human language.

[1050] A "reminding notification" is a notification that alerts the user to the progress of a task or a deadline.

[1051] System Overview

[1052] This system aims to streamline task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[1053] 1. Collecting voice data and converting it to text

[1054] 2. Task Generation and Classification

[1055] 3. Task assignment

[1056] 4. Task progress management and deadline notifications

[1057] Audio data collection and text conversion

[1058] When a user starts a meeting or call, the device records the audio and sends the audio data to a server in real time. The server then converts the received audio data into text using a speech recognition API such as Google Cloud Speech-to-Text API. This text data is later saved as meeting minutes and serves as the basis for analysis.

[1059] Task Generation and Classification

[1060] The server analyzes the text data generated from the voice data using natural language processing algorithms (e.g., spaCy or NLTK). This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[1061] Task assignment

[1062] The server assigns the classified tasks to the appropriate person in charge. The assigned tasks are notified to the user's device via email or push notification to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools (e.g., Trello or Asana) or personal task management tools (e.g., Todoist).

[1063] Task progress management and deadline advance notifications

[1064] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[1065] Adding specific examples

[1066] Meeting Scenarios

[1067] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[1068] User A: We need to decide on a release plan for a new product.

[1069] User B: Let's complete the market research by next week.

[1070] User A: You should also start preparing your marketing materials.

[1071] The server extracts and classifies the following tasks from this text data:

[1072] User A: Determine release plan

[1073] User B: Market research completed

[1074] Artificial Intelligence: Data collection for marketing materials

[1075] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[1076] Example prompts for the generative AI model to use

[1077] Below are some example prompts to input to a generative AI model (e.g., GPT-4):

[1078] Analyze the text data generated from the following meeting recording, extract tasks from important discussions and decisions, and assign them to the appropriate people.

[1079] User A: We need to decide on a release plan for a new product.

[1080] User B: Let's complete the market research by next week.

[1081] User A: You should also start preparing your marketing materials.

[1082] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1083] Step 1: Collecting and transmitting audio data in real time

[1084] When a user starts a meeting or call, the device records the audio. The recording is done in real time and the audio data is sent to a server via the Internet. Specifically, a dedicated app on the device captures the user's voice with a microphone and instantly streams it to the server. The input here is the user's voice, and the output is the raw audio data sent to the server.

[1085] Step 2: Convert audio data to text

[1086] The server converts the received voice data into text data using a voice recognition API (for example, Google Cloud Speech-to-Text API). At this time, the voice recognition API analyzes the voice and performs the optimal text conversion using the language model of the voice data. Specifically, the server sends the voice data to the API and receives it as text data. The input is the received voice data, and the output is the converted text data.

[1087] Step 3: Analyzing text data and extracting tasks

[1088] The server analyzes the converted text data using natural language processing algorithms (e.g., spaCy or NLTK). In this process, important discussions and decisions in the text are identified and extracted as tasks. Specifically, the server begins text analysis and generates tasks based on specific keywords and phrases. The input is the text data, and the output is a list of tasks to be assigned to users or artificial intelligence.

[1089] Step 4: Categorize your tasks

[1090] The extracted tasks are classified by the server into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the task content and keywords. Specifically, the server analyzes the task content and applies an appropriate classification algorithm. The input is a list of extracted tasks, and the output is a classified task list.

[1091] Step 5: Assign tasks

[1092] The server assigns the classified tasks to the appropriate person in charge. The results of the task assignment are notified to the user's device. Specifically, the server calls the API of the task management tool to register the task and sends an email or push notification to the person in charge. The input is the classified task list, and the output is a task assignment notification.

[1093] Step 6: Track your progress and receive reminders

[1094] The server synchronizes data with the project management tool and monitors the progress of tasks. If progress is behind schedule or the deadline is approaching, it sends reminder notifications to the user. Specifically, the server periodically obtains progress data and sends reminder notifications if there is a problem. The input is task progress data, and the output is reminder notifications to the user.

[1095] Each of the above steps will ensure that the overall system functions effectively, improving the efficiency and accuracy of project management.

[1096] (Application example 1)

[1097] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1098] In modern factories, maintenance and quality control tasks are becoming increasingly complex, requiring efficient management. In particular, accurate instruction transmission and task assignment are essential for workers to respond quickly on-site. However, manual task assignment and management takes time, potentially resulting in reduced work efficiency and task delays. Furthermore, even when using robots, the lack of a system that can accurately interpret voice instructions and appropriately assign tasks remains an issue.

[1099] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1100] In this invention, the server includes: means for collecting voice data from conferences and calls and converting the voice data into text data; means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, notifying users before their deadlines, and reassigning tasks as necessary; and means for providing voice instructions from a worker to a robot in factory maintenance work and quality control, analyzing the instructions, generating tasks, and automatically assigning them to the robot and the worker. This enables efficient task assignment and progress management in factory maintenance work and quality control operations.

[1101] "Voice data" refers to raw voice information collected during meetings, phone calls, etc.

[1102] "Text data" is voice data converted into character information.

[1103] "Analysis" refers to the process of analyzing text data to derive meaning.

[1104] A "task" is a specific item that directs a particular activity or work.

[1105] Tasks performed by "people" are tasks that need to be performed by humans, such as workers or managers.

[1106] Tasks performed by "artificial intelligence" are tasks that can be performed by robots or AI systems.

[1107] "Classification" is the process of determining whether a task extracted from text data will be performed by a "person" or by "artificial intelligence."

[1108] "Responsible Person" refers to a person or system that is responsible for performing a specific task.

[1109] A "project management tool" is software or a system that allows you to centrally manage project progress and tasks.

[1110] A "personal task management tool" is software or a system that allows individual users to manage their own tasks.

[1111] "Progress management" is the process of monitoring whether tasks are progressing as planned and taking necessary actions.

[1112] "Pre-deadline notification" is a notification to inform the person in charge that the deadline for a task is approaching.

[1113] "Reassignment" is the process of changing the person responsible for or the deadline for an originally assigned task.

[1114] "Factory maintenance work" refers to a series of tasks performed to maintain factory facilities and equipment.

[1115] "Quality control" refers to the monitoring and control processes used to ensure the quality of products and services.

[1116] "Voice instructions" refers to verbal instructions given by the worker to the robot.

[1117] "Real-time" means processing immediately without delay.

[1118] System Overview

[1119] The system of the present invention is designed to improve the efficiency of maintenance work and quality control in factories. The main functions of the system are to collect voice data and convert it into text, generate and classify tasks, assign tasks, register tasks in project management tools and personal task management tools, manage task progress, and notify users before deadlines. Specific methods for realizing these functions are described below.

[1120] Program processing

[1121] 1. Collecting voice data and converting it to text

[1122] When performing maintenance or quality control tasks in a factory, workers give voice instructions to the robot. These voice instructions are collected through a microphone installed on the robot. The voice data is sent in real time to a server, which then converts the voice data into text data using the Google Cloud Speech-to-Text API. This text data is then used as the basis for subsequent analysis and task generation.

[1123] 2. Task Generation and Classification

[1124] The server analyzes the text data generated from the voice data using the Google Cloud Natural Language API. Through this process, tasks are automatically extracted from important instructions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[1125] 3. Task assignment

[1126] The server automatically assigns the classified tasks to the appropriate person (worker or robot). Tasks assigned to users are notified to the users' devices via email or push notification. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[1127] 4. Task progress management and deadline notifications

[1128] The server periodically monitors the progress of the task. If progress is slow or the deadline is approaching, the server sends a reminder to the user, allowing the user to take appropriate action to complete the task on time. If necessary, the server also reassigns the task's assignee and deadline.

[1129] Specific examples

[1130] Maintenance Scenarios

[1131] Consider a situation where Worker A is performing maintenance work in a factory and needs to give instructions to a robot:

[1132] Worker A: The following line needs to be cleaned.

[1133] Worker B: Let's check all the parts and make sure there are no abnormalities.

[1134] The robot collects this voice data and sends it to the server, which then uses a speech recognition API to generate text data like this:

[1135] Worker A: The following line needs to be cleaned.

[1136] Worker B: Let's check all the parts and make sure there are no abnormalities.

[1137] The server extracts and classifies the following tasks from this text data:

[1138] Worker tasks:

[1139] Worker A: Cleaning the line

[1140] Worker B: Inspection and confirmation of parts

[1141] Robot Task:

[1142] Robot: Collects monitoring data of cleaning operations and sends it to the quality control department

[1143] These tasks are automatically assigned to each worker and robot by the server and registered in project management tools and personal task management tools.

[1144] Prompt Sentence Examples

[1145] Voice recognition result:

[1146] Worker A: The following line needs to be cleaned.

[1147] Worker B: Let's check all the parts and make sure there are no abnormalities.

[1148] Task creation:

[1149] Assign the task of "line cleaning work" to worker A.

[1150] Assign the task of "Inspect and check parts" to worker B.

[1151] The robot is assigned the task of "collecting monitoring data of the cleaning work and sending it to the quality control department."

[1152] This will automate and streamline maintenance and quality control work within factories, enabling workers and robots to work together to smoothly carry out tasks.

