System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting all data related to a project; means for analyzing the data; means for generating a report based on the analysis; means for early discovery and sharing of issues; means for automatically performing follow-up of tasks in the project progress; and means for organizing a story of the entire project.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] When a project spans a wide range of areas, recording and managing its progress can be a heavy workload, making it difficult for managers and outsiders to grasp the project's status. Furthermore, because the project's progress and each member's contribution are difficult to see, it's difficult to properly evaluate the project or request external help. Furthermore, there is a lack of a system for early detection and rapid response of issues and bottlenecks that arise during the project. This can lead to project delays and communication breakdowns. [Means for solving the problem]

[0005] The present invention provides a means for collecting all project-related data (emails, messages on communication platforms, audio data from meetings, deliverables, etc.). It then provides a means for analyzing that data using natural language processing (NLP) and sentiment analysis. It also provides a means for generating daily, weekly, and monthly reports based on the analysis results, thereby visualizing the progress of the project. Furthermore, the present invention provides a means for early detection of issues and bottlenecks based on the analysis results and sharing them with stakeholders, thereby quickly resolving problems that arise during the project. It also provides a means for automatically following up on each project member according to the progress of their tasks. Finally, it provides a means for summarizing the story of the entire project so that it can be easily viewed by future generations. This streamlines project management and promotes appropriate evaluation and the sharing of knowledge.

[0006] "Data collection means" is a function for collecting all data related to the project (emails, messages on communication platforms, audio data from meetings, deliverables, etc.).

[0007] "Data analysis tools" is a function that analyzes collected data using natural language processing (NLP) and sentiment analysis to understand the progress of important topics and tasks.

[0008] The "report generation means" is a function that automatically generates daily, weekly, and monthly reports based on the analysis results, and visualizes the progress of the project.

[0009] "Issue detection means" is a function that uses analysis results to quickly discover issues and bottlenecks that arise during the project and share that information with those involved.

[0010] "Follow-up measures" is a function that automatically sends follow-up emails and notifications depending on the task progress of project members.

[0011] "Story creation tools" is a function that compiles the overall story of the project, important events, and findings, making them easily accessible for future generations.

[0012] "User linking means" is a function that allows users to link their own email accounts and communication platform accounts to the system.

[0013] "Natural language processing" is a technology that allows computers to understand and analyze human language.

[0014] "Sentiment analysis" is a technology that analyzes emotions and attitudes within text data and classifies emotions into positive, negative, neutral, etc. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This system provides a series of means for streamlining project management. Specifically, it collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on the progress of tasks and summarizes the project story. An embodiment of this system is described in detail below.

[0037] 1. Data collection

[0038] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[0039] 2. Data Analysis

[0040] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it analyzes the content of emails and messages to extract important topics, track task progress, and classify sentiment. This allows for a detailed understanding of the current status of the project.

[0041] 3. Generate a report

[0042] The server generates daily, weekly, and monthly reports based on the analysis results, including task progress, important events, and each member's contribution, and the reports are automatically sent to project stakeholders.

[0043] 4. Early detection and sharing of issues

[0044] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[0045] 5. Follow-up

[0046] The server automatically follows up on each project member's task progress, and if progress is delayed or support is needed, follow-up emails and notifications are sent.

[0047] 6. Summary of the project story

[0048] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0049] Specific examples

[0050] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, a weekly report is generated based on these analysis results and sent to the project team.

[0051] Furthermore, if the server detects that the task progress is delayed, it will automatically send a follow-up notification to User B. Finally, based on all the analysis results and progress summary, it will generate the overall story of the project and save it for easy access by the project manager.

[0052] In this way, the present invention provides detailed information on the progress of a project and supports efficient management and problem solving.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] Users connect their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account.

[0056] Step 2:

[0057] The server periodically collects emails and messages related to the project using the linked account information, retrieves data from email servers and communication platforms via API, and stores it in its own database.

[0058] Step 3:

[0059] The server passes the collected data to a natural language processing (NLP) engine for analysis, which is used to extract important topics and task progress from emails and messages.

[0060] Step 4:

[0061] The server performs sentiment analysis based on the extracted information, identifying positive, negative, and neutral emotions in the text data to understand the mental state of project members.

[0062] Step 5:

[0063] The server generates daily, weekly, and monthly reports, summarizing the analysis results and including each member's task progress, important events, and sentiment trends.

[0064] Step 6:

[0065] The server automatically sends the generated reports to project stakeholders, who can share them via email or communication platforms to make the project status transparent.

[0066] Step 7:

[0067] The server detects issues and bottlenecks from the analysis results, identifying delays in tasks and unresolved issues and labeling the information.

[0068] Step 8:

[0069] The server shares detected issues with relevant parties, sending notifications via email or communication platforms to encourage early problem resolution.

[0070] Step 9:

[0071] The server follows up on each member's task progress and, if necessary, automatically sends reminders or support requests to members who are lagging behind.

[0072] Step 10:

[0073] The server will compile the story of the entire project, organizing key events and findings based on collected data and analysis results, and storing them in a format that can be easily accessed by future generations.

[0074] In this way, each step works in tandem, making project management more efficient and clarifying overall progress and issues.

[0075] Example 1

[0076] 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."

[0077] Project management requires a lot of data and communication, making it difficult to detect delays and issues early. Centralized management and analysis of information is particularly difficult for teams using multiple platforms. Manually managing task progress and following up on tasks takes a great deal of time and effort. Furthermore, compiling the entire project story is time-consuming, making efficient project management essential.

[0078] 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.

[0079] In this invention, the server includes means for accessing external services using authentication information provided by the user and collecting all data related to the project, means for analyzing the collected data using natural language processing and sentiment analysis, means for generating daily, weekly, and monthly reports based on the analysis results, means for early detection of issues from the analysis results and sharing them in real time, means for monitoring the progress of tasks as the project progresses and automatically performing follow-up, and means for compiling a story of the entire project based on the collected data and analysis results.This enables centralized management and analysis of data in project management, visualization of progress, early detection of issues, efficient follow-up, and project summary.

[0080] "Authentication Information" means information required for a User to access their account, including a username, password, API key, etc.

[0081] "External services" refers to online services such as email accounts and communication platforms that users use on a daily basis.

[0082] "Data Collection Methods" refers to the methods and technologies used to obtain relevant data from external services.

[0083] "Natural language processing" is a technology that enables computers to understand, interpret, and manipulate human language, and performs tasks such as text analysis and topic extraction.

[0084] "Sentiment analysis" refers to the technology of classifying emotions expressed in text into "positive," "negative," "neutral," etc.

[0085] "Report generation means" refers to the methods and techniques for creating reports based on analyzed data.

[0086] "Problem detection methods" refer to methods and techniques for early detection of problems and bottlenecks during the project.

[0087] "Sharing means" refers to the methods and techniques used to communicate discovered issues and important information to project members.

[0088] "Follow-up measures" refer to technologies that monitor task progress and automatically send reminders or support notifications as needed.

[0089] A "project story" is a report that summarizes the overall progress and important events of a project.

[0090] This invention is a system for streamlining project management, providing the following set of means: This system collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically performs follow-up according to the progress of tasks and can compile the story of the entire project.

[0091] Data collection

[0092] The server accesses external services (e.g., email accounts and communication platforms) using the authentication information provided by the user. Specifically, the user logs in to the system and connects their email account (e.g., Google Gmail) and communication platform (e.g., Slack, Microsoft Teams) accounts. This allows the server to periodically call APIs (e.g., Gmail API, Slack API) to collect data related to the project (e.g., emails, chat messages, file attachments, etc.).

[0093] Data analysis

[0094] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses NLP tools such as Google Natural Language API and IBM Watson to analyze the content of emails and messages and extract important topics. It can also classify the emotional state of the text as "positive," "negative," or "neutral." This analysis provides a detailed understanding of the current status of the project.

[0095] Generate reports

[0096] The server automatically generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, and sends the reports to project stakeholders via email or communication platforms.

[0097] Early detection and sharing of issues

[0098] The server uses the analysis results to quickly identify issues such as task delays and stalled problem-solving. Detected issues are shared with project stakeholders in real time via email or communication platforms.

[0099] Performing follow-up

[0100] The server monitors the task progress of each project member and automatically sends follow-up notifications if progress is delayed or if support is required, allowing users to respond promptly.

[0101] Project Story Summary

[0102] The server aggregates key events and findings from the entire project based on data and analysis, generating a final report that summarizes the overall project story and saving it in an easily accessible format for future project reference.

[0103] Examples and prompts

[0104] In a project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. The system first links the accounts of User A and User B. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, it generates a weekly report based on these analysis results and sends it to the project team. If it detects that task progress is behind schedule, the server automatically sends a follow-up notification to User B. Finally, based on all analysis results and a summary of progress, it generates an overall project story and saves it for easy access by project managers.

[0105] An example of a prompt is, "Based on the following text, please provide the user with an overview of a system that provides project progress reports and issue notifications."

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Step 1:

[0108] When logging in to the system, users enter their email account and communication platform authentication information, which is then used by the server to access external services. Specifically, users enter their email address and password on the login screen and are authenticated using OAuth 2.0.

[0109] Input: User's email account, communication platform account information

[0110] Output: OAuth token (authentication information)

[0111] Step 2:

[0112] The server uses the obtained credentials to access external services (email accounts and communication platforms) and collect data related to the project. For example, it uses the Gmail API or Slack API to retrieve emails and chat messages. These operations are performed automatically on a regular basis.

[0113] Input: OAuth token

[0114] Output: Collected email and chat message data

[0115] Step 3:

[0116] The server normalizes the collected data, for example converting email bodies or chat messages into text data, so that a consistent format of data is available for subsequent analysis steps.

[0117] Input: Collected email and chat message data

[0118] Output: Normalized text data

[0119] Step 4:

[0120] The server then analyzes the normalized data using natural language processing (NLP) and sentiment analysis tools, such as Google Natural Language API and IBM Watson, to extract key keywords from the text and classify the emotional state as "positive," "negative," or "neutral."

[0121] Input: normalized text data

[0122] Output: Analysis results (important keywords, sentiment classification)

[0123] Step 5:

[0124] The server generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, often in JSON or PDF format.

[0125] Input: Analysis results

[0126] Output: Report (JSON format, PDF format)

[0127] Step 6:

[0128] The server then sends the generated reports to project stakeholders via email or a communication platform, automatically distributing the reports using the API of the email server or communication platform.

[0129] Input: Report

[0130] Output: Report sent

[0131] Step 7:

[0132] The server uses the analysis results to detect issues such as task delays and stalled problem-solving. For example, it detects tasks that have not progressed for a certain period of time and lists them as issues.

[0133] Input: Analysis results

[0134] Output: Detected issues

[0135] Step 8:

[0136] The server notifies relevant parties of detected issues in real time via email or a communication platform, and includes the specific details of the issue and a request for action.

[0137] Input: Detected issues

[0138] Output: Issue notification sent

[0139] Step 9:

[0140] The server monitors the task progress of each project member and automatically sends follow-up notifications in the form of emails or messages if there is no progress or delays for a certain period of time.

[0141] Input: Task progress data

[0142] Output: Follow-up notification

[0143] Step 10:

[0144] The server will organize the project's important events and findings based on the data and analysis results of the entire project, and will then compile the overall story of the project into a final report.

[0145] Input: Data and analysis results

[0146] Output: The story of the entire project

[0147] Step 11:

[0148] The server stores the generated project stories in an easily accessible format for future reference, and the reports are stored in a database for easy retrieval and viewing later.

[0149] Input: The overall story of the project

[0150] Output: Saved report

[0151] (Application example 1)

[0152] 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."

[0153] Conventional project management systems have the drawback of being inefficient due to the time and effort required for data collection, analysis, and report generation. They also lack the functionality to detect and respond to abnormalities and issues early, which often leads to human error and time lags, especially in the maintenance management of factory robots.

[0154] 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.

[0155] In this invention, the server includes a means for collecting all data related to the project, a means for analyzing the data to detect abnormalities, a means for generating a maintenance report, and a means for sending a notification when an abnormality is detected. This allows for efficient project management and maintenance management of factory robots, and enables early detection of problems and rapid response.

[0156] "All data related to the project" refers to all information related to the project, such as emails, chats, task management tools, and sentiment analysis results.

[0157] "Robot operation data" refers to all information related to the operation of robots used in factories, such as their operating status, error information, and operating hours.

[0158] "Means of analyzing data to detect anomalies" refers to functions that analyze collected data using technologies such as natural language processing, sentiment analysis, and machine learning to detect anomalies and problems.

[0159] "Means for generating a maintenance report" refers to a function that automatically creates a report summarizing the robot's maintenance status and required maintenance tasks based on the analysis results.

[0160] "Means for sending notifications when an abnormality is detected" refers to the function of notifying the person in charge by email, app notification, or other means when the system detects an abnormality in the robot or a situation requiring emergency maintenance.

[0161] "A means of summarizing the story of the entire project" refers to a function that allows you to summarize all important events and progress from the start to the end of the project as a series of stories.

[0162] To realize this invention, a server, a user terminal (such as a smartphone or PC), and necessary software are required. Specifically, the server plays the following roles:

[0163] First, the server collects all data related to the project. This includes data from email platforms and communication tools, and periodically retrieves data using APIs. Data collection begins when a user logs in to the system and links their platform accounts.

[0164] The server then analyzes the collected data, applying natural language processing (NLP) and sentiment analysis to extract topics from the data content and classify emotions. After analysis, the robot's operational data is also analyzed. Specifically, machine learning algorithms are used to detect abnormalities in operational status.

[0165] Based on the analysis results, the server generates daily, weekly, and monthly reports that include project progress, key events, contributions of each member, and robot maintenance requirements, and these reports are automatically sent to the user's device.

[0166] The server also uses the analysis results to quickly identify issues and share them with relevant parties. For example, it detects delays in tasks or stalled resolutions and notifies relevant users via email or app notifications.

[0167] Additionally, the server automatically performs follow-up on tasks as the project progresses: if a task is delayed or if support is needed, follow-up notifications are sent.

[0168] Finally, the server will compile the overall story of the project, including organizing key events and learnings from the project based on the collected data and analysis results, and preserving them for posterity.

[0169] Hardware and software used:

[0170] Server: Cloud-based Amazon Web Services (AWS) or Google Cloud Platform (GCP)

[0171] User devices: smartphones, PCs

[0172] Natural Language Processing: NLTK (Python library)

[0173] Sentiment Analysis: VADER Sentiment Analysis (part of NLTK)

[0174] Data frame operations: pandas (Python library)

[0175] HTTP requests: requests (Python library)

[0176] Sending email: smtplib (Python library)

[0177] Examples:

[0178] Two users, User A and User B, are participating in a factory project. The server collects User A's email meeting minutes and User B's messages from their communication tools, and applies NLP and sentiment analysis to extract important topics and emotions. A weekly report is then generated and sent to the user. In addition, robot operation data is also collected and analyzed, and if an abnormality is detected, a notification is sent to the person in charge.

[0179] Example prompt sentence:

[0180] "Analyze the robot's operating status and generate a report based on the following data."

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] The server uses the credentials provided by the user to access email accounts and communication platform accounts and collect data related to the project. Specifically, the server periodically calls an API to retrieve the contents of emails and messages. The input is the user's credentials and the associated account, and the output is the collected, unanalyzed data.

[0184] Step 2:

[0185] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses an NLP library (such as NLTK) to classify important topics and sentiment. The input is the raw data collected in step 1, and the output is the analyzed data with classified topics and sentiment.

[0186] Step 3:

[0187] The server generates daily, weekly, and monthly reports based on the analysis results. Specifically, it aggregates the analysis data and summarizes progress and important events. The input is the analysis data obtained in step 2, and the output is the report.

[0188] Step 4:

[0189] The server detects issues and bottlenecks from the analysis results and shares them with relevant parties. For example, it detects task delays and stalls in problem-solving and automatically sends notifications via email or communication platforms. The input is the analysis results data, and the output is notifications to each relevant party.

[0190] Step 5:

[0191] The server automatically follows up on each project member's task progress. If progress is delayed or support is deemed necessary, a follow-up email or notification is sent. The input is task progress data, and the output is a follow-up notification.

[0192] Step 6:

[0193] The server compiles the story of the entire project. Based on the collected data and analysis results, it organizes important events and findings and saves them as a final report. The input is all analysis data and progress data, and the output is a report summarizing the story of the entire project.

