system

Abstract

Provide a system. A means for authenticating user information; a means for obtaining schedule information; A means of analyzing and categorizing the acquired schedule information; A means to summarize work hours based on the analysis results, a means for displaying the summarized results; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's business environment, it is important to efficiently manage individual work time, self-evaluate, and improve time management. However, traditional manual time management and recording methods are cumbersome, time-consuming, and often inaccurate. Furthermore, it is difficult to accurately grasp one's own work activities when multiple schedules coexist. Therefore, there is a need for a system that can efficiently acquire and analyze users' schedule information and automatically summarize and provide task time. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for authenticating user information, a means for acquiring schedule information, a means for analyzing and categorizing the acquired schedule information, a means for summarizing work time based on the analysis results, and a means for displaying the summary results. This system enables users to efficiently understand and manage their own work time, improve their time management, and perform self-evaluation. Furthermore, by automatically acquiring schedule information via a calendar API and analyzing the information using natural language processing, the system can provide accurate summary results.

[0006] "User Information" means any authentication information or profile information required to identify a particular User and access the System.

[0007] "Authentication" is a procedure for verifying that a user is a legitimate user when accessing a system.

[0008] "Schedule information" is information about a plan registered in the user's schedule, and includes data such as start time, end time, title, and description.

[0009] The "Calendar API" is an interface for accessing a calendar from an external system and obtaining, registering, and updating schedule information.

[0010] "Analysis" is the process of understanding the content of schedule information and classifying and evaluating the data based on specific rules and algorithms.

[0011] "Categorization" is the process of classifying analyzed data into specific groups or categories.

[0012] "Summarization" refers to summarizing data and organizing it into a specific format based on the results of analysis.

[0013] "Natural language processing" is the technology of understanding, interpreting, and generating human language, and is used to analyze and classify text data.

[0014] "Display" is the process of presenting the analyzed and summarized results to a user visually, usually in the form of a graph or table. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The system of the present invention efficiently acquires and analyzes a user's schedule information, and automatically summarizes and provides the summary of the user's working hours. Specific embodiments of the present invention will be described below.

[0037] User Authentication

[0038] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[0039] Obtaining schedule information

[0040] The terminal obtains the user's schedule information via the Google (registered trademark) Calendar API. Here, the terminal accesses the user's calendar and obtains JSON data including detailed information about the event (e.g., start time, end time, title, and description).

[0041] Data analysis and categorization

[0042] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to categorize each event. Utilizing string analysis and machine learning models, it automatically categorizes events into categories such as "meetings," "project work," and "breaks."

[0043] Generate summaries

[0044] The device summarizes the user's work time based on the analyzed data. Time is aggregated by category according to existing rules and algorithms, and summary information is generated for periods such as daily, weekly, and monthly.

[0045] Displaying the results

[0046] The results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visualizes the results in graphs and tables, allowing users to intuitively understand the distribution of work time.

[0047] Specific examples

[0048] Summarizing the working hours of the day

[0049] Let's say a user has the following appointments between 9am and 6pm:

[0050] 09:00 - 10:00: Team meeting

[0051] 11:00 - 12:00: Project A work

[0052] 13:00 - 14:00: Client meeting

[0053] 15:00 - 16:00: Project B development

[0054] The device retrieves these events and, through NLP techniques, categorizes them as follows:

[0055] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[0056] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[0057] Based on this, the terminal generates a summary and displays it as follows:

[0058] Total meeting time: 2 hours

[0059] Project duration: 2 hours

[0060] Other: 0 hours

[0061] Summarizing the working week

[0062] For example, if a user has the same schedule every day from Monday to Friday, the device will generate the following weekly summary results:

[0063] Total meeting time (weekly): 10 hours (2 hours / day, 5 days)

[0064] Project work hours (week): 10 hours (2 hours / day, 5 days)

[0065] The results are stored on a server and updated information is provided each time the user accesses the site.

[0066] The system of the present invention allows users to easily understand their own working hours, which can be used to improve time management and self-evaluation. Each of the above functions contributes greatly to improving user productivity and efficient time management.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The user logs in to the system. The user clicks the login button on the screen and grants access to their Google account through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[0070] Step 2:

[0071] The device uses the obtained authentication token to send a request to the Google Calendar API, which returns the user's calendar information (event details) in JSON format.

[0072] Step 3:

[0073] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[0074] Step 4:

[0075] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[0076] Step 5:

[0077] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[0078] Step 6:

[0079] Based on the scheduled data categorized by device, daily, weekly, and monthly working hours are summarized. Specifically, the total time for each category is calculated and aggregated results are generated for each period.

[0080] Step 7:

[0081] The terminal formats the summarized results into graphs and tables, visualizing the data so that it is easy for the user to understand visually.

[0082] Step 8:

[0083] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[0084] Step 9:

[0085] Users access the summary results through a web interface or a dedicated application, ensuring that the latest summary results are displayed even when users re-login to the system.

[0086] Step 10:

[0087] Users can review their own work hours based on the displayed summary results, which allows them to improve their time management and self-evaluate.

[0088] Example 1

[0089] 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."

[0090] Conventional schedule management systems collect and analyze users' schedule information, but the analysis results are often not presented in an intuitive and easy-to-understand format. Furthermore, summarizing and categorizing work time is often done manually, placing a significant burden on users. Therefore, more advanced technology was needed to efficiently manage users' work time and improve productivity.

[0091] 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.

[0092] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summarization results, means for analyzing the schedule information using natural language processing technology, means for aggregating the acquired schedule information into summary information for multiple periods, and means for visually displaying the summary information. This enables users to efficiently manage their own task times and improve productivity.

[0093] "User information" refers to the user's identification information used in the authentication process, specifically, an email address, a password, etc.

[0094] "Schedule information" refers to detailed information (start time, end time, title, description, etc.) of an event listed on a user's calendar.

[0095] "Analysis" refers to the process of using natural language processing technology to understand the content of the acquired schedule information and classify it into specific categories.

[0096] "Categorization" refers to the process of classifying analyzed schedule information into specific categories such as "meetings," "project work," and "breaks."

[0097] "Summarization" refers to the process of summarizing task hours for a specific period based on analyzed data and providing it to the user.

[0098] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language, and includes machine learning models and string analysis algorithms.

[0099] "API" refers to an interface for exchanging data and functions between applications, such as a calendar API.

[0100] "Summary information" refers to information that summarizes the aggregated work hours, category information, etc. in a format that is easy for the user to understand.

[0101] "Visual display" refers to the process of presenting summary information to users in the form of graphs or tables, allowing them to intuitively understand the information.

[0102] To implement the present invention, it is necessary to implement the system program through the following procedure: The system is designed to improve the efficiency of users' work time management and productivity.

[0103] User Authentication

[0104] When a user logs in to the system, they first obtain user information using OAuth2.0 authentication. The device uses the OAuth2.0 framework to send a request to the authentication server and obtain an access token. This token is then used to obtain the user's identification information (such as name and email address) from the authentication server.

[0105] Obtaining schedule information

[0106] The device uses the calendar API to obtain the user's schedule information. The data obtained through this API is in JSON format and includes details such as the start time, end time, title, and description of each event.

[0107] Data analysis and categorization

[0108] The device parses the acquired schedule information and analyzes each event using natural language processing (NLP) techniques. This analysis uses machine learning models and string analysis algorithms. The analyzed information classifies each event into categories such as "meetings," "project work," and "breaks."

[0109] Generate summaries

[0110] The device then uses the analyzed data to summarize the user's work time, aggregating the time spent by category on a daily, weekly, or monthly basis according to specific rules and algorithms.

[0111] Displaying the results

[0112] The aggregated results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visually displays the summarized results in the form of graphs and tables, allowing users to intuitively understand the distribution of work time.

[0113] Specific examples

[0114] Summarizing the working hours of the day

[0115] Let's say a user has the following appointments between 9am and 6pm:

[0116] 09:00 - 10:00: Team meeting

[0117] 11:00 - 12:00: Project A work

[0118] 13:00 - 14:00: Client meeting

[0119] 15:00 - 16:00: Project B development

[0120] The device retrieves these events and uses NLP techniques to categorize them as follows:

[0121] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[0122] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[0123] Based on this, the terminal generates a summary and displays it as follows:

[0124] Total meeting time: 2 hours

[0125] Project duration: 2 hours

[0126] Other: 0 hours

[0127] Prompt Sentence Examples

[0128] "Get the user's schedule information from the Calendar API and generate a categorical process description using natural language processing techniques."

[0129] By implementing this system, users can efficiently manage their work time and significantly improve their productivity. In addition, by visually displaying the summary results, users can intuitively understand how they use their time.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1: User authentication

[0132] Description: When a user logs in to the system, the authentication process begins. Specifically, the user enters their email address and password on the login screen and presses the "Login" button.

[0133] Input: Email address, password

[0134] Data processing / data calculation: The device uses the OAuth 2.0 framework to send a request to the authentication server and obtain an access token. This token is used to obtain user information.

[0135] Output: Access token, user information (name, email address, etc.)

[0136] Specific operation: The terminal sends a request to the authentication server, which verifies the user information and returns an access token.

[0137] Step 2: Obtaining schedule information

[0138] Description: Gets the user's schedule information. The device uses the Calendar API to request schedule information for the specified period.

[0139] Input: Access token, information for the specified period

[0140] Data processing / data calculation: The device uses the access token to send a request to the calendar API and receives JSON data of the schedule information.

[0141] Output: User schedule information (JSON format)

[0142] Specific operation: The device sends an HTTP request to the calendar API, and the API returns schedule information for the specified period.

[0143] Step 3: Analyze and categorize the data

[0144] Description: Analyzes the acquired schedule information and categorizes each event. The device uses natural language processing technology to analyze the title and description of each event.

[0145] Input: User's schedule information (JSON format)

[0146] Data processing / data calculation: The device uses an NLP model to analyze the schedule information and classifies each event into categories such as "meeting," "project work," and "break" through string analysis and machine learning.

[0147] Output: Date information categorized by category

[0148] Specific operation: The device inputs the title and description of the schedule information into the NLP model and outputs the categorized results.

[0149] Step 4: Generate summaries

[0150] Description: Summarizes work hours based on analyzed data. The device aggregates the time for each category and generates summary information for the specified period (e.g., daily, weekly, monthly).

[0151] Input: Date information categorized by category

[0152] Data processing / data calculation: The device calculates the time for each category and applies an algorithm to calculate the total time.

[0153] Output: Aggregated time results for each category

[0154] Specific operation: The device aggregates the schedule information for each category by hour and generates daily, weekly, and monthly summary results.

[0155] Step 5: View the results

[0156] Description: Displays summarized results. Stores the results on the server and allows users to access them through a web interface or dedicated application.

[0157] Input: Aggregation results of time by category

[0158] Data processing / data calculation: The terminal sends the aggregated results in JSON format to the server and stores them in a database.

[0159] Output: Graphs and tables of summarized results

[0160] Specific operation: The terminal visually displays the summary results, and the latest aggregated results are displayed each time the user accesses the terminal.

[0161] (Application example 1)

[0162] 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."

[0163] Conventional work schedule management in factories is often managed individually by human workers, which is inefficient. Furthermore, it is difficult to grasp how much time a robot is spending on each process, making it difficult to improve productivity and optimize time management. The objective of this invention is to provide a system that can efficiently acquire and analyze user schedule information, manage work schedules within the factory, calculate the total time for each work category, and be installed and used on robots.

[0164] 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.

[0165] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summary results, means for managing the work schedule within the factory and calculating the total time for each task category, and means installed on the factory robots. This allows users and managers to centrally manage the work schedule within the factory and understand the time allocation for each specific task.

[0166] "Means for authenticating user information" refers to means for verifying the legitimacy of a user when accessing a system.

[0167] The "means for acquiring schedule information" is a means for collecting the user's schedule data from an external calendar service or the like.

[0168] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing collected schedule data and classifying it into specific task categories.

[0169] "Means for summarizing task times based on analysis results" refers to means for summarizing task times for each category and total time based on the analyzed data.

[0170] The "means for displaying the summary results" is a means for visually presenting the summarized task times and other analysis results to the user.

[0171] "Means for managing work schedules within a factory" refers to a means for centrally organizing and managing the schedules of each work task within a factory.

[0172] The "means for calculating the total time for each task category" is a means for calculating the total task time allocated to each category within a specific period.

[0173] The "means to be installed in the robots in the factory" refers to a means for incorporating the work schedule management system into the robots in the factory.

[0174] The system of the present invention efficiently acquires and analyzes the user's schedule information, manages work schedules within the factory, calculates the total time for each work category, and can be installed and used on a robot.

[0175] Authenticate user information

[0176] When a user logs in to the system, the server obtains user information using OAuth 2.0 authentication. This process verifies that the user is a legitimate user.

[0177] Obtaining schedule information

[0178] The device obtains the user's schedule information via the Google Calendar API. At this time, it accesses the user's calendar and obtains JSON data containing detailed information about the event (start time, end time, title, and description).

[0179] Data analysis and categorization

[0180] The device analyzes the schedule information and categorizes each event using natural language processing (NLP) technology, utilizing string analysis and machine learning models to automatically classify events into categories such as "welding work," "quality check," and "packaging."

[0181] Generate time summaries

[0182] The device then uses the analyzed data to summarize the total time spent in each task category, aggregating the time spent in each category according to existing rules and algorithms, and generating summary information for periods such as daily, weekly, or monthly.

[0183] Displaying the results

[0184] The summarized results are stored on a server and can be accessed by the user through a web interface or a dedicated app. The terminal visualizes the results in graphs and tables, allowing the user to intuitively understand the time allocation for each task.

[0185] Installation on factory robots

[0186] The system can be installed on robots in factories, allowing the robots to automatically manage work schedules and keep track of the progress of each work category in real time.

[0187] Specific examples

[0188] For example, if a user wants to manage the schedule of a factory robot, the following format is possible:

[0189] October 1, 2023, 9:00 - 11:00: "Welding"

[0190] October 1, 2023, 11:30 - 12:30: "Quality Check"

[0191] October 1, 2023, 13:00 - 15:00: "Packaging"

[0192] The system takes this schedule data, categorizes it using NLP technology, and calculates and displays the total time for each work category.

[0193] Hardware and software used

[0194] Hardware: Robot built-in computer, API communication module

[0195] Software: Python (programming language), Google Calendar API (scheduling data acquisition), OAuth2.0 (robot authentication), NLP libraries (e.g., SpaCy, NLTK), Pandas (data processing and visualization)

[0196] Example of generated AI prompt

[0197] "Design an application that automatically calculates the total time for each task category from calendar data, categorizes it using NLP, and summarizes it by day, week, and month."

[0198] The above is a specific embodiment of the system of the present invention. This system allows users and managers to centrally manage work schedules within a factory and understand the time allocation for each specific task.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The server authenticates user information. When a user logs in to the system, it obtains user information using OAuth2.0 authentication. Through this authentication process, the server verifies that the user is a legitimate user. The input is the user's authentication information, and the output is authenticated user information.

[0202] Step 2:

[0203] The device obtains schedule information. Based on the authenticated user information, the device uses the Google Calendar API to obtain the user's schedule information. At this time, the device accesses the user's calendar and obtains JSON data containing detailed event information (start time, end time, title, and description). The input is the authenticated user information and a request for calendar information, and the output is schedule information in JSON format.