[1153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1154] Step 1:

[1155] When a user performs maintenance or quality control work in a factory, the worker gives voice instructions to the robot. A microphone installed on the robot's terminal collects these voice instructions. The input is the worker's voice data, and the output is the voice data collected by the robot's terminal.

[1156] Step 2:

[1157] The device sends the collected voice data to the server in real time, and the server converts the voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is text data.

[1158] Step 3:

[1159] The server analyzes the converted text data using the Google Cloud Natural Language API. This analysis extracts important instructions and decisions from the text. The input is the text data, and the output is the extracted instructions and decisions.

[1160] Step 4:

[1161] The server generates tasks from the analysis results and classifies them into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." The input is the extracted instructions and decisions, and the output is the classified tasks.

[1162] Step 5:

[1163] The server automatically assigns the classified tasks to the appropriate personnel (workers or robots). The input is the classified tasks, and the output is the tasks assigned to each personnel.

[1164] Step 6:

[1165] The server registers the assigned tasks in the project management tool and the personal task management tool. The input is the tasks assigned to the person in charge, and the output is the tasks registered in the management tool.

[1166] Step 7:

[1167] The server periodically monitors the progress of tasks and sends reminder notifications when progress is behind or the deadline is approaching. The input is the progress of tasks registered in the management tool, and the output is reminder notifications.

[1168] Step 8:

[1169] If necessary, the server reassigns task owners and deadlines. The input is tasks that are behind schedule or approaching deadlines, and the output is the reassigned tasks.

[1170] Through the above processing steps, the system is able to efficiently manage and carry out maintenance and quality control work within the factory.

[1171] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1172] System Overview

[1173] This invention aims to improve the efficiency of task management in project management, and by combining it with an emotion engine, it is possible to understand the user's emotions and adjust task priorities and notification timing. The system includes the following main components:

[1174] 1. Collecting voice data and converting it to text

[1175] 2. Task Generation and Classification

[1176] 3. Task assignment

[1177] 4. Task progress management and deadline notifications

[1178] 5. Emotion Recognition Engine and Emotion-Based Adjustments

[1179] Program processing

[1180] Audio data collection and text conversion

[1181] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server converts the audio data into text data using a speech recognition API and generates minutes. The text data is then used for task generation and emotion recognition.

[1182] Task Generation and Classification

[1183] The server analyzes the generated text data using natural language processing algorithms and extracts tasks from key points of discussion and decisions. The extracted tasks are then classified into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on content and keywords.

[1184] Task assignment

[1185] The server assigns the classified tasks to the appropriate person. The assigned tasks are notified to the user via their device. Notification methods include email and push notifications. Tasks are also automatically registered in project management tools and personal task management tools.

[1186] Task progress management and deadline advance notifications

[1187] The server periodically monitors the progress of tasks, and if progress is delayed or the deadline is approaching, it sends reminder notifications to the user, and if necessary, reassigns task owners and deadlines.

[1188] Emotion recognition engine and emotion-based adjustments

[1189] The server is equipped with an emotion engine that recognizes the user's emotions from voice data. The emotion engine identifies the user's emotions by analyzing the tone of the voice and the choice of words. This emotion data is used to adjust task priorities and notification timing.

[1190] For example, if a user is feeling anxious or stressed, the system can lower the priority of the task for that user. Furthermore, based on emotion recognition, the system can send reminders during times when the user is relaxed, promoting efficient task execution.

[1191] Specific examples

[1192] Meeting Scenarios

[1193] User A and User B hold an online conference and record the audio data. The device sends the audio data to the server, which then generates the following text data through a speech recognition API:

[1194] User A: We need to decide on a release plan for our new product.

[1195] User B: Let's complete the market research by next week.

[1196] User A: You should also start preparing your marketing materials.

[1197] The server extracts and classifies the following tasks from the generated text data:

[1198] User A: Determine release plan

[1199] User B: Completes market research

[1200] Artificial Intelligence: Data Collection for Marketing Materials

[1201] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reallocate the task of creating marketing materials to an artificial intelligence.

[1202] The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and timely reminders are sent when deadlines approach. This process streamlines project management and ensures that tasks are completed without omission.

[1203] This invention allows users to keep track of task progress and improve overall project performance in an emotionally sensitive manner.

[1204] The processing flow will be explained below.

[1205] Step 1:

[1206] A user initiates a meeting or call. The device records the conversation in real time and sends the audio data to a server, where it is converted into a digital format and processed.

[1207] Step 2:

[1208] The server converts the received voice data into text data using a voice recognition API. Through this process, text information is automatically generated from the voice.

[1209] Step 3:

[1210] The server analyzes the text data and generates meeting minutes, which are stored in a database and serve as the basis for future task generation and emotion recognition.

[1211] Step 4:

[1212] The server analyzes the stored text data using natural language processing algorithms to extract tasks from key points and decisions during discussions. This analysis includes keyword extraction and contextual analysis.

[1213] Step 5:

[1214] The server classifies the extracted tasks into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on the task content and keywords, and the appropriate person in charge is selected.

[1215] Step 6:

[1216] The emotion engine analyzes the voice data to recognize the user's emotions. The emotion engine analyzes the voice tone and word choice to identify the type of emotion (e.g., stress, anxiety, joy).

[1217] Step 7:

[1218] The server adjusts the priority and placement of tasks based on information from the emotion engine. For example, if the user's emotions indicate stress, it temporarily lowers the priority of urgent tasks.

[1219] Step 8:

[1220] The server assigns the task to the appropriate person, who is then notified of the assigned task via email or push notification.

[1221] Step 9:

[1222] The server automatically registers tasks in project management tools and personal task management tools, allowing the person in charge to check the task content and deadlines.

[1223] Step 10:

[1224] The server periodically monitors the progress of the task and sends reminders when progress is behind or the deadline is approaching. The timing of the reminders is adjusted based on the user's emotional state.

[1225] Step 11:

[1226] The server reassigns tasks as needed. If a task is delayed or needs to be reassigned, a reassignment process is initiated. This process also takes into account the user's emotional state.

[1227] Through this process, the system can understand the user's emotions, improve task management efficiency, and improve overall project performance.

[1228] Example 2

[1229] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1230] Conventional project management systems lack the ability to efficiently manage tasks generated during meetings or phone calls, track progress, and adjust tasks based on user emotions. This can lead to missed tasks and delays in progress, resulting in a decline in overall project performance. There is also the risk that users may feel excessive stress, further reducing productivity. The present invention aims to solve these problems.

[1231] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1232] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to an appropriate person, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, notifying the user before their deadline, and reassigning tasks as necessary, and means for recognizing the user's emotions from the voice data and adjusting task priorities and notification timings based on the emotion data. This enables efficient management of tasks generated during conferences and calls, understanding the progress, and adjusting tasks based on the user's emotions.

[1233] "Voice data" refers to voice information collected during a conference or call, and is data that is converted into text data.

[1234] "Text data" refers to data that has been converted from voice data into text information using voice recognition technology.

[1235] A "task" refers to a work item or instruction generated during a meeting or call, and is a unit of action to be carried out.

[1236] A "natural language processing algorithm" is a language analysis technology that analyzes text data and generates and classifies tasks.

[1237] A "personnel" is a person or artificial intelligence assigned to carry out the generated task.

[1238] "Project management tool" refers to software or a system for tracking project progress and scheduling tasks.

[1239] "Personal task management tool" refers to software or a system that allows individuals to record, manage, and prioritize their tasks.

[1240] "Progress management" is the process of monitoring the status of task implementation and understanding the degree of progress.

[1241] "Pre-deadline notification" is a notification to remind the person in charge when the deadline for a task is approaching.

[1242] "Emotion recognition" is a technology that analyzes and identifies a user's emotions from voice data.

[1243] "Emotion data" refers to information about a user's emotional state extracted using emotion recognition technology.

[1244] "Priority adjustment" is the process of changing the importance and execution order of tasks based on emotional data.

[1245] "Adjusting notification timing" is the process of determining the optimal timing for sending notifications about a task based on emotion data.

[1246] MODE FOR CARRYING OUT THE INVENTION

[1247] This invention aims to efficiently manage tasks created during meetings and phone calls by converting voice data into text data, analyzing it to create tasks, assigning them to people in charge, and managing their progress. It also includes a function to recognize the user's emotions and adjust task priorities and notification timings based on those emotions.

[1248] The system includes the following major hardware and software components:

[1249] Terminal: Equipped with a microphone for recording audio data and a communication module for transmitting audio data to a server in real time.

[1250] Server: A speech recognition API (e.g., Google Cloud Speech-to-Text API) that converts voice data into text data, and software for converting the data into a different format.

[1251] Natural language processing algorithms (e.g., BERT model): Algorithms that analyze generated text data, generate tasks, and appropriately classify them.

[1252] Emotion recognition engine (e.g., IBM Watson Tone Analyzer): An engine for recognizing user emotions from voice data and generating emotion data.

[1253] Project management tools (e.g., JIRA) and personal task management tools (e.g., Todoist): software for managing tasks and tracking progress.

[1254] When a user starts a meeting or call, the device records the voice data and sends it to the server in real time. The server then uses a speech recognition API to convert the voice data into text data. It then analyzes the text data using a natural language processing algorithm to extract and classify tasks. The server then assigns the generated tasks to the appropriate person and automatically registers them in project management tools and personal task management tools.

