System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting usage logs of in-house tools when employees leave work; generation and AI means for automatically extracting work contents based on the collected logs; means for classifying the generated work contents into categories; means for generating a draft of a daily report based on the classified work contents and presenting the draft to employees' terminals; and means for providing the generated performance report to a management layer.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] To maximize a company's productivity and achieve accurate labor-hour management, each employee must accurately and efficiently enter daily reports. However, entering daily reports on a daily basis takes time and effort, and employees with particularly heavy workloads are more likely to miss or miss entries or to follow inconsistent standards. This leads to a decline in the quality and consistency of submitted daily reports, hindering labor-hour management across the organization. A system that can solve these issues and improve the accuracy of labor-hour management is needed. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. A means is provided for collecting usage logs of internal tools when employees leave work. A generation AI is used to automatically extract work content based on the collected log data. A means is further provided for classifying the extracted work content by category, generating a draft daily report based on the classification results, and presenting it to the employee's terminal. After the employee checks the draft and makes any necessary corrections, they submit the daily report. The submitted daily report is saved in a database. The saved daily report data is analyzed by the generation AI, and a performance report for the team and the entire organization is generated. Finally, this report is provided to management and used to support strategic decision-making. This reduces the burden of entering daily reports and enables unified and accurate labor-hour management.

[0006] "Leaving work" refers to the time when an employee finishes their work for the day and leaves the workplace.

[0007] "Internal tools" refers to various software and platforms used within a company (e.g., email, document management systems, code management systems, etc.).

[0008] "Usage logs" refer to data on operation history and activity records generated when employees use internal tools.

[0009] "Generative AI" refers to a program or system that uses artificial intelligence techniques to perform specific tasks (e.g., automatically extracting and classifying work content).

[0010] "Work content" refers to the specific work or tasks performed by an employee.

[0011] "Category" refers to a classification criteria defined for grouping related items.

[0012] "Draft daily report" refers to a provisional document of a daily report automatically created by generative AI.

[0013] "Terminals" refers to devices such as computers and smartphones used by employees.

[0014] A "database" refers to a system that organizes and stores collected data and manages it so that it can be referenced or searched later.

[0015] "Analysis" refers to the process of examining collected data and extracting meaningful information and patterns.

[0016] A "performance report" refers to a report generated as a result of data analysis that evaluates the operational efficiency and results of a team or an entire organization.

[0017] "Management" refers to the executives and management who are responsible for a company's business strategy and important decision-making. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, and then stores and analyzes the daily report in a database before providing a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate labor-hour management.

[0040] Collecting log data

[0041] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using the GitHub API. The collected log data is temporarily stored in memory and prepared for storage in the database.

[0042] Automatic extraction of business content

[0043] The generative AI analyzes the collected log data and extracts business details. It uses natural language processing to generate a summary of the log and identify key business details. For example, it extracts activities such as "code review" and "development of new features" that employees performed on GitHub.

[0044] Business categorization

[0045] The generative AI classifies the extracted work content into predefined categories. For example, if the work content contains the keyword "code," it will be classified into the "development" category. Similarly, logs related to meetings will be classified into the "meeting" category.

[0046] Generate and present daily report drafts

[0047] The server generates a draft of the daily report based on the categorized work content and automatically displays it on the employee's device when they leave work. The draft is provided in a concise and structured format so that employees can easily check and modify it.

[0048] Daily report database storage

[0049] After the user (employee) checks, modifies, and confirms the daily report draft, the confirmed daily report is saved in the database by the server. This saved data is analyzed later, so it is managed accurately.

[0050] Analyze daily data and generate performance reports

[0051] The generation AI analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0052] Providing performance reports

[0053] The server periodically provides the generated performance reports to the management, allowing the users (management) to obtain sufficient information for formulating organizational strategies and optimizing resource allocation.

[0054] Specific examples

[0055] For example, when employee A leaves work, the server collects that day's email and GitHub usage logs. The generation AI extracts tasks such as "fixing issue 123," "code review for new features," and "documentation updates" from the collected log data. These tasks are categorized and a draft daily report is generated in the form of "development," "review," or "documentation." The server presents this draft to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is stored in a database by the server, and the generation AI then analyzes it to create a performance report for the team and the entire organization. This report is provided to management and can be used to improve organizational productivity and accurately manage man-hours.

[0056] Through the above process, the present invention achieves both efficient daily report entry and accurate man-hour management, thereby helping to maximize a company's productivity.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] Server: When employees leave work, internal tools (email, code management tools, etc.) are accessed and usage logs are collected. This includes obtaining email logs using the IMAP protocol and obtaining code management logs using the GitHub API.

[0060] Step 2:

[0061] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is then stored in a database. This accumulates the usage logs and prepares them for analysis.

[0062] Step 3:

[0063] Generative AI: Analyzes log data stored in a database and automatically extracts task details. Based on prompts, natural language processing technology is used to generate a summary of the log and identify key task details. For example, task details such as "client support" can be extracted from email logs.

[0064] Step 4:

[0065] Generative AI: Classifies extracted work content into predefined categories. For example, work containing the keyword "code" is classified into the "development" category, and work containing the keyword "meeting" is classified into the "conference" category.

[0066] Step 5:

[0067] Server: Automatically generates draft daily reports based on categorized work content. These drafts are designed to be concise and structured so that employees can easily review and revise them.

[0068] Step 6:

[0069] Server: Presents the generated draft daily report to the employee's terminal when he / she leaves work. The draft daily report is automatically displayed on the employee's terminal, allowing for easy confirmation and correction.

[0070] Step 7:

[0071] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[0072] Step 8:

[0073] Server: Stores the daily reports submitted by employees in a database, which aggregates the data and allows for later analysis.

[0074] Step 9:

[0075] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0076] Step 10:

[0077] Server: Provides generated performance reports to management, providing them with the information they need to formulate organizational strategies and optimize resource allocation.

[0078] Example 1

[0079] 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."

[0080] Modern companies spend a lot of time and effort manually entering daily reports, which can lead to poor business efficiency. Furthermore, errors and non-standard formats caused by manual entry make accurate labor-hour management and performance analysis difficult. To solve these issues and improve business efficiency, a system is needed that automatically extracts and classifies employee work content and generates draft daily reports.

[0081] 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.

[0082] In this invention, the server includes: means for collecting general-purpose tool usage logs when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; a means for summarizing the extracted work content using natural language processing; and a means for classifying the summarized work content by category. This enables efficient extraction and classification of work content, and the generation and presentation of daily report drafts. The server also includes means for saving daily reports finalized by users in a database; a means for analyzing the saved daily report data using a generation AI to generate a performance report for the entire organization; and a means for providing the generated performance report to a manager. This enables accurate man-hour management and performance evaluation for the entire organization, thereby improving corporate productivity.

[0083] "Means for collecting usage logs of general-purpose tools when employees leave work" refers to a method or device that allows a server to automatically collect usage history of general-purpose tools such as email and source code management tools when employees leave work.

[0084] The "generative AI means for automatically extracting work content based on collected log data" is an artificial intelligence technology that analyzes log data collected by the server and automatically extracts the work content of employees using natural language processing technology.

[0085] "Means for summarizing extracted business content using natural language processing" refers to a technology that analyzes text data, extracts only the important points, and summarizes them concisely in order to summarize the business content extracted by the generation AI.

[0086] A "means for classifying summarized work content by category" is a method or device for dividing summarized work content into specific categories and classifying each task into categories such as "development," "review," and "meeting."

[0087] The "means for generating a draft daily report and presenting it on the employee's user terminal" is a mechanism for automatically creating a draft daily report based on the classified work content and displaying the draft on the user terminal when the employee leaves work.

[0088] "Means for saving daily reports finalized by users to a database" refers to a method or device by which a server receives daily reports that employees have edited and revised on their terminals and finalized, and stores the contents in a database.

[0089] "A means of analyzing saved daily report data using generation AI to generate a performance report for the entire organization" is a technology in which generation AI analyzes daily report data saved in a database and automatically generates a performance report for the entire organization based on the work content and time allocation of each employee.

[0090] The "means for providing the generated performance report to the administrator" refers to a method or device by which the server periodically provides the generated performance report to the administrator in the form of email, dashboard, or the like.

[0091] This invention is a system that collects usage logs of general-purpose tools when employees leave work, automatically extracts work content using generation AI, generates and presents a draft daily report, saves the daily report in a database, analyzes it, and then generates a performance report for the entire organization.

[0092] Hardware and software used

[0093] This system uses the following hardware and software:

[0094] Server: Collects log data, generates and presents daily report drafts, stores them in a database, and generates and provides performance reports.

[0095] User terminal: Functions as a device for employees to check, correct, and confirm draft daily reports.

[0096] Generative AI model: Uses natural language processing technology to extract business details from log data, and generates summaries, categorization, and performance reports.

[0097] Program processing

[0098] The server collects usage logs from the mail server using the IMAP protocol when employees leave work, and also collects log data from the code management system using the GitHub API. These log data are temporarily stored in memory.

[0099] Next, the generative AI analyzes the collected log data and uses natural language processing technology to generate summaries of the log data and identify key business activities. For example, activities such as "fixing Issue 123," "code review of new features," and "documentation updates" can be extracted from GitHub usage logs.

[0100] The extracted work content is then classified by the generation AI into categories such as "development," "review," and "meeting." The server then generates a draft daily report based on these categorizations and automatically displays it on the user's device when the employee leaves work. The draft is provided in a concise, structured format, allowing employees to quickly review the content and make any necessary corrections.

[0101] Once an employee has finalized their daily report draft, the server stores the data in a database. The saved data is then analyzed by the AI ​​to generate a performance report for the entire organization. This report includes each employee's work, time allocation, and progress on each project.

[0102] Finally, the server periodically provides the generated performance reports to the administrator, allowing the user (administrator) to obtain the information necessary to formulate organizational strategies and optimize resource allocation.

[0103] Examples of concrete examples and prompts

[0104] For example, when employee A leaves work, the server collects that day's email and source code management system usage logs. From the collected log data, the generation AI extracts tasks such as "Fixing Issue 123," "Code review of new features," and "Documentation update." These tasks are categorized into categories such as "Development," "Review," and "Documentation." The server presents a draft of the daily report to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is saved in a database by the server, and the generation AI then analyzes it to create a performance report for the entire organization. This report is provided to managers and can be used to improve organizational productivity and accurately manage man-hours.

[0105] An example of a prompt for a generative AI model is, "Summarize the activities obtained from GitHub usage logs (e.g., fixing Issue 123, code review, developing new features, etc.) and classify each activity into the appropriate category."

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

[0107] Step 1: Collect log data

[0108] The server collects general-purpose tool usage logs when employees leave work. Specifically, the server connects to the mail server using the IMAP protocol and retrieves the employee's email log. At this time, the server filters and collects unread emails and emails in specific folders. It also uses the GitHub API to retrieve activity logs from the employee code management system. This log data is temporarily stored in memory.

[0109] Input: Employee email server and code management system usage logs

[0110] Output: Log data stored in memory

[0111] Step 2: Automatic extraction of business content

[0112] The generative AI analyzes the log data collected by the server and extracts the details of the work. Specifically, it uses a natural language processing algorithm to analyze text and extract important activities. For example, from a GitHub log, it can extract work details such as "Fixing Issue 123" and "Code review for new features."

[0113] Input: Log data stored in memory

[0114] Output: Extracted business details

[0115] Step 3: Generate a summary of the business

[0116] The generative AI summarizes the extracted work content, extracting only the important points from the extracted data and summarizing them concisely. For example, long descriptions such as "Fixing Issue 123" and "Code review for new features" are summarized into short keywords such as "code fix" and "review."

[0117] Input: Extracted business details

[0118] Output: Summary of work

[0119] Step 4: Categorize your work

[0120] The generation AI classifies the summarized work content into predefined categories. The generation AI performs keyword analysis and classifies summarized work content such as "code correction" and "review" into categories such as "development" and "review."

[0121] Input: Summary of work

[0122] Output: Jobs categorized by category

[0123] Step 5: Generate and present a draft daily report

[0124] The server creates a draft of the daily report based on the work content categorized by category. The generated draft is automatically displayed on the user's device when the employee leaves work. The draft is presented in a structured format so that employees can easily check and modify it.

[0125] Input: Jobs categorized by category

[0126] Output: A draft of the daily report displayed on the user's terminal

[0127] Step 6: Check the daily report and save it to the database

[0128] The user (employee) checks the draft of the daily report displayed on the terminal and makes any necessary corrections. Once the corrections are complete and the finalized daily report is saved in the database by the server.

[0129] Input: Daily report draft confirmed and corrected by the user

[0130] Output: Daily fixed report stored in the database

[0131] Step 7: Analyze the daily data

[0132] The server analyzes the daily report data stored in the database using a generation AI, which extracts information such as each employee's work content, time allocation, and progress by project from the stored daily report data.

[0133] Input: Finalized daily report saved in the database

[0134] Output: Parsed performance data

[0135] Step 8: Generate and provide performance reports

[0136] The server generates an organization-wide performance report based on the performance data analyzed by the AI, which includes an overview of each employee's work, time allocation, and progress by project, and is provided to managers.

[0137] Input: Parsed performance data

[0138] Output: Performance report provided to management

[0139] (Application example 1)

[0140] 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."

[0141] Employees' daily report entry work is time-consuming, making it difficult to accurately manage man-hours and grasp productivity. Furthermore, particularly in on-site work such as factories, it is difficult for employees to record and understand their work in real time, resulting in insufficient data collection for efficient progress management and productivity improvement. For this reason, a system is needed that reduces the burden on employees and managers and improves productivity.

[0142] 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.

[0143] In this invention, the server includes means for collecting usage logs of internal tools when employees leave work, a generation AI means for automatically extracting work content based on the collected log data, a means for classifying the generated work content by category, a means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal, a means for saving the daily reports submitted by the employees in a database, a means for analyzing the saved daily report data and generating performance reports for the team and the entire organization, a means for providing the generated performance report to management, and a means for collecting the work logs of workers in real time and displaying them on smart glasses or a head-mounted display. This enables more efficient entry of employee daily reports, accurate man-hour management, and real-time understanding of work content.

[0144] "Means for collecting usage logs of internal tools when employees leave work" refers to a system that automatically collects usage history information for various software and systems used within the company when employees finish work and leave the office.

[0145] The "generative AI method for automatically extracting work content" is a technology that analyzes collected usage log data and uses generative AI to automatically identify and extract the specific work content performed by employees.

[0146] The "means for categorizing by category" is a system for dividing the extracted work content into predetermined categories based on specific criteria or keywords.

[0147] "Means for generating a draft daily report and presenting it on employees' devices" refers to a technology that automatically generates an initial version of a daily report based on classified work content and displays it on the computer or mobile device used by the employee.

[0148] "Means for storing daily reports in a database" refers to a system for recording and storing daily report data that has been confirmed, corrected, and confirmed by employees in a company database.

[0149] The "means for generating performance reports" refers to a technology that analyzes saved daily report data and creates reports on the work progress and productivity of a team or the entire organization.

[0150] "Means for providing performance reports to management" refers to a system for periodically distributing and presenting the generated performance reports to the company's senior managers and executives.

[0151] "Means for collecting work logs in real time and displaying them on smart glasses or head-mounted displays" refers to technology that records the work content of employees in real time and immediately displays that information to employees via smart glasses or head-mounted displays.

[0152] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it on the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate man-hour management.It can also be used by factory workers to understand work content in real time using smart glasses or head-mounted displays.

[0153] First, the server collects the usage logs of internal tools when employees leave work. This collection is done using the mail server's IMAP protocol and the code management system's API. The collected log data is temporarily stored in memory and prepared for storage in a database. This data is used to record the details of employee work.

[0154] Next, the Generative AI analyzes the collected log data and automatically extracts work content. It uses natural language processing technology to generate log summaries and identify key work content. For example, activities such as "client meetings" are extracted from email logs, and "bug fixes" are extracted from code management systems. Machine learning algorithms are used in this process to classify work content based on specific keywords and phrases.

[0155] The generation AI then classifies the extracted work content into predefined categories. For example, based on keywords such as "correction" or "review," each work is divided into categories such as "development" or "inspection." A draft daily report is generated based on the classified work content and presented to the employee's device. This draft is provided in a format that employees can easily check and edit.

[0156] The daily report drafts that employees review and revise are stored in a database for later analysis. Specifically, the stored data is analyzed by generative AI to generate performance reports for the team and the entire organization. These reports include each employee's work content, time allocation, progress by project, and more. This provides management with sufficient information to formulate organizational strategies and optimize resource allocation.

[0157] The system also has the ability to collect work logs of factory workers in real time and display them on smart glasses or head-mounted displays. When a worker wears a smart device, the server instantly collects and analyzes the work log, and the generated work details are displayed on the device. This allows workers to understand the details of their work in real time and work efficiently.

[0158] For example, when a worker at a factory puts on smart glasses, the day's work log is collected and a summary of the tasks performed that day (e.g., "machine maintenance" and "product quality check") is automatically presented. When the worker checks and corrects the content and submits it, it is saved in a database and a productivity report is provided to the supervisor.

[0159] Examples of prompts to input to a generative AI model include:

[0160] "Extract the factory work details from today's work log, categorize them, and generate a draft daily report."

[0161] "Based on the extracted work examples ['machine maintenance', 'quality check'], please classify each into the categories of 'maintenance' and 'inspection'."

[0162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0163] Step 1:

[0164] The server periodically collects usage logs from internal tools. Specifically, it retrieves email logs from the mail server using the IMAP protocol and code logs from the code management system using the GitHub API. It receives employee IDs and timestamps as input and obtains the log data to be saved as output.

[0165] Step 2:

[0166] The server temporarily stores the collected log data in memory. This is the preparation stage for storing it in the database. It receives the collected log data as input and outputs the data temporarily stored in memory.

[0167] Step 3:

[0168] Generative AI analyzes log data and automatically extracts work content. It uses natural language processing technology to identify work content, such as "code review" or "bug fix." It receives temporarily stored log data as input and obtains the extracted work content as output.

[0169] Step 4:

[0170] The generative AI categorizes the extracted work content. Based on keywords such as "correction" and "review," it divides the work content into categories such as "development" and "inspection." It receives the extracted work content as input and obtains the categorized work content as output.

[0171] Step 5:

[0172] The server generates a draft of the daily report based on the classified work content. This draft is presented to the terminal in a structured format. It receives the categorized work content as input and obtains the generated draft of the daily report as output.

[0173] Step 6:

[0174] The terminal presents the generated daily report draft to the employee, who then confirms and corrects it. The terminal receives the presented daily report draft as input and obtains corrected daily report data as output.

[0175] Step 7:

[0176] The server stores the corrected daily report in a database. This stored daily report data is used for later analysis. It receives the corrected daily report data as input and obtains the daily report data stored in the database as output.

[0177] Step 8:

[0178] The generation AI analyzes the stored daily report data and generates performance reports for the team and the entire organization, including information on work content, time allocation, progress by project, etc. It receives the daily report data stored in the database as input and obtains the generated performance report as output.

[0179] Step 9:

[0180] The server provides the generated performance reports to management, taking the generated performance reports as input and providing them as output in a format that can be accessed and viewed by management.