[0194] Step 7:

[0195] The server collects robot operation data. Specifically, it periodically obtains operation status and error information from the robots in the factory. The input is operation data from the robots, and the output is the collected, unanalyzed operation data.

[0196] Step 8:

[0197] The server analyzes the collected robot operation data and detects anomalies. It uses machine learning algorithms to identify abnormal operations. The input is the operation data collected in step 7, and the output is the analysis data in which anomalies are detected.

[0198] Step 9:

[0199] The server automatically sends a notification if an anomaly is detected. Specifically, it notifies the person in charge of the anomaly via email or app notification. The input is the analysis data in which the anomaly was detected, and the output is the situation in which the notification was sent.

[0200] 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.

[0201] This system provides a series of methods for streamlining project management. Specifically, it collects all project-related data, analyzes it using natural language processing (NLP) and sentiment analysis, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on task progress and summarizes the project story. It also incorporates an emotion engine that recognizes the user's emotions, allowing it to analyze the user's emotional state and follow up and create reports based on that.

[0202] 1. Data collection

[0203] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[0204] 2. Data Analysis

[0205] The server passes the collected data to the NLP engine for analysis. The NLP engine is used to extract important topics and task progress from emails and messages. Furthermore, an emotion engine is used to identify emotions in the text data and evaluate the user's emotional state.

[0206] 3. Generate a report

[0207] Based on the results of analysis and sentiment analysis, the server generates daily, weekly, and monthly reports, including task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders.

[0208] 4. Early detection and sharing of issues

[0209] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[0210] 5. Follow-up

[0211] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, a follow-up email or notification will be sent.

[0212] 6. Summary of the project story

[0213] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0214] Specific examples

[0215] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress on a communication platform. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and messages from the communication platform, and applies NLP and an emotion engine to analyze important topics, task progress, and emotions. Next, a weekly report is generated based on the results of these analyses and sent to the project team.

[0216] Furthermore, if the progress of the task is delayed or if the emotion engine detects that User B is feeling stressed, the server will automatically send a follow-up notification to User B. Finally, based on all the analysis results, progress summary, and emotional state, the server generates an overall story of the project and saves it for easy access by the project manager.

[0217] In this way, the present invention provides detailed information on the progress of a project, supporting efficient management and problem-solving. Furthermore, the introduction of an emotion engine enables follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of the project.

[0218] The processing flow will be explained below.

[0219] Step 1:

[0220] The user connects their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account. At this stage, the user logs into the system and completes the authentication process.

[0221] Step 2:

[0222] The server periodically collects users' emails and communication platform messages using the linked account information, obtains the data through the respective APIs, and stores it in its own database, which also contains metadata such as the collection date and time and the user's ID.

[0223] Step 3:

[0224] The server passes the collected data to a natural language processing (NLP) engine for analysis. The data includes email text, messages from communication platforms, and meeting minutes. The NLP engine extracts important keywords and topics from this text data.

[0225] Step 4:

[0226] The server uses an emotion engine to perform sentiment analysis based on the important keywords and topics extracted by the NLP engine. The emotion engine classifies the text content into emotional categories such as positive, negative, and neutral, which allows the emotional state of the project members to be evaluated.

[0227] Step 5:

[0228] Based on the analysis results of the NLP and emotion engine, the server generates daily, weekly, and monthly reports that include task progress, each member's contribution, important events, and sentiment trends. The reports are automatically sent to project stakeholders via email or communication platforms.

[0229] Step 6:

[0230] The server detects issues and bottlenecks from the analysis results. For example, it checks whether there are delays in tasks or unresolved issues. Detected issues are automatically notified to the relevant parties.

[0231] Step 7:

[0232] To address detected issues, the server sends follow-up notifications to relevant parties, including details of the problem and recommended actions to resolve it, helping to speed up problem resolution.

[0233] Step 8:

[0234] The server follows up on project members based on their task progress and emotional state. If progress is delayed or the emotional state is judged to be negative, follow-up emails and notifications are automatically sent.

[0235] Step 9:

[0236] The server will compile the story of the entire project, including the collected data, analysis results, emotional state, and significant events, and will organize the story into a final project report, which will be archived in a format that can be easily viewed by future generations.

[0237] In this way, each step works in tandem to ensure efficient project management and detailed understanding of overall progress, issues, and the emotional state of members.

[0238] Example 2

[0239] 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."

[0240] In traditional project management systems, data collection, analysis, report generation, and early issue detection and sharing are often done manually, which is inefficient and makes it difficult to properly understand and follow up on the emotional state of members.To solve this problem, automated data collection, analysis, report generation, follow-up, and emotional state management are needed.

[0241] 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.

[0242] In this invention, the server includes a means for accessing the user's email account and communication platform account using authentication information provided by the user and collecting all data related to the project, a means for passing the collected data to a natural language processing engine for analysis and extracting important topics and task progress, and a means for passing the data to an emotion engine for identifying emotions in the text and evaluating the user's emotional state, which significantly improves the efficiency of project management and enables appropriate follow-up taking into account the emotional state of members.

[0243] "Authentication information" refers to the information required to access a user's email account or communications platform account.

[0244] A "natural language processing engine" is a software component that analyzes text data and extracts important topics and task progress.

[0245] An "emotion engine" is a software component for identifying emotions in text data and assessing a user's emotional state.

[0246] A "Report" is a document generated based on the results of analysis and sentiment analysis, which describes the progress of a task, important events, each member's contribution, and sentiment trends.

[0247] "Issues" refer to problems such as delays in tasks and stagnation in problem-solving during project progress.

[0248] "Follow-up" refers to automated support and notifications based on each project member's task progress and emotional state.

[0249] A "project story" is a summary of the overall progress of a project, including important events and findings.

[0250] This system provides a series of methods to streamline project management. The server, terminals, and users play their respective roles, and the system automatically collects data, analyzes, generates reports, shares issues, follows up, and summarizes stories.

[0251] Data collection

[0252] The server uses the authentication information provided by the user to access the email account and communication platform account and collect data related to the project. Specifically, the user logs in to the system and links the email account and communication platform account. The server periodically obtains data using APIs such as Google Gmail API and Slack API.

[0253] Data analysis

[0254] The server passes the collected data to a natural language processing (NLP) engine for analysis. This NLP engine uses the Google Cloud Natural Language API and other tools to extract important topics and task progress from emails and messages. The server also uses an emotion engine to identify emotions within the text data. This emotion engine uses IBM Watson Tone Analyzer to evaluate the user's emotional state.

[0255] Generate reports

[0256] The server generates daily, weekly, and monthly reports based on the results of analysis and sentiment analysis. These reports include task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders via email or communication platforms.

[0257] Early detection and sharing of issues

[0258] The server detects issues and bottlenecks from the analysis results, such as delays in tasks and stalled problem-solving. The server automatically shares detected issues with relevant parties via email or a communication platform.

[0259] Performing follow-up

[0260] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, the server will send a follow-up email or notification.

[0261] Project Story Summary

[0262] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0263] Specific examples

[0264] For example, in a project team, User A sends weekly meeting minutes via email, and User B reports task progress via a communication platform. In this system, User A and User B's accounts are linked. The server periodically calls an API to collect the weekly meeting minutes emails and messages from the communication platform. This data is passed to an NLP engine and an emotion engine, which analyzes important topics, task progress, and emotional state. Based on the analysis results, the server generates a weekly report and sends it to the project team. In addition, if task progress is delayed or if the emotion engine detects that User B is feeling stressed, the server automatically sends a follow-up notification to User B. Finally, based on all the analysis results, an overall project story is generated and saved for easy access by the project manager.

[0265] Prompt Sentence Examples

[0266] "Using the minutes of daily project team meetings and messages from communication platforms, analyze the task progress and emotional state of members using NLP and an emotion engine to generate a weekly report."

[0267] This system streamlines all aspects of project management, providing detailed insight into progress and support for resolving issues. The introduction of an emotion engine also enables appropriate follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of projects.

[0268] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0269] Step 1:

[0270] A user logs into the system and enters their email account and communication platform account information, including their user ID and password, which then sends authentication information to the server, allowing the server to access the user's email server and communication platform.

[0271] Input: User ID, password, email account information, communication platform information

[0272] Output: Authentication information (token, etc.)

[0273] Step 2:

[0274] The server uses the obtained credentials to call APIs and collect data from mail servers and communication platforms, for example, Google Gmail API to retrieve emails and Slack API to retrieve messages, thus collecting all project-related data.

[0275] Input: Credentials, API call

[0276] Output: Collected data (emails, messages, etc.)

[0277] Step 3:

[0278] The server passes the collected data to a natural language processing (NLP) engine to begin analysis. The NLP engine (e.g., Google Cloud Natural Language API) is used to extract important topics and task progress from emails and messages. This analysis extracts specific keywords and context.

[0279] Input: Collected data

[0280] Output: Extracted topics and task progress information

[0281] Step 4:

[0282] The server then passes the collected text data to an emotion engine for sentiment analysis. Using an emotion engine (e.g., IBM Watson Tone Analyzer), emotions within the text are identified and the user's emotional state is assessed. This analysis results in an emotional label, such as positive, negative, or neutral.

[0283] Input: Collected text data

[0284] Output: Sentiment analysis results (emotion labels)

[0285] Step 5:

[0286] The server generates daily, weekly, and monthly reports based on the analysis results obtained from the NLP engine and the sentiment engine. The generated reports include task progress, important events, each member's contribution, and sentiment trends. Report templates are used to generate the reports.

[0287] Input: Extracted topics, task progress information, sentiment analysis results

[0288] Output: Generated report

[0289] Step 6:

[0290] The server automatically sends the generated report to the project stakeholders via email or a communication platform, for example, sending the report to all project participants via email.

[0291] Input: Generated report

[0292] Output: Report sent (e.g. email)

[0293] Step 7:

[0294] The server uses algorithms to detect issues and bottlenecks from the analysis results, identifying delays in tasks and stalled problem-solving, and records the detected issues along with suggestions for resolving them.

[0295] Input: Analysis results

[0296] Output: Detected issues and their suggestions

[0297] Step 8:

[0298] The server shares detected issues with the relevant parties via email notifications and messages on the communication platform, allowing them to address the issues early.

[0299] Input: Detected issues and their suggestions

[0300] Output: Issue notifications (emails, messages, etc.)

[0301] Step 9:

[0302] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or emotional analysis indicates that support is needed, follow-up emails and notifications are sent.

[0303] Input: Task progress, sentiment analysis results

[0304] Output: Follow-up notification (email, message, etc.)

[0305] Step 10:

[0306] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0307] Input: Collected data, analysis results

[0308] Output: Final report (project story)

[0309] The above is the specific processing flow in implementing this system.

[0310] (Application example 2)

[0311] 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."

[0312] In modern factories, many tasks are performed by multiple work machines. Therefore, it is important to accurately grasp the progress of tasks and manage them efficiently. Furthermore, the emotional state of the work machine operators also has a significant impact on production efficiency, but there are currently insufficient means to appropriately grasp and support this. In such situations, task delays and reduced efficiency due to operator stress are likely to occur, significantly impacting the entire production operation. Therefore, a system is needed that can analyze the progress of tasks and the emotional state of operators in real time and provide appropriate follow-up and improvement measures.

[0313] 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.

[0314] In this invention, the server includes means for collecting all data related to the project, means for analyzing the task progress of the work machine, and means for analyzing the emotional state of the operator of the work machine. This makes it possible to grasp the task progress and the emotional state of the operator in real time, and to propose appropriate follow-up and improvement measures.

[0315] A "data collection means" is a mechanical or software component that captures and stores any data generated by the work machine and its operator.

[0316] "Means for analyzing data" refers to mechanical or software components that analyze collected data using techniques such as natural language processing and sentiment analysis to extract useful information.

[0317] The "means for generating a report" refers to a mechanical or software component that creates a report in a predetermined format based on the analysis results and provides it to the relevant parties.

[0318] "Means for early detection and sharing of issues" refers to mechanical or software components that detect bottlenecks and problems from the analysis results and quickly notify the relevant parties.

[0319] The "means for automatically performing task follow-up" is a mechanical or software component for automatically providing necessary follow-up notification or assistance based on the progress of the task of the work machine and the emotional state of the operator.

[0320] A "means for summarizing the overall project story" is a mechanical or software component that organizes the overall project progress and knowledge gained based on collected data and analysis results, and stores it in a format that can be easily referenced in the future.

[0321] "Work machine" refers to any mechanical device that performs a task in a factory or manufacturing site.

[0322] "Operator" means a person operating a work machine.

[0323] This invention is a system aimed at efficient management of factory robots and their operators. This system has the following components:

[0324] System Configuration

[0325] 1. Data Collection Methods

[0326] The server collects data from the work machines and their operators in real time, including the task progress of each work machine, work records entered by the operators, and sensing data. This data is sent over the network and stored on the server.

[0327] 2. Data analysis methods

[0328] The server uses an NLP (natural language processing) engine and an emotion engine to analyze the collected data. The NLP engine analyzes the task progress of the work machine and extracts important topics and task progress. The emotion engine also identifies and evaluates the emotional state of the operator from the text data.

[0329] 3. Report Generation Methods

[0330] Based on the results of data analysis, the server generates daily, weekly, and monthly reports, including task progress, key events, individual operator contributions, and sentiment trends, and the generated reports are automatically sent to relevant parties.

[0331] 4. Early detection and sharing of issues

[0332] Based on the results obtained from the data analysis tools, the server automatically detects issues and bottlenecks, such as delays in tasks or increased stress among operators. These issues are automatically shared with the relevant parties, enabling early action to be taken.

[0333] 5. Follow-up measures

[0334] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. For example, it notifies an operator whose task is delayed to report progress, and notifies an operator whose emotional state is deteriorating to provide support.

[0335] 6. Project Story Summary

[0336] The server will compile a story of the project based on the overall progress of the project and the knowledge gained, allowing future generations to easily understand the overall picture of the project.

[0337] Specific examples

[0338] For example, when welding work is being carried out in a factory, an operator inputs task progress and collects data from the work machine in real time. The server analyzes this data and evaluates the task progress and the operator's emotional state. If the operator is feeling stressed, the server automatically sends a follow-up notification to encourage support. Reports summarizing the overall progress are also periodically generated and sent to relevant parties.

[0339] Prompt Sentence Examples

[0340] Enter the following task details:

[0341] Task ID: __

[0342] Progress:__

[0343] More information:

[0344]

[0345] Enter the following task details:

[0346] Task ID: 1

[0347] Progress: In progress

[0348] Detailed information: Welding parts A and B

[0349] Such a system will enable efficient management of work machines and operators within a factory, making it possible to grasp the progress of tasks and the emotional state of operators, and to provide appropriate follow-up.

[0350] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0351] Step 1:

[0352] The server collects data from the work machines and operators. Specifically, it receives task progress data from each work machine via the network, and text data on input work records and emotional states from the operators. This input data is stored in a database within the server.

[0353] Step 2:

[0354] The server passes the collected data to a natural language processing (NLP) engine and begins analysis. The server's NLP engine extracts important topics and work progress information from the text data of the work machine's task progress. This analysis reveals the detailed progress of each task and related issues. The output is a list of important topics and progress information.

[0355] Step 3:

[0356] The server passes the collected emotion data to the emotion engine for emotion analysis. The emotion engine evaluates the emotional state of the operator (e.g., stress, satisfaction, anxiety, etc.) from the text data. The evaluation results are output as an emotional state score for each operator.

[0357] Step 4:

[0358] The server integrates the analysis results from the NLP engine and the emotion engine to generate daily, weekly, and monthly reports, including task progress, important events, and the emotional state of operators. The generated reports are automatically sent to designated stakeholders via email or platform notifications.

[0359] Step 5:

[0360] The server automatically detects issues and bottlenecks from the analysis results. For example, if a task is delayed or an operator's emotional score is declining, it extracts related issues. Detected issues are automatically notified to the relevant parties, urging them to take early action. The output is a list of issues and their notifications.

[0361] Step 6:

[0362] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. Specifically, it sends a progress report reminder to operators whose tasks are delayed, and a notification urging appropriate support to operators whose emotional state is deteriorating. The aforementioned analysis results are used as input data.

[0363] Step 7:

[0364] Based on the overall progress and findings of the project, the server compiles a story of the project, including important events, progress, and the emotional state of the operators, and stores this story in a specific format for future generations.

[0365] By dividing the process into steps in this way, efficient management of the work machines and operators within the factory can be achieved.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] [Second embodiment]

[0370] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0371] 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.