[1255] The server periodically monitors task progress and sends reminder notifications if progress is behind or the deadline is approaching. Furthermore, it recognizes the user's emotions from voice data and adjusts task priority and notification timing based on that emotion data. For example, if the user is feeling stressed, it lowers the priority of the task and sends reminder notifications during times when the user is relaxed, promoting efficient task execution.

[1256] Specific examples

[1257] For example, user A and user B hold an online conference and record the audio data. The device sends the audio data to the server, and the server generates the following text data through a speech recognition API:

[1258] User A: We need to decide on a release plan for our new product.

[1259] User B: Let's complete the market research by next week.

[1260] User A: You should also start preparing your marketing materials.

[1261] The server extracts and classifies the following tasks from the generated text data:

[1262] User A: Determine release plan

[1263] User B: Completes market research

[1264] Artificial Intelligence: Data Collection for Marketing Materials

[1265] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reassign the task of creating marketing materials to an artificial intelligence. The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and reminders are sent at the appropriate time when deadlines are approaching. This series of processes streamlines project management and ensures that tasks are completed without any omissions.

[1266] Prompt Sentence Examples

[1267] "Extract tasks from the meeting contents of user A and user B, and adjust the priority of the tasks based on user B's feelings."

[1268] By inputting this prompt into a generative AI model, it can help extract specific tasks and adjust priorities.

[1269] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1270] Program processing flow

[1271] Audio data collection and text conversion

[1272] Step 1:

[1273] Terminal: When a user starts a conference, the terminal's audio recording function is activated to capture audio data in real time.

[1274] Input: Voice of the user in the meeting

[1275] Specific operation: Records audio through the device's microphone and saves it as audio data.

[1276] Output: Real-time recorded audio data

[1277] Step 2:

[1278] Terminal: Recorded audio data is sent to the server in real time.

[1279] Input: Recorded audio data

[1280] Specific operation: The device transmits voice data to the server using Wi-Fi or mobile data.

[1281] Output: Audio data sent to the server

[1282] Step 3:

[1283] Server: Convert the received voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text API).

[1284] Input: Audio data

[1285] Specific operation: Calls the speech recognition API and converts the speech data into text format.

[1286] Output: Generated text data

[1287] Task Generation and Classification

[1288] Step 4:

[1289] Server: Analyze the generated text data using a natural language processing algorithm (e.g., the BERT model).

[1290] Input: Text data

[1291] What it does: Runs natural language processing algorithms to analyze text data and extract important keywords and phrases.

[1292] Output: Keywords and phrases from the parsed text data

[1293] Step 5:

[1294] Server: Extracts tasks from the analysis results and classifies them into "tasks to be performed by humans" and "tasks to be performed by AI."

[1295] Input: Keywords and phrases

[1296] Specific actions: Identify tasks based on keywords and phrases and divide them into "tasks to be performed by humans" and "tasks to be performed by AI."

[1297] Output: Categorized tasks

[1298] Task assignment

[1299] Step 6:

[1300] Server: Assigns the extracted tasks to the appropriate person.

[1301] Input: Categorized tasks

[1302] What it does: Assign tasks to the right people based on project progress and their skill sets.

[1303] Output: Tasks assigned to assignees

[1304] Step 7:

[1305] Server: Sends a notification to the task assignee.

[1306] Input: Tasks assigned to assignees

[1307] What it does: Send task details to assignees via email and / or push notification.

[1308] Output: Notification sent to assignee

[1309] Step 8:

[1310] Server: Automatically registers tasks in project management tools and personal task management tools.

[1311] Input: Tasks assigned to assignees

[1312] Specific operation: Register tasks using each tool's API and manage task schedules.

[1313] Output: Tasks registered with the tool

[1314] Task progress management and deadline advance notifications

[1315] Step 9:

[1316] Server: Periodically monitors the progress of the task.

[1317] Input: Progress data of tasks registered in the tool

[1318] Specific operation: Collect progress information entered by the person in charge into the task management tool and analyze it in real time.

[1319] Output: Progress monitoring results

[1320] Step 10:

[1321] Server: Send reminders when progress is behind or deadlines are approaching.

[1322] Input: Progress monitoring results

[1323] Specific behavior: If progress does not meet certain criteria, a reminder message will be sent to the person in charge via email or push notification.

[1324] Output: Reminder notifications sent

[1325] Step 11:

[1326] Server: Reassign task owners and due dates as needed.

[1327] Input: Progress monitoring results and responses to reminder notifications

[1328] Specific behavior: Change task assignees and adjust deadlines depending on the project situation.

[1329] Output: Reassigned tasks

[1330] Emotion recognition engine and emotion-based adjustments

[1331] Step 12:

[1332] Server: Uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize user emotions from voice data.

[1333] Input: Audio data

[1334] What it does: It uses an emotion recognition engine to analyze voice data and identify the user's emotional state.

[1335] Output: User emotion data

[1336] Step 13:

[1337] Server: Adjust task priorities and notification timing based on emotional data.

[1338] Input: User emotion data

[1339] Specific operation: Optimize task execution order and notification timing based on emotional data. For example, lower the priority of tasks for users who are feeling stressed and notify them during times when they are relaxed.

[1340] Output: Adjusted task priority and notification timing

[1341] (Application example 2)

[1342] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1343] Autonomous vehicle operation managers must efficiently manage a variety of tasks, particularly the content of meetings and phone calls, and assign them appropriately. Furthermore, systems are needed to optimize task priorities and facilitate smooth operation management by taking into account the emotions and stress levels of operation managers. However, current systems have difficulty meeting these requirements, resulting in inefficient task management and assignment, and a consequent decline in the overall efficiency of operation management.

[1344] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1345] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to appropriate personnel, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, providing advance notices of deadlines, and reassigning tasks as necessary, means for recognizing emotions from the voice data and adjusting task priorities based on the emotions, and means for adjusting the timing of task reminder notifications based on the emotion recognition. This enables operations managers to efficiently manage tasks while taking emotions and stress levels into consideration, thereby enabling smooth operation of autonomous vehicles.

[1346] "Audio data" is digital or analog data that records sound waves generated during meetings, telephone calls, etc.

[1347] "Text data" is character information converted from voice data, and is data that expresses the content of a speech as a string of characters.

[1348] A "task" is a set of tasks or activities that must be performed to achieve a specific goal, and can be performed by a human or artificial intelligence.

[1349] A "natural language processing algorithm" is an algorithm that analyzes text data and understands its meaning and context, and is a technology used to generate tasks.

[1350] "Emotion recognition" is a technology that identifies and identifies a person's emotional state from voice data, facial expressions, etc.

[1351] "Priority" refers to the criteria for evaluating and sorting the order and importance of tasks or work.

[1352] "Reminder notification" is a feature that notifies users again when a specific task or deadline is approaching.

[1353] A "project management tool" refers to software or a system that helps effectively manage multiple tasks or projects.

[1354] "Personal task management tool" refers to software or systems used by individuals to manage their daily tasks and schedules.

[1355] "Artificial intelligence" refers to the technology and systems that allow computers to perform intellectual tasks that humans perform.

[1356] The present invention provides a system for enabling an autonomous vehicle operation manager to efficiently manage tasks. The system includes multiple means, including voice data collection and text conversion, task generation and classification, and emotion recognition. Specific embodiments will be described below.

[1357] Hardware and Software Use

[1358] Hardware

[1359] Smartphones: Used to collect and record audio data.

[1360] Server: Performs the main processing of voice-to-text conversion, emotion recognition, and task management.

[1361] software

[1362] Google Cloud Speech-to-Text API: Used to convert audio data into text data.

[1363] Natural language processing algorithms (e.g., NLTK): Analyze text data and generate tasks.

[1364] Emotion Recognition API: Used to recognize emotions from audio data.

[1365] Project management tool and personal task management tool: Register tasks and track progress.

[1366] Data processing and calculation

[1367] 1. Audio data collection and text conversion:

[1368] Users can record audio data from meetings or phone calls using the microphone on their smartphone, and the recorded audio data is immediately sent to the server.

[1369] The server uses the Google Cloud Speech-to-Text API to convert voice data into text data in real time.

[1370] 2. Task generation and classification:

[1371] The server uses natural language processing algorithms to analyze the generated text data and extract tasks from key information and decisions.

[1372] The extracted tasks are classified into tasks performed by "people" and tasks performed by "artificial intelligence."

[1373] For example, if the text data contains the phrase "Complete market research," the task will be classified as being performed by a human.

[1374] 3. Priority adjustment through emotion recognition:

[1375] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data. If the user is feeling stressed, the priority of the task for that user will be lowered.

[1376] For example, if emotions such as "anxiety" or "stress" are detected, the task's priority will be set low and the timing of reminder notifications for other tasks will be adjusted.

[1377] Example scenario

[1378] User A and User B hold an online conference and record the audio data. The device (smartphone) sends the audio data to the server, which then generates the following text data via the Google Cloud Speech-to-Text API:

[1379] User A: We need to decide on a release plan for our new product.

[1380] User B: Let's complete our market research.

[1381] User A: You should also start preparing your marketing materials.