[0181] Step 10:

[0182] When a worker wears smart glasses or a head-mounted display, the server collects and displays work logs in real time, allowing workers to instantly understand the work they are doing. Real-time work data is received as input, and the work content displayed on the device is obtained as output.

[0183] 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.

[0184] The system of this invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management.Furthermore, by combining it with an emotion engine, it becomes possible to recognize and analyze the user's emotional state and reflect it in the daily report and performance report.

[0185] Collecting log data

[0186] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using an API. The collected log data is temporarily stored in memory and later converted into a format that is easy to process.

[0187] Automatic extraction of business content

[0188] Generative AI analyzes collected log data and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract "client support" task details from email logs and "bug fixes" task details from code management logs.

[0189] Business categorization

[0190] The generative AI classifies the extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "meeting" category.

[0191] Generate and present daily report drafts

[0192] The server generates a draft of the daily report based on the work content categorized by category. The generated draft is automatically presented to the employee's terminal when they leave work. The employee can review the presented draft and make corrections or additions as necessary.

[0193] Daily report database storage

[0194] The user (employee) checks the draft daily report, makes corrections and additions, then finalizes and submits the daily report. The submitted daily report is saved in the database by the server. This allows the daily report data to be aggregated and analyzed later.

[0195] Analyze daily data and generate performance reports

[0196] The AI ​​analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0197] Emotion engine integration

[0198] The emotion engine recognizes emotions from the voices and texts employees use while working. For example, it uses voice recognition and text analysis technology to evaluate employees' stress levels and satisfaction. This allows emotional data to be reflected in daily drafts and performance reports.

[0199] Reflecting emotional data

[0200] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is feeling stressed, the server will reflect this in the daily report. The emotion data is also reflected in performance reports, allowing management to understand the emotional health of the organization.

[0201] Feedback and Support

[0202] The server provides appropriate feedback and support messages to users (employees) based on the emotional data obtained from the emotion engine. For example, it may suggest relaxation techniques if stress is detected, or send a message praising the employee's achievements if the employee is emotionally satisfied.

[0203] Providing performance reports

[0204] The server then provides the generated performance reports to management, who can then obtain the information they need to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[0205] Specific examples

[0206] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generation AI extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." A draft daily report is generated based on the categorized work content and presented to employee A's device. Employee A then checks and amends the draft and submits the final version. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in the daily report and performance report, and provided to management.

[0207] Through the above process, the present invention improves the efficiency of daily report entry, enables unified and accurate labor-hour management, and also realizes understanding of employees' emotional states and providing feedback, thereby helping to maximize corporate productivity and manage the mental health of employees.

[0208] The processing flow will be explained below.

[0209] Step 1:

[0210] Server: When employees leave work, internal tools (e.g., mail servers, code management systems) are accessed to collect usage logs. This includes obtaining mail logs using the IMAP protocol and obtaining code management logs using APIs.

[0211] Step 2:

[0212] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is stored in a database and prepared for analysis.

[0213] Step 3:

[0214] Generative AI: Analyzes log data stored in a database and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract the task details "client support" from email logs and "bug fixes" from code management logs.

[0215] Step 4:

[0216] Generative AI: Classifies extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "conference" category.

[0217] Step 5:

[0218] Server: Generates a draft of the daily report based on the categorized work content. This draft is designed to be concise and structured so that employees can easily check and revise it.

[0219] Step 6:

[0220] Server: The generated draft daily report is automatically presented to the employee's terminal when they leave work. The draft daily report is displayed on the employee's terminal, allowing them to easily check and correct it.

[0221] Step 7:

[0222] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[0223] Step 8:

[0224] Server: Stores the daily reports submitted by employees in a database. Daily report data is aggregated and can be analyzed later.

[0225] Step 9:

[0226] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0227] Step 10:

[0228] Emotion engine: Recognizes emotions from employees' voices and input text while they are working. Using voice recognition and text analysis technologies, it evaluates employees' stress levels and satisfaction. For example, it detects the emotional state of "feeling stressed" from voice logs.

[0229] Step 11:

[0230] Server: Adjusts the draft daily report based on the recognized emotion data. For example, if an employee is feeling stressed, this will be reflected in the daily report. This emotion data is also reflected in the performance report and provided to management.

[0231] Step 12:

[0232] Server: Based on the emotional data, the server provides appropriate feedback and support messages to users (employees). For example, if stress is detected, the server suggests relaxation techniques, and if the employee is emotionally satisfied, the server sends a message praising the employee's achievements.

[0233] Step 13:

[0234] Server: Provides the generated performance reports to management, who can use the reports to obtain the data necessary to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[0235] Example 2

[0236] 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."

[0237] In today's corporate environment, organizations are required to increase employee productivity while accurately understanding work content and streamlining report creation. Manually creating daily reports and managing work hours takes time and effort, resulting in reduced productivity and stress. Furthermore, it is difficult for management to grasp not only the performance of individual employees, but also the work progress and emotional state of the entire team and organization in real time.

[0238] 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.

[0239] In this invention, the server includes: means for collecting records of work tool usage when employees leave work; a generation AI means for automatically extracting work content based on the collected record data; means for classifying the generated work content by category; means for generating a draft work report based on the classified work content and presenting it to the employee's device; means for saving the work reports submitted by the employees in a database; means for analyzing the saved work report data and generating performance reports for the team and the entire organization; an emotion engine means for recognizing and analyzing the emotional states of employees; means for reflecting the emotional data acquired by the emotion engine in the work reports and performance reports; and means for providing the generated performance reports to management. This enables efficient entry of employee daily reports, unified and accurate man-hour management, understanding of work progress, and real-time visualization of employee emotional states.

[0240] An "employee" is someone who belongs to a company or organization and performs work.

[0241] "Work tools" are software and hardware used by employees to do their jobs. Examples include email clients and code management systems.

[0242] "Usage logs" are data that is automatically generated when business tools are used. Examples include email sending and receiving logs and code commit logs.

[0243] "Generative AI" is artificial intelligence that automatically analyzes and extracts business content from collected data. It uses natural language processing technology and machine learning algorithms.

[0244] "Category" refers to a group or type for classifying extracted work content. Specifically, it includes "development," "meeting," "support," etc.

[0245] A "work report" is a document that records an employee's daily work, progress, time allocation, etc.

[0246] A "server" is a central computer system that collects, analyzes, stores, and provides data.

[0247] "Devices" refers to computers and devices used by employees, including desktops, laptops, tablets, etc.

[0248] A "database" is a system or platform for organizing and storing information for later use.

[0249] A "performance report" is a report that summarizes the work progress, results, challenges, emotional state, etc. of a team or the entire organization.

[0250] The "emotion engine" is a technology that analyzes the emotional state of employees from their speech and text input, using voice recognition and text analysis.

[0251] "Management" refers to people in a position to give instructions and make management decisions in a company or organization. Specifically, this includes executives and managers.

[0252] This system collects records of employees' use of business tools when they leave work, automatically extracts work content using generation AI, categorizes it, and generates draft work reports. Furthermore, it uses an emotion engine to grasp employees' emotional states and reflects them in work reports and performance reports, providing detailed information to management.

[0253] Collecting log data

[0254] The server accesses the company's business tools (e.g., email server and code management system) once a day at a specified time to collect employee usage logs. It connects to the email server using the IMAP protocol to retrieve mail logs. It connects to the code management system using an API to retrieve project changes and commit logs. The collected log data is temporarily stored in the server's memory.

[0255] Automatic extraction of business content

[0256] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. For example, the task details of "client support" are extracted from email logs, and the task details of "bug fixes" are extracted from code management logs.

[0257] Business categorization

[0258] The generative AI model classifies the extracted tasks into predefined categories (e.g., "development," "meeting," "support," etc.) Using a keyword-based algorithm, tasks containing the keyword "code" are classified as "development," and tasks containing the keyword "meeting" are classified as "meeting."

[0259] Generate and present daily report drafts

[0260] The server uses templates to generate draft work reports based on the classified work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. Employees can review the presented draft and make corrections or additions as necessary.

[0261] Daily report database storage

[0262] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The server then stores the received business report in a database.

[0263] Analyze daily data and generate performance reports

[0264] The generative AI model analyzes work report data stored in a database. Based on this analysis, a performance report for the team or the entire organization is generated. For example, the report includes each employee's work content, time allocation, and progress for each project.

[0265] Emotion engine integration

[0266] The emotion engine recognizes emotions from the voices and texts employees input while working, using voice recognition and text analysis technologies to evaluate stress levels and satisfaction.

[0267] Reflecting emotional data

[0268] The server adjusts draft work reports based on the emotional data obtained from the emotion engine. For example, it can reflect an employee's feelings of stress in the work report. This emotional data can also be reflected in performance reports, allowing management to understand the emotional health of the organization.

[0269] Feedback and Support

[0270] The server provides appropriate feedback and support messages to the user based on the emotional data obtained from the emotion engine. For example, if stress is detected, a message suggesting relaxation techniques is sent, and if the user is emotionally satisfied, a message praising the user's achievement is sent.

[0271] Providing performance reports

[0272] The server then provides the generated performance report to management, which reflects not only each employee's work performance but also their emotional state, allowing managers to gain a more accurate understanding of the overall situation of the organization.

[0273] Specific examples

[0274] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generative AI model extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." Based on the categorized work content, a draft daily report is generated and displayed on employee A's device. Employee A checks and modifies the draft, then finalizes and submits it. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in work reports and performance reports and provided to management.

[0275] Prompt Sentence Examples

[0276] An example of a prompt to be input to the generative AI model is, "Analyze today's email log and code management log, extract the main work content, and create a work report."

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1:

[0279] The server accesses internal business tools (e.g., email servers and code management systems) once a day at a specified time to collect employee usage logs. Specifically, it connects to the email server using the IMAP protocol and retrieves email logs. It also connects to the code management system using an API to retrieve project changes and commit logs. The inputs are the IMAP server connection information and API endpoints, and the output is email logs and code management logs. The collected log data is temporarily stored in the server's memory.

[0280] Step 2:

[0281] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. Specifically, the model is given a prompt: "Analyze email logs and code management logs and extract key task details," and the extracted task details are obtained as output. For example, the task details "client support" are extracted from email logs, and the task details "bug fixes" are extracted from code management logs.

[0282] Step 3:

[0283] The generative AI model classifies the extracted work content into predefined categories (for example, "development," "meeting," "support," etc.). Using a keyword-based algorithm, work content containing the keyword "code" is classified as "development," and work content containing the keyword "meeting" is classified as "meeting." The input is the extracted work content, and the output is the work content categorized by category. In terms of specific operation, the generative AI model follows the rule "classify the work content into categories."

[0284] Step 4:

[0285] The server uses a template to generate a draft of the work report based on the categorized work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. The input is work content categorized by category, and the output is a draft of the work report. Specifically, the server performs the process of "filling in the work content extracted for each category according to the daily report template."

[0286] Step 5:

[0287] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The input is the draft business report that has been corrected and added by the user, and the output is the finalized business report. In concrete terms, the user clicks the "Save" button, and the finalized data is sent to the server.

[0288] Step 6:

[0289] The server stores the received business report in a database. The input is the confirmed business report, and the output is the business report data stored in the database. Specifically, the server performs the process of "storing the confirmed business report in the database."

[0290] Step 7:

[0291] The generative AI model analyzes work report data stored in a database and generates performance reports for teams and the entire organization. The input is all work report data stored in the database, and the output is a performance report. Specifically, the model is input with the prompt "Create a monthly performance report based on the daily report data of all employees," and the analysis results are obtained.

[0292] Step 8:

[0293] The emotion engine recognizes and analyzes emotions from the voices and texts that employees enter during work. This analysis uses voice recognition and text analysis technologies. The input is voice data and text data, and the output is emotion evaluation data. Specifically, the emotion engine analyzes according to the rule, "assess stress level."

[0294] Step 9:

[0295] The server adjusts the draft of the business report based on the emotion data obtained from the emotion engine. The input is emotion data, and the output is a draft of the business report that reflects the emotion data. Specifically, the server performs the process of "if the stress level is high, reflect that in the business report."

[0296] Step 10:

[0297] The server provides the generated performance report to management. This report includes each employee's work content and emotional state. The input is the performance report, and the output is a report provided to management. Specifically, the server performs the process of "automatically sending a performance report containing all analysis results once a month."

[0298] (Application example 2)

[0299] 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."

[0300] Currently, many companies and factories have systems in place to track work logs and tasks and evaluate the performance of employees and robots. However, these systems require manual data entry and human intervention, making them inefficient and resulting in high error rates. Furthermore, there is a lack of systems that can grasp the emotions and operational status of robots and employees in real time and take appropriate action. This hinders productivity improvement and proper maintenance, ultimately resulting in a decline in the performance of robots and employees.

[0301] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting usage logs of in-house tools when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; means for classifying the generated work content by category; means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal; means for saving daily reports submitted by employees in a database; means for analyzing the saved daily report data and generating performance reports for the team and the entire organization; means for providing the generated performance report to management; means for analyzing work logs and sensor data collected by factory robots while they are operating; means for automatically generating daily reports for the factory robots based on the analyzed work logs and sensor data; and means for analyzing abnormal conditions from the factory robot's operating status and error logs using an emotion engine and issuing alerts as necessary. This enables automatic generation of daily reports and real-time performance evaluation.

[0302] An "employee" is a worker who is responsible for a specific task within a company or organization.

[0303] "Clocking out" refers to an employee completing their work hours for the day and leaving the workplace.

[0304] "Internal tools" is a general term for software and systems used by employees within a company to carry out their work.

[0305] "Usage logs" refer to records of employees or devices using specific tools or systems.

[0306] "Generative AI" is a system that uses artificial intelligence technology to generate information from data.

[0307] "Work content" is the details of the work or tasks actually performed by employees or equipment.

[0308] A "category" is a group for classifying multiple business operations based on common characteristics or criteria.

[0309] A "daily report" is a document that reports on the work that employees and equipment performed that day.

[0310] "Draft" means an initial draft of a document prior to its finalization.

[0311] "Terminals" are devices such as computers and smartphones used by employees.

[0312] A "database" is an electronic system for efficiently storing, retrieving, and managing data.

[0313] A "performance report" is a report used to evaluate and analyze the work efficiency and results of employees, teams, and the entire organization.

[0314] "Management" refers to the group of executives who make strategic decisions for a company or organization.

[0315] A "factory robot" is a mechanical device that is programmed to perform specific tasks on a manufacturing floor.

[0316] A "work log" is data that records the work performed by a factory robot.

[0317] "Sensor data" refers to various types of physical information acquired by sensors.

[0318] The "Emotion Engine" is a software system for analyzing emotions and operating status from data.

[0319] "Operating state" refers to the state in which factory robots and equipment are operating.

[0320] An "error log" is recorded data when a system or device experiences an error.

[0321] An "alert" is a function or notification that issues a warning when an abnormality or problem occurs.

[0322] As an example of how to implement this invention, we will explain a system that combines data collection when employees leave work and monitoring the operation of factory robots. The system is composed of multiple modules, each of which performs a specific function.

[0323] Collecting log data

[0324] The server periodically collects usage logs of internal tools (such as mail servers and code management systems) when employees leave work. This collection is done using the IMAP protocol and API. The log data is temporarily stored in memory and later converted into a format that is easy to analyze. In addition, work logs and sensor data generated by factory robots while they are operating are also collected.

[0325] Automatic extraction of business content

[0326] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI incorporates natural language processing technology to summarize and extract key work content from email logs, code management logs, and work logs. The extracted information is categorized into specific work content such as "client support," "bug fixing," and "parts assembly."

[0327] Business categorization

[0328] The generative AI categorizes the extracted tasks into predefined categories: tasks related to "code" are classified into the "development" category, tasks related to "meetings" into the "conference" category, and tasks related to "assembly of parts" into the "manufacturing" category.

[0329] Generate and present daily report drafts

[0330] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is presented to the employee's terminal when they leave work, and the employee can check and edit it. Similarly, a daily report regarding factory robots is also generated.

[0331] Daily report database storage

[0332] After the user (employee) checks and modifies the draft daily report, the final version is saved in the database, which allows the daily report data to be consolidated and analyzed later.

[0333] Analyze daily data and generate performance reports

[0334] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization, including the work content, time allocation, and project progress of each employee and robot.

[0335] Emotion engine integration

[0336] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots, and utilizes voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions.

[0337] Reflecting emotional data

[0338] The emotion engine then uses the emotion data to adjust the draft daily report. For example, if an employee is under stress, this will be reflected in the daily report. The emotion data is also incorporated into performance reports and provided to management.

[0339] Feedback and Support

[0340] The server provides feedback and support messages to users (employees) based on the emotional data. If stress is detected, it suggests relaxation techniques, and if the user is emotionally satisfied, it sends a message praising the user's achievements.

[0341] Providing performance reports

[0342] The generated performance reports are provided to management to help formulate organizational strategies and optimize resource allocation, while reports reflecting emotional data can be used to monitor employee mental health and robot operation status.

[0343] Specific examples

[0344] For example, when a user (Employee A) leaves work, the server collects the day's emails and usage logs of the code management tool. The generation AI extracts work details such as "client support" and "bug fixing" and categorizes them into "development" and "support." Similarly, for Robot A in the factory, work logs such as "parts assembly" and "welding" are collected and analyzed to generate a daily report. An example of an emotion engine analyzing Employee A's stress level and reflecting this in a daily report or report would be, "As stress level is high, we will suggest relaxation methods."

[0345] Example prompt sentence:

[0346] "Generate a draft daily report based on Robot A's work log data and emotion data. Task content: ['Parts assembly', 'Welding', 'Inspection'], Emotional state: {'status': 'stress', 'level': 8}."

[0347] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0348] Step 1: Collect log data

[0349] When employees leave work, the server collects work logs and sensor data from internal tools (for example, email servers and code management systems) and factory robots. Here, the IMAP protocol is used to obtain email logs, and APIs are used to obtain code management logs and robot data. The collected log data is temporarily stored in memory and later converted into a format that is easy to analyze. The input is the operation logs of each tool and robot, and the output is log data in a format suitable for analysis.

[0350] Step 2: Automatic extraction of business content

[0351] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI uses natural language processing technology to identify and summarize key work content from email logs, code management logs, and work logs. For example, it extracts content such as "client support" from email logs, "bug fixing" from code management logs, and "parts assembly" from robot work logs. The input is log data, and the output is a list of extracted work content.

[0352] Step 3: Categorize your work

[0353] The server categorizes the work content extracted by the generation AI. Based on predefined keywords and patterns, "code" is categorized as "development," "meetings" as "conferences," and "parts assembly" as "manufacturing." The input is a list of work content, and the output is the work content categorized by category.

[0354] Step 4: Generate and present a draft daily report

[0355] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is automatically presented to the employee's terminal when they leave work, and the employee can review and edit it. A daily report about the robot is also generated. The input is the work content categorized by category, and the output is the generated draft daily report.

[0356] Step 5: Save daily reports to the database

[0357] After the user (employee) checks the draft daily report and makes corrections or additions, the final version of the daily report is saved in the database. This allows the daily report data to be integrated and analyzed later. The input is the corrected draft daily report, and the output is the finalized daily report saved in the database.

[0358] Step 6: Analyze daily data and generate performance reports

[0359] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization. The reports include the work content, time allocation, and project progress of each employee and robot. The input is the daily report data from the database, and the output is the performance report.