[0204] Step 3:

[0205] The terminal analyzes and categorizes the acquired schedule information. The acquired schedule information is analyzed using natural language processing (NLP) technology, and each schedule is categorized. Specifically, string analysis and machine learning models are used to automatically classify schedules into categories such as "welding work," "quality check," and "packaging." The input is schedule information in JSON format, and the output is categorized schedule data.

[0206] Step 4:

[0207] The terminal summarizes work hours based on the analysis results. Based on the analyzed data, it calculates the total time for each work category. According to existing rules and algorithms, it aggregates the time for each category and generates summary information for periods such as daily, weekly, or monthly. The input is categorized schedule data, and the output is summarized time data.

[0208] Step 5:

[0209] The server displays the summarized results. It saves the summarized results and allows users to access them through a web interface or a dedicated app. The terminal visualizes the aggregated results in graphs and tables, allowing users to intuitively understand the time allocation for each task. The input is summarized time data, and the output is visualized data in graphs and tables.

[0210] Step 6:

[0211] The terminal is installed on the factory robot. By incorporating the system into the robot in the factory, the robot can automatically manage its work schedule and monitor the progress of each work category in real time. The input is the system installation package, and the output is the installed robot system.

[0212] 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.

[0213] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[0214] User Authentication

[0215] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[0216] Obtaining schedule information

[0217] The device obtains the user's schedule information via the calendar API. Here, detailed information (e.g., start time, end time, title, description) of events stored in the user's calendar is obtained in JSON format.

[0218] Data analysis and categorization

[0219] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. Based on the results of this analysis, it then automatically assigns each appointment an appropriate category (e.g., "meeting," "project work," "break").

[0220] Introducing the Emotion Engine

[0221] The device is equipped with an emotion engine that uses data acquired from the user's schedule and conversation history to recognize the user's emotions. This emotion engine uses machine learning models to estimate the user's emotional state and generate emotion tags such as "stress," "satisfaction," and "dissatisfaction."

[0222] Summarizing business hours

[0223] The device summarizes daily, weekly, and monthly working hours based on categorized schedule data. The aggregated results calculate the time spent by category and also include emotion tags generated by the emotion engine.

[0224] Displaying results and integrating emotional information

[0225] The device then formats the summary results into graphs and tables, visualizing them for intuitive understanding by the user. At the same time, emotion tags obtained from the emotion engine are also displayed, providing emotional information related to each task.

[0226] Specific examples

[0227] Summarizing the working hours of the day

[0228] Let's say a user has the following schedule from 9am to 6pm:

[0229] 09:00 - 10:00: Team meeting (emotional state: stress)

[0230] 11:00 - 12:00: Project A work (emotional state: satisfied)

[0231] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[0232] 15:00 - 16:00: Project B development (emotional state: concentration)

[0233] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[0234] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[0235] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[0236] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[0237] Based on this, the terminal generates and displays the summary result as follows:

[0238] Total meeting time: 1 hour (emotional state: stressed)

[0239] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[0240] Client meeting time: 1 hour (emotional state: anxiety)

[0241] These results are stored on a server and are accessible to users through a web interface or dedicated application. Based on the emotional information displayed in the summary results, users can manage their own work time and emotions, which can help improve work efficiency and reduce stress.

[0242] The system of the present invention allows users to not only manage their work time but also understand their emotional state, enabling more comprehensive self-management, which is expected to improve both time efficiency and mental health.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The user logs in to the system. The user clicks the login button on the screen and grants access to calendar information through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[0246] Step 2:

[0247] The device uses the obtained authentication token to send a request to the calendar API, which returns the user's calendar information (event details) in JSON format.

[0248] Step 3:

[0249] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[0250] Step 4:

[0251] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[0252] Step 5:

[0253] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[0254] Step 6:

[0255] The device uses an emotion engine to analyze schedule information and conversation history to estimate the user's emotional state. The emotion engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[0256] Step 7:

[0257] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data and emotion tags generated by the emotion engine. The aggregated results include the total time for each category and the corresponding emotion information.

[0258] Step 8:

[0259] The device then formats the summarized results into graphs and tables, visualizing the data for easy visual understanding. The emotion engine also displays emotion tags, providing emotional information related to each task.

[0260] Step 9:

[0261] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[0262] Step 10:

[0263] Users access the summary results through a web interface or a dedicated application. The latest summary results are displayed even when users re-login to the system.

[0264] Step 11:

[0265] Users can review their own working hours and emotional state based on the displayed summary results and emotional information, which makes it easier to improve time management and self-evaluate, and is expected to improve stress management and work efficiency.

[0266] Example 2

[0267] 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."

[0268] Conventional work management systems provide functions for acquiring and analyzing a user's schedule information to summarize work hours, but do not take into account the user's emotional state. As a result, users have had to use separate tools in situations where they need to manage not only their work efficiency but also their mental state. This invention aims to solve this problem by providing a system that not only efficiently acquires and analyzes a user's schedule information and summarizes work hours, but also recognizes the user's emotional state and integrates it into the results.

[0269] 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.

[0270] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for recognizing the user's emotional state and generating an emotion tag, and means for displaying the summarized result together with the emotion tag. This allows the user to manage their work time and emotional state in a unified manner, enabling efficient time management and improved mental health.

[0271] "Means for authenticating user information" refers to means for verifying that a user is a legitimate user when the user accesses the system.

[0272] The "means for acquiring schedule information" refers to the means for extracting schedule information from the calendar or schedule management tool used by the user and importing it into the system.

[0273] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing acquired schedule information and classifying it into different categories such as "meetings" and "project work" based on its contents.

[0274] The "means for summarizing task time" is a means for summarizing a user's task activities for each period, such as daily, weekly, or monthly, based on analyzed and categorized schedule information.

[0275] The "means for recognizing a user's emotional state and generating an emotion tag" refers to a means for using a machine learning model or an emotion analysis engine to estimate a user's emotional state from their schedule information and conversation history, and generating an emotion tag that reflects the results.

[0276] The "means for displaying summary results together with emotion tags" refers to a means for visualizing the summary results of work hours in graph or table format, and further displaying emotion tags related to each work hour.

[0277] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[0278] User Authentication

[0279] When a user logs in to a system, user information is first obtained via the OAuth2.0 authentication protocol. This process allows the server to verify that the user is a legitimate user. A library such as "OAuthLib" is used for OAuth2.0 authentication.

[0280] Obtaining schedule information

[0281] The device retrieves the user's schedule information via a calendar API (e.g., Google Calendar API). The schedule information includes the start time, end time, title, and description of each event. The retrieved information is saved in JSON format.

[0282] Data analysis and categorization

[0283] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. NLP technology uses tools such as "spaCy" and "Natural Language Toolkit (NLTK)." Based on the analysis results, each appointment is automatically assigned a category, such as "meeting," "project work," or "break."

[0284] Introducing the Emotion Engine

[0285] The device uses an emotion engine to recognize the user's emotional state based on the user's schedule information and conversation history. The emotion engine uses machine learning models (e.g., BERT and GPT). This engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[0286] Summarizing business hours

[0287] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data. The summary results include total time and emotion tags for each category. For example, the total time spent in "meetings" or "project work" is displayed along with the corresponding emotion.

[0288] Displaying results and integrating emotional information

[0289] The device then formats the summarized results into graphs and tables, visualizing them in an intuitive way for the user. The results are also displayed with emotion tags, providing emotional information related to each task. For example, a bar graph showing the emotional state corresponding to each task is displayed.

[0290] Saving and Accessing Results

[0291] The server stores the generated summary results in a database. When a user logs into the system through a web interface or a dedicated application, the server reads and displays the stored summary results.

[0292] Specific examples

[0293] Let's say a user has the following schedule from 9am to 6pm:

[0294] 09:00 - 10:00: Team meeting (emotional state: stress)

[0295] 11:00 - 12:00: Project A work (emotional state: satisfied)

[0296] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[0297] 15:00 - 16:00: Project B development (emotional state: concentration)

[0298] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[0299] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[0300] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[0301] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[0302] Based on this, a summary result is generated and displayed:

[0303] Total meeting time: 1 hour (emotional state: stressed)

[0304] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[0305] Client meeting time: 1 hour (emotional state: anxiety)

[0306] Example prompts to input to the generative AI model

[0307] "Please introduce a system that helps users manage their daily work hours and emotional state. This system not only acquires and analyzes the user's schedule information and summarizes their work hours, but also recognizes the user's emotional state and integrates it into the results. Emotional states include stress, satisfaction, anxiety, and concentration. Please explain with specific examples."

[0308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0309] Processing flow

[0310] Step 1: User authentication

[0311] When a user logs in to the system, the server obtains user information using the OAuth2.0 authentication protocol.

[0312] Input: User login information

[0313] Output: Authentication token

[0314] Specific behavior: The user is redirected to an authentication page and enters their authentication information. After that, if the authentication is successful, an authentication token is returned to the server, and the server uses this token to retrieve user information.

[0315] Step 2: Obtaining schedule information

[0316] The device uses the user's authentication token to access the calendar API (e.g., Google Calendar API) and obtain schedule information.

[0317] Input: Authentication Token

[0318] Output: Schedule information (JSON format)

[0319] Specific operation: The device uses the acquired authentication token to send a request to the calendar API and obtains the user's schedule information (start time, end time, title, description) in JSON format.

[0320] Step 3: Analyze and categorize the data

[0321] The device analyzes the schedule information it acquires, uses NLP technology to understand the content, and assigns a category.

[0322] Input: Schedule information (JSON format)

[0323] Output: Categorized schedule information

[0324] How it works: The device uses an NLP library (e.g., spaCy, NLTK) to parse the schedule information and automatically assign a category such as "meeting" or "project work" based on the content of each appointment.

[0325] Step 4: Implementing the Emotion Engine

[0326] Based on the schedule information acquired and analyzed by the device, an emotion engine is used to recognize the user's emotional state and generate an emotion tag.

[0327] Input: Categorized schedule information

[0328] Output: Emotion tag

[0329] Specific operation: The device uses machine learning models (e.g., BERT, GPT) to analyze the user's emotional state from the text content of the schedule information and conversation history, and generates emotion tags such as "stress" and "satisfaction."

[0330] Step 5: Summarize your working hours

[0331] Based on device-categorized schedule data, the system summarizes daily, weekly, and monthly work hours and integrates emotion tags.

[0332] Input: Categorized schedule information, emotion tags

[0333] Output: Summarized results (working hours and sentiment tags)

[0334] Specific operation: The device aggregates work hours by category, collects emotion tags associated with each work hour, and generates a summary result.

[0335] Step 6: Displaying the results and integrating emotional information

[0336] The device formats the summary results into graphs and tables and displays them to the user along with emotion tags.

[0337] Input: Summarization result (working hours and sentiment tags)

[0338] Output: Visualized results (graphs and tables)

[0339] Specific operation: The device uses a data visualization tool (e.g., Matplotlib or D3.js) to format the work hours and emotion tags into an easily understandable format (e.g., bar graph, pie chart, or table) and display them to the user.

[0340] Step 7: Saving and Accessing Results

[0341] The server stores the generated summarization results in a database for user access.

[0342] Input: Summarization result (working hours and sentiment tags)

[0343] Output: Results stored in the database, displayed to the user

[0344] Specific operation: The server saves the summarized results in a database, and when a user logs in through a web interface or a dedicated application, the server loads and displays the saved results.

[0345] (Application example 2)

[0346] 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."

[0347] In order to improve the efficiency of factory work and the performance of workers (robots), it is necessary to not only manage work schedules but also to take into account the emotional state of workers while they are working. However, conventional systems only manage work time and do not recognize or integrate emotional states, making it difficult to optimize performance or detect anomalies.

[0348] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0349] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the categorized schedule information, means for integrating emotional information into the summarized task times, and means for displaying the summarization results and the emotional information. This enables efficient management of work schedules in factories, as well as optimization of worker (robot) performance and anomaly detection.

[0350] A "means for authenticating user information" is a technique or process for authenticating a legitimate user to a system.

[0351] The "means for acquiring schedule information" refers to a technique or process for collecting data related to a user's schedule or dates.

[0352] The "analysis and categorization means" refers to a technique or process for analyzing acquired schedule information and classifying it into categories based on specific criteria.

[0353] A "summarization method" is a technique or process for aggregating and summarizing analyzed data.

[0354] A "means for integrating emotional information" is a technique or process for recognizing the emotional state of a user or worker and combining it with other data.

[0355] "Display means" refers to a technique or process for visually displaying the summarized results and integrated affective information.

[0356] "Means for analyzing based on natural language processing" refers to a process of understanding schedule information using technology that mechanically analyzes text data.

[0357] A "Calendar API" is an application program interface for obtaining schedule information.

[0358] This invention is a system that efficiently acquires and analyzes a user's schedule information and automatically summarizes work hours, and by integrating and displaying emotional information, aims to optimize work efficiency and improve performance.

[0359] User Authentication

[0360] The server obtains user information through OAuth 2.0 authentication and verifies that the user is a legitimate user. This process uses an authentication server and a token.

[0361] Obtaining schedule information

[0362] The server then retrieves the user's schedule information via the calendar API. The retrieved information includes, for example, start time, end time, title, description, etc., and is saved in JSON format.

[0363] Data analysis and categorization

[0364] The server uses natural language processing (NLP) technology to analyze the acquired schedule information and assign an appropriate category to each event, such as "meeting," "work," or "break."

[0365] Introducing the Emotion Engine

[0366] Furthermore, the server uses an emotion engine to recognize emotions from the user's schedule information, conversation history, etc. This emotion engine uses a machine learning model to generate emotion tags such as "stress," "satisfaction," and "anxiety."

[0367] Summarizing business hours

[0368] The server then summarizes work hours based on the categorized schedule data, including total hours and emotion tags for each category.

[0369] Displaying results and integrating emotional information

[0370] Finally, the server displays the summary results and emotional information in an integrated format using graphs and tables, designed to be intuitive for users, allowing them to grasp their schedule and emotional state at a glance.

[0371] As a concrete example, consider a user with the following schedule:

[0372] 09:00 - 10:00: Assembling parts (emotional state: concentration)

[0373] 11:00 - 12:00: Examination work (emotional state: anxiety)

[0374] In this case, the server will summarize the data as follows:

[0375] Parts assembly time: 1 hour (emotional state: concentration)

[0376] Test duration: 1 hour (emotional state: anxiety)

[0377] Prompt Sentence Examples

[0378] An example of a prompt for a generative AI model is:

[0379] "If a user performs a parts assembly task from 09:00 to 10:00 and an inspection task from 11:00 to 12:00, generate a summary result that includes the emotional state of each task."

[0380] This will enable optimization of work efficiency and performance in factories and other work environments by managing users' schedules and understanding their emotional states.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1:

[0383] Perform user authentication.

[0384] The server obtains user information using OAuth 2.0 authentication. It requires the user's authentication information as input. The server sends a request to the authentication server to obtain a token. It uses this token to verify the user's legitimate access. The output is an access token.

[0385] Step 2:

[0386] Get schedule information.

[0387] The server retrieves the user's schedule information using the calendar API. An access token is required as input. The token is used to retrieve the schedule data from the calendar service and save it in JSON format. The output is the retrieved schedule information.

[0388] Step 3:

[0389] Analyze and categorize schedule information.

[0390] The server analyzes the retrieved schedule information using natural language processing (NLP) techniques. It takes the retrieved schedule information as input. The server analyzes the title and description and assigns an appropriate category to each event, such as "meeting," "work," or "break." The output is the analyzed, categorized schedule information.