[1382] The server extracts and classifies the following tasks from this text data:

[1383] User A: Determine release plan

[1384] User B: Completes market research

[1385] Artificial Intelligence: Data Collection for Marketing Materials

[1386] Furthermore, if the emotion engine senses stress from User B's voice, it will adjust task priorities and reallocate the task of creating marketing materials to the AI. Through this series of processes, the operation manager can efficiently manage tasks while taking into account emotions and stress levels, ensuring the smooth operation of autonomous vehicles.

[1387] Prompt Sentence Examples

[1388] "Generate tasks for the user based on the following audio data and notify them based on that. If possible, recognize the user's emotions and adjust the priority of the tasks."

[1389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1390] Step 1:

[1391] Collection and transmission of voice data

[1392] The user uses the microphone on their smartphone to record audio data from a meeting or call. Once the recording is complete, the device transmits the audio data to a server in real time.

[1393] Input: Audio data from meetings and calls

[1394] Data processing: Digital conversion and streaming of audio data

[1395] Output: Audio data sent to the server

[1396] Step 2:

[1397] Converting audio data to text data

[1398] The server converts the audio data into text using the Google Cloud Speech-to-Text API, which parses the audio data and generates a string of output.

[1399] Input: Audio data sent to the server

[1400] Data Calculation: Speech Recognition and Text Conversion

[1401] Output: Text data

[1402] Step 3:

[1403] Analyzing text data and extracting tasks

[1404] The server uses natural language processing algorithms (e.g., NLTK) to analyze the text data and automatically extract tasks based on key information and decisions.

[1405] Input: Text data

[1406] Data Computing: Information Extraction through Natural Language Processing

[1407] Output: Extracted tasks

[1408] Step 4:

[1409] Task Classification

[1410] The extracted tasks are classified as either performed by a human or by an artificial intelligence. For example, a task such as "Complete market research" is classified as a task performed by a human.

[1411] Input: Extracted tasks

[1412] Data calculation: Task classification (keyword matching, etc.)

[1413] Output: Categorized tasks

[1414] Step 5:

[1415] Emotion recognition

[1416] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data, and the recognized emotion data is used for subsequent task management.

[1417] Input: Audio data

[1418] Data arithmetic: Analysis by emotion recognition algorithms

[1419] Output: Emotion data

[1420] Step 6:

[1421] Adjusting task priorities

[1422] The server adjusts task priorities based on the perceived user emotion, for example, if the user is feeling stressed, it lowers the priority of the tasks for that user.

[1423] Input: Emotion data, classification task

[1424] Data arithmetic: Priority adjustment based on emotional data

[1425] Output: Tasks with adjusted priorities

[1426] Step 7:

[1427] Task assignment and notifications

[1428] The server assigns the prioritized tasks to the appropriate person, automatically registers them in project management tools and personal task management tools, and notifies the user via email and push notifications.

[1429] Input: Priority adjusted tasks

[1430] Data calculation: task allocation and registration with tools, notification generation

[1431] Output: Assigned tasks and notifications

[1432] Step 8:

[1433] Progress management and reminders

[1434] The server periodically monitors the progress of tasks, sending reminders if progress is falling behind or deadlines are approaching, and reassigning tasks as necessary.

[1435] Input: Assigned Tasks

[1436] Data calculation: Progress management, reassignment of deadlines, and generation of reminder notifications

[1437] Output: Reminders and reassigned tasks

[1438] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1439] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1440] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1441] [Fourth embodiment]

[1442] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1443] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1444] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1445] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1446] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1447] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1448] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1449] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1450] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1451] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1452] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1453] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1454] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1455] System Overview

[1456] This system aims to improve the efficiency of task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[1457] 1. Collecting voice data and converting it to text

[1458] 2. Task Generation and Classification

[1459] 3. Task assignment

[1460] 4. Task progress management and deadline notifications

[1461] Program processing

[1462] Audio data collection and text conversion

[1463] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server then converts the received audio data into text data using a speech recognition API. This text data is later saved as minutes and serves as the basis for analysis.

[1464] Task Generation and Classification

[1465] The server uses natural language processing algorithms to analyze the text data generated from the voice data. This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[1466] Task assignment

[1467] The server assigns the classified tasks to the appropriate person in charge. Tasks assigned to users are notified to the users' devices via email or push notifications to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[1468] Task progress management and deadline advance notifications

[1469] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[1470] Specific examples

[1471] Meeting Scenarios

[1472] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[1473] User A: We need to decide on a release plan for a new product.

[1474] User B: Let's complete the market research by next week.

[1475] User A: You should also start preparing your marketing materials.

[1476] The server extracts and classifies the following tasks from this text data:

[1477] User A: Determine release plan

[1478] User B: Market research completed

[1479] Artificial Intelligence: Data collection for marketing materials

[1480] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[1481] This approach streamlines project management, ensures that no tasks are overlooked, and allows users to keep track of task progress, improving overall project performance.

[1482] The processing flow will be explained below.

[1483] Step 1:

[1484] A user starts a meeting or call. The device records the audio in real time and sends the audio data to the server, where it is converted into a digital format.

[1485] Step 2:

[1486] The server receives the voice data. The server then calls a speech recognition API to convert the received voice data into text data. This process uses natural language processing technology.

[1487] Step 3:

[1488] The server analyzes the generated text data and creates minutes, which are stored in a database and serve as the basis for subsequent task generation processes.

[1489] Step 4:

[1490] The server analyzes the text data of the minutes using natural language processing algorithms, and extracts tasks from important discussions and decisions.

[1491] Step 5:

[1492] The server classifies the extracted tasks into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[1493] Step 6:

[1494] The server assigns categorized tasks to appropriate personnel, and this assignment information is recorded in a database.

[1495] Step 7:

[1496] The device will send task notifications to the assignee via email and push notifications, ensuring that the assignee never misses a task.

[1497] Step 8:

[1498] The server automatically registers tasks in project management tools and personal task management tools using API calls.

[1499] Step 9:

[1500] The server periodically monitors the progress of tasks and sends reminders to the person in charge if progress is behind or the deadline is approaching.

[1501] Step 10:

[1502] The server will reassign tasks as needed. This happens if a task is delayed or needs to be reassigned.

[1503] Example 1

[1504] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1505] Task management in project management requires efficient progress and appropriate resource allocation, but there are challenges such as information leakage due to numerous meetings and calls, and difficulty in properly allocating tasks. Automation is also required to properly manage progress and send reminders, but traditional manual management takes time and effort and is prone to errors. A system is needed to solve these problems.

[1506] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1507] In this invention, the server includes: means for collecting voice data from meetings and calls and converting the voice data into text data; means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, providing advance notices, and reassigning tasks as necessary; a terminal for transmitting voice data to the server in real time; a server for converting voice data into text data using a voice recognition API; a natural language processing algorithm for analyzing the text data and extracting tasks; and means for monitoring the progress of tasks and sending reminder notifications. This improves the efficiency and accuracy of task management and enables appropriate progress management.

[1508] "Conference or call audio data" refers to data that includes all audio information generated during a conference or call.

[1509] "Text data" refers to data obtained by converting voice data into character information.

[1510] A "task" is a task or action item that needs to be done to achieve a specific purpose or goal.

[1511] "People" refers to actual people who use the system to perform tasks.

[1512] "Artificial intelligence" refers to computer programs and algorithms that partially or fully automate human tasks.

[1513] "Classifying" refers to the act of separating objects or information into groups based on specific criteria.

[1514] A "person in charge" is someone who is responsible for carrying out a particular task or work.

[1515] A "project management tool" is software that helps you plan projects, track progress, and communicate with team members.

[1516] A "personal task management tool" is software for managing personal tasks and schedules.

[1517] "Progress" refers to how far a task or project has progressed.

[1518] "Early Deadline Notifications" are reminders sent when a task deadline approaches.

[1519] "Reassignment" refers to the act of reassigning a task that has already been assigned to another person or resource.

[1520] "Terminal" refers to a device (e.g., PC, tablet, smartphone) that a user uses to access the system.

[1521] "Speech recognition API" refers to a program interface for analyzing voice input and converting it into text data.

[1522] "Natural language processing algorithms" refer to algorithms for understanding, analyzing, and generating human language.

[1523] A "reminding notification" is a notification that alerts the user to the progress of a task or a deadline.

[1524] System Overview

[1525] This system aims to streamline task management in project management. Specifically, it collects audio data from meetings and calls, converts that data into text data to generate meeting minutes, automatically generates tasks, assigns them to the appropriate person, and provides a series of functions to manage progress. The system includes the following main components:

[1526] 1. Collecting voice data and converting it to text

[1527] 2. Task Generation and Classification

[1528] 3. Task assignment

[1529] 4. Task progress management and deadline notifications

[1530] Audio data collection and text conversion

[1531] When a user starts a meeting or call, the device records the audio and sends the audio data to a server in real time. The server then converts the received audio data into text using a speech recognition API such as Google Cloud Speech-to-Text API. This text data is later saved as meeting minutes and serves as the basis for analysis.