[0372] 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).

[0373] 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.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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."

[0382] This system provides a series of means for streamlining project management. Specifically, it collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on the progress of tasks and summarizes the project story. An embodiment of this system is described in detail below.

[0383] 1. Data collection

[0384] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[0385] 2. Data Analysis

[0386] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it analyzes the content of emails and messages to extract important topics, track task progress, and classify sentiment. This allows for a detailed understanding of the current status of the project.

[0387] 3. Generate a report

[0388] The server generates daily, weekly, and monthly reports based on the analysis results, including task progress, important events, and each member's contribution, and the reports are automatically sent to project stakeholders.

[0389] 4. Early detection and sharing of issues

[0390] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[0391] 5. Follow-up

[0392] The server automatically follows up on each project member's task progress, and if progress is delayed or support is needed, follow-up emails and notifications are sent.

[0393] 6. Summary of the project story

[0394] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0395] Specific examples

[0396] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, a weekly report is generated based on these analysis results and sent to the project team.

[0397] Furthermore, if the server detects that the task progress is delayed, it will automatically send a follow-up notification to User B. Finally, based on all the analysis results and progress summary, it will generate the overall story of the project and save it for easy access by the project manager.

[0398] In this way, the present invention provides detailed information on the progress of a project and supports efficient management and problem solving.

[0399] The processing flow will be explained below.

[0400] Step 1:

[0401] Users connect their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account.

[0402] Step 2:

[0403] The server periodically collects emails and messages related to the project using the linked account information, retrieves data from email servers and communication platforms via API, and stores it in its own database.

[0404] Step 3:

[0405] The server passes the collected data to a natural language processing (NLP) engine for analysis, which is used to extract important topics and task progress from emails and messages.

[0406] Step 4:

[0407] The server performs sentiment analysis based on the extracted information, identifying positive, negative, and neutral emotions in the text data to understand the mental state of project members.

[0408] Step 5:

[0409] The server generates daily, weekly, and monthly reports, summarizing the analysis results and including each member's task progress, important events, and sentiment trends.

[0410] Step 6:

[0411] The server automatically sends the generated reports to project stakeholders, who can share them via email or communication platforms to make the project status transparent.

[0412] Step 7:

[0413] The server detects issues and bottlenecks from the analysis results, identifying delays in tasks and unresolved issues and labeling the information.

[0414] Step 8:

[0415] The server shares detected issues with relevant parties, sending notifications via email or communication platforms to encourage early problem resolution.

[0416] Step 9:

[0417] The server follows up on each member's task progress and, if necessary, automatically sends reminders or support requests to members who are lagging behind.

[0418] Step 10:

[0419] The server will compile the story of the entire project, organizing key events and findings based on collected data and analysis results, and storing them in a format that can be easily accessed by future generations.

[0420] In this way, each step works in tandem, making project management more efficient and clarifying overall progress and issues.

[0421] Example 1

[0422] 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."

[0423] Project management requires a lot of data and communication, making it difficult to detect delays and issues early. Centralized management and analysis of information is particularly difficult for teams using multiple platforms. Manually managing task progress and following up on tasks takes a great deal of time and effort. Furthermore, compiling the entire project story is time-consuming, making efficient project management essential.

[0424] 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.

[0425] In this invention, the server includes means for accessing external services using authentication information provided by the user and collecting all data related to the project, means for analyzing the collected data using natural language processing and sentiment analysis, means for generating daily, weekly, and monthly reports based on the analysis results, means for early detection of issues from the analysis results and sharing them in real time, means for monitoring the progress of tasks as the project progresses and automatically performing follow-up, and means for compiling a story of the entire project based on the collected data and analysis results.This enables centralized management and analysis of data in project management, visualization of progress, early detection of issues, efficient follow-up, and project summary.

[0426] "Authentication Information" means information required for a User to access their account, including a username, password, API key, etc.

[0427] "External services" refers to online services such as email accounts and communication platforms that users use on a daily basis.

[0428] "Data Collection Methods" refers to the methods and technologies used to obtain relevant data from external services.

[0429] "Natural language processing" is a technology that enables computers to understand, interpret, and manipulate human language, and performs tasks such as text analysis and topic extraction.

[0430] "Sentiment analysis" refers to the technology of classifying emotions expressed in text into "positive," "negative," "neutral," etc.

[0431] "Report generation means" refers to the methods and techniques for creating reports based on analyzed data.

[0432] "Problem detection methods" refer to methods and techniques for early detection of problems and bottlenecks during the project.

[0433] "Sharing means" refers to the methods and techniques used to communicate discovered issues and important information to project members.

[0434] "Follow-up measures" refer to technologies that monitor task progress and automatically send reminders or support notifications as needed.

[0435] A "project story" is a report that summarizes the overall progress and important events of a project.

[0436] This invention is a system for streamlining project management, providing the following set of means: This system collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically performs follow-up according to the progress of tasks and can compile the story of the entire project.

[0437] Data collection

[0438] The server accesses external services (e.g., email accounts and communication platforms) using the authentication information provided by the user. Specifically, the user logs in to the system and connects their email account (e.g., Google Gmail) and communication platform (e.g., Slack, Microsoft Teams) accounts. This allows the server to periodically call APIs (e.g., Gmail API, Slack API) to collect data related to the project (e.g., emails, chat messages, file attachments, etc.).

[0439] Data analysis

[0440] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses NLP tools such as Google Natural Language API and IBM Watson to analyze the content of emails and messages and extract important topics. It can also classify the emotional state of the text as "positive," "negative," or "neutral." This analysis provides a detailed understanding of the current status of the project.

[0441] Generate reports

[0442] The server automatically generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, and sends the reports to project stakeholders via email or communication platforms.

[0443] Early detection and sharing of issues

[0444] The server uses the analysis results to quickly identify issues such as task delays and stalled problem-solving. Detected issues are shared with project stakeholders in real time via email or communication platforms.

[0445] Performing follow-up

[0446] The server monitors the task progress of each project member and automatically sends follow-up notifications if progress is delayed or if support is required, allowing users to respond promptly.

[0447] Project Story Summary

[0448] The server aggregates key events and findings from the entire project based on data and analysis, generating a final report that summarizes the overall project story and saving it in an easily accessible format for future project reference.

[0449] Examples and prompts

[0450] In a project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. The system first links the accounts of User A and User B. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, it generates a weekly report based on these analysis results and sends it to the project team. If it detects that task progress is behind schedule, the server automatically sends a follow-up notification to User B. Finally, based on all analysis results and a summary of progress, it generates an overall project story and saves it for easy access by project managers.

[0451] An example of a prompt is, "Based on the following text, please provide the user with an overview of a system that provides project progress reports and issue notifications."

[0452] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0453] Step 1:

[0454] When logging in to the system, users enter their email account and communication platform authentication information, which is then used by the server to access external services. Specifically, users enter their email address and password on the login screen and are authenticated using OAuth 2.0.

[0455] Input: User's email account, communication platform account information

[0456] Output: OAuth token (authentication information)

[0457] Step 2:

[0458] The server uses the obtained credentials to access external services (email accounts and communication platforms) and collect data related to the project. For example, it uses the Gmail API or Slack API to retrieve emails and chat messages. These operations are performed automatically on a regular basis.

[0459] Input: OAuth token

[0460] Output: Collected email and chat message data

[0461] Step 3:

[0462] The server normalizes the collected data, for example converting email bodies or chat messages into text data, so that a consistent format of data is available for subsequent analysis steps.

[0463] Input: Collected email and chat message data

[0464] Output: Normalized text data

[0465] Step 4:

[0466] The server then analyzes the normalized data using natural language processing (NLP) and sentiment analysis tools, such as Google Natural Language API and IBM Watson, to extract key keywords from the text and classify the emotional state as "positive," "negative," or "neutral."

[0467] Input: normalized text data

[0468] Output: Analysis results (important keywords, sentiment classification)

[0469] Step 5:

[0470] The server generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, often in JSON or PDF format.

[0471] Input: Analysis results

[0472] Output: Report (JSON format, PDF format)

[0473] Step 6:

[0474] The server then sends the generated reports to project stakeholders via email or a communication platform, automatically distributing the reports using the API of the email server or communication platform.

[0475] Input: Report

[0476] Output: Report sent

[0477] Step 7:

[0478] The server uses the analysis results to detect issues such as task delays and stalled problem-solving. For example, it detects tasks that have not progressed for a certain period of time and lists them as issues.

[0479] Input: Analysis results

[0480] Output: Detected issues

[0481] Step 8:

[0482] The server notifies relevant parties of detected issues in real time via email or a communication platform, and includes the specific details of the issue and a request for action.

[0483] Input: Detected issues

[0484] Output: Issue notification sent

[0485] Step 9:

[0486] The server monitors the task progress of each project member and automatically sends follow-up notifications in the form of emails or messages if there is no progress or delays for a certain period of time.

[0487] Input: Task progress data

[0488] Output: Follow-up notification

[0489] Step 10:

[0490] The server will organize the project's important events and findings based on the data and analysis results of the entire project, and will then compile the overall story of the project into a final report.

[0491] Input: Data and analysis results

[0492] Output: The story of the entire project

[0493] Step 11:

[0494] The server stores the generated project stories in an easily accessible format for future reference, and the reports are stored in a database for easy retrieval and viewing later.

[0495] Input: The overall story of the project

[0496] Output: Saved report

[0497] (Application example 1)

[0498] 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."

[0499] Conventional project management systems have the drawback of being inefficient due to the time and effort required for data collection, analysis, and report generation. They also lack the functionality to detect and respond to abnormalities and issues early, which often leads to human error and time lags, especially in the maintenance management of factory robots.

[0500] 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.

[0501] In this invention, the server includes a means for collecting all data related to the project, a means for analyzing the data to detect abnormalities, a means for generating a maintenance report, and a means for sending a notification when an abnormality is detected. This allows for efficient project management and maintenance management of factory robots, and enables early detection of problems and rapid response.

[0502] "All data related to the project" refers to all information related to the project, such as emails, chats, task management tools, and sentiment analysis results.

[0503] "Robot operation data" refers to all information related to the operation of robots used in factories, such as their operating status, error information, and operating hours.

[0504] "Means of analyzing data to detect anomalies" refers to functions that analyze collected data using technologies such as natural language processing, sentiment analysis, and machine learning to detect anomalies and problems.

[0505] "Means for generating a maintenance report" refers to a function that automatically creates a report summarizing the robot's maintenance status and required maintenance tasks based on the analysis results.

[0506] "Means for sending notifications when an abnormality is detected" refers to the function of notifying the person in charge by email, app notification, or other means when the system detects an abnormality in the robot or a situation requiring emergency maintenance.

[0507] "A means of summarizing the story of the entire project" refers to a function that allows you to summarize all important events and progress from the start to the end of the project as a series of stories.

[0508] To realize this invention, a server, a user terminal (such as a smartphone or PC), and necessary software are required. Specifically, the server plays the following roles:

[0509] First, the server collects all data related to the project. This includes data from email platforms and communication tools, and periodically retrieves data using APIs. Data collection begins when a user logs in to the system and links their platform accounts.

[0510] The server then analyzes the collected data, applying natural language processing (NLP) and sentiment analysis to extract topics from the data content and classify emotions. After analysis, the robot's operational data is also analyzed. Specifically, machine learning algorithms are used to detect abnormalities in operational status.

[0511] Based on the analysis results, the server generates daily, weekly, and monthly reports that include project progress, key events, contributions of each member, and robot maintenance requirements, and these reports are automatically sent to the user's device.

[0512] The server also uses the analysis results to quickly identify issues and share them with relevant parties. For example, it detects delays in tasks or stalled resolutions and notifies relevant users via email or app notifications.

[0513] Additionally, the server automatically performs follow-up on tasks as the project progresses: if a task is delayed or if support is needed, follow-up notifications are sent.

[0514] Finally, the server will compile the overall story of the project, including organizing key events and learnings from the project based on the collected data and analysis results, and preserving them for posterity.

[0515] Hardware and software used:

[0516] Server: Cloud-based Amazon Web Services (AWS) or Google Cloud Platform (GCP)

[0517] User devices: smartphones, PCs

[0518] Natural Language Processing: NLTK (Python library)

[0519] Sentiment Analysis: VADER Sentiment Analysis (part of NLTK)

[0520] Data frame operations: pandas (Python library)

[0521] HTTP requests: requests (Python library)

[0522] Sending email: smtplib (Python library)

[0523] Examples:

[0524] Two users, User A and User B, are participating in a factory project. The server collects User A's email meeting minutes and User B's messages from their communication tools, and applies NLP and sentiment analysis to extract important topics and emotions. A weekly report is then generated and sent to the user. In addition, robot operation data is also collected and analyzed, and if an abnormality is detected, a notification is sent to the person in charge.

[0525] Example prompt sentence:

[0526] "Analyze the robot's operating status and generate a report based on the following data."

[0527] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0528] Step 1:

[0529] The server uses the credentials provided by the user to access email accounts and communication platform accounts and collect data related to the project. Specifically, the server periodically calls an API to retrieve the contents of emails and messages. The input is the user's credentials and the associated account, and the output is the collected, unanalyzed data.

[0530] Step 2:

[0531] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses an NLP library (such as NLTK) to classify important topics and sentiment. The input is the raw data collected in step 1, and the output is the analyzed data with classified topics and sentiment.

[0532] Step 3:

[0533] The server generates daily, weekly, and monthly reports based on the analysis results. Specifically, it aggregates the analysis data and summarizes progress and important events. The input is the analysis data obtained in step 2, and the output is the report.

[0534] Step 4:

[0535] The server detects issues and bottlenecks from the analysis results and shares them with relevant parties. For example, it detects task delays and stalls in problem-solving and automatically sends notifications via email or communication platforms. The input is the analysis results data, and the output is notifications to each relevant party.

[0536] Step 5:

[0537] The server automatically follows up on each project member's task progress. If progress is delayed or support is deemed necessary, a follow-up email or notification is sent. The input is task progress data, and the output is a follow-up notification.

[0538] Step 6:

[0539] The server compiles the story of the entire project. Based on the collected data and analysis results, it organizes important events and findings and saves them as a final report. The input is all analysis data and progress data, and the output is a report summarizing the story of the entire project.

[0540] Step 7:

[0541] The server collects robot operation data. Specifically, it periodically obtains operation status and error information from the robots in the factory. The input is operation data from the robots, and the output is the collected, unanalyzed operation data.

[0542] Step 8:

[0543] The server analyzes the collected robot operation data and detects anomalies. It uses machine learning algorithms to identify abnormal operations. The input is the operation data collected in step 7, and the output is the analysis data in which anomalies are detected.

[0544] Step 9:

[0545] The server automatically sends a notification if an anomaly is detected. Specifically, it notifies the person in charge of the anomaly via email or app notification. The input is the analysis data in which the anomaly was detected, and the output is the situation in which the notification was sent.

[0546] 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.

[0547] This system provides a series of methods for streamlining project management. Specifically, it collects all project-related data, analyzes it using natural language processing (NLP) and sentiment analysis, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on task progress and summarizes the project story. It also incorporates an emotion engine that recognizes the user's emotions, allowing it to analyze the user's emotional state and follow up and create reports based on that.

[0548] 1. Data collection

[0549] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[0550] 2. Data Analysis

[0551] The server passes the collected data to the NLP engine for analysis. The NLP engine is used to extract important topics and task progress from emails and messages. Furthermore, an emotion engine is used to identify emotions in the text data and evaluate the user's emotional state.

[0552] 3. Generate a report

[0553] Based on the results of analysis and sentiment analysis, the server generates daily, weekly, and monthly reports, including task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders.

[0554] 4. Early detection and sharing of issues

[0555] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[0556] 5. Follow-up

[0557] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, a follow-up email or notification will be sent.

[0558] 6. Summary of the project story

[0559] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0560] Specific examples

[0561] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress on a communication platform. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and messages from the communication platform, and applies NLP and an emotion engine to analyze important topics, task progress, and emotions. Next, a weekly report is generated based on the results of these analyses and sent to the project team.

[0562] Furthermore, if the progress of the task is delayed or if the emotion engine detects that User B is feeling stressed, the server will automatically send a follow-up notification to User B. Finally, based on all the analysis results, progress summary, and emotional state, the server generates an overall story of the project and saves it for easy access by the project manager.