[0360] Step 7: Integrating the Emotion Engine

[0361] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots. It uses voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions. The input is voice and text data, and the output is the analyzed emotional state.

[0362] Step 8: Reflecting emotional data

[0363] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is under stress, this is reflected in the daily report. The emotion data is also incorporated into the performance report and provided to management. The input is emotion data, and the output is the adjusted daily report and performance report.

[0364] Step 9: Feedback and support

[0365] The server provides feedback and support messages to users (employees) based on the emotional data. For example, if stress is detected, it suggests relaxation techniques, and if the employee is emotionally satisfied, it sends a message praising their achievements. The input is emotional data, and the output is a feedback message.

[0366] Step 10: Provide performance reports

[0367] The generated performance reports are provided to management and are useful for formulating organizational strategies and optimizing resource allocation. Reports that reflect emotional data can also be used to manage employee mental health and robot operating status. The input is the performance report, and the output is the provided report.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] [Second embodiment]

[0372] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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."

[0384] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, and then stores and analyzes the daily report in a database before providing a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate labor-hour management.

[0385] Collecting log data

[0386] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using the GitHub API. The collected log data is temporarily stored in memory and prepared for storage in the database.

[0387] Automatic extraction of business content

[0388] The generative AI analyzes the collected log data and extracts business details. It uses natural language processing to generate a summary of the log and identify key business details. For example, it extracts activities such as "code review" and "development of new features" that employees performed on GitHub.

[0389] Business categorization

[0390] The generative AI classifies the extracted work content into predefined categories. For example, if the work content contains the keyword "code," it will be classified into the "development" category. Similarly, logs related to meetings will be classified into the "meeting" category.

[0391] Generate and present daily report drafts

[0392] The server generates a draft of the daily report based on the categorized work content and automatically displays it on the employee's device when they leave work. The draft is provided in a concise and structured format so that employees can easily check and modify it.

[0393] Daily report database storage

[0394] After the user (employee) checks, modifies, and confirms the daily report draft, the confirmed daily report is saved in the database by the server. This saved data is analyzed later, so it is managed accurately.

[0395] Analyze daily data and generate performance reports

[0396] The generation AI analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0397] Providing performance reports

[0398] The server periodically provides the generated performance reports to the management, allowing the users (management) to obtain sufficient information for formulating organizational strategies and optimizing resource allocation.

[0399] Specific examples

[0400] For example, when employee A leaves work, the server collects that day's email and GitHub usage logs. The generation AI extracts tasks such as "fixing issue 123," "code review for new features," and "documentation updates" from the collected log data. These tasks are categorized and a draft daily report is generated in the form of "development," "review," or "documentation." The server presents this draft to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is stored in a database by the server, and the generation AI then analyzes it to create a performance report for the team and the entire organization. This report is provided to management and can be used to improve organizational productivity and accurately manage man-hours.

[0401] Through the above process, the present invention achieves both efficient daily report entry and accurate man-hour management, thereby helping to maximize a company's productivity.

[0402] The processing flow will be explained below.

[0403] Step 1:

[0404] Server: When employees leave work, internal tools (email, code management tools, etc.) are accessed and usage logs are collected. This includes obtaining email logs using the IMAP protocol and obtaining code management logs using the GitHub API.

[0405] Step 2:

[0406] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is then stored in a database. This accumulates the usage logs and prepares them for analysis.

[0407] Step 3:

[0408] Generative AI: Analyzes log data stored in a database and automatically extracts task details. Based on prompts, natural language processing technology is used to generate a summary of the log and identify key task details. For example, task details such as "client support" can be extracted from email logs.

[0409] Step 4:

[0410] Generative AI: Classifies extracted work content into predefined categories. For example, work containing the keyword "code" is classified into the "development" category, and work containing the keyword "meeting" is classified into the "conference" category.

[0411] Step 5:

[0412] Server: Automatically generates draft daily reports based on categorized work content. These drafts are designed to be concise and structured so that employees can easily review and revise them.

[0413] Step 6:

[0414] Server: Presents the generated draft daily report to the employee's terminal when he / she leaves work. The draft daily report is automatically displayed on the employee's terminal, allowing for easy confirmation and correction.

[0415] Step 7:

[0416] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[0417] Step 8:

[0418] Server: Stores the daily reports submitted by employees in a database, which aggregates the data and allows for later analysis.

[0419] Step 9:

[0420] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0421] Step 10:

[0422] Server: Provides generated performance reports to management, providing them with the information they need to formulate organizational strategies and optimize resource allocation.

[0423] Example 1

[0424] 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."

[0425] Modern companies spend a lot of time and effort manually entering daily reports, which can lead to poor business efficiency. Furthermore, errors and non-standard formats caused by manual entry make accurate labor-hour management and performance analysis difficult. To solve these issues and improve business efficiency, a system is needed that automatically extracts and classifies employee work content and generates draft daily reports.

[0426] 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.

[0427] In this invention, the server includes: means for collecting general-purpose tool usage logs when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; a means for summarizing the extracted work content using natural language processing; and a means for classifying the summarized work content by category. This enables efficient extraction and classification of work content, and the generation and presentation of daily report drafts. The server also includes means for saving daily reports finalized by users in a database; a means for analyzing the saved daily report data using a generation AI to generate a performance report for the entire organization; and a means for providing the generated performance report to a manager. This enables accurate man-hour management and performance evaluation for the entire organization, thereby improving corporate productivity.

[0428] "Means for collecting usage logs of general-purpose tools when employees leave work" refers to a method or device that allows a server to automatically collect usage history of general-purpose tools such as email and source code management tools when employees leave work.

[0429] The "generative AI means for automatically extracting work content based on collected log data" is an artificial intelligence technology that analyzes log data collected by the server and automatically extracts the work content of employees using natural language processing technology.

[0430] "Means for summarizing extracted business content using natural language processing" refers to a technology that analyzes text data, extracts only the important points, and summarizes them concisely in order to summarize the business content extracted by the generation AI.

[0431] A "means for classifying summarized work content by category" is a method or device for dividing summarized work content into specific categories and classifying each task into categories such as "development," "review," and "meeting."

[0432] The "means for generating a draft daily report and presenting it on the employee's user terminal" is a mechanism for automatically creating a draft daily report based on the classified work content and displaying the draft on the user terminal when the employee leaves work.

[0433] "Means for saving daily reports finalized by users to a database" refers to a method or device by which a server receives daily reports that employees have edited and revised on their terminals and finalized, and stores the contents in a database.

[0434] "A means of analyzing saved daily report data using generation AI to generate a performance report for the entire organization" is a technology in which generation AI analyzes daily report data saved in a database and automatically generates a performance report for the entire organization based on the work content and time allocation of each employee.

[0435] The "means for providing the generated performance report to the administrator" refers to a method or device by which the server periodically provides the generated performance report to the administrator in the form of email, dashboard, or the like.

[0436] This invention is a system that collects usage logs of general-purpose tools when employees leave work, automatically extracts work content using generation AI, generates and presents a draft daily report, saves the daily report in a database, analyzes it, and then generates a performance report for the entire organization.

[0437] Hardware and software used

[0438] This system uses the following hardware and software:

[0439] Server: Collects log data, generates and presents daily report drafts, stores them in a database, and generates and provides performance reports.

[0440] User terminal: Functions as a device for employees to check, correct, and confirm draft daily reports.

[0441] Generative AI model: Uses natural language processing technology to extract business details from log data, and generates summaries, categorization, and performance reports.

[0442] Program processing

[0443] The server collects usage logs from the mail server using the IMAP protocol when employees leave work, and also collects log data from the code management system using the GitHub API. These log data are temporarily stored in memory.

[0444] Next, the generative AI analyzes the collected log data and uses natural language processing technology to generate summaries of the log data and identify key business activities. For example, activities such as "fixing Issue 123," "code review of new features," and "documentation updates" can be extracted from GitHub usage logs.

[0445] The extracted work content is then classified by the generation AI into categories such as "development," "review," and "meeting." The server then generates a draft daily report based on these categorizations and automatically displays it on the user's device when the employee leaves work. The draft is provided in a concise, structured format, allowing employees to quickly review the content and make any necessary corrections.

[0446] Once an employee has finalized their daily report draft, the server stores the data in a database. The saved data is then analyzed by the AI ​​to generate a performance report for the entire organization. This report includes each employee's work, time allocation, and progress on each project.

[0447] Finally, the server periodically provides the generated performance reports to the administrator, allowing the user (administrator) to obtain the information necessary to formulate organizational strategies and optimize resource allocation.

[0448] Examples of concrete examples and prompts

[0449] For example, when employee A leaves work, the server collects that day's email and source code management system usage logs. From the collected log data, the generation AI extracts tasks such as "Fixing Issue 123," "Code review of new features," and "Documentation update." These tasks are categorized into categories such as "Development," "Review," and "Documentation." The server presents a draft of the daily report to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is saved in a database by the server, and the generation AI then analyzes it to create a performance report for the entire organization. This report is provided to managers and can be used to improve organizational productivity and accurately manage man-hours.

[0450] An example of a prompt for a generative AI model is, "Summarize the activities obtained from GitHub usage logs (e.g., fixing Issue 123, code review, developing new features, etc.) and classify each activity into the appropriate category."

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1: Collect log data

[0453] The server collects general-purpose tool usage logs when employees leave work. Specifically, the server connects to the mail server using the IMAP protocol and retrieves the employee's email log. At this time, the server filters and collects unread emails and emails in specific folders. It also uses the GitHub API to retrieve activity logs from the employee code management system. This log data is temporarily stored in memory.

[0454] Input: Employee email server and code management system usage logs

[0455] Output: Log data stored in memory

[0456] Step 2: Automatic extraction of business content

[0457] The generative AI analyzes the log data collected by the server and extracts the details of the work. Specifically, it uses a natural language processing algorithm to analyze text and extract important activities. For example, from a GitHub log, it can extract work details such as "Fixing Issue 123" and "Code review for new features."

[0458] Input: Log data stored in memory

[0459] Output: Extracted business details

[0460] Step 3: Generate a summary of the business

[0461] The generative AI summarizes the extracted work content, extracting only the important points from the extracted data and summarizing them concisely. For example, long descriptions such as "Fixing Issue 123" and "Code review for new features" are summarized into short keywords such as "code fix" and "review."

[0462] Input: Extracted business details

[0463] Output: Summary of work

[0464] Step 4: Categorize your work

[0465] The generation AI classifies the summarized work content into predefined categories. The generation AI performs keyword analysis and classifies summarized work content such as "code correction" and "review" into categories such as "development" and "review."

[0466] Input: Summary of work

[0467] Output: Jobs categorized by category

[0468] Step 5: Generate and present a draft daily report

[0469] The server creates a draft of the daily report based on the work content categorized by category. The generated draft is automatically displayed on the user's device when the employee leaves work. The draft is presented in a structured format so that employees can easily check and modify it.

[0470] Input: Jobs categorized by category

[0471] Output: A draft of the daily report displayed on the user's terminal

[0472] Step 6: Check the daily report and save it to the database

[0473] The user (employee) checks the draft of the daily report displayed on the terminal and makes any necessary corrections. Once the corrections are complete and the finalized daily report is saved in the database by the server.

[0474] Input: Daily report draft confirmed and corrected by the user

[0475] Output: Daily fixed report stored in the database

[0476] Step 7: Analyze the daily data

[0477] The server analyzes the daily report data stored in the database using a generation AI, which extracts information such as each employee's work content, time allocation, and progress by project from the stored daily report data.

[0478] Input: Finalized daily report saved in the database

[0479] Output: Parsed performance data

[0480] Step 8: Generate and provide performance reports

[0481] The server generates an organization-wide performance report based on the performance data analyzed by the AI, which includes an overview of each employee's work, time allocation, and progress by project, and is provided to managers.

[0482] Input: Parsed performance data

[0483] Output: Performance report provided to management

[0484] (Application example 1)

[0485] 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."

[0486] Employees' daily report entry work is time-consuming, making it difficult to accurately manage man-hours and grasp productivity. Furthermore, particularly in on-site work such as factories, it is difficult for employees to record and understand their work in real time, resulting in insufficient data collection for efficient progress management and productivity improvement. For this reason, a system is needed that reduces the burden on employees and managers and improves productivity.

[0487] 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.

[0488] In this invention, the server includes means for collecting usage logs of internal tools when employees leave work, a generation AI means for automatically extracting work content based on the collected log data, a means for classifying the generated work content by category, a means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal, a means for saving the daily reports submitted by the employees in a database, a means for analyzing the saved daily report data and generating performance reports for the team and the entire organization, a means for providing the generated performance report to management, and a means for collecting the work logs of workers in real time and displaying them on smart glasses or a head-mounted display. This enables more efficient entry of employee daily reports, accurate man-hour management, and real-time understanding of work content.

[0489] "Means for collecting usage logs of internal tools when employees leave work" refers to a system that automatically collects usage history information for various software and systems used within the company when employees finish work and leave the office.

[0490] The "generative AI method for automatically extracting work content" is a technology that analyzes collected usage log data and uses generative AI to automatically identify and extract the specific work content performed by employees.

[0491] The "means for categorizing by category" is a system for dividing the extracted work content into predetermined categories based on specific criteria or keywords.

[0492] "Means for generating a draft daily report and presenting it on employees' devices" refers to a technology that automatically generates an initial version of a daily report based on classified work content and displays it on the computer or mobile device used by the employee.

[0493] "Means for storing daily reports in a database" refers to a system for recording and storing daily report data that has been confirmed, corrected, and confirmed by employees in a company database.

[0494] The "means for generating performance reports" refers to a technology that analyzes saved daily report data and creates reports on the work progress and productivity of a team or the entire organization.

[0495] "Means for providing performance reports to management" refers to a system for periodically distributing and presenting the generated performance reports to the company's senior managers and executives.

[0496] "Means for collecting work logs in real time and displaying them on smart glasses or head-mounted displays" refers to technology that records the work content of employees in real time and immediately displays that information to employees via smart glasses or head-mounted displays.

[0497] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it on the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate man-hour management.It can also be used by factory workers to understand work content in real time using smart glasses or head-mounted displays.

[0498] First, the server collects the usage logs of internal tools when employees leave work. This collection is done using the mail server's IMAP protocol and the code management system's API. The collected log data is temporarily stored in memory and prepared for storage in a database. This data is used to record the details of employee work.

[0499] Next, the Generative AI analyzes the collected log data and automatically extracts work content. It uses natural language processing technology to generate log summaries and identify key work content. For example, activities such as "client meetings" are extracted from email logs, and "bug fixes" are extracted from code management systems. Machine learning algorithms are used in this process to classify work content based on specific keywords and phrases.

[0500] The generation AI then classifies the extracted work content into predefined categories. For example, based on keywords such as "correction" or "review," each work is divided into categories such as "development" or "inspection." A draft daily report is generated based on the classified work content and presented to the employee's device. This draft is provided in a format that employees can easily check and edit.

[0501] The daily report drafts that employees review and revise are stored in a database for later analysis. Specifically, the stored data is analyzed by generative AI to generate performance reports for the team and the entire organization. These reports include each employee's work content, time allocation, progress by project, and more. This provides management with sufficient information to formulate organizational strategies and optimize resource allocation.

[0502] The system also has the ability to collect work logs of factory workers in real time and display them on smart glasses or head-mounted displays. When a worker wears a smart device, the server instantly collects and analyzes the work log, and the generated work details are displayed on the device. This allows workers to understand the details of their work in real time and work efficiently.

[0503] For example, when a worker at a factory puts on smart glasses, the day's work log is collected and a summary of the tasks performed that day (e.g., "machine maintenance" and "product quality check") is automatically presented. When the worker checks and corrects the content and submits it, it is saved in a database and a productivity report is provided to the supervisor.

[0504] Examples of prompts to input to a generative AI model include:

[0505] "Extract the factory work details from today's work log, categorize them, and generate a draft daily report."

[0506] "Based on the extracted work examples ['machine maintenance', 'quality check'], please classify each into the categories of 'maintenance' and 'inspection'."

[0507] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0508] Step 1:

[0509] The server periodically collects usage logs from internal tools. Specifically, it retrieves email logs from the mail server using the IMAP protocol and code logs from the code management system using the GitHub API. It receives employee IDs and timestamps as input and obtains the log data to be saved as output.

[0510] Step 2:

[0511] The server temporarily stores the collected log data in memory. This is the preparation stage for storing it in the database. It receives the collected log data as input and outputs the data temporarily stored in memory.

[0512] Step 3:

[0513] Generative AI analyzes log data and automatically extracts work content. It uses natural language processing technology to identify work content, such as "code review" or "bug fix." It receives temporarily stored log data as input and obtains the extracted work content as output.

[0514] Step 4:

[0515] The generative AI categorizes the extracted work content. Based on keywords such as "correction" and "review," it divides the work content into categories such as "development" and "inspection." It receives the extracted work content as input and obtains the categorized work content as output.

[0516] Step 5:

[0517] The server generates a draft of the daily report based on the classified work content. This draft is presented to the terminal in a structured format. It receives the categorized work content as input and obtains the generated draft of the daily report as output.

[0518] Step 6:

[0519] The terminal presents the generated daily report draft to the employee, who then confirms and corrects it. The terminal receives the presented daily report draft as input and obtains corrected daily report data as output.

[0520] Step 7:

[0521] The server stores the corrected daily report in a database. This stored daily report data is used for later analysis. It receives the corrected daily report data as input and obtains the daily report data stored in the database as output.

[0522] Step 8:

[0523] The generation AI analyzes the stored daily report data and generates performance reports for the team and the entire organization, including information on work content, time allocation, progress by project, etc. It receives the daily report data stored in the database as input and obtains the generated performance report as output.

[0524] Step 9:

[0525] The server provides the generated performance reports to management, taking the generated performance reports as input and providing them as output in a format that can be accessed and viewed by management.

[0526] Step 10:

[0527] When a worker wears smart glasses or a head-mounted display, the server collects and displays work logs in real time, allowing workers to instantly understand the work they are doing. Real-time work data is received as input, and the work content displayed on the device is obtained as output.

[0528] 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.

[0529] The system of this invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management.Furthermore, by combining it with an emotion engine, it becomes possible to recognize and analyze the user's emotional state and reflect it in the daily report and performance report.

[0530] Collecting log data

[0531] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using an API. The collected log data is temporarily stored in memory and later converted into a format that is easy to process.

[0532] Automatic extraction of business content

[0533] Generative AI analyzes collected log data and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract "client support" task details from email logs and "bug fixes" task details from code management logs.

[0534] Business categorization

[0535] The generative AI classifies the extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "meeting" category.

[0536] Generate and present daily report drafts

[0537] The server generates a draft of the daily report based on the work content categorized by category. The generated draft is automatically presented to the employee's terminal when they leave work. The employee can review the presented draft and make corrections or additions as necessary.

[0538] Daily report database storage

[0539] The user (employee) checks the draft daily report, makes corrections and additions, then finalizes and submits the daily report. The submitted daily report is saved in the database by the server. This allows the daily report data to be aggregated and analyzed later.

[0540] Analyze daily data and generate performance reports

[0541] The AI ​​analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0542] Emotion engine integration

[0543] The emotion engine recognizes emotions from the voices and texts employees use while working. For example, it uses voice recognition and text analysis technology to evaluate employees' stress levels and satisfaction. This allows emotional data to be reflected in daily drafts and performance reports.