[1532] Task Generation and Classification

[1533] The server analyzes the text data generated from the voice data using natural language processing algorithms (e.g., spaCy or NLTK). This process extracts tasks from important discussions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[1534] Task assignment

[1535] The server assigns the classified tasks to the appropriate person in charge. The assigned tasks are notified to the user's device via email or push notification to ensure that the person in charge does not miss the task. Furthermore, the server automatically registers these tasks in project management tools (e.g., Trello or Asana) or personal task management tools (e.g., Todoist).

[1536] Task progress management and deadline advance notifications

[1537] The server periodically monitors the progress of the task and sends reminders to the user if the progress is behind or the deadline is approaching, allowing the user to take appropriate action to complete the task within the deadline. If necessary, the server can also reassign the task's assignee and deadline.

[1538] Adding specific examples

[1539] Meeting Scenarios

[1540] User A and User B hold an online conference and record the contents of the conference. The devices send this audio data to the server, and the server generates the following text data through a speech recognition API:

[1541] User A: We need to decide on a release plan for a new product.

[1542] User B: Let's complete the market research by next week.

[1543] User A: You should also start preparing your marketing materials.

[1544] The server extracts and classifies the following tasks from this text data:

[1545] User A: Determine release plan

[1546] User B: Market research completed

[1547] Artificial Intelligence: Data collection for marketing materials

[1548] The server assigns these tasks to the respective people in charge and registers them in the task management tool. The progress of the tasks is monitored, and reminders are sent when the deadline approaches. For example, if the deadline for market research is approaching, a reminder is sent to User B.

[1549] Example prompts for the generative AI model to use

[1550] Below are some example prompts to input to a generative AI model (e.g., GPT-4):

[1551] Analyze the text data generated from the following meeting recording, extract tasks from important discussions and decisions, and assign them to the appropriate people.

[1552] User A: We need to decide on a release plan for a new product.

[1553] User B: Let's complete the market research by next week.

[1554] User A: You should also start preparing your marketing materials.

[1555] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1556] Step 1: Collecting and transmitting audio data in real time

[1557] When a user starts a meeting or call, the device records the audio. The recording is done in real time and the audio data is sent to a server via the Internet. Specifically, a dedicated app on the device captures the user's voice with a microphone and instantly streams it to the server. The input here is the user's voice, and the output is the raw audio data sent to the server.

[1558] Step 2: Convert audio data to text

[1559] The server converts the received voice data into text data using a voice recognition API (for example, Google Cloud Speech-to-Text API). At this time, the voice recognition API analyzes the voice and performs the optimal text conversion using the language model of the voice data. Specifically, the server sends the voice data to the API and receives it as text data. The input is the received voice data, and the output is the converted text data.

[1560] Step 3: Analyzing text data and extracting tasks

[1561] The server analyzes the converted text data using natural language processing algorithms (e.g., spaCy or NLTK). In this process, important discussions and decisions in the text are identified and extracted as tasks. Specifically, the server begins text analysis and generates tasks based on specific keywords and phrases. The input is the text data, and the output is a list of tasks to be assigned to users or artificial intelligence.

[1562] Step 4: Categorize your tasks

[1563] The extracted tasks are classified by the server into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the task content and keywords. Specifically, the server analyzes the task content and applies an appropriate classification algorithm. The input is a list of extracted tasks, and the output is a classified task list.

[1564] Step 5: Assign tasks

[1565] The server assigns the classified tasks to the appropriate person in charge. The results of the task assignment are notified to the user's device. Specifically, the server calls the API of the task management tool to register the task and sends an email or push notification to the person in charge. The input is the classified task list, and the output is a task assignment notification.

[1566] Step 6: Track your progress and receive reminders

[1567] The server synchronizes data with the project management tool and monitors the progress of tasks. If progress is behind schedule or the deadline is approaching, it sends reminder notifications to the user. Specifically, the server periodically obtains progress data and sends reminder notifications if there is a problem. The input is task progress data, and the output is reminder notifications to the user.

[1568] Each of the above steps will ensure that the overall system functions effectively, improving the efficiency and accuracy of project management.

[1569] (Application example 1)

[1570] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1571] In modern factories, maintenance and quality control tasks are becoming increasingly complex, requiring efficient management. In particular, accurate instruction transmission and task assignment are essential for workers to respond quickly on-site. However, manual task assignment and management takes time, potentially resulting in reduced work efficiency and task delays. Furthermore, even when using robots, the lack of a system that can accurately interpret voice instructions and appropriately assign tasks remains an issue.

[1572] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1573] In this invention, the server includes: means for collecting voice data from conferences and calls and converting the voice data into text data; means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence; means for assigning the classified tasks to an appropriate person; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, notifying users before their deadlines, and reassigning tasks as necessary; and means for providing voice instructions from a worker to a robot in factory maintenance work and quality control, analyzing the instructions, generating tasks, and automatically assigning them to the robot and the worker. This enables efficient task assignment and progress management in factory maintenance work and quality control operations.

[1574] "Voice data" refers to raw voice information collected during meetings, phone calls, etc.

[1575] "Text data" is voice data converted into character information.

[1576] "Analysis" refers to the process of analyzing text data to derive meaning.

[1577] A "task" is a specific item that directs a particular activity or work.

[1578] Tasks performed by "people" are tasks that need to be performed by humans, such as workers or managers.

[1579] Tasks performed by "artificial intelligence" are tasks that can be performed by robots or AI systems.

[1580] "Classification" is the process of determining whether a task extracted from text data will be performed by a "person" or by "artificial intelligence."

[1581] "Responsible Person" refers to a person or system that is responsible for performing a specific task.

[1582] A "project management tool" is software or a system that allows you to centrally manage project progress and tasks.

[1583] A "personal task management tool" is software or a system that allows individual users to manage their own tasks.

[1584] "Progress management" is the process of monitoring whether tasks are progressing as planned and taking necessary actions.

[1585] "Pre-deadline notification" is a notification to inform the person in charge that the deadline for a task is approaching.

[1586] "Reassignment" is the process of changing the person responsible for or the deadline for an originally assigned task.

[1587] "Factory maintenance work" refers to a series of tasks performed to maintain factory facilities and equipment.

[1588] "Quality control" refers to the monitoring and control processes used to ensure the quality of products and services.

[1589] "Voice instructions" refers to verbal instructions given by the worker to the robot.

[1590] "Real-time" means processing immediately without delay.

[1591] System Overview

[1592] The system of the present invention is designed to improve the efficiency of maintenance work and quality control in factories. The main functions of the system are to collect voice data and convert it into text, generate and classify tasks, assign tasks, register tasks in project management tools and personal task management tools, manage task progress, and notify users before deadlines. Specific methods for realizing these functions are described below.

[1593] Program processing

[1594] 1. Collecting voice data and converting it to text

[1595] When performing maintenance or quality control tasks in a factory, workers give voice instructions to the robot. These voice instructions are collected through a microphone installed on the robot. The voice data is sent in real time to a server, which then converts the voice data into text data using the Google Cloud Speech-to-Text API. This text data is then used as the basis for subsequent analysis and task generation.

[1596] 2. Task Generation and Classification

[1597] The server analyzes the text data generated from the voice data using the Google Cloud Natural Language API. Through this process, tasks are automatically extracted from important instructions and decisions in the text. The extracted tasks are then classified into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." This classification is based on the content and keywords of the tasks.

[1598] 3. Task assignment

[1599] The server automatically assigns the classified tasks to the appropriate person (worker or robot). Tasks assigned to users are notified to the users' devices via email or push notification. Furthermore, the server automatically registers these tasks in project management tools and personal task management tools.

[1600] 4. Task progress management and deadline notifications

[1601] The server periodically monitors the progress of the task. If progress is slow or the deadline is approaching, the server sends a reminder to the user, allowing the user to take appropriate action to complete the task on time. If necessary, the server also reassigns the task's assignee and deadline.

[1602] Specific examples

[1603] Maintenance Scenarios

[1604] Consider a situation where Worker A is performing maintenance work in a factory and needs to give instructions to a robot:

[1605] Worker A: The following line needs to be cleaned.

[1606] Worker B: Let's check all the parts and make sure there are no abnormalities.

[1607] The robot collects this voice data and sends it to the server, which then uses a speech recognition API to generate text data like this:

[1608] Worker A: The following line needs to be cleaned.

[1609] Worker B: Let's check all the parts and make sure there are no abnormalities.

[1610] The server extracts and classifies the following tasks from this text data:

[1611] Worker tasks:

[1612] Worker A: Cleaning the line

[1613] Worker B: Inspection and confirmation of parts

[1614] Robot Task:

[1615] Robot: Collects monitoring data of cleaning operations and sends it to the quality control department

[1616] These tasks are automatically assigned to each worker and robot by the server and registered in project management tools and personal task management tools.

[1617] Prompt Sentence Examples

[1618] Voice recognition result:

[1619] Worker A: The following line needs to be cleaned.

[1620] Worker B: Let's check all the parts and make sure there are no abnormalities.

[1621] Task creation:

[1622] Assign the task of "line cleaning work" to worker A.

[1623] Assign the task of "Inspect and check parts" to worker B.

[1624] The robot is assigned the task of "collecting monitoring data of the cleaning work and sending it to the quality control department."

[1625] This will automate and streamline maintenance and quality control work within factories, enabling workers and robots to work together to smoothly carry out tasks.