[0563] In this way, the present invention provides detailed information on the progress of a project, supporting efficient management and problem-solving. Furthermore, the introduction of an emotion engine enables follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of the project.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] The user connects their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account. At this stage, the user logs into the system and completes the authentication process.

[0567] Step 2:

[0568] The server periodically collects users' emails and communication platform messages using the linked account information, obtains the data through the respective APIs, and stores it in its own database, which also contains metadata such as the collection date and time and the user's ID.

[0569] Step 3:

[0570] The server passes the collected data to a natural language processing (NLP) engine for analysis. The data includes email text, messages from communication platforms, and meeting minutes. The NLP engine extracts important keywords and topics from this text data.

[0571] Step 4:

[0572] The server uses an emotion engine to perform sentiment analysis based on the important keywords and topics extracted by the NLP engine. The emotion engine classifies the text content into emotional categories such as positive, negative, and neutral, which allows the emotional state of the project members to be evaluated.

[0573] Step 5:

[0574] Based on the analysis results of the NLP and emotion engine, the server generates daily, weekly, and monthly reports that include task progress, each member's contribution, important events, and sentiment trends. The reports are automatically sent to project stakeholders via email or communication platforms.

[0575] Step 6:

[0576] The server detects issues and bottlenecks from the analysis results. For example, it checks whether there are delays in tasks or unresolved issues. Detected issues are automatically notified to the relevant parties.

[0577] Step 7:

[0578] To address detected issues, the server sends follow-up notifications to relevant parties, including details of the problem and recommended actions to resolve it, helping to speed up problem resolution.

[0579] Step 8:

[0580] The server follows up on project members based on their task progress and emotional state. If progress is delayed or the emotional state is judged to be negative, follow-up emails and notifications are automatically sent.

[0581] Step 9:

[0582] The server will compile the story of the entire project, including the collected data, analysis results, emotional state, and significant events, and will organize the story into a final project report, which will be archived in a format that can be easily viewed by future generations.

[0583] In this way, each step works in tandem to ensure efficient project management and detailed understanding of overall progress, issues, and the emotional state of members.

[0584] Example 2

[0585] 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."

[0586] In traditional project management systems, data collection, analysis, report generation, and early issue detection and sharing are often done manually, which is inefficient and makes it difficult to properly understand and follow up on the emotional state of members.To solve this problem, automated data collection, analysis, report generation, follow-up, and emotional state management are needed.

[0587] 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.

[0588] In this invention, the server includes a means for accessing the user's email account and communication platform account using authentication information provided by the user and collecting all data related to the project, a means for passing the collected data to a natural language processing engine for analysis and extracting important topics and task progress, and a means for passing the data to an emotion engine for identifying emotions in the text and evaluating the user's emotional state, which significantly improves the efficiency of project management and enables appropriate follow-up taking into account the emotional state of members.

[0589] "Authentication information" refers to the information required to access a user's email account or communications platform account.

[0590] A "natural language processing engine" is a software component that analyzes text data and extracts important topics and task progress.

[0591] An "emotion engine" is a software component for identifying emotions in text data and assessing a user's emotional state.

[0592] A "Report" is a document generated based on the results of analysis and sentiment analysis, which describes the progress of a task, important events, each member's contribution, and sentiment trends.

[0593] "Issues" refer to problems such as delays in tasks and stagnation in problem-solving during project progress.

[0594] "Follow-up" refers to automated support and notifications based on each project member's task progress and emotional state.

[0595] A "project story" is a summary of the overall progress of a project, including important events and findings.

[0596] This system provides a series of methods to streamline project management. The server, terminals, and users play their respective roles, and the system automatically collects data, analyzes, generates reports, shares issues, follows up, and summarizes stories.

[0597] Data collection

[0598] The server uses the authentication information provided by the user to access the email account and communication platform account and collect data related to the project. Specifically, the user logs in to the system and links the email account and communication platform account. The server periodically obtains data using APIs such as Google Gmail API and Slack API.

[0599] Data analysis

[0600] The server passes the collected data to a natural language processing (NLP) engine for analysis. This NLP engine uses the Google Cloud Natural Language API and other tools to extract important topics and task progress from emails and messages. The server also uses an emotion engine to identify emotions within the text data. This emotion engine uses IBM Watson Tone Analyzer to evaluate the user's emotional state.

[0601] Generate reports

[0602] The server generates daily, weekly, and monthly reports based on the results of analysis and sentiment analysis. These reports include task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders via email or communication platforms.

[0603] Early detection and sharing of issues

[0604] The server detects issues and bottlenecks from the analysis results, such as delays in tasks and stalled problem-solving. The server automatically shares detected issues with relevant parties via email or a communication platform.

[0605] Performing follow-up

[0606] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, the server will send a follow-up email or notification.

[0607] Project Story Summary

[0608] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0609] Specific examples

[0610] For example, in a project team, User A sends weekly meeting minutes via email, and User B reports task progress via a communication platform. In this system, User A and User B's accounts are linked. The server periodically calls an API to collect the weekly meeting minutes emails and messages from the communication platform. This data is passed to an NLP engine and an emotion engine, which analyzes important topics, task progress, and emotional state. Based on the analysis results, the server generates a weekly report and sends it to the project team. In addition, if task progress is delayed or if the emotion engine detects that User B is feeling stressed, the server automatically sends a follow-up notification to User B. Finally, based on all the analysis results, an overall project story is generated and saved for easy access by the project manager.

[0611] Prompt Sentence Examples

[0612] "Using the minutes of daily project team meetings and messages from communication platforms, analyze the task progress and emotional state of members using NLP and an emotion engine to generate a weekly report."

[0613] This system streamlines all aspects of project management, providing detailed insight into progress and support for resolving issues. The introduction of an emotion engine also enables appropriate follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of projects.

[0614] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0615] Step 1:

[0616] A user logs into the system and enters their email account and communication platform account information, including their user ID and password, which then sends authentication information to the server, allowing the server to access the user's email server and communication platform.

[0617] Input: User ID, password, email account information, communication platform information

[0618] Output: Authentication information (token, etc.)

[0619] Step 2:

[0620] The server uses the obtained credentials to call APIs and collect data from mail servers and communication platforms, for example, Google Gmail API to retrieve emails and Slack API to retrieve messages, thus collecting all project-related data.

[0621] Input: Credentials, API call

[0622] Output: Collected data (emails, messages, etc.)

[0623] Step 3:

[0624] The server passes the collected data to a natural language processing (NLP) engine to begin analysis. The NLP engine (e.g., Google Cloud Natural Language API) is used to extract important topics and task progress from emails and messages. This analysis extracts specific keywords and context.

[0625] Input: Collected data

[0626] Output: Extracted topics and task progress information

[0627] Step 4:

[0628] The server then passes the collected text data to an emotion engine for sentiment analysis. Using an emotion engine (e.g., IBM Watson Tone Analyzer), emotions within the text are identified and the user's emotional state is assessed. This analysis results in an emotional label, such as positive, negative, or neutral.

[0629] Input: Collected text data

[0630] Output: Sentiment analysis results (emotion labels)

[0631] Step 5:

[0632] The server generates daily, weekly, and monthly reports based on the analysis results obtained from the NLP engine and the sentiment engine. The generated reports include task progress, important events, each member's contribution, and sentiment trends. Report templates are used to generate the reports.

[0633] Input: Extracted topics, task progress information, sentiment analysis results

[0634] Output: Generated report

[0635] Step 6:

[0636] The server automatically sends the generated report to the project stakeholders via email or a communication platform, for example, sending the report to all project participants via email.

[0637] Input: Generated report

[0638] Output: Report sent (e.g. email)

[0639] Step 7:

[0640] The server uses algorithms to detect issues and bottlenecks from the analysis results, identifying delays in tasks and stalled problem-solving, and records the detected issues along with suggestions for resolving them.

[0641] Input: Analysis results

[0642] Output: Detected issues and their suggestions

[0643] Step 8:

[0644] The server shares detected issues with the relevant parties via email notifications and messages on the communication platform, allowing them to address the issues early.

[0645] Input: Detected issues and their suggestions

[0646] Output: Issue notifications (emails, messages, etc.)

[0647] Step 9:

[0648] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or emotional analysis indicates that support is needed, follow-up emails and notifications are sent.

[0649] Input: Task progress, sentiment analysis results

[0650] Output: Follow-up notification (email, message, etc.)

[0651] Step 10:

[0652] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0653] Input: Collected data, analysis results

[0654] Output: Final report (project story)

[0655] The above is the specific processing flow in implementing this system.

[0656] (Application example 2)

[0657] 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."

[0658] In modern factories, many tasks are performed by multiple work machines. Therefore, it is important to accurately grasp the progress of tasks and manage them efficiently. Furthermore, the emotional state of the work machine operators also has a significant impact on production efficiency, but there are currently insufficient means to appropriately grasp and support this. In such situations, task delays and reduced efficiency due to operator stress are likely to occur, significantly impacting the entire production operation. Therefore, a system is needed that can analyze the progress of tasks and the emotional state of operators in real time and provide appropriate follow-up and improvement measures.

[0659] 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.

[0660] In this invention, the server includes means for collecting all data related to the project, means for analyzing the task progress of the work machine, and means for analyzing the emotional state of the operator of the work machine. This makes it possible to grasp the task progress and the emotional state of the operator in real time, and to propose appropriate follow-up and improvement measures.

[0661] A "data collection means" is a mechanical or software component that captures and stores any data generated by the work machine and its operator.

[0662] "Means for analyzing data" refers to mechanical or software components that analyze collected data using techniques such as natural language processing and sentiment analysis to extract useful information.

[0663] The "means for generating a report" refers to a mechanical or software component that creates a report in a predetermined format based on the analysis results and provides it to the relevant parties.

[0664] "Means for early detection and sharing of issues" refers to mechanical or software components that detect bottlenecks and problems from the analysis results and quickly notify the relevant parties.

[0665] The "means for automatically performing task follow-up" is a mechanical or software component for automatically providing necessary follow-up notification or assistance based on the progress of the task of the work machine and the emotional state of the operator.

[0666] A "means for summarizing the overall project story" is a mechanical or software component that organizes the overall project progress and knowledge gained based on collected data and analysis results, and stores it in a format that can be easily referenced in the future.

[0667] "Work machine" refers to any mechanical device that performs a task in a factory or manufacturing site.

[0668] "Operator" means a person operating a work machine.

[0669] This invention is a system aimed at efficient management of factory robots and their operators. This system has the following components:

[0670] System Configuration

[0671] 1. Data Collection Methods

[0672] The server collects data from the work machines and their operators in real time, including the task progress of each work machine, work records entered by the operators, and sensing data. This data is sent over the network and stored on the server.

[0673] 2. Data analysis methods

[0674] The server uses an NLP (natural language processing) engine and an emotion engine to analyze the collected data. The NLP engine analyzes the task progress of the work machine and extracts important topics and task progress. The emotion engine also identifies and evaluates the emotional state of the operator from the text data.

[0675] 3. Report Generation Methods

[0676] Based on the results of data analysis, the server generates daily, weekly, and monthly reports, including task progress, key events, individual operator contributions, and sentiment trends, and the generated reports are automatically sent to relevant parties.

[0677] 4. Early detection and sharing of issues

[0678] Based on the results obtained from the data analysis tools, the server automatically detects issues and bottlenecks, such as delays in tasks or increased stress among operators. These issues are automatically shared with the relevant parties, enabling early action to be taken.

[0679] 5. Follow-up measures

[0680] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. For example, it notifies an operator whose task is delayed to report progress, and notifies an operator whose emotional state is deteriorating to provide support.

[0681] 6. Project Story Summary

[0682] The server will compile a story of the project based on the overall progress of the project and the knowledge gained, allowing future generations to easily understand the overall picture of the project.

[0683] Specific examples

[0684] For example, when welding work is being carried out in a factory, an operator inputs task progress and collects data from the work machine in real time. The server analyzes this data and evaluates the task progress and the operator's emotional state. If the operator is feeling stressed, the server automatically sends a follow-up notification to encourage support. Reports summarizing the overall progress are also periodically generated and sent to relevant parties.

[0685] Prompt Sentence Examples

[0686] Enter the following task details:

[0687] Task ID: __

[0688] Progress:__

[0689] More information:

[0690]

[0691] Enter the following task details:

[0692] Task ID: 1

[0693] Progress: In progress

[0694] Detailed information: Welding parts A and B

[0695] Such a system will enable efficient management of work machines and operators within a factory, making it possible to grasp the progress of tasks and the emotional state of operators, and to provide appropriate follow-up.

[0696] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0697] Step 1:

[0698] The server collects data from the work machines and operators. Specifically, it receives task progress data from each work machine via the network, and text data on input work records and emotional states from the operators. This input data is stored in a database within the server.

[0699] Step 2:

[0700] The server passes the collected data to a natural language processing (NLP) engine and begins analysis. The server's NLP engine extracts important topics and work progress information from the text data of the work machine's task progress. This analysis reveals the detailed progress of each task and related issues. The output is a list of important topics and progress information.

[0701] Step 3:

[0702] The server passes the collected emotion data to the emotion engine for emotion analysis. The emotion engine evaluates the emotional state of the operator (e.g., stress, satisfaction, anxiety, etc.) from the text data. The evaluation results are output as an emotional state score for each operator.

[0703] Step 4:

[0704] The server integrates the analysis results from the NLP engine and the emotion engine to generate daily, weekly, and monthly reports, including task progress, important events, and the emotional state of operators. The generated reports are automatically sent to designated stakeholders via email or platform notifications.

[0705] Step 5:

[0706] The server automatically detects issues and bottlenecks from the analysis results. For example, if a task is delayed or an operator's emotional score is declining, it extracts related issues. Detected issues are automatically notified to the relevant parties, urging them to take early action. The output is a list of issues and their notifications.

[0707] Step 6:

[0708] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. Specifically, it sends a progress report reminder to operators whose tasks are delayed, and a notification urging appropriate support to operators whose emotional state is deteriorating. The aforementioned analysis results are used as input data.

[0709] Step 7:

[0710] Based on the overall progress and findings of the project, the server compiles a story of the project, including important events, progress, and the emotional state of the operators, and stores this story in a specific format for future generations.

[0711] By dividing the process into steps in this way, efficient management of the work machines and operators within the factory can be achieved.

[0712] 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.

[0713] 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.

[0714] 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.

[0715] [Third embodiment]

[0716] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0717] 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.

[0718] 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).

[0719] 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.

[0720] 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.

[0721] 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).

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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."

[0728] This system provides a series of means for streamlining project management. Specifically, it collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on the progress of tasks and summarizes the project story. An embodiment of this system is described in detail below.

[0729] 1. Data collection

[0730] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[0731] 2. Data Analysis

[0732] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it analyzes the content of emails and messages to extract important topics, track task progress, and classify sentiment. This allows for a detailed understanding of the current status of the project.

[0733] 3. Generate a report

[0734] The server generates daily, weekly, and monthly reports based on the analysis results, including task progress, important events, and each member's contribution, and the reports are automatically sent to project stakeholders.

[0735] 4. Early detection and sharing of issues

[0736] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[0737] 5. Follow-up

[0738] The server automatically follows up on each project member's task progress, and if progress is delayed or support is needed, follow-up emails and notifications are sent.

[0739] 6. Summary of the project story

[0740] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0741] Specific examples

[0742] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, a weekly report is generated based on these analysis results and sent to the project team.

[0743] Furthermore, if the server detects that the task progress is delayed, it will automatically send a follow-up notification to User B. Finally, based on all the analysis results and progress summary, it will generate the overall story of the project and save it for easy access by the project manager.

[0744] In this way, the present invention provides detailed information on the progress of a project and supports efficient management and problem solving.

[0745] The processing flow will be explained below.

[0746] Step 1:

[0747] Users connect their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account.

[0748] Step 2:

[0749] The server periodically collects emails and messages related to the project using the linked account information, retrieves data from email servers and communication platforms via API, and stores it in its own database.

[0750] Step 3:

[0751] The server passes the collected data to a natural language processing (NLP) engine for analysis, which is used to extract important topics and task progress from emails and messages.

[0752] Step 4:

[0753] The server performs sentiment analysis based on the extracted information, identifying positive, negative, and neutral emotions in the text data to understand the mental state of project members.

[0754] Step 5:

[0755] The server generates daily, weekly, and monthly reports, summarizing the analysis results and including each member's task progress, important events, and sentiment trends.

[0756] Step 6:

[0757] The server automatically sends the generated reports to project stakeholders, who can share them via email or communication platforms to make the project status transparent.