[0391] Step 4:

[0392] Recognize emotional information.

[0393] The server uses an emotion engine to recognize user emotions from schedule information and related data. Categorized schedule information is required as input. Using a machine learning model, the server generates emotion tags such as "stress," "satisfaction," and "anxiety." The output is schedule information with emotion tags.

[0394] Step 5:

[0395] Summarize your work hours.

[0396] The server summarizes working hours based on categorized schedule information. It requires schedule information with emotion tags as input. The server calculates the total time for each category and integrates the associated emotion tags. The output is the summarized working hours and emotion information.

[0397] Step 6:

[0398] Display the results.

[0399] The server displays summarized task time and emotion information. The input required is summarized task time and emotion information. The server formats this in graphs and tables, generating an interface that users can intuitively understand. The output is visualized data.

[0400] This allows users to understand their schedule and emotional state at a glance, enabling more efficient time management and mental health management.

[0401] 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.

[0402] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0403] 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.

[0404] [Second embodiment]

[0405] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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."

[0417] The system of the present invention efficiently acquires and analyzes a user's schedule information, and automatically summarizes and provides the summary of the user's working hours. Specific embodiments of the present invention will be described below.

[0418] User Authentication

[0419] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[0420] Obtaining schedule information

[0421] The device obtains the user's schedule information via the Google Calendar API. Here, the device accesses the user's calendar and obtains JSON data including detailed event information (e.g., start time, end time, title, and description).

[0422] Data analysis and categorization

[0423] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to categorize each event. Utilizing string analysis and machine learning models, it automatically categorizes events into categories such as "meetings," "project work," and "breaks."

[0424] Generate summaries

[0425] The device summarizes the user's work time based on the analyzed data. Time is aggregated by category according to existing rules and algorithms, and summary information is generated for periods such as daily, weekly, and monthly.

[0426] Displaying the results

[0427] The results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visualizes the results in graphs and tables, allowing users to intuitively understand the distribution of work time.

[0428] Specific examples

[0429] Summarizing the working hours of the day

[0430] Let's say a user has the following appointments between 9am and 6pm:

[0431] 09:00 - 10:00: Team meeting

[0432] 11:00 - 12:00: Project A work

[0433] 13:00 - 14:00: Client meeting

[0434] 15:00 - 16:00: Project B development

[0435] The device retrieves these events and, through NLP techniques, categorizes them as follows:

[0436] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[0437] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[0438] Based on this, the terminal generates a summary and displays it as follows:

[0439] Total meeting time: 2 hours

[0440] Project duration: 2 hours

[0441] Other: 0 hours

[0442] Summarizing the working week

[0443] For example, if a user has the same schedule every day from Monday to Friday, the device will generate the following weekly summary results:

[0444] Total meeting time (weekly): 10 hours (2 hours / day, 5 days)

[0445] Project work hours (week): 10 hours (2 hours / day, 5 days)

[0446] The results are stored on a server and updated information is provided each time the user accesses the site.

[0447] The system of the present invention allows users to easily understand their own working hours, which can be used to improve time management and self-evaluation. Each of the above functions contributes greatly to improving user productivity and efficient time management.

[0448] The processing flow will be explained below.

[0449] Step 1:

[0450] The user logs in to the system. The user clicks the login button on the screen and grants access to their Google account through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[0451] Step 2:

[0452] The device uses the obtained authentication token to send a request to the Google Calendar API, which returns the user's calendar information (event details) in JSON format.

[0453] Step 3:

[0454] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[0455] Step 4:

[0456] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[0457] Step 5:

[0458] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[0459] Step 6:

[0460] Based on the scheduled data categorized by device, daily, weekly, and monthly working hours are summarized. Specifically, the total time for each category is calculated and aggregated results are generated for each period.

[0461] Step 7:

[0462] The terminal formats the summarized results into graphs and tables, visualizing the data so that it is easy for the user to understand visually.

[0463] Step 8:

[0464] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[0465] Step 9:

[0466] Users access the summary results through a web interface or a dedicated application, ensuring that the latest summary results are displayed even when users re-login to the system.

[0467] Step 10:

[0468] Users can review their own work hours based on the displayed summary results, which allows them to improve their time management and self-evaluate.

[0469] Example 1

[0470] 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."

[0471] Conventional schedule management systems collect and analyze users' schedule information, but the analysis results are often not presented in an intuitive and easy-to-understand format. Furthermore, summarizing and categorizing work time is often done manually, placing a significant burden on users. Therefore, more advanced technology was needed to efficiently manage users' work time and improve productivity.

[0472] 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.

[0473] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summarization results, means for analyzing the schedule information using natural language processing technology, means for aggregating the acquired schedule information into summary information for multiple periods, and means for visually displaying the summary information. This enables users to efficiently manage their own task times and improve productivity.

[0474] "User information" refers to the user's identification information used in the authentication process, specifically, an email address, a password, etc.

[0475] "Schedule information" refers to detailed information (start time, end time, title, description, etc.) of an event listed on a user's calendar.

[0476] "Analysis" refers to the process of using natural language processing technology to understand the content of the acquired schedule information and classify it into specific categories.

[0477] "Categorization" refers to the process of classifying analyzed schedule information into specific categories such as "meetings," "project work," and "breaks."

[0478] "Summarization" refers to the process of summarizing task hours for a specific period based on analyzed data and providing it to the user.

[0479] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language, and includes machine learning models and string analysis algorithms.

[0480] "API" refers to an interface for exchanging data and functions between applications, such as a calendar API.

[0481] "Summary information" refers to information that summarizes the aggregated work hours, category information, etc. in a format that is easy for the user to understand.

[0482] "Visual display" refers to the process of presenting summary information to users in the form of graphs or tables, allowing them to intuitively understand the information.

[0483] To implement the present invention, it is necessary to implement the system program through the following procedure: The system is designed to improve the efficiency of users' work time management and productivity.

[0484] User Authentication

[0485] When a user logs in to the system, they first obtain user information using OAuth2.0 authentication. The device uses the OAuth2.0 framework to send a request to the authentication server and obtain an access token. This token is then used to obtain the user's identification information (such as name and email address) from the authentication server.

[0486] Obtaining schedule information

[0487] The device uses the calendar API to obtain the user's schedule information. The data obtained through this API is in JSON format and includes details such as the start time, end time, title, and description of each event.

[0488] Data analysis and categorization

[0489] The device parses the acquired schedule information and analyzes each event using natural language processing (NLP) techniques. This analysis uses machine learning models and string analysis algorithms. The analyzed information classifies each event into categories such as "meetings," "project work," and "breaks."

[0490] Generate summaries

[0491] The device then uses the analyzed data to summarize the user's work time, aggregating the time spent by category on a daily, weekly, or monthly basis according to specific rules and algorithms.

[0492] Displaying the results

[0493] The aggregated results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visually displays the summarized results in the form of graphs and tables, allowing users to intuitively understand the distribution of work time.

[0494] Specific examples

[0495] Summarizing the working hours of the day

[0496] Let's say a user has the following appointments between 9am and 6pm:

[0497] 09:00 - 10:00: Team meeting

[0498] 11:00 - 12:00: Project A work

[0499] 13:00 - 14:00: Client meeting

[0500] 15:00 - 16:00: Project B development

[0501] The device retrieves these events and uses NLP techniques to categorize them as follows:

[0502] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[0503] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[0504] Based on this, the terminal generates a summary and displays it as follows:

[0505] Total meeting time: 2 hours

[0506] Project duration: 2 hours

[0507] Other: 0 hours

[0508] Prompt Sentence Examples

[0509] "Get the user's schedule information from the Calendar API and generate a categorical process description using natural language processing techniques."

[0510] By implementing this system, users can efficiently manage their work time and significantly improve their productivity. In addition, by visually displaying the summary results, users can intuitively understand how they use their time.

[0511] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0512] Step 1: User authentication

[0513] Description: When a user logs in to the system, the authentication process begins. Specifically, the user enters their email address and password on the login screen and presses the "Login" button.

[0514] Input: Email address, password

[0515] Data processing / data calculation: The device uses the OAuth 2.0 framework to send a request to the authentication server and obtain an access token. This token is used to obtain user information.

[0516] Output: Access token, user information (name, email address, etc.)

[0517] Specific operation: The terminal sends a request to the authentication server, which verifies the user information and returns an access token.

[0518] Step 2: Obtaining schedule information

[0519] Description: Gets the user's schedule information. The device uses the Calendar API to request schedule information for the specified period.

[0520] Input: Access token, information for the specified period

[0521] Data processing / data calculation: The device uses the access token to send a request to the calendar API and receives JSON data of the schedule information.

[0522] Output: User schedule information (JSON format)

[0523] Specific operation: The device sends an HTTP request to the calendar API, and the API returns schedule information for the specified period.

[0524] Step 3: Analyze and categorize the data

[0525] Description: Analyzes the acquired schedule information and categorizes each event. The device uses natural language processing technology to analyze the title and description of each event.

[0526] Input: User's schedule information (JSON format)

[0527] Data processing / data calculation: The device uses an NLP model to analyze the schedule information and classifies each event into categories such as "meeting," "project work," and "break" through string analysis and machine learning.

[0528] Output: Date information categorized by category

[0529] Specific operation: The device inputs the title and description of the schedule information into the NLP model and outputs the categorized results.

[0530] Step 4: Generate summaries

[0531] Description: Summarizes work hours based on analyzed data. The device aggregates the time for each category and generates summary information for the specified period (e.g., daily, weekly, monthly).

[0532] Input: Date information categorized by category

[0533] Data processing / data calculation: The device calculates the time for each category and applies an algorithm to calculate the total time.

[0534] Output: Aggregated time results for each category

[0535] Specific operation: The device aggregates the schedule information for each category by hour and generates daily, weekly, and monthly summary results.

[0536] Step 5: View the results

[0537] Description: Displays summarized results. Stores the results on the server and allows users to access them through a web interface or dedicated application.

[0538] Input: Aggregation results of time by category

[0539] Data processing / data calculation: The terminal sends the aggregated results in JSON format to the server and stores them in a database.

[0540] Output: Graphs and tables of summarized results

[0541] Specific operation: The terminal visually displays the summary results, and the latest aggregated results are displayed each time the user accesses the terminal.

[0542] (Application example 1)

[0543] 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."

[0544] Conventional work schedule management in factories is often managed individually by human workers, which is inefficient. Furthermore, it is difficult to grasp how much time a robot is spending on each process, making it difficult to improve productivity and optimize time management. The objective of this invention is to provide a system that can efficiently acquire and analyze user schedule information, manage work schedules within the factory, calculate the total time for each work category, and be installed and used on robots.

[0545] 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.

[0546] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summary results, means for managing the work schedule within the factory and calculating the total time for each task category, and means installed on the factory robots. This allows users and managers to centrally manage the work schedule within the factory and understand the time allocation for each specific task.

[0547] "Means for authenticating user information" refers to means for verifying the legitimacy of a user when accessing a system.

[0548] The "means for acquiring schedule information" is a means for collecting the user's schedule data from an external calendar service or the like.

[0549] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing collected schedule data and classifying it into specific task categories.

[0550] "Means for summarizing task times based on analysis results" refers to means for summarizing task times for each category and total time based on the analyzed data.

[0551] The "means for displaying the summary results" is a means for visually presenting the summarized task times and other analysis results to the user.

[0552] "Means for managing work schedules within a factory" refers to a means for centrally organizing and managing the schedules of each work task within a factory.

[0553] The "means for calculating the total time for each task category" is a means for calculating the total task time allocated to each category within a specific period.

[0554] The "means to be installed in the robots in the factory" refers to a means for incorporating the work schedule management system into the robots in the factory.

[0555] The system of the present invention efficiently acquires and analyzes the user's schedule information, manages work schedules within the factory, calculates the total time for each work category, and can be installed and used on a robot.

[0556] Authenticate user information

[0557] When a user logs in to the system, the server obtains user information using OAuth 2.0 authentication. This process verifies that the user is a legitimate user.

[0558] Obtaining schedule information

[0559] The device obtains the user's schedule information via the Google Calendar API. At this time, it accesses the user's calendar and obtains JSON data containing detailed information about the event (start time, end time, title, and description).

[0560] Data analysis and categorization

[0561] The device analyzes the schedule information and categorizes each event using natural language processing (NLP) technology, utilizing string analysis and machine learning models to automatically classify events into categories such as "welding work," "quality check," and "packaging."

[0562] Generate time summaries

[0563] The device then uses the analyzed data to summarize the total time spent in each task category, aggregating the time spent in each category according to existing rules and algorithms, and generating summary information for periods such as daily, weekly, or monthly.

[0564] Displaying the results

[0565] The summarized results are stored on a server and can be accessed by the user through a web interface or a dedicated app. The terminal visualizes the results in graphs and tables, allowing the user to intuitively understand the time allocation for each task.

[0566] Installation on factory robots

[0567] The system can be installed on robots in factories, allowing the robots to automatically manage work schedules and keep track of the progress of each work category in real time.

[0568] Specific examples

[0569] For example, if a user wants to manage the schedule of a factory robot, the following format is possible:

[0570] October 1, 2023, 9:00 - 11:00: "Welding"

[0571] October 1, 2023, 11:30 - 12:30: "Quality Check"

[0572] October 1, 2023, 13:00 - 15:00: "Packaging"

[0573] The system takes this schedule data, categorizes it using NLP technology, and calculates and displays the total time for each work category.

[0574] Hardware and software used

[0575] Hardware: Robot built-in computer, API communication module

[0576] Software: Python (programming language), Google Calendar API (scheduling data acquisition), OAuth2.0 (robot authentication), NLP libraries (e.g., SpaCy, NLTK), Pandas (data processing and visualization)

[0577] Example of generated AI prompt

[0578] "Design an application that automatically calculates the total time for each task category from calendar data, categorizes it using NLP, and summarizes it by day, week, and month."

[0579] The above is a specific embodiment of the system of the present invention. This system allows users and managers to centrally manage work schedules within a factory and understand the time allocation for each specific task.

[0580] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0581] Step 1:

[0582] The server authenticates user information. When a user logs in to the system, it obtains user information using OAuth2.0 authentication. Through this authentication process, the server verifies that the user is a legitimate user. The input is the user's authentication information, and the output is authenticated user information.

[0583] Step 2:

[0584] The device obtains schedule information. Based on the authenticated user information, the device uses the Google Calendar API to obtain the user's schedule information. At this time, the device accesses the user's calendar and obtains JSON data containing detailed event information (start time, end time, title, and description). The input is the authenticated user information and a request for calendar information, and the output is schedule information in JSON format.

[0585] Step 3:

[0586] The terminal analyzes and categorizes the acquired schedule information. The acquired schedule information is analyzed using natural language processing (NLP) technology, and each schedule is categorized. Specifically, string analysis and machine learning models are used to automatically classify schedules into categories such as "welding work," "quality check," and "packaging." The input is schedule information in JSON format, and the output is categorized schedule data.

[0587] Step 4:

[0588] The terminal summarizes work hours based on the analysis results. Based on the analyzed data, it calculates the total time for each work category. According to existing rules and algorithms, it aggregates the time for each category and generates summary information for periods such as daily, weekly, or monthly. The input is categorized schedule data, and the output is summarized time data.

[0589] Step 5:

[0590] The server displays the summarized results. It saves the summarized results and allows users to access them through a web interface or a dedicated app. The terminal visualizes the aggregated results in graphs and tables, allowing users to intuitively understand the time allocation for each task. The input is summarized time data, and the output is visualized data in graphs and tables.