[1626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1627] Step 1:

[1628] When a user performs maintenance or quality control work in a factory, the worker gives voice instructions to the robot. A microphone installed on the robot's terminal collects these voice instructions. The input is the worker's voice data, and the output is the voice data collected by the robot's terminal.

[1629] Step 2:

[1630] The device sends the collected voice data to the server in real time, and the server converts the voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is text data.

[1631] Step 3:

[1632] The server analyzes the converted text data using the Google Cloud Natural Language API. This analysis extracts important instructions and decisions from the text. The input is the text data, and the output is the extracted instructions and decisions.

[1633] Step 4:

[1634] The server generates tasks from the analysis results and classifies them into tasks to be performed by "people" and tasks to be performed by "artificial intelligence." The input is the extracted instructions and decisions, and the output is the classified tasks.

[1635] Step 5:

[1636] The server automatically assigns the classified tasks to the appropriate personnel (workers or robots). The input is the classified tasks, and the output is the tasks assigned to each personnel.

[1637] Step 6:

[1638] The server registers the assigned tasks in the project management tool and the personal task management tool. The input is the tasks assigned to the person in charge, and the output is the tasks registered in the management tool.

[1639] Step 7:

[1640] The server periodically monitors the progress of tasks and sends reminder notifications when progress is behind or the deadline is approaching. The input is the progress of tasks registered in the management tool, and the output is reminder notifications.

[1641] Step 8:

[1642] If necessary, the server reassigns task owners and deadlines. The input is tasks that are behind schedule or approaching deadlines, and the output is the reassigned tasks.

[1643] Through the above processing steps, the system is able to efficiently manage and carry out maintenance and quality control work within the factory.

[1644] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1645] System Overview

[1646] This invention aims to improve the efficiency of task management in project management, and by combining it with an emotion engine, it is possible to understand the user's emotions and adjust task priorities and notification timing. The system includes the following main components:

[1647] 1. Collecting voice data and converting it to text

[1648] 2. Task Generation and Classification

[1649] 3. Task assignment

[1650] 4. Task progress management and deadline notifications

[1651] 5. Emotion Recognition Engine and Emotion-Based Adjustments

[1652] Program processing

[1653] Audio data collection and text conversion

[1654] When a user starts a meeting or call, the device records the audio and sends the audio data to the server in real time. The server converts the audio data into text data using a speech recognition API and generates minutes. The text data is then used for task generation and emotion recognition.

[1655] Task Generation and Classification

[1656] The server analyzes the generated text data using natural language processing algorithms and extracts tasks from key points of discussion and decisions. The extracted tasks are then classified into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on content and keywords.

[1657] Task assignment

[1658] The server assigns the classified tasks to the appropriate person. The assigned tasks are notified to the user via their device. Notification methods include email and push notifications. Tasks are also automatically registered in project management tools and personal task management tools.

[1659] Task progress management and deadline advance notifications

[1660] The server periodically monitors the progress of tasks, and if progress is delayed or the deadline is approaching, it sends reminder notifications to the user, and if necessary, reassigns task owners and deadlines.

[1661] Emotion recognition engine and emotion-based adjustments

[1662] The server is equipped with an emotion engine that recognizes the user's emotions from voice data. The emotion engine identifies the user's emotions by analyzing the tone of the voice and the choice of words. This emotion data is used to adjust task priorities and notification timing.

[1663] For example, if a user is feeling anxious or stressed, the system can lower the priority of the task for that user. Furthermore, based on emotion recognition, the system can send reminders during times when the user is relaxed, promoting efficient task execution.

[1664] Specific examples

[1665] Meeting Scenarios

[1666] User A and User B hold an online conference and record the audio data. The device sends the audio data to the server, which then generates the following text data through a speech recognition API:

[1667] User A: We need to decide on a release plan for our new product.

[1668] User B: Let's complete the market research by next week.

[1669] User A: You should also start preparing your marketing materials.

[1670] The server extracts and classifies the following tasks from the generated text data:

[1671] User A: Determine release plan

[1672] User B: Completes market research

[1673] Artificial Intelligence: Data Collection for Marketing Materials

[1674] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reallocate the task of creating marketing materials to an artificial intelligence.

[1675] The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and timely reminders are sent when deadlines approach. This process streamlines project management and ensures that tasks are completed without omission.

[1676] This invention allows users to keep track of task progress and improve overall project performance in an emotionally sensitive manner.

[1677] The processing flow will be explained below.

[1678] Step 1:

[1679] A user initiates a meeting or call. The device records the conversation in real time and sends the audio data to a server, where it is converted into a digital format and processed.

[1680] Step 2:

[1681] The server converts the received voice data into text data using a voice recognition API. Through this process, text information is automatically generated from the voice.

[1682] Step 3:

[1683] The server analyzes the text data and generates meeting minutes, which are stored in a database and serve as the basis for future task generation and emotion recognition.

[1684] Step 4:

[1685] The server analyzes the stored text data using natural language processing algorithms to extract tasks from key points and decisions during discussions. This analysis includes keyword extraction and contextual analysis.

[1686] Step 5:

[1687] The server classifies the extracted tasks into "tasks to be performed by humans" and "tasks to be performed by AI." This classification is based on the task content and keywords, and the appropriate person in charge is selected.

[1688] Step 6:

[1689] The emotion engine analyzes the voice data to recognize the user's emotions. The emotion engine analyzes the voice tone and word choice to identify the type of emotion (e.g., stress, anxiety, joy).

[1690] Step 7:

[1691] The server adjusts the priority and placement of tasks based on information from the emotion engine. For example, if the user's emotions indicate stress, it temporarily lowers the priority of urgent tasks.

[1692] Step 8:

[1693] The server assigns the task to the appropriate person, who is then notified of the assigned task via email or push notification.

[1694] Step 9:

[1695] The server automatically registers tasks in project management tools and personal task management tools, allowing the person in charge to check the task content and deadlines.

[1696] Step 10:

[1697] The server periodically monitors the progress of the task and sends reminders when progress is behind or the deadline is approaching. The timing of the reminders is adjusted based on the user's emotional state.

[1698] Step 11:

[1699] The server reassigns tasks as needed. If a task is delayed or needs to be reassigned, a reassignment process is initiated. This process also takes into account the user's emotional state.

[1700] Through this process, the system can understand the user's emotions, improve task management efficiency, and improve overall project performance.

[1701] Example 2

[1702] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1703] Conventional project management systems lack the ability to efficiently manage tasks generated during meetings or phone calls, track progress, and adjust tasks based on user emotions. This can lead to missed tasks and delays in progress, resulting in a decline in overall project performance. There is also the risk that users may feel excessive stress, further reducing productivity. The present invention aims to solve these problems.

[1704] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1705] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to an appropriate person, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, notifying the user before their deadline, and reassigning tasks as necessary, and means for recognizing the user's emotions from the voice data and adjusting task priorities and notification timings based on the emotion data. This enables efficient management of tasks generated during conferences and calls, understanding the progress, and adjusting tasks based on the user's emotions.

[1706] "Voice data" refers to voice information collected during a conference or call, and is data that is converted into text data.

[1707] "Text data" refers to data that has been converted from voice data into text information using voice recognition technology.

[1708] A "task" refers to a work item or instruction generated during a meeting or call, and is a unit of action to be carried out.

[1709] A "natural language processing algorithm" is a language analysis technology that analyzes text data and generates and classifies tasks.

[1710] A "personnel" is a person or artificial intelligence assigned to carry out the generated task.

[1711] "Project management tool" refers to software or a system for tracking project progress and scheduling tasks.

[1712] "Personal task management tool" refers to software or a system that allows individuals to record, manage, and prioritize their tasks.

[1713] "Progress management" is the process of monitoring the status of task implementation and understanding the degree of progress.

[1714] "Pre-deadline notification" is a notification to remind the person in charge when the deadline for a task is approaching.

[1715] "Emotion recognition" is a technology that analyzes and identifies a user's emotions from voice data.

[1716] "Emotion data" refers to information about a user's emotional state extracted using emotion recognition technology.

[1717] "Priority adjustment" is the process of changing the importance and execution order of tasks based on emotional data.

[1718] "Adjusting notification timing" is the process of determining the optimal timing for sending notifications about a task based on emotion data.

[1719] MODE FOR CARRYING OUT THE INVENTION

[1720] This invention aims to efficiently manage tasks created during meetings and phone calls by converting voice data into text data, analyzing it to create tasks, assigning them to people in charge, and managing their progress. It also includes a function to recognize the user's emotions and adjust task priorities and notification timings based on those emotions.

[1721] The system includes the following major hardware and software components:

[1722] Terminal: Equipped with a microphone for recording audio data and a communication module for transmitting audio data to a server in real time.

[1723] Server: A speech recognition API (e.g., Google Cloud Speech-to-Text API) that converts voice data into text data, and software for converting the data into a different format.

[1724] Natural language processing algorithms (e.g., BERT model): Algorithms that analyze generated text data, generate tasks, and appropriately classify them.

[1725] Emotion recognition engine (e.g., IBM Watson Tone Analyzer): An engine for recognizing user emotions from voice data and generating emotion data.

[1726] Project management tools (e.g., JIRA) and personal task management tools (e.g., Todoist): software for managing tasks and tracking progress.