[0758] Step 7:

[0759] The server detects issues and bottlenecks from the analysis results, identifying delays in tasks and unresolved issues and labeling the information.

[0760] Step 8:

[0761] The server shares detected issues with relevant parties, sending notifications via email or communication platforms to encourage early problem resolution.

[0762] Step 9:

[0763] The server follows up on each member's task progress and, if necessary, automatically sends reminders or support requests to members who are lagging behind.

[0764] Step 10:

[0765] The server will compile the story of the entire project, organizing key events and findings based on collected data and analysis results, and storing them in a format that can be easily accessed by future generations.

[0766] In this way, each step works in tandem, making project management more efficient and clarifying overall progress and issues.

[0767] Example 1

[0768] 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."

[0769] Project management requires a lot of data and communication, making it difficult to detect delays and issues early. Centralized management and analysis of information is particularly difficult for teams using multiple platforms. Manually managing task progress and following up on tasks takes a great deal of time and effort. Furthermore, compiling the entire project story is time-consuming, making efficient project management essential.

[0770] 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.

[0771] In this invention, the server includes means for accessing external services using authentication information provided by the user and collecting all data related to the project, means for analyzing the collected data using natural language processing and sentiment analysis, means for generating daily, weekly, and monthly reports based on the analysis results, means for early detection of issues from the analysis results and sharing them in real time, means for monitoring the progress of tasks as the project progresses and automatically performing follow-up, and means for compiling a story of the entire project based on the collected data and analysis results.This enables centralized management and analysis of data in project management, visualization of progress, early detection of issues, efficient follow-up, and project summary.

[0772] "Authentication Information" means information required for a User to access their account, including a username, password, API key, etc.

[0773] "External services" refers to online services such as email accounts and communication platforms that users use on a daily basis.

[0774] "Data Collection Methods" refers to the methods and technologies used to obtain relevant data from external services.

[0775] "Natural language processing" is a technology that enables computers to understand, interpret, and manipulate human language, and performs tasks such as text analysis and topic extraction.

[0776] "Sentiment analysis" refers to the technology of classifying emotions expressed in text into "positive," "negative," "neutral," etc.

[0777] "Report generation means" refers to the methods and techniques for creating reports based on analyzed data.

[0778] "Problem detection methods" refer to methods and techniques for early detection of problems and bottlenecks during the project.

[0779] "Sharing means" refers to the methods and techniques used to communicate discovered issues and important information to project members.

[0780] "Follow-up measures" refer to technologies that monitor task progress and automatically send reminders or support notifications as needed.

[0781] A "project story" is a report that summarizes the overall progress and important events of a project.

[0782] This invention is a system for streamlining project management, providing the following set of means: This system collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically performs follow-up according to the progress of tasks and can compile the story of the entire project.

[0783] Data collection

[0784] The server accesses external services (e.g., email accounts and communication platforms) using the authentication information provided by the user. Specifically, the user logs in to the system and connects their email account (e.g., Google Gmail) and communication platform (e.g., Slack, Microsoft Teams) accounts. This allows the server to periodically call APIs (e.g., Gmail API, Slack API) to collect data related to the project (e.g., emails, chat messages, file attachments, etc.).

[0785] Data analysis

[0786] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses NLP tools such as Google Natural Language API and IBM Watson to analyze the content of emails and messages and extract important topics. It can also classify the emotional state of the text as "positive," "negative," or "neutral." This analysis provides a detailed understanding of the current status of the project.

[0787] Generate reports

[0788] The server automatically generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, and sends the reports to project stakeholders via email or communication platforms.

[0789] Early detection and sharing of issues

[0790] The server uses the analysis results to quickly identify issues such as task delays and stalled problem-solving. Detected issues are shared with project stakeholders in real time via email or communication platforms.

[0791] Performing follow-up

[0792] The server monitors the task progress of each project member and automatically sends follow-up notifications if progress is delayed or if support is required, allowing users to respond promptly.

[0793] Project Story Summary

[0794] The server aggregates key events and findings from the entire project based on data and analysis, generating a final report that summarizes the overall project story and saving it in an easily accessible format for future project reference.

[0795] Examples and prompts

[0796] In a project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. The system first links the accounts of User A and User B. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, it generates a weekly report based on these analysis results and sends it to the project team. If it detects that task progress is behind schedule, the server automatically sends a follow-up notification to User B. Finally, based on all analysis results and a summary of progress, it generates an overall project story and saves it for easy access by project managers.

[0797] An example of a prompt is, "Based on the following text, please provide the user with an overview of a system that provides project progress reports and issue notifications."

[0798] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0799] Step 1:

[0800] When logging in to the system, users enter their email account and communication platform authentication information, which is then used by the server to access external services. Specifically, users enter their email address and password on the login screen and are authenticated using OAuth 2.0.

[0801] Input: User's email account, communication platform account information

[0802] Output: OAuth token (authentication information)

[0803] Step 2:

[0804] The server uses the obtained credentials to access external services (email accounts and communication platforms) and collect data related to the project. For example, it uses the Gmail API or Slack API to retrieve emails and chat messages. These operations are performed automatically on a regular basis.

[0805] Input: OAuth token

[0806] Output: Collected email and chat message data

[0807] Step 3:

[0808] The server normalizes the collected data, for example converting email bodies or chat messages into text data, so that a consistent format of data is available for subsequent analysis steps.

[0809] Input: Collected email and chat message data

[0810] Output: Normalized text data

[0811] Step 4:

[0812] The server then analyzes the normalized data using natural language processing (NLP) and sentiment analysis tools, such as Google Natural Language API and IBM Watson, to extract key keywords from the text and classify the emotional state as "positive," "negative," or "neutral."

[0813] Input: normalized text data

[0814] Output: Analysis results (important keywords, sentiment classification)

[0815] Step 5:

[0816] The server generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, often in JSON or PDF format.

[0817] Input: Analysis results

[0818] Output: Report (JSON format, PDF format)

[0819] Step 6:

[0820] The server then sends the generated reports to project stakeholders via email or a communication platform, automatically distributing the reports using the API of the email server or communication platform.

[0821] Input: Report

[0822] Output: Report sent

[0823] Step 7:

[0824] The server uses the analysis results to detect issues such as task delays and stalled problem-solving. For example, it detects tasks that have not progressed for a certain period of time and lists them as issues.

[0825] Input: Analysis results

[0826] Output: Detected issues

[0827] Step 8:

[0828] The server notifies relevant parties of detected issues in real time via email or a communication platform, and includes the specific details of the issue and a request for action.

[0829] Input: Detected issues

[0830] Output: Issue notification sent

[0831] Step 9:

[0832] The server monitors the task progress of each project member and automatically sends follow-up notifications in the form of emails or messages if there is no progress or delays for a certain period of time.

[0833] Input: Task progress data

[0834] Output: Follow-up notification

[0835] Step 10:

[0836] The server will organize the project's important events and findings based on the data and analysis results of the entire project, and will then compile the overall story of the project into a final report.

[0837] Input: Data and analysis results

[0838] Output: The story of the entire project

[0839] Step 11:

[0840] The server stores the generated project stories in an easily accessible format for future reference, and the reports are stored in a database for easy retrieval and viewing later.

[0841] Input: The overall story of the project

[0842] Output: Saved report

[0843] (Application example 1)

[0844] 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."

[0845] Conventional project management systems have the drawback of being inefficient due to the time and effort required for data collection, analysis, and report generation. They also lack the functionality to detect and respond to abnormalities and issues early, which often leads to human error and time lags, especially in the maintenance management of factory robots.

[0846] 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.

[0847] In this invention, the server includes a means for collecting all data related to the project, a means for analyzing the data to detect abnormalities, a means for generating a maintenance report, and a means for sending a notification when an abnormality is detected. This allows for efficient project management and maintenance management of factory robots, and enables early detection of problems and rapid response.

[0848] "All data related to the project" refers to all information related to the project, such as emails, chats, task management tools, and sentiment analysis results.

[0849] "Robot operation data" refers to all information related to the operation of robots used in factories, such as their operating status, error information, and operating hours.

[0850] "Means of analyzing data to detect anomalies" refers to functions that analyze collected data using technologies such as natural language processing, sentiment analysis, and machine learning to detect anomalies and problems.

[0851] "Means for generating a maintenance report" refers to a function that automatically creates a report summarizing the robot's maintenance status and required maintenance tasks based on the analysis results.

[0852] "Means for sending notifications when an abnormality is detected" refers to the function of notifying the person in charge by email, app notification, or other means when the system detects an abnormality in the robot or a situation requiring emergency maintenance.

[0853] "A means of summarizing the story of the entire project" refers to a function that allows you to summarize all important events and progress from the start to the end of the project as a series of stories.

[0854] To realize this invention, a server, a user terminal (such as a smartphone or PC), and necessary software are required. Specifically, the server plays the following roles:

[0855] First, the server collects all data related to the project. This includes data from email platforms and communication tools, and periodically retrieves data using APIs. Data collection begins when a user logs in to the system and links their platform accounts.

[0856] The server then analyzes the collected data, applying natural language processing (NLP) and sentiment analysis to extract topics from the data content and classify emotions. After analysis, the robot's operational data is also analyzed. Specifically, machine learning algorithms are used to detect abnormalities in operational status.

[0857] Based on the analysis results, the server generates daily, weekly, and monthly reports that include project progress, key events, contributions of each member, and robot maintenance requirements, and these reports are automatically sent to the user's device.

[0858] The server also uses the analysis results to quickly identify issues and share them with relevant parties. For example, it detects delays in tasks or stalled resolutions and notifies relevant users via email or app notifications.

[0859] Additionally, the server automatically performs follow-up on tasks as the project progresses: if a task is delayed or if support is needed, follow-up notifications are sent.

[0860] Finally, the server will compile the overall story of the project, including organizing key events and learnings from the project based on the collected data and analysis results, and preserving them for posterity.

[0861] Hardware and software used:

[0862] Server: Cloud-based Amazon Web Services (AWS) or Google Cloud Platform (GCP)

[0863] User devices: smartphones, PCs

[0864] Natural Language Processing: NLTK (Python library)

[0865] Sentiment Analysis: VADER Sentiment Analysis (part of NLTK)

[0866] Data frame operations: pandas (Python library)

[0867] HTTP requests: requests (Python library)

[0868] Sending email: smtplib (Python library)

[0869] Examples:

[0870] Two users, User A and User B, are participating in a factory project. The server collects User A's email meeting minutes and User B's messages from their communication tools, and applies NLP and sentiment analysis to extract important topics and emotions. A weekly report is then generated and sent to the user. In addition, robot operation data is also collected and analyzed, and if an abnormality is detected, a notification is sent to the person in charge.

[0871] Example prompt sentence:

[0872] "Analyze the robot's operating status and generate a report based on the following data."

[0873] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0874] Step 1:

[0875] The server uses the credentials provided by the user to access email accounts and communication platform accounts and collect data related to the project. Specifically, the server periodically calls an API to retrieve the contents of emails and messages. The input is the user's credentials and the associated account, and the output is the collected, unanalyzed data.

[0876] Step 2:

[0877] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses an NLP library (such as NLTK) to classify important topics and sentiment. The input is the raw data collected in step 1, and the output is the analyzed data with classified topics and sentiment.

[0878] Step 3:

[0879] The server generates daily, weekly, and monthly reports based on the analysis results. Specifically, it aggregates the analysis data and summarizes progress and important events. The input is the analysis data obtained in step 2, and the output is the report.

[0880] Step 4:

[0881] The server detects issues and bottlenecks from the analysis results and shares them with relevant parties. For example, it detects task delays and stalls in problem-solving and automatically sends notifications via email or communication platforms. The input is the analysis results data, and the output is notifications to each relevant party.

[0882] Step 5:

[0883] The server automatically follows up on each project member's task progress. If progress is delayed or support is deemed necessary, a follow-up email or notification is sent. The input is task progress data, and the output is a follow-up notification.

[0884] Step 6:

[0885] The server compiles the story of the entire project. Based on the collected data and analysis results, it organizes important events and findings and saves them as a final report. The input is all analysis data and progress data, and the output is a report summarizing the story of the entire project.

[0886] Step 7:

[0887] The server collects robot operation data. Specifically, it periodically obtains operation status and error information from the robots in the factory. The input is operation data from the robots, and the output is the collected, unanalyzed operation data.

[0888] Step 8:

[0889] The server analyzes the collected robot operation data and detects anomalies. It uses machine learning algorithms to identify abnormal operations. The input is the operation data collected in step 7, and the output is the analysis data in which anomalies are detected.

[0890] Step 9:

[0891] The server automatically sends a notification if an anomaly is detected. Specifically, it notifies the person in charge of the anomaly via email or app notification. The input is the analysis data in which the anomaly was detected, and the output is the situation in which the notification was sent.

[0892] 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.

[0893] This system provides a series of methods for streamlining project management. Specifically, it collects all project-related data, analyzes it using natural language processing (NLP) and sentiment analysis, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on task progress and summarizes the project story. It also incorporates an emotion engine that recognizes the user's emotions, allowing it to analyze the user's emotional state and follow up and create reports based on that.

[0894] 1. Data collection

[0895] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[0896] 2. Data Analysis

[0897] The server passes the collected data to the NLP engine for analysis. The NLP engine is used to extract important topics and task progress from emails and messages. Furthermore, an emotion engine is used to identify emotions in the text data and evaluate the user's emotional state.

[0898] 3. Generate a report

[0899] Based on the results of analysis and sentiment analysis, the server generates daily, weekly, and monthly reports, including task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders.

[0900] 4. Early detection and sharing of issues

[0901] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[0902] 5. Follow-up

[0903] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, a follow-up email or notification will be sent.

[0904] 6. Summary of the project story

[0905] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0906] Specific examples

[0907] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress on a communication platform. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and messages from the communication platform, and applies NLP and an emotion engine to analyze important topics, task progress, and emotions. Next, a weekly report is generated based on the results of these analyses and sent to the project team.

[0908] Furthermore, if the progress of the task is delayed or if the emotion engine detects that User B is feeling stressed, the server will automatically send a follow-up notification to User B. Finally, based on all the analysis results, progress summary, and emotional state, the server generates an overall story of the project and saves it for easy access by the project manager.

[0909] In this way, the present invention provides detailed information on the progress of a project, supporting efficient management and problem-solving. Furthermore, the introduction of an emotion engine enables follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of the project.

[0910] The processing flow will be explained below.

[0911] Step 1:

[0912] The user connects their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account. At this stage, the user logs into the system and completes the authentication process.

[0913] Step 2:

[0914] The server periodically collects users' emails and communication platform messages using the linked account information, obtains the data through the respective APIs, and stores it in its own database, which also contains metadata such as the collection date and time and the user's ID.

[0915] Step 3:

[0916] The server passes the collected data to a natural language processing (NLP) engine for analysis. The data includes email text, messages from communication platforms, and meeting minutes. The NLP engine extracts important keywords and topics from this text data.

[0917] Step 4:

[0918] The server uses an emotion engine to perform sentiment analysis based on the important keywords and topics extracted by the NLP engine. The emotion engine classifies the text content into emotional categories such as positive, negative, and neutral, which allows the emotional state of the project members to be evaluated.

[0919] Step 5:

[0920] Based on the analysis results of the NLP and emotion engine, the server generates daily, weekly, and monthly reports that include task progress, each member's contribution, important events, and sentiment trends. The reports are automatically sent to project stakeholders via email or communication platforms.

[0921] Step 6:

[0922] The server detects issues and bottlenecks from the analysis results. For example, it checks whether there are delays in tasks or unresolved issues. Detected issues are automatically notified to the relevant parties.

[0923] Step 7:

[0924] To address detected issues, the server sends follow-up notifications to relevant parties, including details of the problem and recommended actions to resolve it, helping to speed up problem resolution.

[0925] Step 8:

[0926] The server follows up on project members based on their task progress and emotional state. If progress is delayed or the emotional state is judged to be negative, follow-up emails and notifications are automatically sent.

[0927] Step 9:

[0928] The server will compile the story of the entire project, including the collected data, analysis results, emotional state, and significant events, and will organize the story into a final project report, which will be archived in a format that can be easily viewed by future generations.

[0929] In this way, each step works in tandem to ensure efficient project management and detailed understanding of overall progress, issues, and the emotional state of members.

[0930] Example 2

[0931] 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."