[0591] Step 6:

[0592] The terminal is installed on the factory robot. By incorporating the system into the robot in the factory, the robot can automatically manage its work schedule and monitor the progress of each work category in real time. The input is the system installation package, and the output is the installed robot system.

[0593] 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.

[0594] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[0595] User Authentication

[0596] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[0597] Obtaining schedule information

[0598] The device obtains the user's schedule information via the calendar API. Here, detailed information (e.g., start time, end time, title, description) of events stored in the user's calendar is obtained in JSON format.

[0599] Data analysis and categorization

[0600] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. Based on the results of this analysis, it then automatically assigns each appointment an appropriate category (e.g., "meeting," "project work," "break").

[0601] Introducing the Emotion Engine

[0602] The device is equipped with an emotion engine that uses data acquired from the user's schedule and conversation history to recognize the user's emotions. This emotion engine uses machine learning models to estimate the user's emotional state and generate emotion tags such as "stress," "satisfaction," and "dissatisfaction."

[0603] Summarizing business hours

[0604] The device summarizes daily, weekly, and monthly working hours based on categorized schedule data. The aggregated results calculate the time spent by category and also include emotion tags generated by the emotion engine.

[0605] Displaying results and integrating emotional information

[0606] The device then formats the summary results into graphs and tables, visualizing them for intuitive understanding by the user. At the same time, emotion tags obtained from the emotion engine are also displayed, providing emotional information related to each task.

[0607] Specific examples

[0608] Summarizing the working hours of the day

[0609] Let's say a user has the following schedule from 9am to 6pm:

[0610] 09:00 - 10:00: Team meeting (emotional state: stress)

[0611] 11:00 - 12:00: Project A work (emotional state: satisfied)

[0612] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[0613] 15:00 - 16:00: Project B development (emotional state: concentration)

[0614] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[0615] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[0616] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[0617] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[0618] Based on this, the terminal generates and displays the summary result as follows:

[0619] Total meeting time: 1 hour (emotional state: stressed)

[0620] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[0621] Client meeting time: 1 hour (emotional state: anxiety)

[0622] These results are stored on a server and are accessible to users through a web interface or dedicated application. Based on the emotional information displayed in the summary results, users can manage their own work time and emotions, which can help improve work efficiency and reduce stress.

[0623] The system of the present invention allows users to not only manage their work time but also understand their emotional state, enabling more comprehensive self-management, which is expected to improve both time efficiency and mental health.

[0624] The processing flow will be explained below.

[0625] Step 1:

[0626] The user logs in to the system. The user clicks the login button on the screen and grants access to calendar information through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[0627] Step 2:

[0628] The device uses the obtained authentication token to send a request to the calendar API, which returns the user's calendar information (event details) in JSON format.

[0629] Step 3:

[0630] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[0631] Step 4:

[0632] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[0633] Step 5:

[0634] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[0635] Step 6:

[0636] The device uses an emotion engine to analyze schedule information and conversation history to estimate the user's emotional state. The emotion engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[0637] Step 7:

[0638] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data and emotion tags generated by the emotion engine. The aggregated results include the total time for each category and the corresponding emotion information.

[0639] Step 8:

[0640] The device then formats the summarized results into graphs and tables, visualizing the data for easy visual understanding. The emotion engine also displays emotion tags, providing emotional information related to each task.

[0641] Step 9:

[0642] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[0643] Step 10:

[0644] Users access the summary results through a web interface or a dedicated application. The latest summary results are displayed even when users re-login to the system.

[0645] Step 11:

[0646] Users can review their own working hours and emotional state based on the displayed summary results and emotional information, which makes it easier to improve time management and self-evaluate, and is expected to improve stress management and work efficiency.

[0647] Example 2

[0648] 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."

[0649] Conventional work management systems provide functions for acquiring and analyzing a user's schedule information to summarize work hours, but do not take into account the user's emotional state. As a result, users have had to use separate tools in situations where they need to manage not only their work efficiency but also their mental state. This invention aims to solve this problem by providing a system that not only efficiently acquires and analyzes a user's schedule information and summarizes work hours, but also recognizes the user's emotional state and integrates it into the results.

[0650] 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.

[0651] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for recognizing the user's emotional state and generating an emotion tag, and means for displaying the summarized result together with the emotion tag. This allows the user to manage their work time and emotional state in a unified manner, enabling efficient time management and improved mental health.

[0652] "Means for authenticating user information" refers to means for verifying that a user is a legitimate user when the user accesses the system.

[0653] The "means for acquiring schedule information" refers to the means for extracting schedule information from the calendar or schedule management tool used by the user and importing it into the system.

[0654] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing acquired schedule information and classifying it into different categories such as "meetings" and "project work" based on its contents.

[0655] The "means for summarizing task time" is a means for summarizing a user's task activities for each period, such as daily, weekly, or monthly, based on analyzed and categorized schedule information.

[0656] The "means for recognizing a user's emotional state and generating an emotion tag" refers to a means for using a machine learning model or an emotion analysis engine to estimate a user's emotional state from their schedule information and conversation history, and generating an emotion tag that reflects the results.

[0657] The "means for displaying summary results together with emotion tags" refers to a means for visualizing the summary results of work hours in graph or table format, and further displaying emotion tags related to each work hour.

[0658] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[0659] User Authentication

[0660] When a user logs in to a system, user information is first obtained via the OAuth2.0 authentication protocol. This process allows the server to verify that the user is a legitimate user. A library such as "OAuthLib" is used for OAuth2.0 authentication.

[0661] Obtaining schedule information

[0662] The device retrieves the user's schedule information via a calendar API (e.g., Google Calendar API). The schedule information includes the start time, end time, title, and description of each event. The retrieved information is saved in JSON format.

[0663] Data analysis and categorization

[0664] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. NLP technology uses tools such as "spaCy" and "Natural Language Toolkit (NLTK)." Based on the analysis results, each appointment is automatically assigned a category, such as "meeting," "project work," or "break."

[0665] Introducing the Emotion Engine

[0666] The device uses an emotion engine to recognize the user's emotional state based on the user's schedule information and conversation history. The emotion engine uses machine learning models (e.g., BERT and GPT). This engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[0667] Summarizing business hours

[0668] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data. The summary results include total time and emotion tags for each category. For example, the total time spent in "meetings" or "project work" is displayed along with the corresponding emotion.

[0669] Displaying results and integrating emotional information

[0670] The device then formats the summarized results into graphs and tables, visualizing them in an intuitive way for the user. The results are also displayed with emotion tags, providing emotional information related to each task. For example, a bar graph showing the emotional state corresponding to each task is displayed.

[0671] Saving and Accessing Results

[0672] The server stores the generated summary results in a database. When a user logs into the system through a web interface or a dedicated application, the server reads and displays the stored summary results.

[0673] Specific examples

[0674] Let's say a user has the following schedule from 9am to 6pm:

[0675] 09:00 - 10:00: Team meeting (emotional state: stress)

[0676] 11:00 - 12:00: Project A work (emotional state: satisfied)

[0677] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[0678] 15:00 - 16:00: Project B development (emotional state: concentration)

[0679] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[0680] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[0681] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[0682] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[0683] Based on this, a summary result is generated and displayed:

[0684] Total meeting time: 1 hour (emotional state: stressed)

[0685] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[0686] Client meeting time: 1 hour (emotional state: anxiety)

[0687] Example prompts to input to the generative AI model

[0688] "Please introduce a system that helps users manage their daily work hours and emotional state. This system not only acquires and analyzes the user's schedule information and summarizes their work hours, but also recognizes the user's emotional state and integrates it into the results. Emotional states include stress, satisfaction, anxiety, and concentration. Please explain with specific examples."

[0689] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0690] Processing flow

[0691] Step 1: User authentication

[0692] When a user logs in to the system, the server obtains user information using the OAuth2.0 authentication protocol.

[0693] Input: User login information

[0694] Output: Authentication token

[0695] Specific behavior: The user is redirected to an authentication page and enters their authentication information. After that, if the authentication is successful, an authentication token is returned to the server, and the server uses this token to retrieve user information.

[0696] Step 2: Obtaining schedule information

[0697] The device uses the user's authentication token to access the calendar API (e.g., Google Calendar API) and obtain schedule information.

[0698] Input: Authentication Token

[0699] Output: Schedule information (JSON format)

[0700] Specific operation: The device uses the acquired authentication token to send a request to the calendar API and obtains the user's schedule information (start time, end time, title, description) in JSON format.

[0701] Step 3: Analyze and categorize the data

[0702] The device analyzes the schedule information it acquires, uses NLP technology to understand the content, and assigns a category.

[0703] Input: Schedule information (JSON format)

[0704] Output: Categorized schedule information

[0705] How it works: The device uses an NLP library (e.g., spaCy, NLTK) to parse the schedule information and automatically assign a category such as "meeting" or "project work" based on the content of each appointment.

[0706] Step 4: Implementing the Emotion Engine

[0707] Based on the schedule information acquired and analyzed by the device, an emotion engine is used to recognize the user's emotional state and generate an emotion tag.

[0708] Input: Categorized schedule information

[0709] Output: Emotion tag

[0710] Specific operation: The device uses machine learning models (e.g., BERT, GPT) to analyze the user's emotional state from the text content of the schedule information and conversation history, and generates emotion tags such as "stress" and "satisfaction."

[0711] Step 5: Summarize your working hours

[0712] Based on device-categorized schedule data, the system summarizes daily, weekly, and monthly work hours and integrates emotion tags.

[0713] Input: Categorized schedule information, emotion tags

[0714] Output: Summarized results (working hours and sentiment tags)

[0715] Specific operation: The device aggregates work hours by category, collects emotion tags associated with each work hour, and generates a summary result.

[0716] Step 6: Displaying the results and integrating emotional information

[0717] The device formats the summary results into graphs and tables and displays them to the user along with emotion tags.

[0718] Input: Summarization result (working hours and sentiment tags)

[0719] Output: Visualized results (graphs and tables)

[0720] Specific operation: The device uses a data visualization tool (e.g., Matplotlib or D3.js) to format the work hours and emotion tags into an easily understandable format (e.g., bar graph, pie chart, or table) and display them to the user.

[0721] Step 7: Saving and Accessing Results

[0722] The server stores the generated summarization results in a database for user access.

[0723] Input: Summarization result (working hours and sentiment tags)

[0724] Output: Results stored in the database, displayed to the user

[0725] Specific operation: The server saves the summarized results in a database, and when a user logs in through a web interface or a dedicated application, the server loads and displays the saved results.

[0726] (Application example 2)

[0727] 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."

[0728] In order to improve the efficiency of factory work and the performance of workers (robots), it is necessary to not only manage work schedules but also to take into account the emotional state of workers while they are working. However, conventional systems only manage work time and do not recognize or integrate emotional states, making it difficult to optimize performance or detect anomalies.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0730] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the categorized schedule information, means for integrating emotional information into the summarized task times, and means for displaying the summarization results and the emotional information. This enables efficient management of work schedules in factories, as well as optimization of worker (robot) performance and anomaly detection.

[0731] A "means for authenticating user information" is a technique or process for authenticating a legitimate user to a system.

[0732] The "means for acquiring schedule information" refers to a technique or process for collecting data related to a user's schedule or dates.

[0733] The "analysis and categorization means" refers to a technique or process for analyzing acquired schedule information and classifying it into categories based on specific criteria.

[0734] A "summarization method" is a technique or process for aggregating and summarizing analyzed data.

[0735] A "means for integrating emotional information" is a technique or process for recognizing the emotional state of a user or worker and combining it with other data.

[0736] "Display means" refers to a technique or process for visually displaying the summarized results and integrated affective information.

[0737] "Means for analyzing based on natural language processing" refers to a process of understanding schedule information using technology that mechanically analyzes text data.

[0738] A "Calendar API" is an application program interface for obtaining schedule information.

[0739] This invention is a system that efficiently acquires and analyzes a user's schedule information and automatically summarizes work hours, and by integrating and displaying emotional information, aims to optimize work efficiency and improve performance.

[0740] User Authentication

[0741] The server obtains user information through OAuth 2.0 authentication and verifies that the user is a legitimate user. This process uses an authentication server and a token.

[0742] Obtaining schedule information

[0743] The server then retrieves the user's schedule information via the calendar API. The retrieved information includes, for example, start time, end time, title, description, etc., and is saved in JSON format.

[0744] Data analysis and categorization

[0745] The server uses natural language processing (NLP) technology to analyze the acquired schedule information and assign an appropriate category to each event, such as "meeting," "work," or "break."

[0746] Introducing the Emotion Engine

[0747] Furthermore, the server uses an emotion engine to recognize emotions from the user's schedule information, conversation history, etc. This emotion engine uses a machine learning model to generate emotion tags such as "stress," "satisfaction," and "anxiety."

[0748] Summarizing business hours

[0749] The server then summarizes work hours based on the categorized schedule data, including total hours and emotion tags for each category.

[0750] Displaying results and integrating emotional information

[0751] Finally, the server displays the summary results and emotional information in an integrated format using graphs and tables, designed to be intuitive for users, allowing them to grasp their schedule and emotional state at a glance.

[0752] As a concrete example, consider a user with the following schedule:

[0753] 09:00 - 10:00: Assembling parts (emotional state: concentration)

[0754] 11:00 - 12:00: Examination work (emotional state: anxiety)

[0755] In this case, the server will summarize the data as follows:

[0756] Parts assembly time: 1 hour (emotional state: concentration)

[0757] Test duration: 1 hour (emotional state: anxiety)

[0758] Prompt Sentence Examples

[0759] An example of a prompt for a generative AI model is:

[0760] "If a user performs a parts assembly task from 09:00 to 10:00 and an inspection task from 11:00 to 12:00, generate a summary result that includes the emotional state of each task."

[0761] This will enable optimization of work efficiency and performance in factories and other work environments by managing users' schedules and understanding their emotional states.

[0762] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0763] Step 1:

[0764] Perform user authentication.

[0765] The server obtains user information using OAuth 2.0 authentication. It requires the user's authentication information as input. The server sends a request to the authentication server to obtain a token. It uses this token to verify the user's legitimate access. The output is an access token.

[0766] Step 2:

[0767] Get schedule information.

[0768] The server retrieves the user's schedule information using the calendar API. An access token is required as input. The token is used to retrieve the schedule data from the calendar service and save it in JSON format. The output is the retrieved schedule information.

[0769] Step 3:

[0770] Analyze and categorize schedule information.

[0771] The server analyzes the retrieved schedule information using natural language processing (NLP) techniques. It takes the retrieved schedule information as input. The server analyzes the title and description and assigns an appropriate category to each event, such as "meeting," "work," or "break." The output is the analyzed, categorized schedule information.

[0772] Step 4:

[0773] Recognize emotional information.

[0774] The server uses an emotion engine to recognize user emotions from schedule information and related data. Categorized schedule information is required as input. Using a machine learning model, the server generates emotion tags such as "stress," "satisfaction," and "anxiety." The output is schedule information with emotion tags.

[0775] Step 5:

[0776] Summarize your work hours.

[0777] The server summarizes working hours based on categorized schedule information. It requires schedule information with emotion tags as input. The server calculates the total time for each category and integrates the associated emotion tags. The output is the summarized working hours and emotion information.

[0778] Step 6:

[0779] Display the results.