[1727] When a user starts a meeting or call, the device records the voice data and sends it to the server in real time. The server then uses a speech recognition API to convert the voice data into text data. It then analyzes the text data using a natural language processing algorithm to extract and classify tasks. The server then assigns the generated tasks to the appropriate person and automatically registers them in project management tools and personal task management tools.

[1728] The server periodically monitors task progress and sends reminder notifications if progress is behind or the deadline is approaching. Furthermore, it recognizes the user's emotions from voice data and adjusts task priority and notification timing based on that emotion data. For example, if the user is feeling stressed, it lowers the priority of the task and sends reminder notifications during times when the user is relaxed, promoting efficient task execution.

[1729] Specific examples

[1730] For example, user A and user B hold an online conference and record the audio data. The device sends the audio data to the server, and the server generates the following text data through a speech recognition API:

[1731] User A: We need to decide on a release plan for our new product.

[1732] User B: Let's complete the market research by next week.

[1733] User A: You should also start preparing your marketing materials.

[1734] The server extracts and classifies the following tasks from the generated text data:

[1735] User A: Determine release plan

[1736] User B: Completes market research

[1737] Artificial Intelligence: Data Collection for Marketing Materials

[1738] Furthermore, if the emotion engine senses stress from User B's voice, it can adjust task priorities and reassign the task of creating marketing materials to an artificial intelligence. The server assigns tasks to each person in charge and registers them in the project management tool and personal task management tool. Task progress is monitored, and reminders are sent at the appropriate time when deadlines are approaching. This series of processes streamlines project management and ensures that tasks are completed without any omissions.

[1739] Prompt Sentence Examples

[1740] "Extract tasks from the meeting contents of user A and user B, and adjust the priority of the tasks based on user B's feelings."

[1741] By inputting this prompt into a generative AI model, it can help extract specific tasks and adjust priorities.

[1742] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1743] Program processing flow

[1744] Audio data collection and text conversion

[1745] Step 1:

[1746] Terminal: When a user starts a conference, the terminal's audio recording function is activated to capture audio data in real time.

[1747] Input: Voice of the user in the meeting

[1748] Specific operation: Records audio through the device's microphone and saves it as audio data.

[1749] Output: Real-time recorded audio data

[1750] Step 2:

[1751] Terminal: Recorded audio data is sent to the server in real time.

[1752] Input: Recorded audio data

[1753] Specific operation: The device transmits voice data to the server using Wi-Fi or mobile data.

[1754] Output: Audio data sent to the server

[1755] Step 3:

[1756] Server: Convert the received voice data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text API).

[1757] Input: Audio data

[1758] Specific operation: Calls the speech recognition API and converts the speech data into text format.

[1759] Output: Generated text data

[1760] Task Generation and Classification

[1761] Step 4:

[1762] Server: Analyze the generated text data using a natural language processing algorithm (e.g., the BERT model).

[1763] Input: Text data

[1764] What it does: Runs natural language processing algorithms to analyze text data and extract important keywords and phrases.

[1765] Output: Keywords and phrases from the parsed text data

[1766] Step 5:

[1767] Server: Extracts tasks from the analysis results and classifies them into "tasks to be performed by humans" and "tasks to be performed by AI."

[1768] Input: Keywords and phrases

[1769] Specific actions: Identify tasks based on keywords and phrases and divide them into "tasks to be performed by humans" and "tasks to be performed by AI."

[1770] Output: Categorized tasks

[1771] Task assignment

[1772] Step 6:

[1773] Server: Assigns the extracted tasks to the appropriate person.

[1774] Input: Categorized tasks

[1775] What it does: Assign tasks to the right people based on project progress and their skill sets.

[1776] Output: Tasks assigned to assignees

[1777] Step 7:

[1778] Server: Sends a notification to the task assignee.

[1779] Input: Tasks assigned to assignees

[1780] What it does: Send task details to assignees via email and / or push notification.

[1781] Output: Notification sent to assignee

[1782] Step 8:

[1783] Server: Automatically registers tasks in project management tools and personal task management tools.

[1784] Input: Tasks assigned to assignees

[1785] Specific operation: Register tasks using each tool's API and manage task schedules.

[1786] Output: Tasks registered with the tool

[1787] Task progress management and deadline advance notifications

[1788] Step 9:

[1789] Server: Periodically monitors the progress of the task.

[1790] Input: Progress data of tasks registered in the tool

[1791] Specific operation: Collect progress information entered by the person in charge into the task management tool and analyze it in real time.

[1792] Output: Progress monitoring results

[1793] Step 10:

[1794] Server: Send reminders when progress is behind or deadlines are approaching.

[1795] Input: Progress monitoring results

[1796] Specific behavior: If progress does not meet certain criteria, a reminder message will be sent to the person in charge via email or push notification.

[1797] Output: Reminder notifications sent

[1798] Step 11:

[1799] Server: Reassign task owners and due dates as needed.

[1800] Input: Progress monitoring results and responses to reminder notifications

[1801] Specific behavior: Change task assignees and adjust deadlines depending on the project situation.

[1802] Output: Reassigned tasks

[1803] Emotion recognition engine and emotion-based adjustments

[1804] Step 12:

[1805] Server: Uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize user emotions from voice data.

[1806] Input: Audio data

[1807] What it does: It uses an emotion recognition engine to analyze voice data and identify the user's emotional state.

[1808] Output: User emotion data

[1809] Step 13:

[1810] Server: Adjust task priorities and notification timing based on emotional data.

[1811] Input: User emotion data

[1812] Specific operation: Optimize task execution order and notification timing based on emotional data. For example, lower the priority of tasks for users who are feeling stressed and notify them during times when they are relaxed.

[1813] Output: Adjusted task priority and notification timing

[1814] (Application example 2)

[1815] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1816] Autonomous vehicle operation managers must efficiently manage a variety of tasks, particularly the content of meetings and phone calls, and assign them appropriately. Furthermore, systems are needed to optimize task priorities and facilitate smooth operation management by taking into account the emotions and stress levels of operation managers. However, current systems have difficulty meeting these requirements, resulting in inefficient task management and assignment, and a consequent decline in the overall efficiency of operation management.

[1817] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1818] In this invention, the server includes means for collecting voice data from conferences and calls and converting the voice data into text data, means for analyzing the text data to generate tasks and classifying the generated tasks as to whether they will be performed by a person or an artificial intelligence system, means for assigning the classified tasks to appropriate personnel, means for registering the assigned tasks in a project management tool and a personal task management tool, means for managing the progress of the tasks, providing advance notices of deadlines, and reassigning tasks as necessary, means for recognizing emotions from the voice data and adjusting task priorities based on the emotions, and means for adjusting the timing of task reminder notifications based on the emotion recognition. This enables operations managers to efficiently manage tasks while taking emotions and stress levels into consideration, thereby enabling smooth operation of autonomous vehicles.

[1819] "Audio data" is digital or analog data that records sound waves generated during meetings, telephone calls, etc.

[1820] "Text data" is character information converted from voice data, and is data that expresses the content of a speech as a string of characters.

[1821] A "task" is a set of tasks or activities that must be performed to achieve a specific goal, and can be performed by a human or artificial intelligence.

[1822] A "natural language processing algorithm" is an algorithm that analyzes text data and understands its meaning and context, and is a technology used to generate tasks.

[1823] "Emotion recognition" is a technology that identifies and identifies a person's emotional state from voice data, facial expressions, etc.

[1824] "Priority" refers to the criteria for evaluating and sorting the order and importance of tasks or work.

[1825] "Reminder notification" is a feature that notifies users again when a specific task or deadline is approaching.

[1826] A "project management tool" refers to software or a system that helps effectively manage multiple tasks or projects.

[1827] "Personal task management tool" refers to software or systems used by individuals to manage their daily tasks and schedules.

[1828] "Artificial intelligence" refers to the technology and systems that allow computers to perform intellectual tasks that humans perform.

[1829] The present invention provides a system for enabling an autonomous vehicle operation manager to efficiently manage tasks. The system includes multiple means, including voice data collection and text conversion, task generation and classification, and emotion recognition. Specific embodiments will be described below.

[1830] Hardware and Software Use

[1831] Hardware

[1832] Smartphones: Used to collect and record audio data.

[1833] Server: Performs the main processing of voice-to-text conversion, emotion recognition, and task management.

[1834] software

[1835] Google Cloud Speech-to-Text API: Used to convert audio data into text data.

[1836] Natural language processing algorithms (e.g., NLTK): Analyze text data and generate tasks.

[1837] Emotion Recognition API: Used to recognize emotions from audio data.

[1838] Project management tool and personal task management tool: Register tasks and track progress.

[1839] Data processing and calculation

[1840] 1. Audio data collection and text conversion:

[1841] Users can record audio data from meetings or phone calls using the microphone on their smartphone, and the recorded audio data is immediately sent to the server.

[1842] The server uses the Google Cloud Speech-to-Text API to convert voice data into text data in real time.

[1843] 2. Task generation and classification:

[1844] The server uses natural language processing algorithms to analyze the generated text data and extract tasks from key information and decisions.

[1845] The extracted tasks are classified into tasks performed by "people" and tasks performed by "artificial intelligence."