[0932] In traditional project management systems, data collection, analysis, report generation, and early issue detection and sharing are often done manually, which is inefficient and makes it difficult to properly understand and follow up on the emotional state of members.To solve this problem, automated data collection, analysis, report generation, follow-up, and emotional state management are needed.

[0933] 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.

[0934] In this invention, the server includes a means for accessing the user's email account and communication platform account using authentication information provided by the user and collecting all data related to the project, a means for passing the collected data to a natural language processing engine for analysis and extracting important topics and task progress, and a means for passing the data to an emotion engine for identifying emotions in the text and evaluating the user's emotional state, which significantly improves the efficiency of project management and enables appropriate follow-up taking into account the emotional state of members.

[0935] "Authentication information" refers to the information required to access a user's email account or communications platform account.

[0936] A "natural language processing engine" is a software component that analyzes text data and extracts important topics and task progress.

[0937] An "emotion engine" is a software component for identifying emotions in text data and assessing a user's emotional state.

[0938] A "Report" is a document generated based on the results of analysis and sentiment analysis, which describes the progress of a task, important events, each member's contribution, and sentiment trends.

[0939] "Issues" refer to problems such as delays in tasks and stagnation in problem-solving during project progress.

[0940] "Follow-up" refers to automated support and notifications based on each project member's task progress and emotional state.

[0941] A "project story" is a summary of the overall progress of a project, including important events and findings.

[0942] This system provides a series of methods to streamline project management. The server, terminals, and users play their respective roles, and the system automatically collects data, analyzes, generates reports, shares issues, follows up, and summarizes stories.

[0943] Data collection

[0944] The server uses the authentication information provided by the user to access the email account and communication platform account and collect data related to the project. Specifically, the user logs in to the system and links the email account and communication platform account. The server periodically obtains data using APIs such as Google Gmail API and Slack API.

[0945] Data analysis

[0946] The server passes the collected data to a natural language processing (NLP) engine for analysis. This NLP engine uses the Google Cloud Natural Language API and other tools to extract important topics and task progress from emails and messages. The server also uses an emotion engine to identify emotions within the text data. This emotion engine uses IBM Watson Tone Analyzer to evaluate the user's emotional state.

[0947] Generate reports

[0948] The server generates daily, weekly, and monthly reports based on the results of analysis and sentiment analysis. These reports include task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders via email or communication platforms.

[0949] Early detection and sharing of issues

[0950] The server detects issues and bottlenecks from the analysis results, such as delays in tasks and stalled problem-solving. The server automatically shares detected issues with relevant parties via email or a communication platform.

[0951] Performing follow-up

[0952] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, the server will send a follow-up email or notification.

[0953] Project Story Summary

[0954] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0955] Specific examples

[0956] For example, in a project team, User A sends weekly meeting minutes via email, and User B reports task progress via a communication platform. In this system, User A and User B's accounts are linked. The server periodically calls an API to collect the weekly meeting minutes emails and messages from the communication platform. This data is passed to an NLP engine and an emotion engine, which analyzes important topics, task progress, and emotional state. Based on the analysis results, the server generates a weekly report and sends it to the project team. In addition, if task progress is delayed or if the emotion engine detects that User B is feeling stressed, the server automatically sends a follow-up notification to User B. Finally, based on all the analysis results, an overall project story is generated and saved for easy access by the project manager.

[0957] Prompt Sentence Examples

[0958] "Using the minutes of daily project team meetings and messages from communication platforms, analyze the task progress and emotional state of members using NLP and an emotion engine to generate a weekly report."

[0959] This system streamlines all aspects of project management, providing detailed insight into progress and support for resolving issues. The introduction of an emotion engine also enables appropriate follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of projects.

[0960] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0961] Step 1:

[0962] A user logs into the system and enters their email account and communication platform account information, including their user ID and password, which then sends authentication information to the server, allowing the server to access the user's email server and communication platform.

[0963] Input: User ID, password, email account information, communication platform information

[0964] Output: Authentication information (token, etc.)

[0965] Step 2:

[0966] The server uses the obtained credentials to call APIs and collect data from mail servers and communication platforms, for example, Google Gmail API to retrieve emails and Slack API to retrieve messages, thus collecting all project-related data.

[0967] Input: Credentials, API call

[0968] Output: Collected data (emails, messages, etc.)

[0969] Step 3:

[0970] The server passes the collected data to a natural language processing (NLP) engine to begin analysis. The NLP engine (e.g., Google Cloud Natural Language API) is used to extract important topics and task progress from emails and messages. This analysis extracts specific keywords and context.

[0971] Input: Collected data

[0972] Output: Extracted topics and task progress information

[0973] Step 4:

[0974] The server then passes the collected text data to an emotion engine for sentiment analysis. Using an emotion engine (e.g., IBM Watson Tone Analyzer), emotions within the text are identified and the user's emotional state is assessed. This analysis results in an emotional label, such as positive, negative, or neutral.

[0975] Input: Collected text data

[0976] Output: Sentiment analysis results (emotion labels)

[0977] Step 5:

[0978] The server generates daily, weekly, and monthly reports based on the analysis results obtained from the NLP engine and the sentiment engine. The generated reports include task progress, important events, each member's contribution, and sentiment trends. Report templates are used to generate the reports.

[0979] Input: Extracted topics, task progress information, sentiment analysis results

[0980] Output: Generated report

[0981] Step 6:

[0982] The server automatically sends the generated report to the project stakeholders via email or a communication platform, for example, sending the report to all project participants via email.

[0983] Input: Generated report

[0984] Output: Report sent (e.g. email)

[0985] Step 7:

[0986] The server uses algorithms to detect issues and bottlenecks from the analysis results, identifying delays in tasks and stalled problem-solving, and records the detected issues along with suggestions for resolving them.

[0987] Input: Analysis results

[0988] Output: Detected issues and their suggestions

[0989] Step 8:

[0990] The server shares detected issues with the relevant parties via email notifications and messages on the communication platform, allowing them to address the issues early.

[0991] Input: Detected issues and their suggestions

[0992] Output: Issue notifications (emails, messages, etc.)

[0993] Step 9:

[0994] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or emotional analysis indicates that support is needed, follow-up emails and notifications are sent.

[0995] Input: Task progress, sentiment analysis results

[0996] Output: Follow-up notification (email, message, etc.)

[0997] Step 10:

[0998] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[0999] Input: Collected data, analysis results

[1000] Output: Final report (project story)

[1001] The above is the specific processing flow in implementing this system.

[1002] (Application example 2)

[1003] 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."

[1004] In modern factories, many tasks are performed by multiple work machines. Therefore, it is important to accurately grasp the progress of tasks and manage them efficiently. Furthermore, the emotional state of the work machine operators also has a significant impact on production efficiency, but there are currently insufficient means to appropriately grasp and support this. In such situations, task delays and reduced efficiency due to operator stress are likely to occur, significantly impacting the entire production operation. Therefore, a system is needed that can analyze the progress of tasks and the emotional state of operators in real time and provide appropriate follow-up and improvement measures.

[1005] 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.

[1006] In this invention, the server includes means for collecting all data related to the project, means for analyzing the task progress of the work machine, and means for analyzing the emotional state of the operator of the work machine. This makes it possible to grasp the task progress and the emotional state of the operator in real time, and to propose appropriate follow-up and improvement measures.

[1007] A "data collection means" is a mechanical or software component that captures and stores any data generated by the work machine and its operator.

[1008] "Means for analyzing data" refers to mechanical or software components that analyze collected data using techniques such as natural language processing and sentiment analysis to extract useful information.

[1009] The "means for generating a report" refers to a mechanical or software component that creates a report in a predetermined format based on the analysis results and provides it to the relevant parties.

[1010] "Means for early detection and sharing of issues" refers to mechanical or software components that detect bottlenecks and problems from the analysis results and quickly notify the relevant parties.

[1011] The "means for automatically performing task follow-up" is a mechanical or software component for automatically providing necessary follow-up notification or assistance based on the progress of the task of the work machine and the emotional state of the operator.

[1012] A "means for summarizing the overall project story" is a mechanical or software component that organizes the overall project progress and knowledge gained based on collected data and analysis results, and stores it in a format that can be easily referenced in the future.

[1013] "Work machine" refers to any mechanical device that performs a task in a factory or manufacturing site.

[1014] "Operator" means a person operating a work machine.

[1015] This invention is a system aimed at efficient management of factory robots and their operators. This system has the following components:

[1016] System Configuration

[1017] 1. Data Collection Methods

[1018] The server collects data from the work machines and their operators in real time, including the task progress of each work machine, work records entered by the operators, and sensing data. This data is sent over the network and stored on the server.

[1019] 2. Data analysis methods

[1020] The server uses an NLP (natural language processing) engine and an emotion engine to analyze the collected data. The NLP engine analyzes the task progress of the work machine and extracts important topics and task progress. The emotion engine also identifies and evaluates the emotional state of the operator from the text data.

[1021] 3. Report Generation Methods

[1022] Based on the results of data analysis, the server generates daily, weekly, and monthly reports, including task progress, key events, individual operator contributions, and sentiment trends, and the generated reports are automatically sent to relevant parties.

[1023] 4. Early detection and sharing of issues

[1024] Based on the results obtained from the data analysis tools, the server automatically detects issues and bottlenecks, such as delays in tasks or increased stress among operators. These issues are automatically shared with the relevant parties, enabling early action to be taken.

[1025] 5. Follow-up measures

[1026] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. For example, it notifies an operator whose task is delayed to report progress, and notifies an operator whose emotional state is deteriorating to provide support.

[1027] 6. Project Story Summary

[1028] The server will compile a story of the project based on the overall progress of the project and the knowledge gained, allowing future generations to easily understand the overall picture of the project.

[1029] Specific examples

[1030] For example, when welding work is being carried out in a factory, an operator inputs task progress and collects data from the work machine in real time. The server analyzes this data and evaluates the task progress and the operator's emotional state. If the operator is feeling stressed, the server automatically sends a follow-up notification to encourage support. Reports summarizing the overall progress are also periodically generated and sent to relevant parties.

[1031] Prompt Sentence Examples

[1032] Enter the following task details:

[1033] Task ID: __

[1034] Progress:__

[1035] More information:

[1036]

[1037] Enter the following task details:

[1038] Task ID: 1

[1039] Progress: In progress

[1040] Detailed information: Welding parts A and B

[1041] Such a system will enable efficient management of work machines and operators within a factory, making it possible to grasp the progress of tasks and the emotional state of operators, and to provide appropriate follow-up.

[1042] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1043] Step 1:

[1044] The server collects data from the work machines and operators. Specifically, it receives task progress data from each work machine via the network, and text data on input work records and emotional states from the operators. This input data is stored in a database within the server.

[1045] Step 2:

[1046] The server passes the collected data to a natural language processing (NLP) engine and begins analysis. The server's NLP engine extracts important topics and work progress information from the text data of the work machine's task progress. This analysis reveals the detailed progress of each task and related issues. The output is a list of important topics and progress information.

[1047] Step 3:

[1048] The server passes the collected emotion data to the emotion engine for emotion analysis. The emotion engine evaluates the emotional state of the operator (e.g., stress, satisfaction, anxiety, etc.) from the text data. The evaluation results are output as an emotional state score for each operator.

[1049] Step 4:

[1050] The server integrates the analysis results from the NLP engine and the emotion engine to generate daily, weekly, and monthly reports, including task progress, important events, and the emotional state of operators. The generated reports are automatically sent to designated stakeholders via email or platform notifications.

[1051] Step 5:

[1052] The server automatically detects issues and bottlenecks from the analysis results. For example, if a task is delayed or an operator's emotional score is declining, it extracts related issues. Detected issues are automatically notified to the relevant parties, urging them to take early action. The output is a list of issues and their notifications.

[1053] Step 6:

[1054] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. Specifically, it sends a progress report reminder to operators whose tasks are delayed, and a notification urging appropriate support to operators whose emotional state is deteriorating. The aforementioned analysis results are used as input data.

[1055] Step 7:

[1056] Based on the overall progress and findings of the project, the server compiles a story of the project, including important events, progress, and the emotional state of the operators, and stores this story in a specific format for future generations.

[1057] By dividing the process into steps in this way, efficient management of the work machines and operators within the factory can be achieved.

[1058] 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.

[1059] 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.

[1060] 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.

[1061] [Fourth embodiment]

[1062] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1063] 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.

[1064] 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).

[1065] 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.

[1066] 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.

[1067] 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).

[1068] 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.

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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.

[1073] 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.

[1074] 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."

[1075] This system provides a series of means for streamlining project management. Specifically, it collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on the progress of tasks and summarizes the project story. An embodiment of this system is described in detail below.

[1076] 1. Data collection

[1077] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[1078] 2. Data Analysis

[1079] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it analyzes the content of emails and messages to extract important topics, track task progress, and classify sentiment. This allows for a detailed understanding of the current status of the project.

[1080] 3. Generate a report

[1081] The server generates daily, weekly, and monthly reports based on the analysis results, including task progress, important events, and each member's contribution, and the reports are automatically sent to project stakeholders.

[1082] 4. Early detection and sharing of issues

[1083] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[1084] 5. Follow-up

[1085] The server automatically follows up on each project member's task progress, and if progress is delayed or support is needed, follow-up emails and notifications are sent.

[1086] 6. Summary of the project story

[1087] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[1088] Specific examples

[1089] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, a weekly report is generated based on these analysis results and sent to the project team.

[1090] Furthermore, if the server detects that the task progress is delayed, it will automatically send a follow-up notification to User B. Finally, based on all the analysis results and progress summary, it will generate the overall story of the project and save it for easy access by the project manager.

[1091] In this way, the present invention provides detailed information on the progress of a project and supports efficient management and problem solving.

[1092] The processing flow will be explained below.

[1093] Step 1:

[1094] Users connect their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account.

[1095] Step 2:

[1096] The server periodically collects emails and messages related to the project using the linked account information, retrieves data from email servers and communication platforms via API, and stores it in its own database.

[1097] Step 3:

[1098] The server passes the collected data to a natural language processing (NLP) engine for analysis, which is used to extract important topics and task progress from emails and messages.

[1099] Step 4:

[1100] The server performs sentiment analysis based on the extracted information, identifying positive, negative, and neutral emotions in the text data to understand the mental state of project members.

[1101] Step 5:

[1102] The server generates daily, weekly, and monthly reports, summarizing the analysis results and including each member's task progress, important events, and sentiment trends.

[1103] Step 6:

[1104] The server automatically sends the generated reports to project stakeholders, who can share them via email or communication platforms to make the project status transparent.

[1105] Step 7:

[1106] The server detects issues and bottlenecks from the analysis results, identifying delays in tasks and unresolved issues and labeling the information.

[1107] Step 8:

[1108] The server shares detected issues with relevant parties, sending notifications via email or communication platforms to encourage early problem resolution.

[1109] Step 9:

[1110] The server follows up on each member's task progress and, if necessary, automatically sends reminders or support requests to members who are lagging behind.

[1111] Step 10:

[1112] The server will compile the story of the entire project, organizing key events and findings based on collected data and analysis results, and storing them in a format that can be easily accessed by future generations.

[1113] In this way, each step works in tandem, making project management more efficient and clarifying overall progress and issues.

[1114] Example 1

[1115] 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."

[1116] Project management requires a lot of data and communication, making it difficult to detect delays and issues early. Centralized management and analysis of information is particularly difficult for teams using multiple platforms. Manually managing task progress and following up on tasks takes a great deal of time and effort. Furthermore, compiling the entire project story is time-consuming, making efficient project management essential.

[1117] 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.

[1118] In this invention, the server includes means for accessing external services using authentication information provided by the user and collecting all data related to the project, means for analyzing the collected data using natural language processing and sentiment analysis, means for generating daily, weekly, and monthly reports based on the analysis results, means for early detection of issues from the analysis results and sharing them in real time, means for monitoring the progress of tasks as the project progresses and automatically performing follow-up, and means for compiling a story of the entire project based on the collected data and analysis results.This enables centralized management and analysis of data in project management, visualization of progress, early detection of issues, efficient follow-up, and project summary.

[1119] "Authentication Information" means information required for a User to access their account, including a username, password, API key, etc.

[1120] "External services" refers to online services such as email accounts and communication platforms that users use on a daily basis.

[1121] "Data Collection Methods" refers to the methods and technologies used to obtain relevant data from external services.

[1122] "Natural language processing" is a technology that enables computers to understand, interpret, and manipulate human language, and performs tasks such as text analysis and topic extraction.

[1123] "Sentiment analysis" refers to the technology of classifying emotions expressed in text into "positive," "negative," "neutral," etc.