[0780] The server displays summarized task time and emotion information. The input required is summarized task time and emotion information. The server formats this in graphs and tables, generating an interface that users can intuitively understand. The output is visualized data.

[0781] This allows users to understand their schedule and emotional state at a glance, enabling more efficient time management and mental health management.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] [Third embodiment]

[0786] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0787] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0788] 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).

[0789] 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.

[0790] 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.

[0791] 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).

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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."

[0798] The system of the present invention efficiently acquires and analyzes a user's schedule information, and automatically summarizes and provides the summary of the user's working hours. Specific embodiments of the present invention will be described below.

[0799] User Authentication

[0800] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[0801] Obtaining schedule information

[0802] The device obtains the user's schedule information via the Google Calendar API. Here, the device accesses the user's calendar and obtains JSON data including detailed event information (e.g., start time, end time, title, and description).

[0803] Data analysis and categorization

[0804] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to categorize each event. Utilizing string analysis and machine learning models, it automatically categorizes events into categories such as "meetings," "project work," and "breaks."

[0805] Generate summaries

[0806] The device summarizes the user's work time based on the analyzed data. Time is aggregated by category according to existing rules and algorithms, and summary information is generated for periods such as daily, weekly, and monthly.

[0807] Displaying the results

[0808] The results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visualizes the results in graphs and tables, allowing users to intuitively understand the distribution of work time.

[0809] Specific examples

[0810] Summarizing the working hours of the day

[0811] Let's say a user has the following appointments between 9am and 6pm:

[0812] 09:00 - 10:00: Team meeting

[0813] 11:00 - 12:00: Project A work

[0814] 13:00 - 14:00: Client meeting

[0815] 15:00 - 16:00: Project B development

[0816] The device retrieves these events and, through NLP techniques, categorizes them as follows:

[0817] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[0818] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[0819] Based on this, the terminal generates a summary and displays it as follows:

[0820] Total meeting time: 2 hours

[0821] Project duration: 2 hours

[0822] Other: 0 hours

[0823] Summarizing the working week

[0824] For example, if a user has the same schedule every day from Monday to Friday, the device will generate the following weekly summary results:

[0825] Total meeting time (weekly): 10 hours (2 hours / day, 5 days)

[0826] Project work hours (week): 10 hours (2 hours / day, 5 days)

[0827] The results are stored on a server and updated information is provided each time the user accesses the site.

[0828] The system of the present invention allows users to easily understand their own working hours, which can be used to improve time management and self-evaluation. Each of the above functions contributes greatly to improving user productivity and efficient time management.

[0829] The processing flow will be explained below.

[0830] Step 1:

[0831] The user logs in to the system. The user clicks the login button on the screen and grants access to their Google account through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[0832] Step 2:

[0833] The device uses the obtained authentication token to send a request to the Google Calendar API, which returns the user's calendar information (event details) in JSON format.

[0834] Step 3:

[0835] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[0836] Step 4:

[0837] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[0838] Step 5:

[0839] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[0840] Step 6:

[0841] Based on the scheduled data categorized by device, daily, weekly, and monthly working hours are summarized. Specifically, the total time for each category is calculated and aggregated results are generated for each period.

[0842] Step 7:

[0843] The terminal formats the summarized results into graphs and tables, visualizing the data so that it is easy for the user to understand visually.

[0844] Step 8:

[0845] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[0846] Step 9:

[0847] Users access the summary results through a web interface or a dedicated application, ensuring that the latest summary results are displayed even when users re-login to the system.

[0848] Step 10:

[0849] Users can review their own work hours based on the displayed summary results, which allows them to improve their time management and self-evaluate.

[0850] Example 1

[0851] 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."

[0852] Conventional schedule management systems collect and analyze users' schedule information, but the analysis results are often not presented in an intuitive and easy-to-understand format. Furthermore, summarizing and categorizing work time is often done manually, placing a significant burden on users. Therefore, more advanced technology was needed to efficiently manage users' work time and improve productivity.

[0853] 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.

[0854] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summarization results, means for analyzing the schedule information using natural language processing technology, means for aggregating the acquired schedule information into summary information for multiple periods, and means for visually displaying the summary information. This enables users to efficiently manage their own task times and improve productivity.

[0855] "User information" refers to the user's identification information used in the authentication process, specifically, an email address, a password, etc.

[0856] "Schedule information" refers to detailed information (start time, end time, title, description, etc.) of an event listed on a user's calendar.

[0857] "Analysis" refers to the process of using natural language processing technology to understand the content of the acquired schedule information and classify it into specific categories.

[0858] "Categorization" refers to the process of classifying analyzed schedule information into specific categories such as "meetings," "project work," and "breaks."

[0859] "Summarization" refers to the process of summarizing task hours for a specific period based on analyzed data and providing it to the user.

[0860] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language, and includes machine learning models and string analysis algorithms.

[0861] "API" refers to an interface for exchanging data and functions between applications, such as a calendar API.

[0862] "Summary information" refers to information that summarizes the aggregated work hours, category information, etc. in a format that is easy for the user to understand.

[0863] "Visual display" refers to the process of presenting summary information to users in the form of graphs or tables, allowing them to intuitively understand the information.

[0864] To implement the present invention, it is necessary to implement the system program through the following procedure: The system is designed to improve the efficiency of users' work time management and productivity.

[0865] User Authentication

[0866] When a user logs in to the system, they first obtain user information using OAuth2.0 authentication. The device uses the OAuth2.0 framework to send a request to the authentication server and obtain an access token. This token is then used to obtain the user's identification information (such as name and email address) from the authentication server.

[0867] Obtaining schedule information

[0868] The device uses the calendar API to obtain the user's schedule information. The data obtained through this API is in JSON format and includes details such as the start time, end time, title, and description of each event.

[0869] Data analysis and categorization

[0870] The device parses the acquired schedule information and analyzes each event using natural language processing (NLP) techniques. This analysis uses machine learning models and string analysis algorithms. The analyzed information classifies each event into categories such as "meetings," "project work," and "breaks."

[0871] Generate summaries

[0872] The device then uses the analyzed data to summarize the user's work time, aggregating the time spent by category on a daily, weekly, or monthly basis according to specific rules and algorithms.

[0873] Displaying the results

[0874] The aggregated results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visually displays the summarized results in the form of graphs and tables, allowing users to intuitively understand the distribution of work time.

[0875] Specific examples

[0876] Summarizing the working hours of the day

[0877] Let's say a user has the following appointments between 9am and 6pm:

[0878] 09:00 - 10:00: Team meeting

[0879] 11:00 - 12:00: Project A work

[0880] 13:00 - 14:00: Client meeting

[0881] 15:00 - 16:00: Project B development

[0882] The device retrieves these events and uses NLP techniques to categorize them as follows:

[0883] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[0884] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[0885] Based on this, the terminal generates a summary and displays it as follows:

[0886] Total meeting time: 2 hours

[0887] Project duration: 2 hours

[0888] Other: 0 hours

[0889] Prompt Sentence Examples

[0890] "Get the user's schedule information from the Calendar API and generate a categorical process description using natural language processing techniques."

[0891] By implementing this system, users can efficiently manage their work time and significantly improve their productivity. In addition, by visually displaying the summary results, users can intuitively understand how they use their time.

[0892] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0893] Step 1: User authentication

[0894] Description: When a user logs in to the system, the authentication process begins. Specifically, the user enters their email address and password on the login screen and presses the "Login" button.

[0895] Input: Email address, password

[0896] Data processing / data calculation: The device uses the OAuth 2.0 framework to send a request to the authentication server and obtain an access token. This token is used to obtain user information.

[0897] Output: Access token, user information (name, email address, etc.)

[0898] Specific operation: The terminal sends a request to the authentication server, which verifies the user information and returns an access token.

[0899] Step 2: Obtaining schedule information

[0900] Description: Gets the user's schedule information. The device uses the Calendar API to request schedule information for the specified period.

[0901] Input: Access token, information for the specified period

[0902] Data processing / data calculation: The device uses the access token to send a request to the calendar API and receives JSON data of the schedule information.

[0903] Output: User schedule information (JSON format)

[0904] Specific operation: The device sends an HTTP request to the calendar API, and the API returns schedule information for the specified period.

[0905] Step 3: Analyze and categorize the data

[0906] Description: Analyzes the acquired schedule information and categorizes each event. The device uses natural language processing technology to analyze the title and description of each event.

[0907] Input: User's schedule information (JSON format)

[0908] Data processing / data calculation: The device uses an NLP model to analyze the schedule information and classifies each event into categories such as "meeting," "project work," and "break" through string analysis and machine learning.

[0909] Output: Date information categorized by category

[0910] Specific operation: The device inputs the title and description of the schedule information into the NLP model and outputs the categorized results.

[0911] Step 4: Generate summaries

[0912] Description: Summarizes work hours based on analyzed data. The device aggregates the time for each category and generates summary information for the specified period (e.g., daily, weekly, monthly).

[0913] Input: Date information categorized by category

[0914] Data processing / data calculation: The device calculates the time for each category and applies an algorithm to calculate the total time.

[0915] Output: Aggregated time results for each category

[0916] Specific operation: The device aggregates the schedule information for each category by hour and generates daily, weekly, and monthly summary results.

[0917] Step 5: View the results

[0918] Description: Displays summarized results. Stores the results on the server and allows users to access them through a web interface or dedicated application.

[0919] Input: Aggregation results of time by category

[0920] Data processing / data calculation: The terminal sends the aggregated results in JSON format to the server and stores them in a database.

[0921] Output: Graphs and tables of summarized results

[0922] Specific operation: The terminal visually displays the summary results, and the latest aggregated results are displayed each time the user accesses the terminal.

[0923] (Application example 1)

[0924] 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."

[0925] Conventional work schedule management in factories is often managed individually by human workers, which is inefficient. Furthermore, it is difficult to grasp how much time a robot is spending on each process, making it difficult to improve productivity and optimize time management. The objective of this invention is to provide a system that can efficiently acquire and analyze user schedule information, manage work schedules within the factory, calculate the total time for each work category, and be installed and used on robots.

[0926] 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.

[0927] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summary results, means for managing the work schedule within the factory and calculating the total time for each task category, and means installed on the factory robots. This allows users and managers to centrally manage the work schedule within the factory and understand the time allocation for each specific task.

[0928] "Means for authenticating user information" refers to means for verifying the legitimacy of a user when accessing a system.

[0929] The "means for acquiring schedule information" is a means for collecting the user's schedule data from an external calendar service or the like.

[0930] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing collected schedule data and classifying it into specific task categories.

[0931] "Means for summarizing task times based on analysis results" refers to means for summarizing task times for each category and total time based on the analyzed data.

[0932] The "means for displaying the summary results" is a means for visually presenting the summarized task times and other analysis results to the user.

[0933] "Means for managing work schedules within a factory" refers to a means for centrally organizing and managing the schedules of each work task within a factory.

[0934] The "means for calculating the total time for each task category" is a means for calculating the total task time allocated to each category within a specific period.

[0935] The "means to be installed in the robots in the factory" refers to a means for incorporating the work schedule management system into the robots in the factory.

[0936] The system of the present invention efficiently acquires and analyzes the user's schedule information, manages work schedules within the factory, calculates the total time for each work category, and can be installed and used on a robot.

[0937] Authenticate user information

[0938] When a user logs in to the system, the server obtains user information using OAuth 2.0 authentication. This process verifies that the user is a legitimate user.

[0939] Obtaining schedule information

[0940] The device obtains the user's schedule information via the Google Calendar API. At this time, it accesses the user's calendar and obtains JSON data containing detailed information about the event (start time, end time, title, and description).

[0941] Data analysis and categorization

[0942] The device analyzes the schedule information and categorizes each event using natural language processing (NLP) technology, utilizing string analysis and machine learning models to automatically classify events into categories such as "welding work," "quality check," and "packaging."

[0943] Generate time summaries

[0944] The device then uses the analyzed data to summarize the total time spent in each task category, aggregating the time spent in each category according to existing rules and algorithms, and generating summary information for periods such as daily, weekly, or monthly.

[0945] Displaying the results

[0946] The summarized results are stored on a server and can be accessed by the user through a web interface or a dedicated app. The terminal visualizes the results in graphs and tables, allowing the user to intuitively understand the time allocation for each task.

[0947] Installation on factory robots

[0948] The system can be installed on robots in factories, allowing the robots to automatically manage work schedules and keep track of the progress of each work category in real time.

[0949] Specific examples

[0950] For example, if a user wants to manage the schedule of a factory robot, the following format is possible:

[0951] October 1, 2023, 9:00 - 11:00: "Welding"

[0952] October 1, 2023, 11:30 - 12:30: "Quality Check"

[0953] October 1, 2023, 13:00 - 15:00: "Packaging"

[0954] The system takes this schedule data, categorizes it using NLP technology, and calculates and displays the total time for each work category.

[0955] Hardware and software used

[0956] Hardware: Robot built-in computer, API communication module

[0957] Software: Python (programming language), Google Calendar API (scheduling data acquisition), OAuth2.0 (robot authentication), NLP libraries (e.g., SpaCy, NLTK), Pandas (data processing and visualization)

[0958] Example of generated AI prompt

[0959] "Design an application that automatically calculates the total time for each task category from calendar data, categorizes it using NLP, and summarizes it by day, week, and month."

[0960] The above is a specific embodiment of the system of the present invention. This system allows users and managers to centrally manage work schedules within a factory and understand the time allocation for each specific task.

[0961] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0962] Step 1:

[0963] The server authenticates user information. When a user logs in to the system, it obtains user information using OAuth2.0 authentication. Through this authentication process, the server verifies that the user is a legitimate user. The input is the user's authentication information, and the output is authenticated user information.

[0964] Step 2:

[0965] The device obtains schedule information. Based on the authenticated user information, the device uses the Google Calendar API to obtain the user's schedule information. At this time, the device accesses the user's calendar and obtains JSON data containing detailed event information (start time, end time, title, and description). The input is the authenticated user information and a request for calendar information, and the output is schedule information in JSON format.

[0966] Step 3:

[0967] The terminal analyzes and categorizes the acquired schedule information. The acquired schedule information is analyzed using natural language processing (NLP) technology, and each schedule is categorized. Specifically, string analysis and machine learning models are used to automatically classify schedules into categories such as "welding work," "quality check," and "packaging." The input is schedule information in JSON format, and the output is categorized schedule data.

[0968] Step 4:

[0969] The terminal summarizes work hours based on the analysis results. Based on the analyzed data, it calculates the total time for each work category. According to existing rules and algorithms, it aggregates the time for each category and generates summary information for periods such as daily, weekly, or monthly. The input is categorized schedule data, and the output is summarized time data.

[0970] Step 5:

[0971] The server displays the summarized results. It saves the summarized results and allows users to access them through a web interface or a dedicated app. The terminal visualizes the aggregated results in graphs and tables, allowing users to intuitively understand the time allocation for each task. The input is summarized time data, and the output is visualized data in graphs and tables.

[0972] Step 6:

[0973] The terminal is installed on the factory robot. By incorporating the system into the robot in the factory, the robot can automatically manage its work schedule and monitor the progress of each work category in real time. The input is the system installation package, and the output is the installed robot system.

[0974] 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.

[0975] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[0976] User Authentication

[0977] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[0978] Obtaining schedule information

[0979] The device obtains the user's schedule information via the calendar API. Here, detailed information (e.g., start time, end time, title, description) of events stored in the user's calendar is obtained in JSON format.