[0544] Reflecting emotional data

[0545] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is feeling stressed, the server will reflect this in the daily report. The emotion data is also reflected in performance reports, allowing management to understand the emotional health of the organization.

[0546] Feedback and Support

[0547] The server provides appropriate feedback and support messages to users (employees) based on the emotional data obtained from the emotion engine. For example, it may suggest relaxation techniques if stress is detected, or send a message praising the employee's achievements if the employee is emotionally satisfied.

[0548] Providing performance reports

[0549] The server then provides the generated performance reports to management, who can then obtain the information they need to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[0550] Specific examples

[0551] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generation AI extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." A draft daily report is generated based on the categorized work content and presented to employee A's device. Employee A then checks and amends the draft and submits the final version. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in the daily report and performance report, and provided to management.

[0552] Through the above process, the present invention improves the efficiency of daily report entry, enables unified and accurate labor-hour management, and also realizes understanding of employees' emotional states and providing feedback, thereby helping to maximize corporate productivity and manage the mental health of employees.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] Server: When employees leave work, internal tools (e.g., mail servers, code management systems) are accessed to collect usage logs. This includes obtaining mail logs using the IMAP protocol and obtaining code management logs using APIs.

[0556] Step 2:

[0557] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is stored in a database and prepared for analysis.

[0558] Step 3:

[0559] Generative AI: Analyzes log data stored in a database and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract the task details "client support" from email logs and "bug fixes" from code management logs.

[0560] Step 4:

[0561] Generative AI: Classifies extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "conference" category.

[0562] Step 5:

[0563] Server: Generates a draft of the daily report based on the categorized work content. This draft is designed to be concise and structured so that employees can easily check and revise it.

[0564] Step 6:

[0565] Server: The generated draft daily report is automatically presented to the employee's terminal when they leave work. The draft daily report is displayed on the employee's terminal, allowing them to easily check and correct it.

[0566] Step 7:

[0567] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[0568] Step 8:

[0569] Server: Stores the daily reports submitted by employees in a database. Daily report data is aggregated and can be analyzed later.

[0570] Step 9:

[0571] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0572] Step 10:

[0573] Emotion engine: Recognizes emotions from employees' voices and input text while they are working. Using voice recognition and text analysis technologies, it evaluates employees' stress levels and satisfaction. For example, it detects the emotional state of "feeling stressed" from voice logs.

[0574] Step 11:

[0575] Server: Adjusts the draft daily report based on the recognized emotion data. For example, if an employee is feeling stressed, this will be reflected in the daily report. This emotion data is also reflected in the performance report and provided to management.

[0576] Step 12:

[0577] Server: Based on the emotional data, the server provides appropriate feedback and support messages to users (employees). For example, if stress is detected, the server suggests relaxation techniques, and if the employee is emotionally satisfied, the server sends a message praising the employee's achievements.

[0578] Step 13:

[0579] Server: Provides the generated performance reports to management, who can use the reports to obtain the data necessary to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[0580] Example 2

[0581] 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."

[0582] In today's corporate environment, organizations are required to increase employee productivity while accurately understanding work content and streamlining report creation. Manually creating daily reports and managing work hours takes time and effort, resulting in reduced productivity and stress. Furthermore, it is difficult for management to grasp not only the performance of individual employees, but also the work progress and emotional state of the entire team and organization in real time.

[0583] 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.

[0584] In this invention, the server includes: means for collecting records of work tool usage when employees leave work; a generation AI means for automatically extracting work content based on the collected record data; means for classifying the generated work content by category; means for generating a draft work report based on the classified work content and presenting it to the employee's device; means for saving the work reports submitted by the employees in a database; means for analyzing the saved work report data and generating performance reports for the team and the entire organization; an emotion engine means for recognizing and analyzing the emotional states of employees; means for reflecting the emotional data acquired by the emotion engine in the work reports and performance reports; and means for providing the generated performance reports to management. This enables efficient entry of employee daily reports, unified and accurate man-hour management, understanding of work progress, and real-time visualization of employee emotional states.

[0585] An "employee" is someone who belongs to a company or organization and performs work.

[0586] "Work tools" are software and hardware used by employees to do their jobs. Examples include email clients and code management systems.

[0587] "Usage logs" are data that is automatically generated when business tools are used. Examples include email sending and receiving logs and code commit logs.

[0588] "Generative AI" is artificial intelligence that automatically analyzes and extracts business content from collected data. It uses natural language processing technology and machine learning algorithms.

[0589] "Category" refers to a group or type for classifying extracted work content. Specifically, it includes "development," "meeting," "support," etc.

[0590] A "work report" is a document that records an employee's daily work, progress, time allocation, etc.

[0591] A "server" is a central computer system that collects, analyzes, stores, and provides data.

[0592] "Devices" refers to computers and devices used by employees, including desktops, laptops, tablets, etc.

[0593] A "database" is a system or platform for organizing and storing information for later use.

[0594] A "performance report" is a report that summarizes the work progress, results, challenges, emotional state, etc. of a team or the entire organization.

[0595] The "emotion engine" is a technology that analyzes the emotional state of employees from their speech and text input, using voice recognition and text analysis.

[0596] "Management" refers to people in a position to give instructions and make management decisions in a company or organization. Specifically, this includes executives and managers.

[0597] This system collects records of employees' use of business tools when they leave work, automatically extracts work content using generation AI, categorizes it, and generates draft work reports. Furthermore, it uses an emotion engine to grasp employees' emotional states and reflects them in work reports and performance reports, providing detailed information to management.

[0598] Collecting log data

[0599] The server accesses the company's business tools (e.g., email server and code management system) once a day at a specified time to collect employee usage logs. It connects to the email server using the IMAP protocol to retrieve mail logs. It connects to the code management system using an API to retrieve project changes and commit logs. The collected log data is temporarily stored in the server's memory.

[0600] Automatic extraction of business content

[0601] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. For example, the task details of "client support" are extracted from email logs, and the task details of "bug fixes" are extracted from code management logs.

[0602] Business categorization

[0603] The generative AI model classifies the extracted tasks into predefined categories (e.g., "development," "meeting," "support," etc.) Using a keyword-based algorithm, tasks containing the keyword "code" are classified as "development," and tasks containing the keyword "meeting" are classified as "meeting."

[0604] Generate and present daily report drafts

[0605] The server uses templates to generate draft work reports based on the classified work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. Employees can review the presented draft and make corrections or additions as necessary.

[0606] Daily report database storage

[0607] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The server then stores the received business report in a database.

[0608] Analyze daily data and generate performance reports

[0609] The generative AI model analyzes work report data stored in a database. Based on this analysis, a performance report for the team or the entire organization is generated. For example, the report includes each employee's work content, time allocation, and progress for each project.

[0610] Emotion engine integration

[0611] The emotion engine recognizes emotions from the voices and texts employees input while working, using voice recognition and text analysis technologies to evaluate stress levels and satisfaction.

[0612] Reflecting emotional data

[0613] The server adjusts draft work reports based on the emotional data obtained from the emotion engine. For example, it can reflect an employee's feelings of stress in the work report. This emotional data can also be reflected in performance reports, allowing management to understand the emotional health of the organization.

[0614] Feedback and Support

[0615] The server provides appropriate feedback and support messages to the user based on the emotional data obtained from the emotion engine. For example, if stress is detected, a message suggesting relaxation techniques is sent, and if the user is emotionally satisfied, a message praising the user's achievement is sent.

[0616] Providing performance reports

[0617] The server then provides the generated performance report to management, which reflects not only each employee's work performance but also their emotional state, allowing managers to gain a more accurate understanding of the overall situation of the organization.

[0618] Specific examples

[0619] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generative AI model extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." Based on the categorized work content, a draft daily report is generated and displayed on employee A's device. Employee A checks and modifies the draft, then finalizes and submits it. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in work reports and performance reports and provided to management.

[0620] Prompt Sentence Examples

[0621] An example of a prompt to be input to the generative AI model is, "Analyze today's email log and code management log, extract the main work content, and create a work report."

[0622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0623] Step 1:

[0624] The server accesses internal business tools (e.g., email servers and code management systems) once a day at a specified time to collect employee usage logs. Specifically, it connects to the email server using the IMAP protocol and retrieves email logs. It also connects to the code management system using an API to retrieve project changes and commit logs. The inputs are the IMAP server connection information and API endpoints, and the output is email logs and code management logs. The collected log data is temporarily stored in the server's memory.

[0625] Step 2:

[0626] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. Specifically, the model is given a prompt: "Analyze email logs and code management logs and extract key task details," and the extracted task details are obtained as output. For example, the task details "client support" are extracted from email logs, and the task details "bug fixes" are extracted from code management logs.

[0627] Step 3:

[0628] The generative AI model classifies the extracted work content into predefined categories (for example, "development," "meeting," "support," etc.). Using a keyword-based algorithm, work content containing the keyword "code" is classified as "development," and work content containing the keyword "meeting" is classified as "meeting." The input is the extracted work content, and the output is the work content categorized by category. In terms of specific operation, the generative AI model follows the rule "classify the work content into categories."

[0629] Step 4:

[0630] The server uses a template to generate a draft of the work report based on the categorized work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. The input is work content categorized by category, and the output is a draft of the work report. Specifically, the server performs the process of "filling in the work content extracted for each category according to the daily report template."

[0631] Step 5:

[0632] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The input is the draft business report that has been corrected and added by the user, and the output is the finalized business report. In concrete terms, the user clicks the "Save" button, and the finalized data is sent to the server.

[0633] Step 6:

[0634] The server stores the received business report in a database. The input is the confirmed business report, and the output is the business report data stored in the database. Specifically, the server performs the process of "storing the confirmed business report in the database."

[0635] Step 7:

[0636] The generative AI model analyzes work report data stored in a database and generates performance reports for teams and the entire organization. The input is all work report data stored in the database, and the output is a performance report. Specifically, the model is input with the prompt "Create a monthly performance report based on the daily report data of all employees," and the analysis results are obtained.

[0637] Step 8:

[0638] The emotion engine recognizes and analyzes emotions from the voices and texts that employees enter during work. This analysis uses voice recognition and text analysis technologies. The input is voice data and text data, and the output is emotion evaluation data. Specifically, the emotion engine analyzes according to the rule, "assess stress level."

[0639] Step 9:

[0640] The server adjusts the draft of the business report based on the emotion data obtained from the emotion engine. The input is emotion data, and the output is a draft of the business report that reflects the emotion data. Specifically, the server performs the process of "if the stress level is high, reflect that in the business report."

[0641] Step 10:

[0642] The server provides the generated performance report to management. This report includes each employee's work content and emotional state. The input is the performance report, and the output is a report provided to management. Specifically, the server performs the process of "automatically sending a performance report containing all analysis results once a month."

[0643] (Application example 2)

[0644] 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."

[0645] Currently, many companies and factories have systems in place to track work logs and tasks and evaluate the performance of employees and robots. However, these systems require manual data entry and human intervention, making them inefficient and resulting in high error rates. Furthermore, there is a lack of systems that can grasp the emotions and operational status of robots and employees in real time and take appropriate action. This hinders productivity improvement and proper maintenance, ultimately resulting in a decline in the performance of robots and employees.

[0646] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting usage logs of in-house tools when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; means for classifying the generated work content by category; means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal; means for saving daily reports submitted by employees in a database; means for analyzing the saved daily report data and generating performance reports for the team and the entire organization; means for providing the generated performance report to management; means for analyzing work logs and sensor data collected by factory robots while they are operating; means for automatically generating daily reports for the factory robots based on the analyzed work logs and sensor data; and means for analyzing abnormal conditions from the factory robot's operating status and error logs using an emotion engine and issuing alerts as necessary. This enables automatic generation of daily reports and real-time performance evaluation.

[0647] An "employee" is a worker who is responsible for a specific task within a company or organization.

[0648] "Clocking out" refers to an employee completing their work hours for the day and leaving the workplace.

[0649] "Internal tools" is a general term for software and systems used by employees within a company to carry out their work.

[0650] "Usage logs" refer to records of employees or devices using specific tools or systems.

[0651] "Generative AI" is a system that uses artificial intelligence technology to generate information from data.

[0652] "Work content" is the details of the work or tasks actually performed by employees or equipment.

[0653] A "category" is a group for classifying multiple business operations based on common characteristics or criteria.

[0654] A "daily report" is a document that reports on the work that employees and equipment performed that day.

[0655] "Draft" means an initial draft of a document prior to its finalization.

[0656] "Terminals" are devices such as computers and smartphones used by employees.

[0657] A "database" is an electronic system for efficiently storing, retrieving, and managing data.

[0658] A "performance report" is a report used to evaluate and analyze the work efficiency and results of employees, teams, and the entire organization.

[0659] "Management" refers to the group of executives who make strategic decisions for a company or organization.

[0660] A "factory robot" is a mechanical device that is programmed to perform specific tasks on a manufacturing floor.

[0661] A "work log" is data that records the work performed by a factory robot.

[0662] "Sensor data" refers to various types of physical information acquired by sensors.

[0663] The "Emotion Engine" is a software system for analyzing emotions and operating status from data.

[0664] "Operating state" refers to the state in which factory robots and equipment are operating.

[0665] An "error log" is recorded data when a system or device experiences an error.

[0666] An "alert" is a function or notification that issues a warning when an abnormality or problem occurs.

[0667] As an example of how to implement this invention, we will explain a system that combines data collection when employees leave work and monitoring the operation of factory robots. The system is composed of multiple modules, each of which performs a specific function.

[0668] Collecting log data

[0669] The server periodically collects usage logs of internal tools (such as mail servers and code management systems) when employees leave work. This collection is done using the IMAP protocol and API. The log data is temporarily stored in memory and later converted into a format that is easy to analyze. In addition, work logs and sensor data generated by factory robots while they are operating are also collected.

[0670] Automatic extraction of business content

[0671] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI incorporates natural language processing technology to summarize and extract key work content from email logs, code management logs, and work logs. The extracted information is categorized into specific work content such as "client support," "bug fixing," and "parts assembly."

[0672] Business categorization

[0673] The generative AI categorizes the extracted tasks into predefined categories: tasks related to "code" are classified into the "development" category, tasks related to "meetings" into the "conference" category, and tasks related to "assembly of parts" into the "manufacturing" category.

[0674] Generate and present daily report drafts

[0675] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is presented to the employee's terminal when they leave work, and the employee can check and edit it. Similarly, a daily report regarding factory robots is also generated.

[0676] Daily report database storage

[0677] After the user (employee) checks and modifies the draft daily report, the final version is saved in the database, which allows the daily report data to be consolidated and analyzed later.

[0678] Analyze daily data and generate performance reports

[0679] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization, including the work content, time allocation, and project progress of each employee and robot.

[0680] Emotion engine integration

[0681] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots, and utilizes voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions.

[0682] Reflecting emotional data

[0683] The emotion engine then uses the emotion data to adjust the draft daily report. For example, if an employee is under stress, this will be reflected in the daily report. The emotion data is also incorporated into performance reports and provided to management.

[0684] Feedback and Support

[0685] The server provides feedback and support messages to users (employees) based on the emotional data. If stress is detected, it suggests relaxation techniques, and if the user is emotionally satisfied, it sends a message praising the user's achievements.

[0686] Providing performance reports

[0687] The generated performance reports are provided to management to help formulate organizational strategies and optimize resource allocation, while reports reflecting emotional data can be used to monitor employee mental health and robot operation status.

[0688] Specific examples

[0689] For example, when a user (Employee A) leaves work, the server collects the day's emails and usage logs of the code management tool. The generation AI extracts work details such as "client support" and "bug fixing" and categorizes them into "development" and "support." Similarly, for Robot A in the factory, work logs such as "parts assembly" and "welding" are collected and analyzed to generate a daily report. An example of an emotion engine analyzing Employee A's stress level and reflecting this in a daily report or report would be, "As stress level is high, we will suggest relaxation methods."

[0690] Example prompt sentence:

[0691] "Generate a draft daily report based on Robot A's work log data and emotion data. Task content: ['Parts assembly', 'Welding', 'Inspection'], Emotional state: {'status': 'stress', 'level': 8}."

[0692] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0693] Step 1: Collect log data

[0694] When employees leave work, the server collects work logs and sensor data from internal tools (for example, email servers and code management systems) and factory robots. Here, the IMAP protocol is used to obtain email logs, and APIs are used to obtain code management logs and robot data. The collected log data is temporarily stored in memory and later converted into a format that is easy to analyze. The input is the operation logs of each tool and robot, and the output is log data in a format suitable for analysis.

[0695] Step 2: Automatic extraction of business content

[0696] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI uses natural language processing technology to identify and summarize key work content from email logs, code management logs, and work logs. For example, it extracts content such as "client support" from email logs, "bug fixing" from code management logs, and "parts assembly" from robot work logs. The input is log data, and the output is a list of extracted work content.

[0697] Step 3: Categorize your work

[0698] The server categorizes the work content extracted by the generation AI. Based on predefined keywords and patterns, "code" is categorized as "development," "meetings" as "conferences," and "parts assembly" as "manufacturing." The input is a list of work content, and the output is the work content categorized by category.

[0699] Step 4: Generate and present a draft daily report

[0700] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is automatically presented to the employee's terminal when they leave work, and the employee can review and edit it. A daily report about the robot is also generated. The input is the work content categorized by category, and the output is the generated draft daily report.

[0701] Step 5: Save daily reports to the database

[0702] After the user (employee) checks the draft daily report and makes corrections or additions, the final version of the daily report is saved in the database. This allows the daily report data to be integrated and analyzed later. The input is the corrected draft daily report, and the output is the finalized daily report saved in the database.

[0703] Step 6: Analyze daily data and generate performance reports

[0704] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization. The reports include the work content, time allocation, and project progress of each employee and robot. The input is the daily report data from the database, and the output is the performance report.

[0705] Step 7: Integrating the Emotion Engine

[0706] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots. It uses voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions. The input is voice and text data, and the output is the analyzed emotional state.

[0707] Step 8: Reflecting emotional data

[0708] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is under stress, this is reflected in the daily report. The emotion data is also incorporated into the performance report and provided to management. The input is emotion data, and the output is the adjusted daily report and performance report.

[0709] Step 9: Feedback and support

[0710] The server provides feedback and support messages to users (employees) based on the emotional data. For example, if stress is detected, it suggests relaxation techniques, and if the employee is emotionally satisfied, it sends a message praising their achievements. The input is emotional data, and the output is a feedback message.

[0711] Step 10: Provide performance reports

[0712] The generated performance reports are provided to management and are useful for formulating organizational strategies and optimizing resource allocation. Reports that reflect emotional data can also be used to manage employee mental health and robot operating status. The input is the performance report, and the output is the provided report.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] [Third embodiment]

[0717] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0718] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0719] 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).

[0720] 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.

[0721] 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.

[0722] 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).

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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."

[0729] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, and then stores and analyzes the daily report in a database before providing a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate labor-hour management.

[0730] Collecting log data

[0731] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using the GitHub API. The collected log data is temporarily stored in memory and prepared for storage in the database.

[0732] Automatic extraction of business content

[0733] The generative AI analyzes the collected log data and extracts business details. It uses natural language processing to generate a summary of the log and identify key business details. For example, it extracts activities such as "code review" and "development of new features" that employees performed on GitHub.