[1124] "Report generation means" refers to the methods and techniques for creating reports based on analyzed data.

[1125] "Problem detection methods" refer to methods and techniques for early detection of problems and bottlenecks during the project.

[1126] "Sharing means" refers to the methods and techniques used to communicate discovered issues and important information to project members.

[1127] "Follow-up measures" refer to technologies that monitor task progress and automatically send reminders or support notifications as needed.

[1128] A "project story" is a report that summarizes the overall progress and important events of a project.

[1129] This invention is a system for streamlining project management, providing the following set of means: This system collects and analyzes all data related to the project, generates reports based on the results, and identifies and shares issues early. It also automatically performs follow-up according to the progress of tasks and can compile the story of the entire project.

[1130] Data collection

[1131] The server accesses external services (e.g., email accounts and communication platforms) using the authentication information provided by the user. Specifically, the user logs in to the system and connects their email account (e.g., Google Gmail) and communication platform (e.g., Slack, Microsoft Teams) accounts. This allows the server to periodically call APIs (e.g., Gmail API, Slack API) to collect data related to the project (e.g., emails, chat messages, file attachments, etc.).

[1132] Data analysis

[1133] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses NLP tools such as Google Natural Language API and IBM Watson to analyze the content of emails and messages and extract important topics. It can also classify the emotional state of the text as "positive," "negative," or "neutral." This analysis provides a detailed understanding of the current status of the project.

[1134] Generate reports

[1135] The server automatically generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, and sends the reports to project stakeholders via email or communication platforms.

[1136] Early detection and sharing of issues

[1137] The server uses the analysis results to quickly identify issues such as task delays and stalled problem-solving. Detected issues are shared with project stakeholders in real time via email or communication platforms.

[1138] Performing follow-up

[1139] The server monitors the task progress of each project member and automatically sends follow-up notifications if progress is delayed or if support is required, allowing users to respond promptly.

[1140] Project Story Summary

[1141] The server aggregates key events and findings from the entire project based on data and analysis, generating a final report that summarizes the overall project story and saving it in an easily accessible format for future project reference.

[1142] Examples and prompts

[1143] In a project team, User A sends weekly meeting minutes via email, and User B reports task progress via Slack. The system first links the accounts of User A and User B. The server collects the weekly meeting minutes emails and Slack messages, and applies NLP and sentiment analysis to extract important topics and task progress. Next, it generates a weekly report based on these analysis results and sends it to the project team. If it detects that task progress is behind schedule, the server automatically sends a follow-up notification to User B. Finally, based on all analysis results and a summary of progress, it generates an overall project story and saves it for easy access by project managers.

[1144] An example of a prompt is, "Based on the following text, please provide the user with an overview of a system that provides project progress reports and issue notifications."

[1145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1146] Step 1:

[1147] When logging in to the system, users enter their email account and communication platform authentication information, which is then used by the server to access external services. Specifically, users enter their email address and password on the login screen and are authenticated using OAuth 2.0.

[1148] Input: User's email account, communication platform account information

[1149] Output: OAuth token (authentication information)

[1150] Step 2:

[1151] The server uses the obtained credentials to access external services (email accounts and communication platforms) and collect data related to the project. For example, it uses the Gmail API or Slack API to retrieve emails and chat messages. These operations are performed automatically on a regular basis.

[1152] Input: OAuth token

[1153] Output: Collected email and chat message data

[1154] Step 3:

[1155] The server normalizes the collected data, for example converting email bodies or chat messages into text data, so that a consistent format of data is available for subsequent analysis steps.

[1156] Input: Collected email and chat message data

[1157] Output: Normalized text data

[1158] Step 4:

[1159] The server then analyzes the normalized data using natural language processing (NLP) and sentiment analysis tools, such as Google Natural Language API and IBM Watson, to extract key keywords from the text and classify the emotional state as "positive," "negative," or "neutral."

[1160] Input: normalized text data

[1161] Output: Analysis results (important keywords, sentiment classification)

[1162] Step 5:

[1163] The server generates daily, weekly, and monthly reports based on the analysis, including task progress, key milestones, and each member's contribution, often in JSON or PDF format.

[1164] Input: Analysis results

[1165] Output: Report (JSON format, PDF format)

[1166] Step 6:

[1167] The server then sends the generated reports to project stakeholders via email or a communication platform, automatically distributing the reports using the API of the email server or communication platform.

[1168] Input: Report

[1169] Output: Report sent

[1170] Step 7:

[1171] The server uses the analysis results to detect issues such as task delays and stalled problem-solving. For example, it detects tasks that have not progressed for a certain period of time and lists them as issues.

[1172] Input: Analysis results

[1173] Output: Detected issues

[1174] Step 8:

[1175] The server notifies relevant parties of detected issues in real time via email or a communication platform, and includes the specific details of the issue and a request for action.

[1176] Input: Detected issues

[1177] Output: Issue notification sent

[1178] Step 9:

[1179] The server monitors the task progress of each project member and automatically sends follow-up notifications in the form of emails or messages if there is no progress or delays for a certain period of time.

[1180] Input: Task progress data

[1181] Output: Follow-up notification

[1182] Step 10:

[1183] The server will organize the project's important events and findings based on the data and analysis results of the entire project, and will then compile the overall story of the project into a final report.

[1184] Input: Data and analysis results

[1185] Output: The story of the entire project

[1186] Step 11:

[1187] The server stores the generated project stories in an easily accessible format for future reference, and the reports are stored in a database for easy retrieval and viewing later.

[1188] Input: The overall story of the project

[1189] Output: Saved report

[1190] (Application example 1)

[1191] 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."

[1192] Conventional project management systems have the drawback of being inefficient due to the time and effort required for data collection, analysis, and report generation. They also lack the functionality to detect and respond to abnormalities and issues early, which often leads to human error and time lags, especially in the maintenance management of factory robots.

[1193] 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.

[1194] In this invention, the server includes a means for collecting all data related to the project, a means for analyzing the data to detect abnormalities, a means for generating a maintenance report, and a means for sending a notification when an abnormality is detected. This allows for efficient project management and maintenance management of factory robots, and enables early detection of problems and rapid response.

[1195] "All data related to the project" refers to all information related to the project, such as emails, chats, task management tools, and sentiment analysis results.

[1196] "Robot operation data" refers to all information related to the operation of robots used in factories, such as their operating status, error information, and operating hours.

[1197] "Means of analyzing data to detect anomalies" refers to functions that analyze collected data using technologies such as natural language processing, sentiment analysis, and machine learning to detect anomalies and problems.

[1198] "Means for generating a maintenance report" refers to a function that automatically creates a report summarizing the robot's maintenance status and required maintenance tasks based on the analysis results.

[1199] "Means for sending notifications when an abnormality is detected" refers to the function of notifying the person in charge by email, app notification, or other means when the system detects an abnormality in the robot or a situation requiring emergency maintenance.

[1200] "A means of summarizing the story of the entire project" refers to a function that allows you to summarize all important events and progress from the start to the end of the project as a series of stories.

[1201] To realize this invention, a server, a user terminal (such as a smartphone or PC), and necessary software are required. Specifically, the server plays the following roles:

[1202] First, the server collects all data related to the project. This includes data from email platforms and communication tools, and periodically retrieves data using APIs. Data collection begins when a user logs in to the system and links their platform accounts.

[1203] The server then analyzes the collected data, applying natural language processing (NLP) and sentiment analysis to extract topics from the data content and classify emotions. After analysis, the robot's operational data is also analyzed. Specifically, machine learning algorithms are used to detect abnormalities in operational status.

[1204] Based on the analysis results, the server generates daily, weekly, and monthly reports that include project progress, key events, contributions of each member, and robot maintenance requirements, and these reports are automatically sent to the user's device.

[1205] The server also uses the analysis results to quickly identify issues and share them with relevant parties. For example, it detects delays in tasks or stalled resolutions and notifies relevant users via email or app notifications.

[1206] Additionally, the server automatically performs follow-up on tasks as the project progresses: if a task is delayed or if support is needed, follow-up notifications are sent.

[1207] Finally, the server will compile the overall story of the project, including organizing key events and learnings from the project based on the collected data and analysis results, and preserving them for posterity.

[1208] Hardware and software used:

[1209] Server: Cloud-based Amazon Web Services (AWS) or Google Cloud Platform (GCP)

[1210] User devices: smartphones, PCs

[1211] Natural Language Processing: NLTK (Python library)

[1212] Sentiment Analysis: VADER Sentiment Analysis (part of NLTK)

[1213] Data frame operations: pandas (Python library)

[1214] HTTP requests: requests (Python library)

[1215] Sending email: smtplib (Python library)

[1216] Examples:

[1217] Two users, User A and User B, are participating in a factory project. The server collects User A's email meeting minutes and User B's messages from their communication tools, and applies NLP and sentiment analysis to extract important topics and emotions. A weekly report is then generated and sent to the user. In addition, robot operation data is also collected and analyzed, and if an abnormality is detected, a notification is sent to the person in charge.

[1218] Example prompt sentence:

[1219] "Analyze the robot's operating status and generate a report based on the following data."

[1220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1221] Step 1:

[1222] The server uses the credentials provided by the user to access email accounts and communication platform accounts and collect data related to the project. Specifically, the server periodically calls an API to retrieve the contents of emails and messages. The input is the user's credentials and the associated account, and the output is the collected, unanalyzed data.

[1223] Step 2:

[1224] The server analyzes the collected data using natural language processing (NLP) and sentiment analysis. Specifically, it uses an NLP library (such as NLTK) to classify important topics and sentiment. The input is the raw data collected in step 1, and the output is the analyzed data with classified topics and sentiment.

[1225] Step 3:

[1226] The server generates daily, weekly, and monthly reports based on the analysis results. Specifically, it aggregates the analysis data and summarizes progress and important events. The input is the analysis data obtained in step 2, and the output is the report.

[1227] Step 4:

[1228] The server detects issues and bottlenecks from the analysis results and shares them with relevant parties. For example, it detects task delays and stalls in problem-solving and automatically sends notifications via email or communication platforms. The input is the analysis results data, and the output is notifications to each relevant party.

[1229] Step 5:

[1230] The server automatically follows up on each project member's task progress. If progress is delayed or support is deemed necessary, a follow-up email or notification is sent. The input is task progress data, and the output is a follow-up notification.

[1231] Step 6:

[1232] The server compiles the story of the entire project. Based on the collected data and analysis results, it organizes important events and findings and saves them as a final report. The input is all analysis data and progress data, and the output is a report summarizing the story of the entire project.

[1233] Step 7:

[1234] The server collects robot operation data. Specifically, it periodically obtains operation status and error information from the robots in the factory. The input is operation data from the robots, and the output is the collected, unanalyzed operation data.

[1235] Step 8:

[1236] The server analyzes the collected robot operation data and detects anomalies. It uses machine learning algorithms to identify abnormal operations. The input is the operation data collected in step 7, and the output is the analysis data in which anomalies are detected.

[1237] Step 9:

[1238] The server automatically sends a notification if an anomaly is detected. Specifically, it notifies the person in charge of the anomaly via email or app notification. The input is the analysis data in which the anomaly was detected, and the output is the situation in which the notification was sent.

[1239] 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.

[1240] This system provides a series of methods for streamlining project management. Specifically, it collects all project-related data, analyzes it using natural language processing (NLP) and sentiment analysis, generates reports based on the results, and identifies and shares issues early. It also automatically follows up on task progress and summarizes the project story. It also incorporates an emotion engine that recognizes the user's emotions, allowing it to analyze the user's emotional state and follow up and create reports based on that.

[1241] 1. Data collection

[1242] The server uses the authentication information provided by the user to access the user's email account and communication platform account and collect data related to the project. When the user logs in to the system and links their email account and communication platform account, the server periodically calls the API to obtain data.

[1243] 2. Data Analysis

[1244] The server passes the collected data to the NLP engine for analysis. The NLP engine is used to extract important topics and task progress from emails and messages. Furthermore, an emotion engine is used to identify emotions in the text data and evaluate the user's emotional state.

[1245] 3. Generate a report

[1246] Based on the results of analysis and sentiment analysis, the server generates daily, weekly, and monthly reports, including task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders.

[1247] 4. Early detection and sharing of issues

[1248] The server uses the analysis results to detect issues and bottlenecks, such as delays in tasks or stalled problem-solving. Detected issues are automatically shared with relevant parties via email or communication platforms.

[1249] 5. Follow-up

[1250] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, a follow-up email or notification will be sent.

[1251] 6. Summary of the project story

[1252] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[1253] Specific examples

[1254] Next, we will explain how the system works using a concrete example. In a certain project team, User A sends weekly meeting minutes via email, and User B reports task progress on a communication platform. In this system, the accounts of Users A and B are first linked. The server collects the weekly meeting minutes emails and messages from the communication platform, and applies NLP and an emotion engine to analyze important topics, task progress, and emotions. Next, a weekly report is generated based on the results of these analyses and sent to the project team.

[1255] Furthermore, if the progress of the task is delayed or if the emotion engine detects that User B is feeling stressed, the server will automatically send a follow-up notification to User B. Finally, based on all the analysis results, progress summary, and emotional state, the server generates an overall story of the project and saves it for easy access by the project manager.

[1256] In this way, the present invention provides detailed information on the progress of a project, supporting efficient management and problem-solving. Furthermore, the introduction of an emotion engine enables follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of the project.

[1257] The processing flow will be explained below.

[1258] Step 1:

[1259] The user connects their email and communication platform accounts to the server, using an authentication protocol such as OAuth 2.0 to grant permission to access each account. At this stage, the user logs into the system and completes the authentication process.

[1260] Step 2:

[1261] The server periodically collects users' emails and communication platform messages using the linked account information, obtains the data through the respective APIs, and stores it in its own database, which also contains metadata such as the collection date and time and the user's ID.

[1262] Step 3:

[1263] The server passes the collected data to a natural language processing (NLP) engine for analysis. The data includes email text, messages from communication platforms, and meeting minutes. The NLP engine extracts important keywords and topics from this text data.

[1264] Step 4:

[1265] The server uses an emotion engine to perform sentiment analysis based on the important keywords and topics extracted by the NLP engine. The emotion engine classifies the text content into emotional categories such as positive, negative, and neutral, which allows the emotional state of the project members to be evaluated.

[1266] Step 5:

[1267] Based on the analysis results of the NLP and emotion engine, the server generates daily, weekly, and monthly reports that include task progress, each member's contribution, important events, and sentiment trends. The reports are automatically sent to project stakeholders via email or communication platforms.

[1268] Step 6:

[1269] The server detects issues and bottlenecks from the analysis results. For example, it checks whether there are delays in tasks or unresolved issues. Detected issues are automatically notified to the relevant parties.

[1270] Step 7:

[1271] To address detected issues, the server sends follow-up notifications to relevant parties, including details of the problem and recommended actions to resolve it, helping to speed up problem resolution.

[1272] Step 8:

[1273] The server follows up on project members based on their task progress and emotional state. If progress is delayed or the emotional state is judged to be negative, follow-up emails and notifications are automatically sent.

[1274] Step 9:

[1275] The server will compile the story of the entire project, including the collected data, analysis results, emotional state, and significant events, and will organize the story into a final project report, which will be archived in a format that can be easily viewed by future generations.

[1276] In this way, each step works in tandem to ensure efficient project management and detailed understanding of overall progress, issues, and the emotional state of members.

[1277] Example 2

[1278] 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."

[1279] In traditional project management systems, data collection, analysis, report generation, and early issue detection and sharing are often done manually, which is inefficient and makes it difficult to properly understand and follow up on the emotional state of members.To solve this problem, automated data collection, analysis, report generation, follow-up, and emotional state management are needed.

[1280] 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.

[1281] In this invention, the server includes a means for accessing the user's email account and communication platform account using authentication information provided by the user and collecting all data related to the project, a means for passing the collected data to a natural language processing engine for analysis and extracting important topics and task progress, and a means for passing the data to an emotion engine for identifying emotions in the text and evaluating the user's emotional state, which significantly improves the efficiency of project management and enables appropriate follow-up taking into account the emotional state of members.

[1282] "Authentication information" refers to the information required to access a user's email account or communications platform account.

[1283] A "natural language processing engine" is a software component that analyzes text data and extracts important topics and task progress.

[1284] An "emotion engine" is a software component for identifying emotions in text data and assessing a user's emotional state.