[0980] Data analysis and categorization

[0981] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. Based on the results of this analysis, it then automatically assigns each appointment an appropriate category (e.g., "meeting," "project work," "break").

[0982] Introducing the Emotion Engine

[0983] The device is equipped with an emotion engine that uses data acquired from the user's schedule and conversation history to recognize the user's emotions. This emotion engine uses machine learning models to estimate the user's emotional state and generate emotion tags such as "stress," "satisfaction," and "dissatisfaction."

[0984] Summarizing business hours

[0985] The device summarizes daily, weekly, and monthly working hours based on categorized schedule data. The aggregated results calculate the time spent by category and also include emotion tags generated by the emotion engine.

[0986] Displaying results and integrating emotional information

[0987] The device then formats the summary results into graphs and tables, visualizing them for intuitive understanding by the user. At the same time, emotion tags obtained from the emotion engine are also displayed, providing emotional information related to each task.

[0988] Specific examples

[0989] Summarizing the working hours of the day

[0990] Let's say a user has the following schedule from 9am to 6pm:

[0991] 09:00 - 10:00: Team meeting (emotional state: stress)

[0992] 11:00 - 12:00: Project A work (emotional state: satisfied)

[0993] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[0994] 15:00 - 16:00: Project B development (emotional state: concentration)

[0995] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[0996] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[0997] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[0998] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[0999] Based on this, the terminal generates and displays the summary result as follows:

[1000] Total meeting time: 1 hour (emotional state: stressed)

[1001] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[1002] Client meeting time: 1 hour (emotional state: anxiety)

[1003] These results are stored on a server and are accessible to users through a web interface or dedicated application. Based on the emotional information displayed in the summary results, users can manage their own work time and emotions, which can help improve work efficiency and reduce stress.

[1004] The system of the present invention allows users to not only manage their work time but also understand their emotional state, enabling more comprehensive self-management, which is expected to improve both time efficiency and mental health.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The user logs in to the system. The user clicks the login button on the screen and grants access to calendar information through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[1008] Step 2:

[1009] The device uses the obtained authentication token to send a request to the calendar API, which returns the user's calendar information (event details) in JSON format.

[1010] Step 3:

[1011] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[1012] Step 4:

[1013] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[1014] Step 5:

[1015] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[1016] Step 6:

[1017] The device uses an emotion engine to analyze schedule information and conversation history to estimate the user's emotional state. The emotion engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[1018] Step 7:

[1019] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data and emotion tags generated by the emotion engine. The aggregated results include the total time for each category and the corresponding emotion information.

[1020] Step 8:

[1021] The device then formats the summarized results into graphs and tables, visualizing the data for easy visual understanding. The emotion engine also displays emotion tags, providing emotional information related to each task.

[1022] Step 9:

[1023] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[1024] Step 10:

[1025] Users access the summary results through a web interface or a dedicated application. The latest summary results are displayed even when users re-login to the system.

[1026] Step 11:

[1027] Users can review their own working hours and emotional state based on the displayed summary results and emotional information, which makes it easier to improve time management and self-evaluate, and is expected to improve stress management and work efficiency.

[1028] Example 2

[1029] 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."

[1030] Conventional work management systems provide functions for acquiring and analyzing a user's schedule information to summarize work hours, but do not take into account the user's emotional state. As a result, users have had to use separate tools in situations where they need to manage not only their work efficiency but also their mental state. This invention aims to solve this problem by providing a system that not only efficiently acquires and analyzes a user's schedule information and summarizes work hours, but also recognizes the user's emotional state and integrates it into the results.

[1031] 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.

[1032] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for recognizing the user's emotional state and generating an emotion tag, and means for displaying the summarized result together with the emotion tag. This allows the user to manage their work time and emotional state in a unified manner, enabling efficient time management and improved mental health.

[1033] "Means for authenticating user information" refers to means for verifying that a user is a legitimate user when the user accesses the system.

[1034] The "means for acquiring schedule information" refers to the means for extracting schedule information from the calendar or schedule management tool used by the user and importing it into the system.

[1035] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing acquired schedule information and classifying it into different categories such as "meetings" and "project work" based on its contents.

[1036] The "means for summarizing task time" is a means for summarizing a user's task activities for each period, such as daily, weekly, or monthly, based on analyzed and categorized schedule information.

[1037] The "means for recognizing a user's emotional state and generating an emotion tag" refers to a means for using a machine learning model or an emotion analysis engine to estimate a user's emotional state from their schedule information and conversation history, and generating an emotion tag that reflects the results.

[1038] The "means for displaying summary results together with emotion tags" refers to a means for visualizing the summary results of work hours in graph or table format, and further displaying emotion tags related to each work hour.

[1039] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[1040] User Authentication

[1041] When a user logs in to a system, user information is first obtained via the OAuth2.0 authentication protocol. This process allows the server to verify that the user is a legitimate user. A library such as "OAuthLib" is used for OAuth2.0 authentication.

[1042] Obtaining schedule information

[1043] The device retrieves the user's schedule information via a calendar API (e.g., Google Calendar API). The schedule information includes the start time, end time, title, and description of each event. The retrieved information is saved in JSON format.

[1044] Data analysis and categorization

[1045] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. NLP technology uses tools such as "spaCy" and "Natural Language Toolkit (NLTK)." Based on the analysis results, each appointment is automatically assigned a category, such as "meeting," "project work," or "break."

[1046] Introducing the Emotion Engine

[1047] The device uses an emotion engine to recognize the user's emotional state based on the user's schedule information and conversation history. The emotion engine uses machine learning models (e.g., BERT and GPT). This engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[1048] Summarizing business hours

[1049] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data. The summary results include total time and emotion tags for each category. For example, the total time spent in "meetings" or "project work" is displayed along with the corresponding emotion.

[1050] Displaying results and integrating emotional information

[1051] The device then formats the summarized results into graphs and tables, visualizing them in an intuitive way for the user. The results are also displayed with emotion tags, providing emotional information related to each task. For example, a bar graph showing the emotional state corresponding to each task is displayed.

[1052] Saving and Accessing Results

[1053] The server stores the generated summary results in a database. When a user logs into the system through a web interface or a dedicated application, the server reads and displays the stored summary results.

[1054] Specific examples

[1055] Let's say a user has the following schedule from 9am to 6pm:

[1056] 09:00 - 10:00: Team meeting (emotional state: stress)

[1057] 11:00 - 12:00: Project A work (emotional state: satisfied)

[1058] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[1059] 15:00 - 16:00: Project B development (emotional state: concentration)

[1060] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[1061] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[1062] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[1063] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[1064] Based on this, a summary result is generated and displayed:

[1065] Total meeting time: 1 hour (emotional state: stressed)

[1066] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[1067] Client meeting time: 1 hour (emotional state: anxiety)

[1068] Example prompts to input to the generative AI model

[1069] "Please introduce a system that helps users manage their daily work hours and emotional state. This system not only acquires and analyzes the user's schedule information and summarizes their work hours, but also recognizes the user's emotional state and integrates it into the results. Emotional states include stress, satisfaction, anxiety, and concentration. Please explain with specific examples."

[1070] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1071] Processing flow

[1072] Step 1: User authentication

[1073] When a user logs in to the system, the server obtains user information using the OAuth2.0 authentication protocol.

[1074] Input: User login information

[1075] Output: Authentication token

[1076] Specific behavior: The user is redirected to an authentication page and enters their authentication information. After that, if the authentication is successful, an authentication token is returned to the server, and the server uses this token to retrieve user information.

[1077] Step 2: Obtaining schedule information

[1078] The device uses the user's authentication token to access the calendar API (e.g., Google Calendar API) and obtain schedule information.

[1079] Input: Authentication Token

[1080] Output: Schedule information (JSON format)

[1081] Specific operation: The device uses the acquired authentication token to send a request to the calendar API and obtains the user's schedule information (start time, end time, title, description) in JSON format.

[1082] Step 3: Analyze and categorize the data

[1083] The device analyzes the schedule information it acquires, uses NLP technology to understand the content, and assigns a category.

[1084] Input: Schedule information (JSON format)

[1085] Output: Categorized schedule information

[1086] How it works: The device uses an NLP library (e.g., spaCy, NLTK) to parse the schedule information and automatically assign a category such as "meeting" or "project work" based on the content of each appointment.

[1087] Step 4: Implementing the Emotion Engine

[1088] Based on the schedule information acquired and analyzed by the device, an emotion engine is used to recognize the user's emotional state and generate an emotion tag.

[1089] Input: Categorized schedule information

[1090] Output: Emotion tag

[1091] Specific operation: The device uses machine learning models (e.g., BERT, GPT) to analyze the user's emotional state from the text content of the schedule information and conversation history, and generates emotion tags such as "stress" and "satisfaction."

[1092] Step 5: Summarize your working hours

[1093] Based on device-categorized schedule data, the system summarizes daily, weekly, and monthly work hours and integrates emotion tags.

[1094] Input: Categorized schedule information, emotion tags

[1095] Output: Summarized results (working hours and sentiment tags)

[1096] Specific operation: The device aggregates work hours by category, collects emotion tags associated with each work hour, and generates a summary result.

[1097] Step 6: Displaying the results and integrating emotional information

[1098] The device formats the summary results into graphs and tables and displays them to the user along with emotion tags.

[1099] Input: Summarization result (working hours and sentiment tags)

[1100] Output: Visualized results (graphs and tables)

[1101] Specific operation: The device uses a data visualization tool (e.g., Matplotlib or D3.js) to format the work hours and emotion tags into an easily understandable format (e.g., bar graph, pie chart, or table) and display them to the user.

[1102] Step 7: Saving and Accessing Results

[1103] The server stores the generated summarization results in a database for user access.

[1104] Input: Summarization result (working hours and sentiment tags)

[1105] Output: Results stored in the database, displayed to the user

[1106] Specific operation: The server saves the summarized results in a database, and when a user logs in through a web interface or a dedicated application, the server loads and displays the saved results.

[1107] (Application example 2)

[1108] 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."

[1109] In order to improve the efficiency of factory work and the performance of workers (robots), it is necessary to not only manage work schedules but also to take into account the emotional state of workers while they are working. However, conventional systems only manage work time and do not recognize or integrate emotional states, making it difficult to optimize performance or detect anomalies.

[1110] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1111] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the categorized schedule information, means for integrating emotional information into the summarized task times, and means for displaying the summarization results and the emotional information. This enables efficient management of work schedules in factories, as well as optimization of worker (robot) performance and anomaly detection.

[1112] A "means for authenticating user information" is a technique or process for authenticating a legitimate user to a system.

[1113] The "means for acquiring schedule information" refers to a technique or process for collecting data related to a user's schedule or dates.

[1114] The "analysis and categorization means" refers to a technique or process for analyzing acquired schedule information and classifying it into categories based on specific criteria.

[1115] A "summarization method" is a technique or process for aggregating and summarizing analyzed data.

[1116] A "means for integrating emotional information" is a technique or process for recognizing the emotional state of a user or worker and combining it with other data.

[1117] "Display means" refers to a technique or process for visually displaying the summarized results and integrated affective information.

[1118] "Means for analyzing based on natural language processing" refers to a process of understanding schedule information using technology that mechanically analyzes text data.

[1119] A "Calendar API" is an application program interface for obtaining schedule information.

[1120] This invention is a system that efficiently acquires and analyzes a user's schedule information and automatically summarizes work hours, and by integrating and displaying emotional information, aims to optimize work efficiency and improve performance.

[1121] User Authentication

[1122] The server obtains user information through OAuth 2.0 authentication and verifies that the user is a legitimate user. This process uses an authentication server and a token.

[1123] Obtaining schedule information

[1124] The server then retrieves the user's schedule information via the calendar API. The retrieved information includes, for example, start time, end time, title, description, etc., and is saved in JSON format.

[1125] Data analysis and categorization

[1126] The server uses natural language processing (NLP) technology to analyze the acquired schedule information and assign an appropriate category to each event, such as "meeting," "work," or "break."

[1127] Introducing the Emotion Engine

[1128] Furthermore, the server uses an emotion engine to recognize emotions from the user's schedule information, conversation history, etc. This emotion engine uses a machine learning model to generate emotion tags such as "stress," "satisfaction," and "anxiety."

[1129] Summarizing business hours

[1130] The server then summarizes work hours based on the categorized schedule data, including total hours and emotion tags for each category.

[1131] Displaying results and integrating emotional information

[1132] Finally, the server displays the summary results and emotional information in an integrated format using graphs and tables, designed to be intuitive for users, allowing them to grasp their schedule and emotional state at a glance.

[1133] As a concrete example, consider a user with the following schedule:

[1134] 09:00 - 10:00: Assembling parts (emotional state: concentration)

[1135] 11:00 - 12:00: Examination work (emotional state: anxiety)

[1136] In this case, the server will summarize the data as follows:

[1137] Parts assembly time: 1 hour (emotional state: concentration)

[1138] Test duration: 1 hour (emotional state: anxiety)

[1139] Prompt Sentence Examples

[1140] An example of a prompt for a generative AI model is:

[1141] "If a user performs a parts assembly task from 09:00 to 10:00 and an inspection task from 11:00 to 12:00, generate a summary result that includes the emotional state of each task."

[1142] This will enable optimization of work efficiency and performance in factories and other work environments by managing users' schedules and understanding their emotional states.

[1143] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1144] Step 1:

[1145] Perform user authentication.

[1146] The server obtains user information using OAuth 2.0 authentication. It requires the user's authentication information as input. The server sends a request to the authentication server to obtain a token. It uses this token to verify the user's legitimate access. The output is an access token.

[1147] Step 2:

[1148] Get schedule information.

[1149] The server retrieves the user's schedule information using the calendar API. An access token is required as input. The token is used to retrieve the schedule data from the calendar service and save it in JSON format. The output is the retrieved schedule information.

[1150] Step 3:

[1151] Analyze and categorize schedule information.

[1152] The server analyzes the retrieved schedule information using natural language processing (NLP) techniques. It takes the retrieved schedule information as input. The server analyzes the title and description and assigns an appropriate category to each event, such as "meeting," "work," or "break." The output is the analyzed, categorized schedule information.

[1153] Step 4:

[1154] Recognize emotional information.

[1155] The server uses an emotion engine to recognize user emotions from schedule information and related data. Categorized schedule information is required as input. Using a machine learning model, the server generates emotion tags such as "stress," "satisfaction," and "anxiety." The output is schedule information with emotion tags.

[1156] Step 5:

[1157] Summarize your work hours.

[1158] The server summarizes working hours based on categorized schedule information. It requires schedule information with emotion tags as input. The server calculates the total time for each category and integrates the associated emotion tags. The output is the summarized working hours and emotion information.

[1159] Step 6:

[1160] Display the results.

[1161] The server displays summarized task time and emotion information. The input required is summarized task time and emotion information. The server formats this in graphs and tables, generating an interface that users can intuitively understand. The output is visualized data.

[1162] This allows users to understand their schedule and emotional state at a glance, enabling more efficient time management and mental health management.

[1163] 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.

[1164] 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.

[1165] 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.

[1166] [Fourth embodiment]

[1167] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1168] 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.

[1169] 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).

[1170] 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.

[1171] 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.

[1172] 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).

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] 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.

[1178] 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.

[1179] 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."

[1180] The system of the present invention efficiently acquires and analyzes a user's schedule information, and automatically summarizes and provides the summary of the user's working hours. Specific embodiments of the present invention will be described below.