[0734] Business categorization

[0735] The generative AI classifies the extracted work content into predefined categories. For example, if the work content contains the keyword "code," it will be classified into the "development" category. Similarly, logs related to meetings will be classified into the "meeting" category.

[0736] Generate and present daily report drafts

[0737] The server generates a draft of the daily report based on the categorized work content and automatically displays it on the employee's device when they leave work. The draft is provided in a concise and structured format so that employees can easily check and modify it.

[0738] Daily report database storage

[0739] After the user (employee) checks, modifies, and confirms the daily report draft, the confirmed daily report is saved in the database by the server. This saved data is analyzed later, so it is managed accurately.

[0740] Analyze daily data and generate performance reports

[0741] The generation AI analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0742] Providing performance reports

[0743] The server periodically provides the generated performance reports to the management, allowing the users (management) to obtain sufficient information for formulating organizational strategies and optimizing resource allocation.

[0744] Specific examples

[0745] For example, when employee A leaves work, the server collects that day's email and GitHub usage logs. The generation AI extracts tasks such as "fixing issue 123," "code review for new features," and "documentation updates" from the collected log data. These tasks are categorized and a draft daily report is generated in the form of "development," "review," or "documentation." The server presents this draft to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is stored in a database by the server, and the generation AI then analyzes it to create a performance report for the team and the entire organization. This report is provided to management and can be used to improve organizational productivity and accurately manage man-hours.

[0746] Through the above process, the present invention achieves both efficient daily report entry and accurate man-hour management, thereby helping to maximize a company's productivity.

[0747] The processing flow will be explained below.

[0748] Step 1:

[0749] Server: When employees leave work, internal tools (email, code management tools, etc.) are accessed and usage logs are collected. This includes obtaining email logs using the IMAP protocol and obtaining code management logs using the GitHub API.

[0750] Step 2:

[0751] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is then stored in a database. This accumulates the usage logs and prepares them for analysis.

[0752] Step 3:

[0753] Generative AI: Analyzes log data stored in a database and automatically extracts task details. Based on prompts, natural language processing technology is used to generate a summary of the log and identify key task details. For example, task details such as "client support" can be extracted from email logs.

[0754] Step 4:

[0755] Generative AI: Classifies extracted work content into predefined categories. For example, work containing the keyword "code" is classified into the "development" category, and work containing the keyword "meeting" is classified into the "conference" category.

[0756] Step 5:

[0757] Server: Automatically generates draft daily reports based on categorized work content. These drafts are designed to be concise and structured so that employees can easily review and revise them.

[0758] Step 6:

[0759] Server: Presents the generated draft daily report to the employee's terminal when he / she leaves work. The draft daily report is automatically displayed on the employee's terminal, allowing for easy confirmation and correction.

[0760] Step 7:

[0761] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[0762] Step 8:

[0763] Server: Stores the daily reports submitted by employees in a database, which aggregates the data and allows for later analysis.

[0764] Step 9:

[0765] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0766] Step 10:

[0767] Server: Provides generated performance reports to management, providing them with the information they need to formulate organizational strategies and optimize resource allocation.

[0768] Example 1

[0769] 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."

[0770] Modern companies spend a lot of time and effort manually entering daily reports, which can lead to poor business efficiency. Furthermore, errors and non-standard formats caused by manual entry make accurate labor-hour management and performance analysis difficult. To solve these issues and improve business efficiency, a system is needed that automatically extracts and classifies employee work content and generates draft daily reports.

[0771] 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.

[0772] In this invention, the server includes: means for collecting general-purpose tool usage logs when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; a means for summarizing the extracted work content using natural language processing; and a means for classifying the summarized work content by category. This enables efficient extraction and classification of work content, and the generation and presentation of daily report drafts. The server also includes means for saving daily reports finalized by users in a database; a means for analyzing the saved daily report data using a generation AI to generate a performance report for the entire organization; and a means for providing the generated performance report to a manager. This enables accurate man-hour management and performance evaluation for the entire organization, thereby improving corporate productivity.

[0773] "Means for collecting usage logs of general-purpose tools when employees leave work" refers to a method or device that allows a server to automatically collect usage history of general-purpose tools such as email and source code management tools when employees leave work.

[0774] The "generative AI means for automatically extracting work content based on collected log data" is an artificial intelligence technology that analyzes log data collected by the server and automatically extracts the work content of employees using natural language processing technology.

[0775] "Means for summarizing extracted business content using natural language processing" refers to a technology that analyzes text data, extracts only the important points, and summarizes them concisely in order to summarize the business content extracted by the generation AI.

[0776] A "means for classifying summarized work content by category" is a method or device for dividing summarized work content into specific categories and classifying each task into categories such as "development," "review," and "meeting."

[0777] The "means for generating a draft daily report and presenting it on the employee's user terminal" is a mechanism for automatically creating a draft daily report based on the classified work content and displaying the draft on the user terminal when the employee leaves work.

[0778] "Means for saving daily reports finalized by users to a database" refers to a method or device by which a server receives daily reports that employees have edited and revised on their terminals and finalized, and stores the contents in a database.

[0779] "A means of analyzing saved daily report data using generation AI to generate a performance report for the entire organization" is a technology in which generation AI analyzes daily report data saved in a database and automatically generates a performance report for the entire organization based on the work content and time allocation of each employee.

[0780] The "means for providing the generated performance report to the administrator" refers to a method or device by which the server periodically provides the generated performance report to the administrator in the form of email, dashboard, or the like.

[0781] This invention is a system that collects usage logs of general-purpose tools when employees leave work, automatically extracts work content using generation AI, generates and presents a draft daily report, saves the daily report in a database, analyzes it, and then generates a performance report for the entire organization.

[0782] Hardware and software used

[0783] This system uses the following hardware and software:

[0784] Server: Collects log data, generates and presents daily report drafts, stores them in a database, and generates and provides performance reports.

[0785] User terminal: Functions as a device for employees to check, correct, and confirm draft daily reports.

[0786] Generative AI model: Uses natural language processing technology to extract business details from log data, and generates summaries, categorization, and performance reports.

[0787] Program processing

[0788] The server collects usage logs from the mail server using the IMAP protocol when employees leave work, and also collects log data from the code management system using the GitHub API. These log data are temporarily stored in memory.

[0789] Next, the generative AI analyzes the collected log data and uses natural language processing technology to generate summaries of the log data and identify key business activities. For example, activities such as "fixing Issue 123," "code review of new features," and "documentation updates" can be extracted from GitHub usage logs.

[0790] The extracted work content is then classified by the generation AI into categories such as "development," "review," and "meeting." The server then generates a draft daily report based on these categorizations and automatically displays it on the user's device when the employee leaves work. The draft is provided in a concise, structured format, allowing employees to quickly review the content and make any necessary corrections.

[0791] Once an employee has finalized their daily report draft, the server stores the data in a database. The saved data is then analyzed by the AI ​​to generate a performance report for the entire organization. This report includes each employee's work, time allocation, and progress on each project.

[0792] Finally, the server periodically provides the generated performance reports to the administrator, allowing the user (administrator) to obtain the information necessary to formulate organizational strategies and optimize resource allocation.

[0793] Examples of concrete examples and prompts

[0794] For example, when employee A leaves work, the server collects that day's email and source code management system usage logs. From the collected log data, the generation AI extracts tasks such as "Fixing Issue 123," "Code review of new features," and "Documentation update." These tasks are categorized into categories such as "Development," "Review," and "Documentation." The server presents a draft of the daily report to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is saved in a database by the server, and the generation AI then analyzes it to create a performance report for the entire organization. This report is provided to managers and can be used to improve organizational productivity and accurately manage man-hours.

[0795] An example of a prompt for a generative AI model is, "Summarize the activities obtained from GitHub usage logs (e.g., fixing Issue 123, code review, developing new features, etc.) and classify each activity into the appropriate category."

[0796] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0797] Step 1: Collect log data

[0798] The server collects general-purpose tool usage logs when employees leave work. Specifically, the server connects to the mail server using the IMAP protocol and retrieves the employee's email log. At this time, the server filters and collects unread emails and emails in specific folders. It also uses the GitHub API to retrieve activity logs from the employee code management system. This log data is temporarily stored in memory.

[0799] Input: Employee email server and code management system usage logs

[0800] Output: Log data stored in memory

[0801] Step 2: Automatic extraction of business content

[0802] The generative AI analyzes the log data collected by the server and extracts the details of the work. Specifically, it uses a natural language processing algorithm to analyze text and extract important activities. For example, from a GitHub log, it can extract work details such as "Fixing Issue 123" and "Code review for new features."

[0803] Input: Log data stored in memory

[0804] Output: Extracted business details

[0805] Step 3: Generate a summary of the business

[0806] The generative AI summarizes the extracted work content, extracting only the important points from the extracted data and summarizing them concisely. For example, long descriptions such as "Fixing Issue 123" and "Code review for new features" are summarized into short keywords such as "code fix" and "review."

[0807] Input: Extracted business details

[0808] Output: Summary of work

[0809] Step 4: Categorize your work

[0810] The generation AI classifies the summarized work content into predefined categories. The generation AI performs keyword analysis and classifies summarized work content such as "code correction" and "review" into categories such as "development" and "review."

[0811] Input: Summary of work

[0812] Output: Jobs categorized by category

[0813] Step 5: Generate and present a draft daily report

[0814] The server creates a draft of the daily report based on the work content categorized by category. The generated draft is automatically displayed on the user's device when the employee leaves work. The draft is presented in a structured format so that employees can easily check and modify it.

[0815] Input: Jobs categorized by category

[0816] Output: A draft of the daily report displayed on the user's terminal

[0817] Step 6: Check the daily report and save it to the database

[0818] The user (employee) checks the draft of the daily report displayed on the terminal and makes any necessary corrections. Once the corrections are complete and the finalized daily report is saved in the database by the server.

[0819] Input: Daily report draft confirmed and corrected by the user

[0820] Output: Daily fixed report stored in the database

[0821] Step 7: Analyze the daily data

[0822] The server analyzes the daily report data stored in the database using a generation AI, which extracts information such as each employee's work content, time allocation, and progress by project from the stored daily report data.

[0823] Input: Finalized daily report saved in the database

[0824] Output: Parsed performance data

[0825] Step 8: Generate and provide performance reports

[0826] The server generates an organization-wide performance report based on the performance data analyzed by the AI, which includes an overview of each employee's work, time allocation, and progress by project, and is provided to managers.

[0827] Input: Parsed performance data

[0828] Output: Performance report provided to management

[0829] (Application example 1)

[0830] 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."

[0831] Employees' daily report entry work is time-consuming, making it difficult to accurately manage man-hours and grasp productivity. Furthermore, particularly in on-site work such as factories, it is difficult for employees to record and understand their work in real time, resulting in insufficient data collection for efficient progress management and productivity improvement. For this reason, a system is needed that reduces the burden on employees and managers and improves productivity.

[0832] 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.

[0833] In this invention, the server includes means for collecting usage logs of internal tools when employees leave work, a generation AI means for automatically extracting work content based on the collected log data, a means for classifying the generated work content by category, a means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal, a means for saving the daily reports submitted by the employees in a database, a means for analyzing the saved daily report data and generating performance reports for the team and the entire organization, a means for providing the generated performance report to management, and a means for collecting the work logs of workers in real time and displaying them on smart glasses or a head-mounted display. This enables more efficient entry of employee daily reports, accurate man-hour management, and real-time understanding of work content.

[0834] "Means for collecting usage logs of internal tools when employees leave work" refers to a system that automatically collects usage history information for various software and systems used within the company when employees finish work and leave the office.

[0835] The "generative AI method for automatically extracting work content" is a technology that analyzes collected usage log data and uses generative AI to automatically identify and extract the specific work content performed by employees.

[0836] The "means for categorizing by category" is a system for dividing the extracted work content into predetermined categories based on specific criteria or keywords.

[0837] "Means for generating a draft daily report and presenting it on employees' devices" refers to a technology that automatically generates an initial version of a daily report based on classified work content and displays it on the computer or mobile device used by the employee.

[0838] "Means for storing daily reports in a database" refers to a system for recording and storing daily report data that has been confirmed, corrected, and confirmed by employees in a company database.

[0839] The "means for generating performance reports" refers to a technology that analyzes saved daily report data and creates reports on the work progress and productivity of a team or the entire organization.

[0840] "Means for providing performance reports to management" refers to a system for periodically distributing and presenting the generated performance reports to the company's senior managers and executives.

[0841] "Means for collecting work logs in real time and displaying them on smart glasses or head-mounted displays" refers to technology that records the work content of employees in real time and immediately displays that information to employees via smart glasses or head-mounted displays.

[0842] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it on the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate man-hour management.It can also be used by factory workers to understand work content in real time using smart glasses or head-mounted displays.

[0843] First, the server collects the usage logs of internal tools when employees leave work. This collection is done using the mail server's IMAP protocol and the code management system's API. The collected log data is temporarily stored in memory and prepared for storage in a database. This data is used to record the details of employee work.

[0844] Next, the Generative AI analyzes the collected log data and automatically extracts work content. It uses natural language processing technology to generate log summaries and identify key work content. For example, activities such as "client meetings" are extracted from email logs, and "bug fixes" are extracted from code management systems. Machine learning algorithms are used in this process to classify work content based on specific keywords and phrases.

[0845] The generation AI then classifies the extracted work content into predefined categories. For example, based on keywords such as "correction" or "review," each work is divided into categories such as "development" or "inspection." A draft daily report is generated based on the classified work content and presented to the employee's device. This draft is provided in a format that employees can easily check and edit.

[0846] The daily report drafts that employees review and revise are stored in a database for later analysis. Specifically, the stored data is analyzed by generative AI to generate performance reports for the team and the entire organization. These reports include each employee's work content, time allocation, progress by project, and more. This provides management with sufficient information to formulate organizational strategies and optimize resource allocation.

[0847] The system also has the ability to collect work logs of factory workers in real time and display them on smart glasses or head-mounted displays. When a worker wears a smart device, the server instantly collects and analyzes the work log, and the generated work details are displayed on the device. This allows workers to understand the details of their work in real time and work efficiently.

[0848] For example, when a worker at a factory puts on smart glasses, the day's work log is collected and a summary of the tasks performed that day (e.g., "machine maintenance" and "product quality check") is automatically presented. When the worker checks and corrects the content and submits it, it is saved in a database and a productivity report is provided to the supervisor.

[0849] Examples of prompts to input to a generative AI model include:

[0850] "Extract the factory work details from today's work log, categorize them, and generate a draft daily report."

[0851] "Based on the extracted work examples ['machine maintenance', 'quality check'], please classify each into the categories of 'maintenance' and 'inspection'."

[0852] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0853] Step 1:

[0854] The server periodically collects usage logs from internal tools. Specifically, it retrieves email logs from the mail server using the IMAP protocol and code logs from the code management system using the GitHub API. It receives employee IDs and timestamps as input and obtains the log data to be saved as output.

[0855] Step 2:

[0856] The server temporarily stores the collected log data in memory. This is the preparation stage for storing it in the database. It receives the collected log data as input and outputs the data temporarily stored in memory.

[0857] Step 3:

[0858] Generative AI analyzes log data and automatically extracts work content. It uses natural language processing technology to identify work content, such as "code review" or "bug fix." It receives temporarily stored log data as input and obtains the extracted work content as output.

[0859] Step 4:

[0860] The generative AI categorizes the extracted work content. Based on keywords such as "correction" and "review," it divides the work content into categories such as "development" and "inspection." It receives the extracted work content as input and obtains the categorized work content as output.

[0861] Step 5:

[0862] The server generates a draft of the daily report based on the classified work content. This draft is presented to the terminal in a structured format. It receives the categorized work content as input and obtains the generated draft of the daily report as output.

[0863] Step 6:

[0864] The terminal presents the generated daily report draft to the employee, who then confirms and corrects it. The terminal receives the presented daily report draft as input and obtains corrected daily report data as output.

[0865] Step 7:

[0866] The server stores the corrected daily report in a database. This stored daily report data is used for later analysis. It receives the corrected daily report data as input and obtains the daily report data stored in the database as output.

[0867] Step 8:

[0868] The generation AI analyzes the stored daily report data and generates performance reports for the team and the entire organization, including information on work content, time allocation, progress by project, etc. It receives the daily report data stored in the database as input and obtains the generated performance report as output.

[0869] Step 9:

[0870] The server provides the generated performance reports to management, taking the generated performance reports as input and providing them as output in a format that can be accessed and viewed by management.

[0871] Step 10:

[0872] When a worker wears smart glasses or a head-mounted display, the server collects and displays work logs in real time, allowing workers to instantly understand the work they are doing. Real-time work data is received as input, and the work content displayed on the device is obtained as output.

[0873] 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.

[0874] The system of this invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management.Furthermore, by combining it with an emotion engine, it becomes possible to recognize and analyze the user's emotional state and reflect it in the daily report and performance report.

[0875] Collecting log data

[0876] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using an API. The collected log data is temporarily stored in memory and later converted into a format that is easy to process.

[0877] Automatic extraction of business content

[0878] Generative AI analyzes collected log data and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract "client support" task details from email logs and "bug fixes" task details from code management logs.

[0879] Business categorization

[0880] The generative AI classifies the extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "meeting" category.

[0881] Generate and present daily report drafts

[0882] The server generates a draft of the daily report based on the work content categorized by category. The generated draft is automatically presented to the employee's terminal when they leave work. The employee can review the presented draft and make corrections or additions as necessary.

[0883] Daily report database storage

[0884] The user (employee) checks the draft daily report, makes corrections and additions, then finalizes and submits the daily report. The submitted daily report is saved in the database by the server. This allows the daily report data to be aggregated and analyzed later.

[0885] Analyze daily data and generate performance reports

[0886] The AI ​​analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0887] Emotion engine integration

[0888] The emotion engine recognizes emotions from the voices and texts employees use while working. For example, it uses voice recognition and text analysis technology to evaluate employees' stress levels and satisfaction. This allows emotional data to be reflected in daily drafts and performance reports.

[0889] Reflecting emotional data

[0890] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is feeling stressed, the server will reflect this in the daily report. The emotion data is also reflected in performance reports, allowing management to understand the emotional health of the organization.

[0891] Feedback and Support

[0892] The server provides appropriate feedback and support messages to users (employees) based on the emotional data obtained from the emotion engine. For example, it may suggest relaxation techniques if stress is detected, or send a message praising the employee's achievements if the employee is emotionally satisfied.

[0893] Providing performance reports

[0894] The server then provides the generated performance reports to management, who can then obtain the information they need to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[0895] Specific examples

[0896] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generation AI extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." A draft daily report is generated based on the categorized work content and presented to employee A's device. Employee A then checks and amends the draft and submits the final version. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in the daily report and performance report, and provided to management.

[0897] Through the above process, the present invention improves the efficiency of daily report entry, enables unified and accurate labor-hour management, and also realizes understanding of employees' emotional states and providing feedback, thereby helping to maximize corporate productivity and manage the mental health of employees.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] Server: When employees leave work, internal tools (e.g., mail servers, code management systems) are accessed to collect usage logs. This includes obtaining mail logs using the IMAP protocol and obtaining code management logs using APIs.