[1285] A "Report" is a document generated based on the results of analysis and sentiment analysis, which describes the progress of a task, important events, each member's contribution, and sentiment trends.

[1286] "Issues" refer to problems such as delays in tasks and stagnation in problem-solving during project progress.

[1287] "Follow-up" refers to automated support and notifications based on each project member's task progress and emotional state.

[1288] A "project story" is a summary of the overall progress of a project, including important events and findings.

[1289] This system provides a series of methods to streamline project management. The server, terminals, and users play their respective roles, and the system automatically collects data, analyzes, generates reports, shares issues, follows up, and summarizes stories.

[1290] Data collection

[1291] The server uses the authentication information provided by the user to access the email account and communication platform account and collect data related to the project. Specifically, the user logs in to the system and links the email account and communication platform account. The server periodically obtains data using APIs such as Google Gmail API and Slack API.

[1292] Data analysis

[1293] The server passes the collected data to a natural language processing (NLP) engine for analysis. This NLP engine uses the Google Cloud Natural Language API and other tools to extract important topics and task progress from emails and messages. The server also uses an emotion engine to identify emotions within the text data. This emotion engine uses IBM Watson Tone Analyzer to evaluate the user's emotional state.

[1294] Generate reports

[1295] The server generates daily, weekly, and monthly reports based on the results of analysis and sentiment analysis. These reports include task progress, important events, each member's contribution, and sentiment trends. The generated reports are automatically sent to project stakeholders via email or communication platforms.

[1296] Early detection and sharing of issues

[1297] The server detects issues and bottlenecks from the analysis results, such as delays in tasks and stalled problem-solving. The server automatically shares detected issues with relevant parties via email or a communication platform.

[1298] Performing follow-up

[1299] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or if support is needed based on their emotional state, the server will send a follow-up email or notification.

[1300] Project Story Summary

[1301] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[1302] Specific examples

[1303] For example, in a project team, User A sends weekly meeting minutes via email, and User B reports task progress via a communication platform. In this system, User A and User B's accounts are linked. The server periodically calls an API to collect the weekly meeting minutes emails and messages from the communication platform. This data is passed to an NLP engine and an emotion engine, which analyzes important topics, task progress, and emotional state. Based on the analysis results, the server generates a weekly report and sends it to the project team. In addition, if task progress is delayed or if the emotion engine detects that User B is feeling stressed, the server automatically sends a follow-up notification to User B. Finally, based on all the analysis results, an overall project story is generated and saved for easy access by the project manager.

[1304] Prompt Sentence Examples

[1305] "Using the minutes of daily project team meetings and messages from communication platforms, analyze the task progress and emotional state of members using NLP and an emotion engine to generate a weekly report."

[1306] This system streamlines all aspects of project management, providing detailed insight into progress and support for resolving issues. The introduction of an emotion engine also enables appropriate follow-up that takes into account the emotions and psychological state of members, thereby increasing the success rate of projects.

[1307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1308] Step 1:

[1309] A user logs into the system and enters their email account and communication platform account information, including their user ID and password, which then sends authentication information to the server, allowing the server to access the user's email server and communication platform.

[1310] Input: User ID, password, email account information, communication platform information

[1311] Output: Authentication information (token, etc.)

[1312] Step 2:

[1313] The server uses the obtained credentials to call APIs and collect data from mail servers and communication platforms, for example, Google Gmail API to retrieve emails and Slack API to retrieve messages, thus collecting all project-related data.

[1314] Input: Credentials, API call

[1315] Output: Collected data (emails, messages, etc.)

[1316] Step 3:

[1317] The server passes the collected data to a natural language processing (NLP) engine to begin analysis. The NLP engine (e.g., Google Cloud Natural Language API) is used to extract important topics and task progress from emails and messages. This analysis extracts specific keywords and context.

[1318] Input: Collected data

[1319] Output: Extracted topics and task progress information

[1320] Step 4:

[1321] The server then passes the collected text data to an emotion engine for sentiment analysis. Using an emotion engine (e.g., IBM Watson Tone Analyzer), emotions within the text are identified and the user's emotional state is assessed. This analysis results in an emotional label, such as positive, negative, or neutral.

[1322] Input: Collected text data

[1323] Output: Sentiment analysis results (emotion labels)

[1324] Step 5:

[1325] The server generates daily, weekly, and monthly reports based on the analysis results obtained from the NLP engine and the sentiment engine. The generated reports include task progress, important events, each member's contribution, and sentiment trends. Report templates are used to generate the reports.

[1326] Input: Extracted topics, task progress information, sentiment analysis results

[1327] Output: Generated report

[1328] Step 6:

[1329] The server automatically sends the generated report to the project stakeholders via email or a communication platform, for example, sending the report to all project participants via email.

[1330] Input: Generated report

[1331] Output: Report sent (e.g. email)

[1332] Step 7:

[1333] The server uses algorithms to detect issues and bottlenecks from the analysis results, identifying delays in tasks and stalled problem-solving, and records the detected issues along with suggestions for resolving them.

[1334] Input: Analysis results

[1335] Output: Detected issues and their suggestions

[1336] Step 8:

[1337] The server shares detected issues with the relevant parties via email notifications and messages on the communication platform, allowing them to address the issues early.

[1338] Input: Detected issues and their suggestions

[1339] Output: Issue notifications (emails, messages, etc.)

[1340] Step 9:

[1341] The server automatically follows up on each project member based on their task progress and emotional state. If progress is delayed or emotional analysis indicates that support is needed, follow-up emails and notifications are sent.

[1342] Input: Task progress, sentiment analysis results

[1343] Output: Follow-up notification (email, message, etc.)

[1344] Step 10:

[1345] The server will compile the story of the entire project. Based on the collected data and analysis results, it will organize important events and findings into a final project report. This report will be saved in a format that can be easily accessed by future generations.

[1346] Input: Collected data, analysis results

[1347] Output: Final report (project story)

[1348] The above is the specific processing flow in implementing this system.

[1349] (Application example 2)

[1350] 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."

[1351] In modern factories, many tasks are performed by multiple work machines. Therefore, it is important to accurately grasp the progress of tasks and manage them efficiently. Furthermore, the emotional state of the work machine operators also has a significant impact on production efficiency, but there are currently insufficient means to appropriately grasp and support this. In such situations, task delays and reduced efficiency due to operator stress are likely to occur, significantly impacting the entire production operation. Therefore, a system is needed that can analyze the progress of tasks and the emotional state of operators in real time and provide appropriate follow-up and improvement measures.

[1352] 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.

[1353] In this invention, the server includes means for collecting all data related to the project, means for analyzing the task progress of the work machine, and means for analyzing the emotional state of the operator of the work machine. This makes it possible to grasp the task progress and the emotional state of the operator in real time, and to propose appropriate follow-up and improvement measures.

[1354] A "data collection means" is a mechanical or software component that captures and stores any data generated by the work machine and its operator.

[1355] "Means for analyzing data" refers to mechanical or software components that analyze collected data using techniques such as natural language processing and sentiment analysis to extract useful information.

[1356] The "means for generating a report" refers to a mechanical or software component that creates a report in a predetermined format based on the analysis results and provides it to the relevant parties.

[1357] "Means for early detection and sharing of issues" refers to mechanical or software components that detect bottlenecks and problems from the analysis results and quickly notify the relevant parties.

[1358] The "means for automatically performing task follow-up" is a mechanical or software component for automatically providing necessary follow-up notification or assistance based on the progress of the task of the work machine and the emotional state of the operator.

[1359] A "means for summarizing the overall project story" is a mechanical or software component that organizes the overall project progress and knowledge gained based on collected data and analysis results, and stores it in a format that can be easily referenced in the future.

[1360] "Work machine" refers to any mechanical device that performs a task in a factory or manufacturing site.

[1361] "Operator" means a person operating a work machine.

[1362] This invention is a system aimed at efficient management of factory robots and their operators. This system has the following components:

[1363] System Configuration

[1364] 1. Data Collection Methods

[1365] The server collects data from the work machines and their operators in real time, including the task progress of each work machine, work records entered by the operators, and sensing data. This data is sent over the network and stored on the server.

[1366] 2. Data analysis methods

[1367] The server uses an NLP (natural language processing) engine and an emotion engine to analyze the collected data. The NLP engine analyzes the task progress of the work machine and extracts important topics and task progress. The emotion engine also identifies and evaluates the emotional state of the operator from the text data.

[1368] 3. Report Generation Methods

[1369] Based on the results of data analysis, the server generates daily, weekly, and monthly reports, including task progress, key events, individual operator contributions, and sentiment trends, and the generated reports are automatically sent to relevant parties.

[1370] 4. Early detection and sharing of issues

[1371] Based on the results obtained from the data analysis tools, the server automatically detects issues and bottlenecks, such as delays in tasks or increased stress among operators. These issues are automatically shared with the relevant parties, enabling early action to be taken.

[1372] 5. Follow-up measures

[1373] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. For example, it notifies an operator whose task is delayed to report progress, and notifies an operator whose emotional state is deteriorating to provide support.

[1374] 6. Project Story Summary

[1375] The server will compile a story of the project based on the overall progress of the project and the knowledge gained, allowing future generations to easily understand the overall picture of the project.

[1376] Specific examples

[1377] For example, when welding work is being carried out in a factory, an operator inputs task progress and collects data from the work machine in real time. The server analyzes this data and evaluates the task progress and the operator's emotional state. If the operator is feeling stressed, the server automatically sends a follow-up notification to encourage support. Reports summarizing the overall progress are also periodically generated and sent to relevant parties.

[1378] Prompt Sentence Examples

[1379] Enter the following task details:

[1380] Task ID: __

[1381] Progress:__

[1382] More information:

[1383]

[1384] Enter the following task details:

[1385] Task ID: 1

[1386] Progress: In progress

[1387] Detailed information: Welding parts A and B

[1388] Such a system will enable efficient management of work machines and operators within a factory, making it possible to grasp the progress of tasks and the emotional state of operators, and to provide appropriate follow-up.

[1389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1390] Step 1:

[1391] The server collects data from the work machines and operators. Specifically, it receives task progress data from each work machine via the network, and text data on input work records and emotional states from the operators. This input data is stored in a database within the server.

[1392] Step 2:

[1393] The server passes the collected data to a natural language processing (NLP) engine and begins analysis. The server's NLP engine extracts important topics and work progress information from the text data of the work machine's task progress. This analysis reveals the detailed progress of each task and related issues. The output is a list of important topics and progress information.

[1394] Step 3:

[1395] The server passes the collected emotion data to the emotion engine for emotion analysis. The emotion engine evaluates the emotional state of the operator (e.g., stress, satisfaction, anxiety, etc.) from the text data. The evaluation results are output as an emotional state score for each operator.

[1396] Step 4:

[1397] The server integrates the analysis results from the NLP engine and the emotion engine to generate daily, weekly, and monthly reports, including task progress, important events, and the emotional state of operators. The generated reports are automatically sent to designated stakeholders via email or platform notifications.

[1398] Step 5:

[1399] The server automatically detects issues and bottlenecks from the analysis results. For example, if a task is delayed or an operator's emotional score is declining, it extracts related issues. Detected issues are automatically notified to the relevant parties, urging them to take early action. The output is a list of issues and their notifications.

[1400] Step 6:

[1401] The server automatically provides follow-up notifications and support according to the operator's emotional state and task progress. Specifically, it sends a progress report reminder to operators whose tasks are delayed, and a notification urging appropriate support to operators whose emotional state is deteriorating. The aforementioned analysis results are used as input data.

[1402] Step 7:

[1403] Based on the overall progress and findings of the project, the server compiles a story of the project, including important events, progress, and the emotional state of the operators, and stores this story in a specific format for future generations.

[1404] By dividing the process into steps in this way, efficient management of the work machines and operators within the factory can be achieved.

[1405] 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.

[1406] 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.

[1407] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1408] 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.

[1409] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1410] 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.

[1411] 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).

[1412] 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.

[1413] 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."

[1414] 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.

[1415] 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).

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] The following is further disclosed regarding the above embodiment.

[1427] (Claim 1)

[1428] A means of collecting all data related to the project, and

[1429] A means of analyzing the data; and

[1430] means for generating a report based on the analysis results;

[1431] A means to discover and share issues early,

[1432] A means for automatically performing follow-up on tasks in the progress of a project;

[1433] A way to summarise the story of the entire project,

[1434] A system including:

[1435] (Claim 2)

[1436] 10. The system of claim 1, further comprising means for a user to link email accounts and communication platform accounts.

[1437] (Claim 3)

[1438] 10. The system of claim 1, further comprising means for analyzing the data using natural language processing and sentiment analysis.

[1439] "Example 1"

[1440] (Claim 1)

[1441] A means of accessing external services using user-provided credentials to collect all data related to the project;

[1442] A means of analyzing the collected data using natural language processing and sentiment analysis,

[1443] A means to generate daily, weekly, and monthly reports based on the analysis results;

[1444] A means to quickly identify issues from analysis results and share them in real time,

[1445] A means for automatically monitoring and following up on the progress of tasks in the project;

[1446] A means of summarizing the story of the entire project based on the collected data and analysis results, and

[1447] A system including:

[1448] (Claim 2)

[1449] 10. The system of claim 1, further comprising means for a user to link email accounts and communication platform accounts.

[1450] (Claim 3)

[1451] 10. The system of claim 1, further comprising means for analyzing the collected data using natural language processing and sentiment analysis.

[1452] "Application Example 1"

[1453] (Claim 1)

[1454] A means of collecting all data related to the project, and

[1455] A means of analyzing the data; and

[1456] means for generating a report based on the analysis results;

[1457] A means to discover and share issues early,

[1458] A means for automatically performing follow-up on tasks in the progress of a project;

[1459] A way to summarise the story of the entire project,

[1460] A means for collecting operational data of the robot;

[1461] A means for analyzing the collected data to detect anomalies;

[1462] means for generating a maintenance report based on the analysis results;

[1463] means for sending a notification when an anomaly is detected;

[1464] A system including:

[1465] (Claim 2)

[1466] 10. The system of claim 1, further comprising means for a user to link email accounts and communication platform accounts.

[1467] (Claim 3)

[1468] 10. The system of claim 1, further comprising means for analyzing the data using natural language processing and sentiment analysis.

[1469] "Example 2: Combining Emotion Engines"

[1470] (Claim 1)

[1471] a means of accessing the User's email and communication platform accounts using the credentials provided by the User and collecting all data relating to the Project;

[1472] The collected data is then analyzed through a natural language processing engine to extract important topics and task progress.

[1473] means for passing the data to an emotion engine to identify emotions in the text and assess the emotional state of the user;

[1474] means for generating a report based on the analysis results and the sentiment analysis results;

[1475] A method to detect issues and bottlenecks from the analysis results and automatically share them with relevant parties.

[1476] A means for automatically performing follow-up according to the task progress and emotional state of each project member;

[1477] A way to summarize the story of the entire project and save it as a final report,

[1478] A system including:

[1479] (Claim 2)

[1480] 10. The system of claim 1, further comprising means for a user to link an email account and a communications platform account.

[1481] (Claim 3)

[1482] 10. The system of claim 1, further comprising means for analyzing the data using natural language processing and sentiment analysis.

[1483] "Application example 2 when combining emotion engines"

[1484] (Claim 1)

[1485] A means of collecting all data related to the project, and

[1486] A means of analyzing the data; and

[1487] means for generating a report based on the analysis results;

[1488] A means to discover and share issues early,

[1489] A means for automatically performing follow-up on tasks in the progress of a project;

[1490] A way to summarise the story of the entire project,

[1491] A means for analyzing task progress of the work machine;

[1492] means for analyzing the emotional state of an operator of the work machine;

[1493] A means of suggesting improvement measures based on the progress of the work machine and the emotional state of the operator;

[1494] A system including:

[1495] (Claim 2)

[1496] 10. The system of claim 1, further comprising means for a user to link email accounts and communication platform accounts.

[1497] (Claim 3)

[1498] 10. The system of claim 1, further comprising means for analyzing the data using natural language processing and sentiment analysis. [Explanation of symbols]

[1499] 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 of collecting all data related to the project, and A means of analyzing the data; and means for generating a report based on the analysis results; A means to discover and share issues early, A means for automatically performing follow-up on tasks in the progress of a project; A way to summarise the story of the entire project, A system including:

2. 10. The system of claim 1, further comprising means for a user to link an email account and a communications platform account.

3. 10. The system of claim 1, further comprising means for analyzing the data using natural language processing and sentiment analysis.

Images