[1181] User Authentication

[1182] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[1183] Obtaining schedule information

[1184] The device obtains the user's schedule information via the Google Calendar API. Here, the device accesses the user's calendar and obtains JSON data including detailed event information (e.g., start time, end time, title, and description).

[1185] Data analysis and categorization

[1186] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to categorize each event. Utilizing string analysis and machine learning models, it automatically categorizes events into categories such as "meetings," "project work," and "breaks."

[1187] Generate summaries

[1188] The device summarizes the user's work time based on the analyzed data. Time is aggregated by category according to existing rules and algorithms, and summary information is generated for periods such as daily, weekly, and monthly.

[1189] Displaying the results

[1190] The results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visualizes the results in graphs and tables, allowing users to intuitively understand the distribution of work time.

[1191] Specific examples

[1192] Summarizing the working hours of the day

[1193] Let's say a user has the following appointments between 9am and 6pm:

[1194] 09:00 - 10:00: Team meeting

[1195] 11:00 - 12:00: Project A work

[1196] 13:00 - 14:00: Client meeting

[1197] 15:00 - 16:00: Project B development

[1198] The device retrieves these events and, through NLP techniques, categorizes them as follows:

[1199] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[1200] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[1201] Based on this, the terminal generates a summary and displays it as follows:

[1202] Total meeting time: 2 hours

[1203] Project duration: 2 hours

[1204] Other: 0 hours

[1205] Summarizing the working week

[1206] For example, if a user has the same schedule every day from Monday to Friday, the device will generate the following weekly summary results:

[1207] Total meeting time (weekly): 10 hours (2 hours / day, 5 days)

[1208] Project work hours (week): 10 hours (2 hours / day, 5 days)

[1209] The results are stored on a server and updated information is provided each time the user accesses the site.

[1210] The system of the present invention allows users to easily understand their own working hours, which can be used to improve time management and self-evaluation. Each of the above functions contributes greatly to improving user productivity and efficient time management.

[1211] The processing flow will be explained below.

[1212] Step 1:

[1213] The user logs in to the system. The user clicks the login button on the screen and grants access to their Google account through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[1214] Step 2:

[1215] The device uses the obtained authentication token to send a request to the Google Calendar API, which returns the user's calendar information (event details) in JSON format.

[1216] Step 3:

[1217] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[1218] Step 4:

[1219] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[1220] Step 5:

[1221] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[1222] Step 6:

[1223] Based on the scheduled data categorized by device, daily, weekly, and monthly working hours are summarized. Specifically, the total time for each category is calculated and aggregated results are generated for each period.

[1224] Step 7:

[1225] The terminal formats the summarized results into graphs and tables, visualizing the data so that it is easy for the user to understand visually.

[1226] Step 8:

[1227] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[1228] Step 9:

[1229] Users access the summary results through a web interface or a dedicated application, ensuring that the latest summary results are displayed even when users re-login to the system.

[1230] Step 10:

[1231] Users can review their own work hours based on the displayed summary results, which allows them to improve their time management and self-evaluate.

[1232] Example 1

[1233] 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."

[1234] Conventional schedule management systems collect and analyze users' schedule information, but the analysis results are often not presented in an intuitive and easy-to-understand format. Furthermore, summarizing and categorizing work time is often done manually, placing a significant burden on users. Therefore, more advanced technology was needed to efficiently manage users' work time and improve productivity.

[1235] 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.

[1236] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summarization results, means for analyzing the schedule information using natural language processing technology, means for aggregating the acquired schedule information into summary information for multiple periods, and means for visually displaying the summary information. This enables users to efficiently manage their own task times and improve productivity.

[1237] "User information" refers to the user's identification information used in the authentication process, specifically, an email address, a password, etc.

[1238] "Schedule information" refers to detailed information (start time, end time, title, description, etc.) of an event listed on a user's calendar.

[1239] "Analysis" refers to the process of using natural language processing technology to understand the content of the acquired schedule information and classify it into specific categories.

[1240] "Categorization" refers to the process of classifying analyzed schedule information into specific categories such as "meetings," "project work," and "breaks."

[1241] "Summarization" refers to the process of summarizing task hours for a specific period based on analyzed data and providing it to the user.

[1242] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language, and includes machine learning models and string analysis algorithms.

[1243] "API" refers to an interface for exchanging data and functions between applications, such as a calendar API.

[1244] "Summary information" refers to information that summarizes the aggregated work hours, category information, etc. in a format that is easy for the user to understand.

[1245] "Visual display" refers to the process of presenting summary information to users in the form of graphs or tables, allowing them to intuitively understand the information.

[1246] To implement the present invention, it is necessary to implement the system program through the following procedure: The system is designed to improve the efficiency of users' work time management and productivity.

[1247] User Authentication

[1248] When a user logs in to the system, they first obtain user information using OAuth2.0 authentication. The device uses the OAuth2.0 framework to send a request to the authentication server and obtain an access token. This token is then used to obtain the user's identification information (such as name and email address) from the authentication server.

[1249] Obtaining schedule information

[1250] The device uses the calendar API to obtain the user's schedule information. The data obtained through this API is in JSON format and includes details such as the start time, end time, title, and description of each event.

[1251] Data analysis and categorization

[1252] The device parses the acquired schedule information and analyzes each event using natural language processing (NLP) techniques. This analysis uses machine learning models and string analysis algorithms. The analyzed information classifies each event into categories such as "meetings," "project work," and "breaks."

[1253] Generate summaries

[1254] The device then uses the analyzed data to summarize the user's work time, aggregating the time spent by category on a daily, weekly, or monthly basis according to specific rules and algorithms.

[1255] Displaying the results

[1256] The aggregated results are stored on a server and can be accessed by users through a web interface or a dedicated application. The terminal visually displays the summarized results in the form of graphs and tables, allowing users to intuitively understand the distribution of work time.

[1257] Specific examples

[1258] Summarizing the working hours of the day

[1259] Let's say a user has the following appointments between 9am and 6pm:

[1260] 09:00 - 10:00: Team meeting

[1261] 11:00 - 12:00: Project A work

[1262] 13:00 - 14:00: Client meeting

[1263] 15:00 - 16:00: Project B development

[1264] The device retrieves these events and uses NLP techniques to categorize them as follows:

[1265] Meeting: 2 hours (09:00 - 10:00, 13:00 - 14:00)

[1266] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00)

[1267] Based on this, the terminal generates a summary and displays it as follows:

[1268] Total meeting time: 2 hours

[1269] Project duration: 2 hours

[1270] Other: 0 hours

[1271] Prompt Sentence Examples

[1272] "Get the user's schedule information from the Calendar API and generate a categorical process description using natural language processing techniques."

[1273] By implementing this system, users can efficiently manage their work time and significantly improve their productivity. In addition, by visually displaying the summary results, users can intuitively understand how they use their time.

[1274] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1275] Step 1: User authentication

[1276] Description: When a user logs in to the system, the authentication process begins. Specifically, the user enters their email address and password on the login screen and presses the "Login" button.

[1277] Input: Email address, password

[1278] Data processing / data calculation: The device uses the OAuth 2.0 framework to send a request to the authentication server and obtain an access token. This token is used to obtain user information.

[1279] Output: Access token, user information (name, email address, etc.)

[1280] Specific operation: The terminal sends a request to the authentication server, which verifies the user information and returns an access token.

[1281] Step 2: Obtaining schedule information

[1282] Description: Gets the user's schedule information. The device uses the Calendar API to request schedule information for the specified period.

[1283] Input: Access token, information for the specified period

[1284] Data processing / data calculation: The device uses the access token to send a request to the calendar API and receives JSON data of the schedule information.

[1285] Output: User schedule information (JSON format)

[1286] Specific operation: The device sends an HTTP request to the calendar API, and the API returns schedule information for the specified period.

[1287] Step 3: Analyze and categorize the data

[1288] Description: Analyzes the acquired schedule information and categorizes each event. The device uses natural language processing technology to analyze the title and description of each event.

[1289] Input: User's schedule information (JSON format)

[1290] Data processing / data calculation: The device uses an NLP model to analyze the schedule information and classifies each event into categories such as "meeting," "project work," and "break" through string analysis and machine learning.

[1291] Output: Date information categorized by category

[1292] Specific operation: The device inputs the title and description of the schedule information into the NLP model and outputs the categorized results.

[1293] Step 4: Generate summaries

[1294] Description: Summarizes work hours based on analyzed data. The device aggregates the time for each category and generates summary information for the specified period (e.g., daily, weekly, monthly).

[1295] Input: Date information categorized by category

[1296] Data processing / data calculation: The device calculates the time for each category and applies an algorithm to calculate the total time.

[1297] Output: Aggregated time results for each category

[1298] Specific operation: The device aggregates the schedule information for each category by hour and generates daily, weekly, and monthly summary results.

[1299] Step 5: View the results

[1300] Description: Displays summarized results. Stores the results on the server and allows users to access them through a web interface or dedicated application.

[1301] Input: Aggregation results of time by category

[1302] Data processing / data calculation: The terminal sends the aggregated results in JSON format to the server and stores them in a database.

[1303] Output: Graphs and tables of summarized results

[1304] Specific operation: The terminal visually displays the summary results, and the latest aggregated results are displayed each time the user accesses the terminal.

[1305] (Application example 1)

[1306] 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."

[1307] Conventional work schedule management in factories is often managed individually by human workers, which is inefficient. Furthermore, it is difficult to grasp how much time a robot is spending on each process, making it difficult to improve productivity and optimize time management. The objective of this invention is to provide a system that can efficiently acquire and analyze user schedule information, manage work schedules within the factory, calculate the total time for each work category, and be installed and used on robots.

[1308] 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.

[1309] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the analysis results, means for displaying the summary results, means for managing the work schedule within the factory and calculating the total time for each task category, and means installed on the factory robots. This allows users and managers to centrally manage the work schedule within the factory and understand the time allocation for each specific task.

[1310] "Means for authenticating user information" refers to means for verifying the legitimacy of a user when accessing a system.

[1311] The "means for acquiring schedule information" is a means for collecting the user's schedule data from an external calendar service or the like.

[1312] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing collected schedule data and classifying it into specific task categories.

[1313] "Means for summarizing task times based on analysis results" refers to means for summarizing task times for each category and total time based on the analyzed data.

[1314] The "means for displaying the summary results" is a means for visually presenting the summarized task times and other analysis results to the user.

[1315] "Means for managing work schedules within a factory" refers to a means for centrally organizing and managing the schedules of each work task within a factory.

[1316] The "means for calculating the total time for each task category" is a means for calculating the total task time allocated to each category within a specific period.

[1317] The "means to be installed in the robots in the factory" refers to a means for incorporating the work schedule management system into the robots in the factory.

[1318] The system of the present invention efficiently acquires and analyzes the user's schedule information, manages work schedules within the factory, calculates the total time for each work category, and can be installed and used on a robot.

[1319] Authenticate user information

[1320] When a user logs in to the system, the server obtains user information using OAuth 2.0 authentication. This process verifies that the user is a legitimate user.

[1321] Obtaining schedule information

[1322] The device obtains the user's schedule information via the Google Calendar API. At this time, it accesses the user's calendar and obtains JSON data containing detailed information about the event (start time, end time, title, and description).

[1323] Data analysis and categorization

[1324] The device analyzes the schedule information and categorizes each event using natural language processing (NLP) technology, utilizing string analysis and machine learning models to automatically classify events into categories such as "welding work," "quality check," and "packaging."

[1325] Generate time summaries

[1326] The device then uses the analyzed data to summarize the total time spent in each task category, aggregating the time spent in each category according to existing rules and algorithms, and generating summary information for periods such as daily, weekly, or monthly.

[1327] Displaying the results

[1328] The summarized results are stored on a server and can be accessed by the user through a web interface or a dedicated app. The terminal visualizes the results in graphs and tables, allowing the user to intuitively understand the time allocation for each task.

[1329] Installation on factory robots

[1330] The system can be installed on robots in factories, allowing the robots to automatically manage work schedules and keep track of the progress of each work category in real time.

[1331] Specific examples

[1332] For example, if a user wants to manage the schedule of a factory robot, the following format is possible:

[1333] October 1, 2023, 9:00 - 11:00: "Welding"

[1334] October 1, 2023, 11:30 - 12:30: "Quality Check"

[1335] October 1, 2023, 13:00 - 15:00: "Packaging"

[1336] The system takes this schedule data, categorizes it using NLP technology, and calculates and displays the total time for each work category.

[1337] Hardware and software used

[1338] Hardware: Robot built-in computer, API communication module

[1339] Software: Python (programming language), Google Calendar API (scheduling data acquisition), OAuth2.0 (robot authentication), NLP libraries (e.g., SpaCy, NLTK), Pandas (data processing and visualization)

[1340] Example of generated AI prompt

[1341] "Design an application that automatically calculates the total time for each task category from calendar data, categorizes it using NLP, and summarizes it by day, week, and month."

[1342] The above is a specific embodiment of the system of the present invention. This system allows users and managers to centrally manage work schedules within a factory and understand the time allocation for each specific task.

[1343] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1344] Step 1:

[1345] The server authenticates user information. When a user logs in to the system, it obtains user information using OAuth2.0 authentication. Through this authentication process, the server verifies that the user is a legitimate user. The input is the user's authentication information, and the output is authenticated user information.

[1346] Step 2:

[1347] The device obtains schedule information. Based on the authenticated user information, the device uses the Google Calendar API to obtain the user's schedule information. At this time, the device accesses the user's calendar and obtains JSON data containing detailed event information (start time, end time, title, and description). The input is the authenticated user information and a request for calendar information, and the output is schedule information in JSON format.

[1348] Step 3:

[1349] The terminal analyzes and categorizes the acquired schedule information. The acquired schedule information is analyzed using natural language processing (NLP) technology, and each schedule is categorized. Specifically, string analysis and machine learning models are used to automatically classify schedules into categories such as "welding work," "quality check," and "packaging." The input is schedule information in JSON format, and the output is categorized schedule data.

[1350] Step 4:

[1351] The terminal summarizes work hours based on the analysis results. Based on the analyzed data, it calculates the total time for each work category. According to existing rules and algorithms, it aggregates the time for each category and generates summary information for periods such as daily, weekly, or monthly. The input is categorized schedule data, and the output is summarized time data.

[1352] Step 5:

[1353] The server displays the summarized results. It saves the summarized results and allows users to access them through a web interface or a dedicated app. The terminal visualizes the aggregated results in graphs and tables, allowing users to intuitively understand the time allocation for each task. The input is summarized time data, and the output is visualized data in graphs and tables.

[1354] Step 6:

[1355] The terminal is installed on the factory robot. By incorporating the system into the robot in the factory, the robot can automatically manage its work schedule and monitor the progress of each work category in real time. The input is the system installation package, and the output is the installed robot system.

[1356] 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.

[1357] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[1358] User Authentication

[1359] When a user logs in to the system, user information is first obtained through OAuth 2.0 authentication. This process allows the system to verify that the user is a legitimate user.

[1360] Obtaining schedule information

[1361] The device obtains the user's schedule information via the calendar API. Here, detailed information (e.g., start time, end time, title, description) of events stored in the user's calendar is obtained in JSON format.

[1362] Data analysis and categorization

[1363] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. Based on the results of this analysis, it then automatically assigns each appointment an appropriate category (e.g., "meeting," "project work," "break").

[1364] Introducing the Emotion Engine

[1365] The device is equipped with an emotion engine that uses data acquired from the user's schedule and conversation history to recognize the user's emotions. This emotion engine uses machine learning models to estimate the user's emotional state and generate emotion tags such as "stress," "satisfaction," and "dissatisfaction."