[0901] Step 2:

[0902] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is stored in a database and prepared for analysis.

[0903] Step 3:

[0904] Generative AI: Analyzes log data stored in a database and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract the task details "client support" from email logs and "bug fixes" from code management logs.

[0905] Step 4:

[0906] Generative AI: Classifies extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "conference" category.

[0907] Step 5:

[0908] Server: Generates a draft of the daily report based on the categorized work content. This draft is designed to be concise and structured so that employees can easily check and revise it.

[0909] Step 6:

[0910] Server: The generated draft daily report is automatically presented to the employee's terminal when they leave work. The draft daily report is displayed on the employee's terminal, allowing them to easily check and correct it.

[0911] Step 7:

[0912] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[0913] Step 8:

[0914] Server: Stores the daily reports submitted by employees in a database. Daily report data is aggregated and can be analyzed later.

[0915] Step 9:

[0916] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[0917] Step 10:

[0918] Emotion engine: Recognizes emotions from employees' voices and input text while they are working. Using voice recognition and text analysis technologies, it evaluates employees' stress levels and satisfaction. For example, it detects the emotional state of "feeling stressed" from voice logs.

[0919] Step 11:

[0920] Server: Adjusts the draft daily report based on the recognized emotion data. For example, if an employee is feeling stressed, this will be reflected in the daily report. This emotion data is also reflected in the performance report and provided to management.

[0921] Step 12:

[0922] Server: Based on the emotional data, the server provides appropriate feedback and support messages to users (employees). For example, if stress is detected, the server suggests relaxation techniques, and if the employee is emotionally satisfied, the server sends a message praising the employee's achievements.

[0923] Step 13:

[0924] Server: Provides the generated performance reports to management, who can use the reports to obtain the data necessary to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[0925] Example 2

[0926] 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."

[0927] In today's corporate environment, organizations are required to increase employee productivity while accurately understanding work content and streamlining report creation. Manually creating daily reports and managing work hours takes time and effort, resulting in reduced productivity and stress. Furthermore, it is difficult for management to grasp not only the performance of individual employees, but also the work progress and emotional state of the entire team and organization in real time.

[0928] 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.

[0929] In this invention, the server includes: means for collecting records of work tool usage when employees leave work; a generation AI means for automatically extracting work content based on the collected record data; means for classifying the generated work content by category; means for generating a draft work report based on the classified work content and presenting it to the employee's device; means for saving the work reports submitted by the employees in a database; means for analyzing the saved work report data and generating performance reports for the team and the entire organization; an emotion engine means for recognizing and analyzing the emotional states of employees; means for reflecting the emotional data acquired by the emotion engine in the work reports and performance reports; and means for providing the generated performance reports to management. This enables efficient entry of employee daily reports, unified and accurate man-hour management, understanding of work progress, and real-time visualization of employee emotional states.

[0930] An "employee" is someone who belongs to a company or organization and performs work.

[0931] "Work tools" are software and hardware used by employees to do their jobs. Examples include email clients and code management systems.

[0932] "Usage logs" are data that is automatically generated when business tools are used. Examples include email sending and receiving logs and code commit logs.

[0933] "Generative AI" is artificial intelligence that automatically analyzes and extracts business content from collected data. It uses natural language processing technology and machine learning algorithms.

[0934] "Category" refers to a group or type for classifying extracted work content. Specifically, it includes "development," "meeting," "support," etc.

[0935] A "work report" is a document that records an employee's daily work, progress, time allocation, etc.

[0936] A "server" is a central computer system that collects, analyzes, stores, and provides data.

[0937] "Devices" refers to computers and devices used by employees, including desktops, laptops, tablets, etc.

[0938] A "database" is a system or platform for organizing and storing information for later use.

[0939] A "performance report" is a report that summarizes the work progress, results, challenges, emotional state, etc. of a team or the entire organization.

[0940] The "emotion engine" is a technology that analyzes the emotional state of employees from their speech and text input, using voice recognition and text analysis.

[0941] "Management" refers to people in a position to give instructions and make management decisions in a company or organization. Specifically, this includes executives and managers.

[0942] This system collects records of employees' use of business tools when they leave work, automatically extracts work content using generation AI, categorizes it, and generates draft work reports. Furthermore, it uses an emotion engine to grasp employees' emotional states and reflects them in work reports and performance reports, providing detailed information to management.

[0943] Collecting log data

[0944] The server accesses the company's business tools (e.g., email server and code management system) once a day at a specified time to collect employee usage logs. It connects to the email server using the IMAP protocol to retrieve mail logs. It connects to the code management system using an API to retrieve project changes and commit logs. The collected log data is temporarily stored in the server's memory.

[0945] Automatic extraction of business content

[0946] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. For example, the task details of "client support" are extracted from email logs, and the task details of "bug fixes" are extracted from code management logs.

[0947] Business categorization

[0948] The generative AI model classifies the extracted tasks into predefined categories (e.g., "development," "meeting," "support," etc.) Using a keyword-based algorithm, tasks containing the keyword "code" are classified as "development," and tasks containing the keyword "meeting" are classified as "meeting."

[0949] Generate and present daily report drafts

[0950] The server uses templates to generate draft work reports based on the classified work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. Employees can review the presented draft and make corrections or additions as necessary.

[0951] Daily report database storage

[0952] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The server then stores the received business report in a database.

[0953] Analyze daily data and generate performance reports

[0954] The generative AI model analyzes work report data stored in a database. Based on this analysis, a performance report for the team or the entire organization is generated. For example, the report includes each employee's work content, time allocation, and progress for each project.

[0955] Emotion engine integration

[0956] The emotion engine recognizes emotions from the voices and texts employees input while working, using voice recognition and text analysis technologies to evaluate stress levels and satisfaction.

[0957] Reflecting emotional data

[0958] The server adjusts draft work reports based on the emotional data obtained from the emotion engine. For example, it can reflect an employee's feelings of stress in the work report. This emotional data can also be reflected in performance reports, allowing management to understand the emotional health of the organization.

[0959] Feedback and Support

[0960] The server provides appropriate feedback and support messages to the user based on the emotional data obtained from the emotion engine. For example, if stress is detected, a message suggesting relaxation techniques is sent, and if the user is emotionally satisfied, a message praising the user's achievement is sent.

[0961] Providing performance reports

[0962] The server then provides the generated performance report to management, which reflects not only each employee's work performance but also their emotional state, allowing managers to gain a more accurate understanding of the overall situation of the organization.

[0963] Specific examples

[0964] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generative AI model extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." Based on the categorized work content, a draft daily report is generated and displayed on employee A's device. Employee A checks and modifies the draft, then finalizes and submits it. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in work reports and performance reports and provided to management.

[0965] Prompt Sentence Examples

[0966] An example of a prompt to be input to the generative AI model is, "Analyze today's email log and code management log, extract the main work content, and create a work report."

[0967] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0968] Step 1:

[0969] The server accesses internal business tools (e.g., email servers and code management systems) once a day at a specified time to collect employee usage logs. Specifically, it connects to the email server using the IMAP protocol and retrieves email logs. It also connects to the code management system using an API to retrieve project changes and commit logs. The inputs are the IMAP server connection information and API endpoints, and the output is email logs and code management logs. The collected log data is temporarily stored in the server's memory.

[0970] Step 2:

[0971] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. Specifically, the model is given a prompt: "Analyze email logs and code management logs and extract key task details," and the extracted task details are obtained as output. For example, the task details "client support" are extracted from email logs, and the task details "bug fixes" are extracted from code management logs.

[0972] Step 3:

[0973] The generative AI model classifies the extracted work content into predefined categories (for example, "development," "meeting," "support," etc.). Using a keyword-based algorithm, work content containing the keyword "code" is classified as "development," and work content containing the keyword "meeting" is classified as "meeting." The input is the extracted work content, and the output is the work content categorized by category. In terms of specific operation, the generative AI model follows the rule "classify the work content into categories."

[0974] Step 4:

[0975] The server uses a template to generate a draft of the work report based on the categorized work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. The input is work content categorized by category, and the output is a draft of the work report. Specifically, the server performs the process of "filling in the work content extracted for each category according to the daily report template."

[0976] Step 5:

[0977] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The input is the draft business report that has been corrected and added by the user, and the output is the finalized business report. In concrete terms, the user clicks the "Save" button, and the finalized data is sent to the server.

[0978] Step 6:

[0979] The server stores the received business report in a database. The input is the confirmed business report, and the output is the business report data stored in the database. Specifically, the server performs the process of "storing the confirmed business report in the database."

[0980] Step 7:

[0981] The generative AI model analyzes work report data stored in a database and generates performance reports for teams and the entire organization. The input is all work report data stored in the database, and the output is a performance report. Specifically, the model is input with the prompt "Create a monthly performance report based on the daily report data of all employees," and the analysis results are obtained.

[0982] Step 8:

[0983] The emotion engine recognizes and analyzes emotions from the voices and texts that employees enter during work. This analysis uses voice recognition and text analysis technologies. The input is voice data and text data, and the output is emotion evaluation data. Specifically, the emotion engine analyzes according to the rule, "assess stress level."

[0984] Step 9:

[0985] The server adjusts the draft of the business report based on the emotion data obtained from the emotion engine. The input is emotion data, and the output is a draft of the business report that reflects the emotion data. Specifically, the server performs the process of "if the stress level is high, reflect that in the business report."

[0986] Step 10:

[0987] The server provides the generated performance report to management. This report includes each employee's work content and emotional state. The input is the performance report, and the output is a report provided to management. Specifically, the server performs the process of "automatically sending a performance report containing all analysis results once a month."

[0988] (Application example 2)

[0989] 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."

[0990] Currently, many companies and factories have systems in place to track work logs and tasks and evaluate the performance of employees and robots. However, these systems require manual data entry and human intervention, making them inefficient and resulting in high error rates. Furthermore, there is a lack of systems that can grasp the emotions and operational status of robots and employees in real time and take appropriate action. This hinders productivity improvement and proper maintenance, ultimately resulting in a decline in the performance of robots and employees.

[0991] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting usage logs of in-house tools when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; means for classifying the generated work content by category; means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal; means for saving daily reports submitted by employees in a database; means for analyzing the saved daily report data and generating performance reports for the team and the entire organization; means for providing the generated performance report to management; means for analyzing work logs and sensor data collected by factory robots while they are operating; means for automatically generating daily reports for the factory robots based on the analyzed work logs and sensor data; and means for analyzing abnormal conditions from the factory robot's operating status and error logs using an emotion engine and issuing alerts as necessary. This enables automatic generation of daily reports and real-time performance evaluation.

[0992] An "employee" is a worker who is responsible for a specific task within a company or organization.

[0993] "Clocking out" refers to an employee completing their work hours for the day and leaving the workplace.

[0994] "Internal tools" is a general term for software and systems used by employees within a company to carry out their work.

[0995] "Usage logs" refer to records of employees or devices using specific tools or systems.

[0996] "Generative AI" is a system that uses artificial intelligence technology to generate information from data.

[0997] "Work content" is the details of the work or tasks actually performed by employees or equipment.

[0998] A "category" is a group for classifying multiple business operations based on common characteristics or criteria.

[0999] A "daily report" is a document that reports on the work that employees and equipment performed that day.

[1000] "Draft" means an initial draft of a document prior to its finalization.

[1001] "Terminals" are devices such as computers and smartphones used by employees.

[1002] A "database" is an electronic system for efficiently storing, retrieving, and managing data.

[1003] A "performance report" is a report used to evaluate and analyze the work efficiency and results of employees, teams, and the entire organization.

[1004] "Management" refers to the group of executives who make strategic decisions for a company or organization.

[1005] A "factory robot" is a mechanical device that is programmed to perform specific tasks on a manufacturing floor.

[1006] A "work log" is data that records the work performed by a factory robot.

[1007] "Sensor data" refers to various types of physical information acquired by sensors.

[1008] The "Emotion Engine" is a software system for analyzing emotions and operating status from data.

[1009] "Operating state" refers to the state in which factory robots and equipment are operating.

[1010] An "error log" is recorded data when a system or device experiences an error.

[1011] An "alert" is a function or notification that issues a warning when an abnormality or problem occurs.

[1012] As an example of how to implement this invention, we will explain a system that combines data collection when employees leave work and monitoring the operation of factory robots. The system is composed of multiple modules, each of which performs a specific function.

[1013] Collecting log data

[1014] The server periodically collects usage logs of internal tools (such as mail servers and code management systems) when employees leave work. This collection is done using the IMAP protocol and API. The log data is temporarily stored in memory and later converted into a format that is easy to analyze. In addition, work logs and sensor data generated by factory robots while they are operating are also collected.

[1015] Automatic extraction of business content

[1016] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI incorporates natural language processing technology to summarize and extract key work content from email logs, code management logs, and work logs. The extracted information is categorized into specific work content such as "client support," "bug fixing," and "parts assembly."

[1017] Business categorization

[1018] The generative AI categorizes the extracted tasks into predefined categories: tasks related to "code" are classified into the "development" category, tasks related to "meetings" into the "conference" category, and tasks related to "assembly of parts" into the "manufacturing" category.

[1019] Generate and present daily report drafts

[1020] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is presented to the employee's terminal when they leave work, and the employee can check and edit it. Similarly, a daily report regarding factory robots is also generated.

[1021] Daily report database storage

[1022] After the user (employee) checks and modifies the draft daily report, the final version is saved in the database, which allows the daily report data to be consolidated and analyzed later.

[1023] Analyze daily data and generate performance reports

[1024] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization, including the work content, time allocation, and project progress of each employee and robot.

[1025] Emotion engine integration

[1026] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots, and utilizes voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions.

[1027] Reflecting emotional data

[1028] The emotion engine then uses the emotion data to adjust the draft daily report. For example, if an employee is under stress, this will be reflected in the daily report. The emotion data is also incorporated into performance reports and provided to management.

[1029] Feedback and Support

[1030] The server provides feedback and support messages to users (employees) based on the emotional data. If stress is detected, it suggests relaxation techniques, and if the user is emotionally satisfied, it sends a message praising the user's achievements.

[1031] Providing performance reports

[1032] The generated performance reports are provided to management to help formulate organizational strategies and optimize resource allocation, while reports reflecting emotional data can be used to monitor employee mental health and robot operation status.

[1033] Specific examples

[1034] For example, when a user (Employee A) leaves work, the server collects the day's emails and usage logs of the code management tool. The generation AI extracts work details such as "client support" and "bug fixing" and categorizes them into "development" and "support." Similarly, for Robot A in the factory, work logs such as "parts assembly" and "welding" are collected and analyzed to generate a daily report. An example of an emotion engine analyzing Employee A's stress level and reflecting this in a daily report or report would be, "As stress level is high, we will suggest relaxation methods."

[1035] Example prompt sentence:

[1036] "Generate a draft daily report based on Robot A's work log data and emotion data. Task content: ['Parts assembly', 'Welding', 'Inspection'], Emotional state: {'status': 'stress', 'level': 8}."

[1037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1038] Step 1: Collect log data

[1039] When employees leave work, the server collects work logs and sensor data from internal tools (for example, email servers and code management systems) and factory robots. Here, the IMAP protocol is used to obtain email logs, and APIs are used to obtain code management logs and robot data. The collected log data is temporarily stored in memory and later converted into a format that is easy to analyze. The input is the operation logs of each tool and robot, and the output is log data in a format suitable for analysis.

[1040] Step 2: Automatic extraction of business content

[1041] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI uses natural language processing technology to identify and summarize key work content from email logs, code management logs, and work logs. For example, it extracts content such as "client support" from email logs, "bug fixing" from code management logs, and "parts assembly" from robot work logs. The input is log data, and the output is a list of extracted work content.

[1042] Step 3: Categorize your work

[1043] The server categorizes the work content extracted by the generation AI. Based on predefined keywords and patterns, "code" is categorized as "development," "meetings" as "conferences," and "parts assembly" as "manufacturing." The input is a list of work content, and the output is the work content categorized by category.

[1044] Step 4: Generate and present a draft daily report

[1045] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is automatically presented to the employee's terminal when they leave work, and the employee can review and edit it. A daily report about the robot is also generated. The input is the work content categorized by category, and the output is the generated draft daily report.

[1046] Step 5: Save daily reports to the database

[1047] After the user (employee) checks the draft daily report and makes corrections or additions, the final version of the daily report is saved in the database. This allows the daily report data to be integrated and analyzed later. The input is the corrected draft daily report, and the output is the finalized daily report saved in the database.

[1048] Step 6: Analyze daily data and generate performance reports

[1049] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization. The reports include the work content, time allocation, and project progress of each employee and robot. The input is the daily report data from the database, and the output is the performance report.

[1050] Step 7: Integrating the Emotion Engine

[1051] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots. It uses voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions. The input is voice and text data, and the output is the analyzed emotional state.

[1052] Step 8: Reflecting emotional data

[1053] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is under stress, this is reflected in the daily report. The emotion data is also incorporated into the performance report and provided to management. The input is emotion data, and the output is the adjusted daily report and performance report.

[1054] Step 9: Feedback and support

[1055] The server provides feedback and support messages to users (employees) based on the emotional data. For example, if stress is detected, it suggests relaxation techniques, and if the employee is emotionally satisfied, it sends a message praising their achievements. The input is emotional data, and the output is a feedback message.

[1056] Step 10: Provide performance reports

[1057] The generated performance reports are provided to management and are useful for formulating organizational strategies and optimizing resource allocation. Reports that reflect emotional data can also be used to manage employee mental health and robot operating status. The input is the performance report, and the output is the provided report.

[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] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, and then stores and analyzes the daily report in a database before providing a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate labor-hour management.

[1076] Collecting log data

[1077] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using the GitHub API. The collected log data is temporarily stored in memory and prepared for storage in the database.

[1078] Automatic extraction of business content

[1079] The generative AI analyzes the collected log data and extracts business details. It uses natural language processing to generate a summary of the log and identify key business details. For example, it extracts activities such as "code review" and "development of new features" that employees performed on GitHub.

[1080] Business categorization

[1081] The generative AI classifies the extracted work content into predefined categories. For example, if the work content contains the keyword "code," it will be classified into the "development" category. Similarly, logs related to meetings will be classified into the "meeting" category.

[1082] Generate and present daily report drafts

[1083] The server generates a draft of the daily report based on the categorized work content and automatically displays it on the employee's device when they leave work. The draft is provided in a concise and structured format so that employees can easily check and modify it.

[1084] Daily report database storage

[1085] After the user (employee) checks, modifies, and confirms the daily report draft, the confirmed daily report is saved in the database by the server. This saved data is analyzed later, so it is managed accurately.

[1086] Analyze daily data and generate performance reports

[1087] The generation AI analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[1088] Providing performance reports

[1089] The server periodically provides the generated performance reports to the management, allowing the users (management) to obtain sufficient information for formulating organizational strategies and optimizing resource allocation.

[1090] Specific examples

[1091] For example, when employee A leaves work, the server collects that day's email and GitHub usage logs. The generation AI extracts tasks such as "fixing issue 123," "code review for new features," and "documentation updates" from the collected log data. These tasks are categorized and a draft daily report is generated in the form of "development," "review," or "documentation." The server presents this draft to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is stored in a database by the server, and the generation AI then analyzes it to create a performance report for the team and the entire organization. This report is provided to management and can be used to improve organizational productivity and accurately manage man-hours.