[1846] For example, if the text data contains the phrase "Complete market research," the task will be classified as being performed by a human.

[1847] 3. Priority adjustment through emotion recognition:

[1848] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data. If the user is feeling stressed, the priority of the task for that user will be lowered.

[1849] For example, if emotions such as "anxiety" or "stress" are detected, the task's priority will be set low and the timing of reminder notifications for other tasks will be adjusted.

[1850] Example scenario

[1851] User A and User B hold an online conference and record the audio data. The device (smartphone) sends the audio data to the server, which then generates the following text data via the Google Cloud Speech-to-Text API:

[1852] User A: We need to decide on a release plan for our new product.

[1853] User B: Let's complete our market research.

[1854] User A: You should also start preparing your marketing materials.

[1855] The server extracts and classifies the following tasks from this text data:

[1856] User A: Determine release plan

[1857] User B: Completes market research

[1858] Artificial Intelligence: Data Collection for Marketing Materials

[1859] Furthermore, if the emotion engine senses stress from User B's voice, it will adjust task priorities and reallocate the task of creating marketing materials to the AI. Through this series of processes, the operation manager can efficiently manage tasks while taking into account emotions and stress levels, ensuring the smooth operation of autonomous vehicles.

[1860] Prompt Sentence Examples

[1861] "Generate tasks for the user based on the following audio data and notify them based on that. If possible, recognize the user's emotions and adjust the priority of the tasks."

[1862] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1863] Step 1:

[1864] Collection and transmission of voice data

[1865] The user uses the microphone on their smartphone to record audio data from a meeting or call. Once the recording is complete, the device transmits the audio data to a server in real time.

[1866] Input: Audio data from meetings and calls

[1867] Data processing: Digital conversion and streaming of audio data

[1868] Output: Audio data sent to the server

[1869] Step 2:

[1870] Converting audio data to text data

[1871] The server converts the audio data into text using the Google Cloud Speech-to-Text API, which parses the audio data and generates a string of output.

[1872] Input: Audio data sent to the server

[1873] Data Calculation: Speech Recognition and Text Conversion

[1874] Output: Text data

[1875] Step 3:

[1876] Analyzing text data and extracting tasks

[1877] The server uses natural language processing algorithms (e.g., NLTK) to analyze the text data and automatically extract tasks based on key information and decisions.

[1878] Input: Text data

[1879] Data Computing: Information Extraction through Natural Language Processing

[1880] Output: Extracted tasks

[1881] Step 4:

[1882] Task Classification

[1883] The extracted tasks are classified as either performed by a human or by an artificial intelligence. For example, a task such as "Complete market research" is classified as a task performed by a human.

[1884] Input: Extracted tasks

[1885] Data calculation: Task classification (keyword matching, etc.)

[1886] Output: Categorized tasks

[1887] Step 5:

[1888] Emotion recognition

[1889] The server uses the Emotion Recognition API to recognize the user's emotions from the voice data, and the recognized emotion data is used for subsequent task management.

[1890] Input: Audio data

[1891] Data arithmetic: Analysis by emotion recognition algorithms

[1892] Output: Emotion data

[1893] Step 6:

[1894] Adjusting task priorities

[1895] The server adjusts task priorities based on the perceived user emotion, for example, if the user is feeling stressed, it lowers the priority of the tasks for that user.

[1896] Input: Emotion data, classification task

[1897] Data arithmetic: Priority adjustment based on emotional data

[1898] Output: Tasks with adjusted priorities

[1899] Step 7:

[1900] Task assignment and notifications

[1901] The server assigns the prioritized tasks to the appropriate person, automatically registers them in project management tools and personal task management tools, and notifies the user via email and push notifications.

[1902] Input: Priority adjusted tasks

[1903] Data calculation: task allocation and registration with tools, notification generation

[1904] Output: Assigned tasks and notifications

[1905] Step 8:

[1906] Progress management and reminders

[1907] The server periodically monitors the progress of tasks, sending reminders if progress is falling behind or deadlines are approaching, and reassigning tasks as necessary.

[1908] Input: Assigned Tasks

[1909] Data calculation: Progress management, reassignment of deadlines, and generation of reminder notifications

[1910] Output: Reminders and reassigned tasks

[1911] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1912] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1913] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1914] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1915] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1916] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1917] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1918] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1919] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1920] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1921] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1922] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1923] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1924] 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.

[1925] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1926] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1927] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1928] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1929] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1930] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1931] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1932] The following is further disclosed regarding the above embodiment.

[1933] (Claim 1)

[1934] A means for collecting audio data from meetings and calls and converting the audio data into text data;

[1935] means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a "person" or an "artificial intelligence";

[1936] means for assigning the classified tasks to appropriate personnel;

[1937] means for registering the assigned tasks in a project management tool and a personal task management tool;

[1938] means for managing the progress of the tasks, notifying them before their deadlines, and reassigning tasks as necessary;

[1939] A system including:

[1940] (Claim 2)

[1941] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to generate the tasks.

[1942] (Claim 3)

[1943] 2. The system according to claim 1, further comprising means for automatically registering tasks in the project management tool and the personal task management tool.

[1944] "Example 1"

[1945] (Claim 1)

[1946] A means for collecting audio data from meetings and calls and converting the audio data into text data;

[1947] means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a "person" or an "artificial intelligence";

[1948] means for assigning the classified tasks to appropriate personnel;

[1949] means for registering the assigned tasks in a project management tool and a personal task management tool;

[1950] means for managing the progress of the tasks, notifying them before their deadlines, and reassigning tasks as necessary;

[1951] a terminal that transmits voice data to a server in real time;

[1952] A server that converts voice data into text data using a voice recognition API;

[1953] A natural language processing algorithm that analyzes text data and extracts tasks.

[1954] A means to monitor task progress and send reminders;

[1955] A system including:

[1956] (Claim 2)

[1957] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to generate the tasks.

[1958] (Claim 3)

[1959] 2. The system according to claim 1, further comprising means for automatically registering tasks in the project management tool and the personal task management tool.

[1960] "Application Example 1"

[1961] (Claim 1)

[1962] A means for collecting audio data from meetings and calls and converting the audio data into text data;

[1963] means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a "person" or an "artificial intelligence";

[1964] means for assigning the classified tasks to appropriate personnel;

[1965] means for registering the assigned tasks in a project management tool and a personal task management tool;

[1966] means for managing the progress of the tasks, notifying them before their deadlines, and reassigning tasks as necessary;

[1967] In maintenance work and quality control in a factory, a worker gives voice instructions to a robot, the instructions are analyzed, tasks are generated, and the tasks are automatically assigned to the robot and the worker;

[1968] A system including:

[1969] (Claim 2)

[1970] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to generate the tasks.

[1971] (Claim 3)

[1972] 2. The system according to claim 1, further comprising means for automatically registering tasks in the project management tool and the personal task management tool.

[1973] "Example 2: Combining Emotion Engines"

[1974] (Claim 1)

[1975] A means for collecting audio data from meetings and calls and converting the audio data into text data;

[1976] means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a "person" or an "artificial intelligence";

[1977] means for assigning the classified tasks to appropriate personnel;

[1978] means for registering the assigned tasks in a project management tool and a personal task management tool;

[1979] means for managing the progress of the tasks, notifying them before their deadlines, and reassigning tasks as necessary;

[1980] A means for recognizing a user's emotions from voice data and adjusting task priorities and notification timings based on the emotion data;

[1981] A system including:

[1982] (Claim 2)

[1983] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to generate the tasks.

[1984] (Claim 3)

[1985] 2. The system according to claim 1, further comprising means for automatically registering tasks in the project management tool and the personal task management tool.

[1986] "Application example 2 when combining emotion engines"

[1987] (Claim 1)

[1988] A means for collecting audio data from meetings and calls and converting the audio data into text data;

[1989] means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a "person" or an "artificial intelligence";

[1990] means for assigning the classified tasks to appropriate personnel;

[1991] means for registering the assigned tasks in a project management tool and a personal task management tool;

[1992] means for managing the progress of the tasks, notifying them before their deadlines, and reassigning tasks as necessary;

[1993] a means for recognizing emotions from speech data and adjusting task priorities based on the emotions;

[1994] means for adjusting timing of task reminder notifications based on the emotion recognition;

[1995] A system including:

[1996] (Claim 2)

[1997] 10. The system of claim 1, further comprising means for using a natural language processing algorithm to generate the tasks.

[1998] (Claim 3)

[1999] 2. The system according to claim 1, further comprising means for automatically registering tasks in the project management tool and the personal task management tool. [Explanation of symbols]

[2000] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting audio data from meetings and calls and converting the audio data into text data; means for analyzing the text data, generating tasks, and classifying the generated tasks as to whether they will be performed by a "person" or an "artificial intelligence"; means for assigning the classified tasks to appropriate personnel; means for registering the assigned tasks in a project management tool and a personal task management tool; means for managing the progress of the tasks, notifying them before their deadlines, and reassigning tasks as necessary; A system including:

2. 10. The system of claim 1, further comprising means for using a natural language processing algorithm to generate the tasks.

3. 2. The system according to claim 1, further comprising means for automatically registering tasks in said project management tool and said personal task management tool.

Images