[1092] Through the above process, the present invention achieves both efficient daily report entry and accurate man-hour management, thereby helping to maximize a company's productivity.

[1093] The processing flow will be explained below.

[1094] Step 1:

[1095] Server: When employees leave work, internal tools (email, code management tools, etc.) are accessed and usage logs are collected. This includes obtaining email logs using the IMAP protocol and obtaining code management logs using the GitHub API.

[1096] Step 2:

[1097] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is then stored in a database. This accumulates the usage logs and prepares them for analysis.

[1098] Step 3:

[1099] Generative AI: Analyzes log data stored in a database and automatically extracts task details. Based on prompts, natural language processing technology is used to generate a summary of the log and identify key task details. For example, task details such as "client support" can be extracted from email logs.

[1100] Step 4:

[1101] Generative AI: Classifies extracted work content into predefined categories. For example, work containing the keyword "code" is classified into the "development" category, and work containing the keyword "meeting" is classified into the "conference" category.

[1102] Step 5:

[1103] Server: Automatically generates draft daily reports based on categorized work content. These drafts are designed to be concise and structured so that employees can easily review and revise them.

[1104] Step 6:

[1105] Server: Presents the generated draft daily report to the employee's terminal when he / she leaves work. The draft daily report is automatically displayed on the employee's terminal, allowing for easy confirmation and correction.

[1106] Step 7:

[1107] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[1108] Step 8:

[1109] Server: Stores the daily reports submitted by employees in a database, which aggregates the data and allows for later analysis.

[1110] Step 9:

[1111] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[1112] Step 10:

[1113] Server: Provides generated performance reports to management, providing them with the information they need to formulate organizational strategies and optimize resource allocation.

[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] Modern companies spend a lot of time and effort manually entering daily reports, which can lead to poor business efficiency. Furthermore, errors and non-standard formats caused by manual entry make accurate labor-hour management and performance analysis difficult. To solve these issues and improve business efficiency, a system is needed that automatically extracts and classifies employee work content and generates draft daily reports.

[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 collecting general-purpose tool usage logs when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; a means for summarizing the extracted work content using natural language processing; and a means for classifying the summarized work content by category. This enables efficient extraction and classification of work content, and the generation and presentation of daily report drafts. The server also includes means for saving daily reports finalized by users in a database; a means for analyzing the saved daily report data using a generation AI to generate a performance report for the entire organization; and a means for providing the generated performance report to a manager. This enables accurate man-hour management and performance evaluation for the entire organization, thereby improving corporate productivity.

[1119] "Means for collecting usage logs of general-purpose tools when employees leave work" refers to a method or device that allows a server to automatically collect usage history of general-purpose tools such as email and source code management tools when employees leave work.

[1120] The "generative AI means for automatically extracting work content based on collected log data" is an artificial intelligence technology that analyzes log data collected by the server and automatically extracts the work content of employees using natural language processing technology.

[1121] "Means for summarizing extracted business content using natural language processing" refers to a technology that analyzes text data, extracts only the important points, and summarizes them concisely in order to summarize the business content extracted by the generation AI.

[1122] A "means for classifying summarized work content by category" is a method or device for dividing summarized work content into specific categories and classifying each task into categories such as "development," "review," and "meeting."

[1123] The "means for generating a draft daily report and presenting it on the employee's user terminal" is a mechanism for automatically creating a draft daily report based on the classified work content and displaying the draft on the user terminal when the employee leaves work.

[1124] "Means for saving daily reports finalized by users to a database" refers to a method or device by which a server receives daily reports that employees have edited and revised on their terminals and finalized, and stores the contents in a database.

[1125] "A means of analyzing saved daily report data using generation AI to generate a performance report for the entire organization" is a technology in which generation AI analyzes daily report data saved in a database and automatically generates a performance report for the entire organization based on the work content and time allocation of each employee.

[1126] The "means for providing the generated performance report to the administrator" refers to a method or device by which the server periodically provides the generated performance report to the administrator in the form of email, dashboard, or the like.

[1127] This invention is a system that collects usage logs of general-purpose tools when employees leave work, automatically extracts work content using generation AI, generates and presents a draft daily report, saves the daily report in a database, analyzes it, and then generates a performance report for the entire organization.

[1128] Hardware and software used

[1129] This system uses the following hardware and software:

[1130] Server: Collects log data, generates and presents daily report drafts, stores them in a database, and generates and provides performance reports.

[1131] User terminal: Functions as a device for employees to check, correct, and confirm draft daily reports.

[1132] Generative AI model: Uses natural language processing technology to extract business details from log data, and generates summaries, categorization, and performance reports.

[1133] Program processing

[1134] The server collects usage logs from the mail server using the IMAP protocol when employees leave work, and also collects log data from the code management system using the GitHub API. These log data are temporarily stored in memory.

[1135] Next, the generative AI analyzes the collected log data and uses natural language processing technology to generate summaries of the log data and identify key business activities. For example, activities such as "fixing Issue 123," "code review of new features," and "documentation updates" can be extracted from GitHub usage logs.

[1136] The extracted work content is then classified by the generation AI into categories such as "development," "review," and "meeting." The server then generates a draft daily report based on these categorizations and automatically displays it on the user's device when the employee leaves work. The draft is provided in a concise, structured format, allowing employees to quickly review the content and make any necessary corrections.

[1137] Once an employee has finalized their daily report draft, the server stores the data in a database. The saved data is then analyzed by the AI ​​to generate a performance report for the entire organization. This report includes each employee's work, time allocation, and progress on each project.

[1138] Finally, the server periodically provides the generated performance reports to the administrator, allowing the user (administrator) to obtain the information necessary to formulate organizational strategies and optimize resource allocation.

[1139] Examples of concrete examples and prompts

[1140] For example, when employee A leaves work, the server collects that day's email and source code management system usage logs. From the collected log data, the generation AI extracts tasks such as "Fixing Issue 123," "Code review of new features," and "Documentation update." These tasks are categorized into categories such as "Development," "Review," and "Documentation." The server presents a draft of the daily report to employee A's device, who then checks and amends it before submitting it as a daily report. The submitted daily report is saved in a database by the server, and the generation AI then analyzes it to create a performance report for the entire organization. This report is provided to managers and can be used to improve organizational productivity and accurately manage man-hours.

[1141] An example of a prompt for a generative AI model is, "Summarize the activities obtained from GitHub usage logs (e.g., fixing Issue 123, code review, developing new features, etc.) and classify each activity into the appropriate category."

[1142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1143] Step 1: Collect log data

[1144] The server collects general-purpose tool usage logs when employees leave work. Specifically, the server connects to the mail server using the IMAP protocol and retrieves the employee's email log. At this time, the server filters and collects unread emails and emails in specific folders. It also uses the GitHub API to retrieve activity logs from the employee code management system. This log data is temporarily stored in memory.

[1145] Input: Employee email server and code management system usage logs

[1146] Output: Log data stored in memory

[1147] Step 2: Automatic extraction of business content

[1148] The generative AI analyzes the log data collected by the server and extracts the details of the work. Specifically, it uses a natural language processing algorithm to analyze text and extract important activities. For example, from a GitHub log, it can extract work details such as "Fixing Issue 123" and "Code review for new features."

[1149] Input: Log data stored in memory

[1150] Output: Extracted business details

[1151] Step 3: Generate a summary of the business

[1152] The generative AI summarizes the extracted work content, extracting only the important points from the extracted data and summarizing them concisely. For example, long descriptions such as "Fixing Issue 123" and "Code review for new features" are summarized into short keywords such as "code fix" and "review."

[1153] Input: Extracted business details

[1154] Output: Summary of work

[1155] Step 4: Categorize your work

[1156] The generation AI classifies the summarized work content into predefined categories. The generation AI performs keyword analysis and classifies summarized work content such as "code correction" and "review" into categories such as "development" and "review."

[1157] Input: Summary of work

[1158] Output: Jobs categorized by category

[1159] Step 5: Generate and present a draft daily report

[1160] The server creates a draft of the daily report based on the work content categorized by category. The generated draft is automatically displayed on the user's device when the employee leaves work. The draft is presented in a structured format so that employees can easily check and modify it.

[1161] Input: Jobs categorized by category

[1162] Output: A draft of the daily report displayed on the user's terminal

[1163] Step 6: Check the daily report and save it to the database

[1164] The user (employee) checks the draft of the daily report displayed on the terminal and makes any necessary corrections. Once the corrections are complete and the finalized daily report is saved in the database by the server.

[1165] Input: Daily report draft confirmed and corrected by the user

[1166] Output: Daily fixed report stored in the database

[1167] Step 7: Analyze the daily data

[1168] The server analyzes the daily report data stored in the database using a generation AI, which extracts information such as each employee's work content, time allocation, and progress by project from the stored daily report data.

[1169] Input: Finalized daily report saved in the database

[1170] Output: Parsed performance data

[1171] Step 8: Generate and provide performance reports

[1172] The server generates an organization-wide performance report based on the performance data analyzed by the AI, which includes an overview of each employee's work, time allocation, and progress by project, and is provided to managers.

[1173] Input: Parsed performance data

[1174] Output: Performance report provided to management

[1175] (Application example 1)

[1176] 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."

[1177] Employees' daily report entry work is time-consuming, making it difficult to accurately manage man-hours and grasp productivity. Furthermore, particularly in on-site work such as factories, it is difficult for employees to record and understand their work in real time, resulting in insufficient data collection for efficient progress management and productivity improvement. For this reason, a system is needed that reduces the burden on employees and managers and improves productivity.

[1178] 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.

[1179] In this invention, the server includes means for collecting usage logs of internal tools when employees leave work, a generation AI means for automatically extracting work content based on the collected log data, a means for classifying the generated work content by category, a means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal, a means for saving the daily reports submitted by the employees in a database, a means for analyzing the saved daily report data and generating performance reports for the team and the entire organization, a means for providing the generated performance report to management, and a means for collecting the work logs of workers in real time and displaying them on smart glasses or a head-mounted display. This enables more efficient entry of employee daily reports, accurate man-hour management, and real-time understanding of work content.

[1180] "Means for collecting usage logs of internal tools when employees leave work" refers to a system that automatically collects usage history information for various software and systems used within the company when employees finish work and leave the office.

[1181] The "generative AI method for automatically extracting work content" is a technology that analyzes collected usage log data and uses generative AI to automatically identify and extract the specific work content performed by employees.

[1182] The "means for categorizing by category" is a system for dividing the extracted work content into predetermined categories based on specific criteria or keywords.

[1183] "Means for generating a draft daily report and presenting it on employees' devices" refers to a technology that automatically generates an initial version of a daily report based on classified work content and displays it on the computer or mobile device used by the employee.

[1184] "Means for storing daily reports in a database" refers to a system for recording and storing daily report data that has been confirmed, corrected, and confirmed by employees in a company database.

[1185] The "means for generating performance reports" refers to a technology that analyzes saved daily report data and creates reports on the work progress and productivity of a team or the entire organization.

[1186] "Means for providing performance reports to management" refers to a system for periodically distributing and presenting the generated performance reports to the company's senior managers and executives.

[1187] "Means for collecting work logs in real time and displaying them on smart glasses or head-mounted displays" refers to technology that records the work content of employees in real time and immediately displays that information to employees via smart glasses or head-mounted displays.

[1188] The system of the present invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it on the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management, thereby reducing the burden of entering daily reports and achieving unified and accurate man-hour management.It can also be used by factory workers to understand work content in real time using smart glasses or head-mounted displays.

[1189] First, the server collects the usage logs of internal tools when employees leave work. This collection is done using the mail server's IMAP protocol and the code management system's API. The collected log data is temporarily stored in memory and prepared for storage in a database. This data is used to record the details of employee work.

[1190] Next, the Generative AI analyzes the collected log data and automatically extracts work content. It uses natural language processing technology to generate log summaries and identify key work content. For example, activities such as "client meetings" are extracted from email logs, and "bug fixes" are extracted from code management systems. Machine learning algorithms are used in this process to classify work content based on specific keywords and phrases.

[1191] The generation AI then classifies the extracted work content into predefined categories. For example, based on keywords such as "correction" or "review," each work is divided into categories such as "development" or "inspection." A draft daily report is generated based on the classified work content and presented to the employee's device. This draft is provided in a format that employees can easily check and edit.

[1192] The daily report drafts that employees review and revise are stored in a database for later analysis. Specifically, the stored data is analyzed by generative AI to generate performance reports for the team and the entire organization. These reports include each employee's work content, time allocation, progress by project, and more. This provides management with sufficient information to formulate organizational strategies and optimize resource allocation.

[1193] The system also has the ability to collect work logs of factory workers in real time and display them on smart glasses or head-mounted displays. When a worker wears a smart device, the server instantly collects and analyzes the work log, and the generated work details are displayed on the device. This allows workers to understand the details of their work in real time and work efficiently.

[1194] For example, when a worker at a factory puts on smart glasses, the day's work log is collected and a summary of the tasks performed that day (e.g., "machine maintenance" and "product quality check") is automatically presented. When the worker checks and corrects the content and submits it, it is saved in a database and a productivity report is provided to the supervisor.

[1195] Examples of prompts to input to a generative AI model include:

[1196] "Extract the factory work details from today's work log, categorize them, and generate a draft daily report."

[1197] "Based on the extracted work examples ['machine maintenance', 'quality check'], please classify each into the categories of 'maintenance' and 'inspection'."

[1198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1199] Step 1:

[1200] The server periodically collects usage logs from internal tools. Specifically, it retrieves email logs from the mail server using the IMAP protocol and code logs from the code management system using the GitHub API. It receives employee IDs and timestamps as input and obtains the log data to be saved as output.

[1201] Step 2:

[1202] The server temporarily stores the collected log data in memory. This is the preparation stage for storing it in the database. It receives the collected log data as input and outputs the data temporarily stored in memory.

[1203] Step 3:

[1204] Generative AI analyzes log data and automatically extracts work content. It uses natural language processing technology to identify work content, such as "code review" or "bug fix." It receives temporarily stored log data as input and obtains the extracted work content as output.

[1205] Step 4:

[1206] The generative AI categorizes the extracted work content. Based on keywords such as "correction" and "review," it divides the work content into categories such as "development" and "inspection." It receives the extracted work content as input and obtains the categorized work content as output.

[1207] Step 5:

[1208] The server generates a draft of the daily report based on the classified work content. This draft is presented to the terminal in a structured format. It receives the categorized work content as input and obtains the generated draft of the daily report as output.

[1209] Step 6:

[1210] The terminal presents the generated daily report draft to the employee, who then confirms and corrects it. The terminal receives the presented daily report draft as input and obtains corrected daily report data as output.

[1211] Step 7:

[1212] The server stores the corrected daily report in a database. This stored daily report data is used for later analysis. It receives the corrected daily report data as input and obtains the daily report data stored in the database as output.

[1213] Step 8:

[1214] The generation AI analyzes the stored daily report data and generates performance reports for the team and the entire organization, including information on work content, time allocation, progress by project, etc. It receives the daily report data stored in the database as input and obtains the generated performance report as output.

[1215] Step 9:

[1216] The server provides the generated performance reports to management, taking the generated performance reports as input and providing them as output in a format that can be accessed and viewed by management.

[1217] Step 10:

[1218] When a worker wears smart glasses or a head-mounted display, the server collects and displays work logs in real time, allowing workers to instantly understand the work they are doing. Real-time work data is received as input, and the work content displayed on the device is obtained as output.

[1219] 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.

[1220] The system of this invention collects usage logs of internal tools when employees leave work, automatically extracts work content using generation AI, generates a draft daily report, presents it to the employee's device, saves the daily report in a database, analyzes it, and provides a performance report to management.Furthermore, by combining it with an emotion engine, it becomes possible to recognize and analyze the user's emotional state and reflect it in the daily report and performance report.

[1221] Collecting log data

[1222] The server periodically accesses internal tools (e.g., mail server, code management system) to collect employee usage logs. This includes obtaining email logs using the IMAP protocol and code management logs using an API. The collected log data is temporarily stored in memory and later converted into a format that is easy to process.

[1223] Automatic extraction of business content

[1224] Generative AI analyzes collected log data and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract "client support" task details from email logs and "bug fixes" task details from code management logs.

[1225] Business categorization

[1226] The generative AI classifies the extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "meeting" category.

[1227] Generate and present daily report drafts

[1228] The server generates a draft of the daily report based on the work content categorized by category. The generated draft is automatically presented to the employee's terminal when they leave work. The employee can review the presented draft and make corrections or additions as necessary.

[1229] Daily report database storage

[1230] The user (employee) checks the draft daily report, makes corrections and additions, then finalizes and submits the daily report. The submitted daily report is saved in the database by the server. This allows the daily report data to be aggregated and analyzed later.

[1231] Analyze daily data and generate performance reports

[1232] The AI ​​analyzes the daily report data stored in the database and generates performance reports for the team and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[1233] Emotion engine integration

[1234] The emotion engine recognizes emotions from the voices and texts employees use while working. For example, it uses voice recognition and text analysis technology to evaluate employees' stress levels and satisfaction. This allows emotional data to be reflected in daily drafts and performance reports.

[1235] Reflecting emotional data

[1236] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is feeling stressed, the server will reflect this in the daily report. The emotion data is also reflected in performance reports, allowing management to understand the emotional health of the organization.

[1237] Feedback and Support

[1238] The server provides appropriate feedback and support messages to users (employees) based on the emotional data obtained from the emotion engine. For example, it may suggest relaxation techniques if stress is detected, or send a message praising the employee's achievements if the employee is emotionally satisfied.

[1239] Providing performance reports

[1240] The server then provides the generated performance reports to management, who can then obtain the information they need to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[1241] Specific examples

[1242] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generation AI extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." A draft daily report is generated based on the categorized work content and presented to employee A's device. Employee A then checks and amends the draft and submits the final version. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in the daily report and performance report, and provided to management.

[1243] Through the above process, the present invention improves the efficiency of daily report entry, enables unified and accurate labor-hour management, and also realizes understanding of employees' emotional states and providing feedback, thereby helping to maximize corporate productivity and manage the mental health of employees.

[1244] The processing flow will be explained below.

[1245] Step 1:

[1246] Server: When employees leave work, internal tools (e.g., mail servers, code management systems) are accessed to collect usage logs. This includes obtaining mail logs using the IMAP protocol and obtaining code management logs using APIs.

[1247] Step 2:

[1248] Server: Collected usage logs are temporarily stored in memory and later converted into a format that is easy to process. The converted log data is stored in a database and prepared for analysis.

[1249] Step 3:

[1250] Generative AI: Analyzes log data stored in a database and automatically extracts task details. It uses natural language processing technology to generate log summaries and identify key task details. For example, it can extract the task details "client support" from email logs and "bug fixes" from code management logs.

[1251] Step 4:

[1252] Generative AI: Classifies extracted work content into predefined categories. For example, work content containing the keyword "code" is classified into the "development" category, and work content containing the keyword "meeting" is classified into the "conference" category.

[1253] Step 5:

[1254] Server: Generates a draft of the daily report based on the categorized work content. This draft is designed to be concise and structured so that employees can easily check and revise it.

[1255] Step 6:

[1256] Server: The generated draft daily report is automatically presented to the employee's terminal when they leave work. The draft daily report is displayed on the employee's terminal, allowing them to easily check and correct it.

[1257] Step 7:

[1258] User (employee): Checks the presented daily report draft and makes corrections and additions as necessary. After corrections, finalizes the daily report and submits it to the database.

[1259] Step 8:

[1260] Server: Stores the daily reports submitted by employees in a database. Daily report data is aggregated and can be analyzed later.

[1261] Step 9:

[1262] Generative AI: Analyzes daily report data stored in a database and generates performance reports for teams and the entire organization, including information on each employee's work, time allocation, and progress on each project.

[1263] Step 10:

[1264] Emotion engine: Recognizes emotions from employees' voices and input text while they are working. Using voice recognition and text analysis technologies, it evaluates employees' stress levels and satisfaction. For example, it detects the emotional state of "feeling stressed" from voice logs.

[1265] Step 11:

[1266] Server: Adjusts the draft daily report based on the recognized emotion data. For example, if an employee is feeling stressed, this will be reflected in the daily report. This emotion data is also reflected in the performance report and provided to management.

[1267] Step 12:

[1268] Server: Based on the emotional data, the server provides appropriate feedback and support messages to users (employees). For example, if stress is detected, the server suggests relaxation techniques, and if the employee is emotionally satisfied, the server sends a message praising the employee's achievements.

[1269] Step 13:

[1270] Server: Provides the generated performance reports to management, who can use the reports to obtain the data necessary to formulate organizational strategies and optimize resource allocation. Reports incorporating emotional data can also be useful for managing employee mental health and motivation.

[1271] Example 2

[1272] 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."

[1273] In today's corporate environment, organizations are required to increase employee productivity while accurately understanding work content and streamlining report creation. Manually creating daily reports and managing work hours takes time and effort, resulting in reduced productivity and stress. Furthermore, it is difficult for management to grasp not only the performance of individual employees, but also the work progress and emotional state of the entire team and organization in real time.

[1274] 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.

[1275] In this invention, the server includes: means for collecting records of work tool usage when employees leave work; a generation AI means for automatically extracting work content based on the collected record data; means for classifying the generated work content by category; means for generating a draft work report based on the classified work content and presenting it to the employee's device; means for saving the work reports submitted by the employees in a database; means for analyzing the saved work report data and generating performance reports for the team and the entire organization; an emotion engine means for recognizing and analyzing the emotional states of employees; means for reflecting the emotional data acquired by the emotion engine in the work reports and performance reports; and means for providing the generated performance reports to management. This enables efficient entry of employee daily reports, unified and accurate man-hour management, understanding of work progress, and real-time visualization of employee emotional states.

[1276] An "employee" is someone who belongs to a company or organization and performs work.

[1277] "Work tools" are software and hardware used by employees to do their jobs. Examples include email clients and code management systems.

[1278] "Usage logs" are data that is automatically generated when business tools are used. Examples include email sending and receiving logs and code commit logs.

[1279] "Generative AI" is artificial intelligence that automatically analyzes and extracts business content from collected data. It uses natural language processing technology and machine learning algorithms.

[1280] "Category" refers to a group or type for classifying extracted work content. Specifically, it includes "development," "meeting," "support," etc.

[1281] A "work report" is a document that records an employee's daily work, progress, time allocation, etc.

[1282] A "server" is a central computer system that collects, analyzes, stores, and provides data.

[1283] "Devices" refers to computers and devices used by employees, including desktops, laptops, tablets, etc.

[1284] A "database" is a system or platform for organizing and storing information for later use.

[1285] A "performance report" is a report that summarizes the work progress, results, challenges, emotional state, etc. of a team or the entire organization.

[1286] The "emotion engine" is a technology that analyzes the emotional state of employees from their speech and text input, using voice recognition and text analysis.

[1287] "Management" refers to people in a position to give instructions and make management decisions in a company or organization. Specifically, this includes executives and managers.

[1288] This system collects records of employees' use of business tools when they leave work, automatically extracts work content using generation AI, categorizes it, and generates draft work reports. Furthermore, it uses an emotion engine to grasp employees' emotional states and reflects them in work reports and performance reports, providing detailed information to management.

[1289] Collecting log data

[1290] The server accesses the company's business tools (e.g., email server and code management system) once a day at a specified time to collect employee usage logs. It connects to the email server using the IMAP protocol to retrieve mail logs. It connects to the code management system using an API to retrieve project changes and commit logs. The collected log data is temporarily stored in the server's memory.

[1291] Automatic extraction of business content

[1292] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. For example, the task details of "client support" are extracted from email logs, and the task details of "bug fixes" are extracted from code management logs.

[1293] Business categorization

[1294] The generative AI model classifies the extracted tasks into predefined categories (e.g., "development," "meeting," "support," etc.) Using a keyword-based algorithm, tasks containing the keyword "code" are classified as "development," and tasks containing the keyword "meeting" are classified as "meeting."

[1295] Generate and present daily report drafts

[1296] The server uses templates to generate draft work reports based on the classified work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. Employees can review the presented draft and make corrections or additions as necessary.

[1297] Daily report database storage

[1298] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The server then stores the received business report in a database.

[1299] Analyze daily data and generate performance reports

[1300] The generative AI model analyzes work report data stored in a database. Based on this analysis, a performance report for the team or the entire organization is generated. For example, the report includes each employee's work content, time allocation, and progress for each project.

[1301] Emotion engine integration

[1302] The emotion engine recognizes emotions from the voices and texts employees input while working, using voice recognition and text analysis technologies to evaluate stress levels and satisfaction.

[1303] Reflecting emotional data

[1304] The server adjusts draft work reports based on the emotional data obtained from the emotion engine. For example, it can reflect an employee's feelings of stress in the work report. This emotional data can also be reflected in performance reports, allowing management to understand the emotional health of the organization.

[1305] Feedback and Support

[1306] The server provides appropriate feedback and support messages to the user based on the emotional data obtained from the emotion engine. For example, if stress is detected, a message suggesting relaxation techniques is sent, and if the user is emotionally satisfied, a message praising the user's achievement is sent.

[1307] Providing performance reports

[1308] The server then provides the generated performance report to management, which reflects not only each employee's work performance but also their emotional state, allowing managers to gain a more accurate understanding of the overall situation of the organization.

[1309] Specific examples

[1310] For example, when employee A leaves work, the server collects the day's email and code management tool usage logs. The generative AI model extracts work content, such as "client support" and "bug fixing," from the collected log data and categorizes it into categories such as "development" and "support." Based on the categorized work content, a draft daily report is generated and displayed on employee A's device. Employee A checks and modifies the draft, then finalizes and submits it. The emotion engine analyzes the voice and text data captured during the day's work and recognizes that employee A is feeling stressed. This emotion data is reflected in work reports and performance reports and provided to management.

[1311] Prompt Sentence Examples

[1312] An example of a prompt to be input to the generative AI model is, "Analyze today's email log and code management log, extract the main work content, and create a work report."

[1313] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1314] Step 1:

[1315] The server accesses internal business tools (e.g., email servers and code management systems) once a day at a specified time to collect employee usage logs. Specifically, it connects to the email server using the IMAP protocol and retrieves email logs. It also connects to the code management system using an API to retrieve project changes and commit logs. The inputs are the IMAP server connection information and API endpoints, and the output is email logs and code management logs. The collected log data is temporarily stored in the server's memory.

[1316] Step 2:

[1317] The generative AI model analyzes log data collected on the server. This analysis uses natural language processing technology to extract key task details from keywords and context within the logs. Specifically, the model is given a prompt: "Analyze email logs and code management logs and extract key task details," and the extracted task details are obtained as output. For example, the task details "client support" are extracted from email logs, and the task details "bug fixes" are extracted from code management logs.

[1318] Step 3:

[1319] The generative AI model classifies the extracted work content into predefined categories (for example, "development," "meeting," "support," etc.). Using a keyword-based algorithm, work content containing the keyword "code" is classified as "development," and work content containing the keyword "meeting" is classified as "meeting." The input is the extracted work content, and the output is the work content categorized by category. In terms of specific operation, the generative AI model follows the rule "classify the work content into categories."

[1320] Step 4:

[1321] The server uses a template to generate a draft of the work report based on the categorized work content. The generated draft is automatically sent to the employee's device and displayed when they leave work. The input is work content categorized by category, and the output is a draft of the work report. Specifically, the server performs the process of "filling in the work content extracted for each category according to the daily report template."

[1322] Step 5:

[1323] The user (employee) checks the displayed draft of the business report, makes any corrections or additions, and then presses the "Submit" button. This finalizes the business report and sends it to the server. The input is the draft business report that has been corrected and added by the user, and the output is the finalized business report. In concrete terms, the user clicks the "Save" button, and the finalized data is sent to the server.

[1324] Step 6:

[1325] The server stores the received business report in a database. The input is the confirmed business report, and the output is the business report data stored in the database. Specifically, the server performs the process of "storing the confirmed business report in the database."

[1326] Step 7:

[1327] The generative AI model analyzes work report data stored in a database and generates performance reports for teams and the entire organization. The input is all work report data stored in the database, and the output is a performance report. Specifically, the model is input with the prompt "Create a monthly performance report based on the daily report data of all employees," and the analysis results are obtained.

[1328] Step 8:

[1329] The emotion engine recognizes and analyzes emotions from the voices and texts that employees enter during work. This analysis uses voice recognition and text analysis technologies. The input is voice data and text data, and the output is emotion evaluation data. Specifically, the emotion engine analyzes according to the rule, "assess stress level."

[1330] Step 9:

[1331] The server adjusts the draft of the business report based on the emotion data obtained from the emotion engine. The input is emotion data, and the output is a draft of the business report that reflects the emotion data. Specifically, the server performs the process of "if the stress level is high, reflect that in the business report."

[1332] Step 10:

[1333] The server provides the generated performance report to management. This report includes each employee's work content and emotional state. The input is the performance report, and the output is a report provided to management. Specifically, the server performs the process of "automatically sending a performance report containing all analysis results once a month."

[1334] (Application example 2)

[1335] 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."

[1336] Currently, many companies and factories have systems in place to track work logs and tasks and evaluate the performance of employees and robots. However, these systems require manual data entry and human intervention, making them inefficient and resulting in high error rates. Furthermore, there is a lack of systems that can grasp the emotions and operational status of robots and employees in real time and take appropriate action. This hinders productivity improvement and proper maintenance, ultimately resulting in a decline in the performance of robots and employees.

[1337] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting usage logs of in-house tools when employees leave work; a generation AI means for automatically extracting work content based on the collected log data; means for classifying the generated work content by category; means for generating a draft daily report based on the classified work content and presenting it to the employee's terminal; means for saving daily reports submitted by employees in a database; means for analyzing the saved daily report data and generating performance reports for the team and the entire organization; means for providing the generated performance report to management; means for analyzing work logs and sensor data collected by factory robots while they are operating; means for automatically generating daily reports for the factory robots based on the analyzed work logs and sensor data; and means for analyzing abnormal conditions from the factory robot's operating status and error logs using an emotion engine and issuing alerts as necessary. This enables automatic generation of daily reports and real-time performance evaluation.

[1338] An "employee" is a worker who is responsible for a specific task within a company or organization.

[1339] "Clocking out" refers to an employee completing their work hours for the day and leaving the workplace.

[1340] "Internal tools" is a general term for software and systems used by employees within a company to carry out their work.

[1341] "Usage logs" refer to records of employees or devices using specific tools or systems.

[1342] "Generative AI" is a system that uses artificial intelligence technology to generate information from data.

[1343] "Work content" is the details of the work or tasks actually performed by employees or equipment.

[1344] A "category" is a group for classifying multiple business operations based on common characteristics or criteria.

[1345] A "daily report" is a document that reports on the work that employees and equipment performed that day.

[1346] "Draft" means an initial draft of a document prior to its finalization.

[1347] "Terminals" are devices such as computers and smartphones used by employees.

[1348] A "database" is an electronic system for efficiently storing, retrieving, and managing data.

[1349] A "performance report" is a report used to evaluate and analyze the work efficiency and results of employees, teams, and the entire organization.

[1350] "Management" refers to the group of executives who make strategic decisions for a company or organization.

[1351] A "factory robot" is a mechanical device that is programmed to perform specific tasks on a manufacturing floor.

[1352] A "work log" is data that records the work performed by a factory robot.

[1353] "Sensor data" refers to various types of physical information acquired by sensors.

[1354] The "Emotion Engine" is a software system for analyzing emotions and operating status from data.

[1355] "Operating state" refers to the state in which factory robots and equipment are operating.

[1356] An "error log" is recorded data when a system or device experiences an error.

[1357] An "alert" is a function or notification that issues a warning when an abnormality or problem occurs.

[1358] As an example of how to implement this invention, we will explain a system that combines data collection when employees leave work and monitoring the operation of factory robots. The system is composed of multiple modules, each of which performs a specific function.

[1359] Collecting log data

[1360] The server periodically collects usage logs of internal tools (such as mail servers and code management systems) when employees leave work. This collection is done using the IMAP protocol and API. The log data is temporarily stored in memory and later converted into a format that is easy to analyze. In addition, work logs and sensor data generated by factory robots while they are operating are also collected.

[1361] Automatic extraction of business content

[1362] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI incorporates natural language processing technology to summarize and extract key work content from email logs, code management logs, and work logs. The extracted information is categorized into specific work content such as "client support," "bug fixing," and "parts assembly."

[1363] Business categorization

[1364] The generative AI categorizes the extracted tasks into predefined categories: tasks related to "code" are classified into the "development" category, tasks related to "meetings" into the "conference" category, and tasks related to "assembly of parts" into the "manufacturing" category.

[1365] Generate and present daily report drafts

[1366] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is presented to the employee's terminal when they leave work, and the employee can check and edit it. Similarly, a daily report regarding factory robots is also generated.

[1367] Daily report database storage

[1368] After the user (employee) checks and modifies the draft daily report, the final version is saved in the database, which allows the daily report data to be consolidated and analyzed later.

[1369] Analyze daily data and generate performance reports

[1370] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization, including the work content, time allocation, and project progress of each employee and robot.

[1371] Emotion engine integration

[1372] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots, and utilizes voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions.

[1373] Reflecting emotional data

[1374] The emotion engine then uses the emotion data to adjust the draft daily report. For example, if an employee is under stress, this will be reflected in the daily report. The emotion data is also incorporated into performance reports and provided to management.

[1375] Feedback and Support

[1376] The server provides feedback and support messages to users (employees) based on the emotional data. If stress is detected, it suggests relaxation techniques, and if the user is emotionally satisfied, it sends a message praising the user's achievements.

[1377] Providing performance reports

[1378] The generated performance reports are provided to management to help formulate organizational strategies and optimize resource allocation, while reports reflecting emotional data can be used to monitor employee mental health and robot operation status.

[1379] Specific examples

[1380] For example, when a user (Employee A) leaves work, the server collects the day's emails and usage logs of the code management tool. The generation AI extracts work details such as "client support" and "bug fixing" and categorizes them into "development" and "support." Similarly, for Robot A in the factory, work logs such as "parts assembly" and "welding" are collected and analyzed to generate a daily report. An example of an emotion engine analyzing Employee A's stress level and reflecting this in a daily report or report would be, "As stress level is high, we will suggest relaxation methods."

[1381] Example prompt sentence:

[1382] "Generate a draft daily report based on Robot A's work log data and emotion data. Task content: ['Parts assembly', 'Welding', 'Inspection'], Emotional state: {'status': 'stress', 'level': 8}."

[1383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1384] Step 1: Collect log data

[1385] When employees leave work, the server collects work logs and sensor data from internal tools (for example, email servers and code management systems) and factory robots. Here, the IMAP protocol is used to obtain email logs, and APIs are used to obtain code management logs and robot data. The collected log data is temporarily stored in memory and later converted into a format that is easy to analyze. The input is the operation logs of each tool and robot, and the output is log data in a format suitable for analysis.

[1386] Step 2: Automatic extraction of business content

[1387] The server passes the collected log data to the generation AI, which automatically extracts the work content. The generation AI uses natural language processing technology to identify and summarize key work content from email logs, code management logs, and work logs. For example, it extracts content such as "client support" from email logs, "bug fixing" from code management logs, and "parts assembly" from robot work logs. The input is log data, and the output is a list of extracted work content.

[1388] Step 3: Categorize your work

[1389] The server categorizes the work content extracted by the generation AI. Based on predefined keywords and patterns, "code" is categorized as "development," "meetings" as "conferences," and "parts assembly" as "manufacturing." The input is a list of work content, and the output is the work content categorized by category.

[1390] Step 4: Generate and present a draft daily report

[1391] The server generates a draft daily report based on the work content categorized by category. The generated draft daily report is automatically presented to the employee's terminal when they leave work, and the employee can review and edit it. A daily report about the robot is also generated. The input is the work content categorized by category, and the output is the generated draft daily report.

[1392] Step 5: Save daily reports to the database

[1393] After the user (employee) checks the draft daily report and makes corrections or additions, the final version of the daily report is saved in the database. This allows the daily report data to be integrated and analyzed later. The input is the corrected draft daily report, and the output is the finalized daily report saved in the database.

[1394] Step 6: Analyze daily data and generate performance reports

[1395] The server uses AI to analyze the daily report data stored in the database and generate performance reports for the team and the entire organization. The reports include the work content, time allocation, and project progress of each employee and robot. The input is the daily report data from the database, and the output is the performance report.

[1396] Step 7: Integrating the Emotion Engine

[1397] The server uses an emotion engine to analyze the emotional state and operating status of employees and robots. It uses voice recognition and text analysis technologies to evaluate stress levels and abnormal conditions. The input is voice and text data, and the output is the analyzed emotional state.

[1398] Step 8: Reflecting emotional data

[1399] The server adjusts the draft daily report based on the emotion data obtained from the emotion engine. For example, if an employee is under stress, this is reflected in the daily report. The emotion data is also incorporated into the performance report and provided to management. The input is emotion data, and the output is the adjusted daily report and performance report.

[1400] Step 9: Feedback and support

[1401] The server provides feedback and support messages to users (employees) based on the emotional data. For example, if stress is detected, it suggests relaxation techniques, and if the employee is emotionally satisfied, it sends a message praising their achievements. The input is emotional data, and the output is a feedback message.

[1402] Step 10: Provide performance reports

[1403] The generated performance reports are provided to management and are useful for formulating organizational strategies and optimizing resource allocation. Reports that reflect emotional data can also be used to manage employee mental health and robot operating status. The input is the performance report, and the output is the provided report.

[1404] 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.

[1405] 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.

[1406] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1407] 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.

[1408] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1409] 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.

[1410] 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).

[1411] 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.

[1412] 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."

[1413] 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.

[1414] 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).

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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 p...

Claims

1. A means of collecting logs of internal tool usage when employees leave work, A generation AI method that automatically extracts business content based on collected log data, A means for classifying the generated business content into categories; A means for generating a draft of a daily report based on the classified work content and presenting it to the employee's terminal; a means for storing the daily reports submitted by employees in a database; A means for analyzing the stored daily report data and generating performance reports for the team and the entire organization; A means of providing generated performance reports to management; A system including:

2. The system of claim 1 , wherein the collected log data includes employee email and code management tool usage logs.

3. 2. The system according to claim 1, wherein the generated daily report draft can be edited and revised by employees, and the confirmed daily report is stored in a database.

Images