[1366] Summarizing business hours

[1367] The device summarizes daily, weekly, and monthly working hours based on categorized schedule data. The aggregated results calculate the time spent by category and also include emotion tags generated by the emotion engine.

[1368] Displaying results and integrating emotional information

[1369] The device then formats the summary results into graphs and tables, visualizing them for intuitive understanding by the user. At the same time, emotion tags obtained from the emotion engine are also displayed, providing emotional information related to each task.

[1370] Specific examples

[1371] Summarizing the working hours of the day

[1372] Let's say a user has the following schedule from 9am to 6pm:

[1373] 09:00 - 10:00: Team meeting (emotional state: stress)

[1374] 11:00 - 12:00: Project A work (emotional state: satisfied)

[1375] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[1376] 15:00 - 16:00: Project B development (emotional state: concentration)

[1377] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[1378] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[1379] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[1380] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[1381] Based on this, the terminal generates and displays the summary result as follows:

[1382] Total meeting time: 1 hour (emotional state: stressed)

[1383] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[1384] Client meeting time: 1 hour (emotional state: anxiety)

[1385] These results are stored on a server and are accessible to users through a web interface or dedicated application. Based on the emotional information displayed in the summary results, users can manage their own work time and emotions, which can help improve work efficiency and reduce stress.

[1386] The system of the present invention allows users to not only manage their work time but also understand their emotional state, enabling more comprehensive self-management, which is expected to improve both time efficiency and mental health.

[1387] The processing flow will be explained below.

[1388] Step 1:

[1389] The user logs in to the system. The user clicks the login button on the screen and grants access to calendar information through OAuth 2.0 authentication. The device performs this authentication process and obtains an authentication token.

[1390] Step 2:

[1391] The device uses the obtained authentication token to send a request to the calendar API, which returns the user's calendar information (event details) in JSON format.

[1392] Step 3:

[1393] The device parses the calendar information in JSON format, extracting the start time, end time, title, and description of each event.

[1394] Step 4:

[1395] The device begins analyzing the schedule data it has acquired. It applies natural language processing (NLP) technology to the title and description of each schedule to understand the schedule's content.

[1396] Step 5:

[1397] The device uses NLP technology to automatically assign an appropriate category (e.g., "Meeting," "Project work," "Break") to each event, thereby categorizing the event.

[1398] Step 6:

[1399] The device uses an emotion engine to analyze schedule information and conversation history to estimate the user's emotional state. The emotion engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[1400] Step 7:

[1401] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data and emotion tags generated by the emotion engine. The aggregated results include the total time for each category and the corresponding emotion information.

[1402] Step 8:

[1403] The device then formats the summarized results into graphs and tables, visualizing the data for easy visual understanding. The emotion engine also displays emotion tags, providing emotional information related to each task.

[1404] Step 9:

[1405] The device sends the summarized results to the server, which stores the received data in a database and associates it with the user's account.

[1406] Step 10:

[1407] Users access the summary results through a web interface or a dedicated application. The latest summary results are displayed even when users re-login to the system.

[1408] Step 11:

[1409] Users can review their own working hours and emotional state based on the displayed summary results and emotional information, which makes it easier to improve time management and self-evaluate, and is expected to improve stress management and work efficiency.

[1410] Example 2

[1411] 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."

[1412] Conventional work management systems provide functions for acquiring and analyzing a user's schedule information to summarize work hours, but do not take into account the user's emotional state. As a result, users have had to use separate tools in situations where they need to manage not only their work efficiency but also their mental state. This invention aims to solve this problem by providing a system that not only efficiently acquires and analyzes a user's schedule information and summarizes work hours, but also recognizes the user's emotional state and integrates it into the results.

[1413] 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.

[1414] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for recognizing the user's emotional state and generating an emotion tag, and means for displaying the summarized result together with the emotion tag. This allows the user to manage their work time and emotional state in a unified manner, enabling efficient time management and improved mental health.

[1415] "Means for authenticating user information" refers to means for verifying that a user is a legitimate user when the user accesses the system.

[1416] The "means for acquiring schedule information" refers to the means for extracting schedule information from the calendar or schedule management tool used by the user and importing it into the system.

[1417] The "means for analyzing and categorizing acquired schedule information" is a means for analyzing acquired schedule information and classifying it into different categories such as "meetings" and "project work" based on its contents.

[1418] The "means for summarizing task time" is a means for summarizing a user's task activities for each period, such as daily, weekly, or monthly, based on analyzed and categorized schedule information.

[1419] The "means for recognizing a user's emotional state and generating an emotion tag" refers to a means for using a machine learning model or an emotion analysis engine to estimate a user's emotional state from their schedule information and conversation history, and generating an emotion tag that reflects the results.

[1420] The "means for displaying summary results together with emotion tags" refers to a means for visualizing the summary results of work hours in graph or table format, and further displaying emotion tags related to each work hour.

[1421] The present invention is a system that efficiently acquires and analyzes a user's schedule information, automatically summarizes and provides the summary of the user's work time, and recognizes the user's emotions and integrates them into the summary results. Specific embodiments of the present invention are described below.

[1422] User Authentication

[1423] When a user logs in to a system, user information is first obtained via the OAuth2.0 authentication protocol. This process allows the server to verify that the user is a legitimate user. A library such as "OAuthLib" is used for OAuth2.0 authentication.

[1424] Obtaining schedule information

[1425] The device retrieves the user's schedule information via a calendar API (e.g., Google Calendar API). The schedule information includes the start time, end time, title, and description of each event. The retrieved information is saved in JSON format.

[1426] Data analysis and categorization

[1427] The device analyzes the schedule information it acquires and uses natural language processing (NLP) technology to understand the content of each appointment. NLP technology uses tools such as "spaCy" and "Natural Language Toolkit (NLTK)." Based on the analysis results, each appointment is automatically assigned a category, such as "meeting," "project work," or "break."

[1428] Introducing the Emotion Engine

[1429] The device uses an emotion engine to recognize the user's emotional state based on the user's schedule information and conversation history. The emotion engine uses machine learning models (e.g., BERT and GPT). This engine generates emotion tags such as "stress," "satisfaction," and "anxiety."

[1430] Summarizing business hours

[1431] The device summarizes daily, weekly, and monthly work hours based on categorized schedule data. The summary results include total time and emotion tags for each category. For example, the total time spent in "meetings" or "project work" is displayed along with the corresponding emotion.

[1432] Displaying results and integrating emotional information

[1433] The device then formats the summarized results into graphs and tables, visualizing them in an intuitive way for the user. The results are also displayed with emotion tags, providing emotional information related to each task. For example, a bar graph showing the emotional state corresponding to each task is displayed.

[1434] Saving and Accessing Results

[1435] The server stores the generated summary results in a database. When a user logs into the system through a web interface or a dedicated application, the server reads and displays the stored summary results.

[1436] Specific examples

[1437] Let's say a user has the following schedule from 9am to 6pm:

[1438] 09:00 - 10:00: Team meeting (emotional state: stress)

[1439] 11:00 - 12:00: Project A work (emotional state: satisfied)

[1440] 13:00 - 14:00: Client meeting (emotional state: anxiety)

[1441] 15:00 - 16:00: Project B development (emotional state: concentration)

[1442] The device retrieves these appointments and uses NLP technology and an emotion engine to analyze and categorize them as follows:

[1443] Meeting: 1 hour (9:00 - 10:00, Emotional state: Stressed)

[1444] Project work: 2 hours (11:00 - 12:00, 15:00 - 16:00, emotional state: satisfied, focused)

[1445] Client meeting: 1 hour (13:00 - 14:00, emotional state: anxiety)

[1446] Based on this, a summary result is generated and displayed:

[1447] Total meeting time: 1 hour (emotional state: stressed)

[1448] Project Work Time: 2 hours (Emotional State: Satisfied, Focused)

[1449] Client meeting time: 1 hour (emotional state: anxiety)

[1450] Example prompts to input to the generative AI model

[1451] "Please introduce a system that helps users manage their daily work hours and emotional state. This system not only acquires and analyzes the user's schedule information and summarizes their work hours, but also recognizes the user's emotional state and integrates it into the results. Emotional states include stress, satisfaction, anxiety, and concentration. Please explain with specific examples."

[1452] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1453] Processing flow

[1454] Step 1: User authentication

[1455] When a user logs in to the system, the server obtains user information using the OAuth2.0 authentication protocol.

[1456] Input: User login information

[1457] Output: Authentication token

[1458] Specific behavior: The user is redirected to an authentication page and enters their authentication information. After that, if the authentication is successful, an authentication token is returned to the server, and the server uses this token to retrieve user information.

[1459] Step 2: Obtaining schedule information

[1460] The device uses the user's authentication token to access the calendar API (e.g., Google Calendar API) and obtain schedule information.

[1461] Input: Authentication Token

[1462] Output: Schedule information (JSON format)

[1463] Specific operation: The device uses the acquired authentication token to send a request to the calendar API and obtains the user's schedule information (start time, end time, title, description) in JSON format.

[1464] Step 3: Analyze and categorize the data

[1465] The device analyzes the schedule information it acquires, uses NLP technology to understand the content, and assigns a category.

[1466] Input: Schedule information (JSON format)

[1467] Output: Categorized schedule information

[1468] How it works: The device uses an NLP library (e.g., spaCy, NLTK) to parse the schedule information and automatically assign a category such as "meeting" or "project work" based on the content of each appointment.

[1469] Step 4: Implementing the Emotion Engine

[1470] Based on the schedule information acquired and analyzed by the device, an emotion engine is used to recognize the user's emotional state and generate an emotion tag.

[1471] Input: Categorized schedule information

[1472] Output: Emotion tag

[1473] Specific operation: The device uses machine learning models (e.g., BERT, GPT) to analyze the user's emotional state from the text content of the schedule information and conversation history, and generates emotion tags such as "stress" and "satisfaction."

[1474] Step 5: Summarize your working hours

[1475] Based on device-categorized schedule data, the system summarizes daily, weekly, and monthly work hours and integrates emotion tags.

[1476] Input: Categorized schedule information, emotion tags

[1477] Output: Summarized results (working hours and sentiment tags)

[1478] Specific operation: The device aggregates work hours by category, collects emotion tags associated with each work hour, and generates a summary result.

[1479] Step 6: Displaying the results and integrating emotional information

[1480] The device formats the summary results into graphs and tables and displays them to the user along with emotion tags.

[1481] Input: Summarization result (working hours and sentiment tags)

[1482] Output: Visualized results (graphs and tables)

[1483] Specific operation: The device uses a data visualization tool (e.g., Matplotlib or D3.js) to format the work hours and emotion tags into an easily understandable format (e.g., bar graph, pie chart, or table) and display them to the user.

[1484] Step 7: Saving and Accessing Results

[1485] The server stores the generated summarization results in a database for user access.

[1486] Input: Summarization result (working hours and sentiment tags)

[1487] Output: Results stored in the database, displayed to the user

[1488] Specific operation: The server saves the summarized results in a database, and when a user logs in through a web interface or a dedicated application, the server loads and displays the saved results.

[1489] (Application example 2)

[1490] 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."

[1491] In order to improve the efficiency of factory work and the performance of workers (robots), it is necessary to not only manage work schedules but also to take into account the emotional state of workers while they are working. However, conventional systems only manage work time and do not recognize or integrate emotional states, making it difficult to optimize performance or detect anomalies.

[1492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1493] In this invention, the server includes means for authenticating user information, means for acquiring schedule information, means for analyzing and categorizing the acquired schedule information, means for summarizing task times based on the categorized schedule information, means for integrating emotional information into the summarized task times, and means for displaying the summarization results and the emotional information. This enables efficient management of work schedules in factories, as well as optimization of worker (robot) performance and anomaly detection.

[1494] A "means for authenticating user information" is a technique or process for authenticating a legitimate user to a system.

[1495] The "means for acquiring schedule information" refers to a technique or process for collecting data related to a user's schedule or dates.

[1496] The "analysis and categorization means" refers to a technique or process for analyzing acquired schedule information and classifying it into categories based on specific criteria.

[1497] A "summarization method" is a technique or process for aggregating and summarizing analyzed data.

[1498] A "means for integrating emotional information" is a technique or process for recognizing the emotional state of a user or worker and combining it with other data.

[1499] "Display means" refers to a technique or process for visually displaying the summarized results and integrated affective information.

[1500] "Means for analyzing based on natural language processing" refers to a process of understanding schedule information using technology that mechanically analyzes text data.

[1501] A "Calendar API" is an application program interface for obtaining schedule information.

[1502] This invention is a system that efficiently acquires and analyzes a user's schedule information and automatically summarizes work hours, and by integrating and displaying emotional information, aims to optimize work efficiency and improve performance.

[1503] User Authentication

[1504] The server obtains user information through OAuth 2.0 authentication and verifies that the user is a legitimate user. This process uses an authentication server and a token.

[1505] Obtaining schedule information

[1506] The server then retrieves the user's schedule information via the calendar API. The retrieved information includes, for example, start time, end time, title, description, etc., and is saved in JSON format.

[1507] Data analysis and categorization

[1508] The server uses natural language processing (NLP) technology to analyze the acquired schedule information and assign an appropriate category to each event, such as "meeting," "work," or "break."

[1509] Introducing the Emotion Engine

[1510] Furthermore, the server uses an emotion engine to recognize emotions from the user's schedule information, conversation history, etc. This emotion engine uses a machine learning model to generate emotion tags such as "stress," "satisfaction," and "anxiety."

[1511] Summarizing business hours

[1512] The server then summarizes work hours based on the categorized schedule data, including total hours and emotion tags for each category.

[1513] Displaying results and integrating emotional information

[1514] Finally, the server displays the summary results and emotional information in an integrated format using graphs and tables, designed to be intuitive for users, allowing them to grasp their schedule and emotional state at a glance.

[1515] As a concrete example, consider a user with the following schedule:

[1516] 09:00 - 10:00: Assembling parts (emotional state: concentration)

[1517] 11:00 - 12:00: Examination work (emotional state: anxiety)

[1518] In this case, the server will summarize the data as follows:

[1519] Parts assembly time: 1 hour (emotional state: concentration)

[1520] Test duration: 1 hour (emotional state: anxiety)

[1521] Prompt Sentence Examples

[1522] An example of a prompt for a generative AI model is:

[1523] "If a user performs a parts assembly task from 09:00 to 10:00 and an inspection task from 11:00 to 12:00, generate a summary result that includes the emotional state of each task."

[1524] This will enable optimization of work efficiency and performance in factories and other work environments by managing users' schedules and understanding their emotional states.

[1525] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1526] Step 1:

[1527] Perform user authentication.

[1528] The server obtains user information using OAuth 2.0 authentication. It requires the user's authentication information as input. The server sends a request to the authentication server to obtain a token. It uses this token to verify the user's legitimate access. The output is an access token.

[1529] Step 2:

[1530] Get schedule information.

[1531] The server retrieves the user's schedule information using the calendar API. An access token is required as input. The token is used to retrieve the schedule data from the calendar service and save it in JSON format. The output is the retrieved schedule information.

[1532] Step 3:

[1533] Analyze and categorize schedule information.

[1534] The server analyzes the retrieved schedule information using natural language processing (NLP) techniques. It takes the retrieved schedule information as input. The server analyzes the title and description and assigns an appropriate category to each event, such as "meeting," "work," or "break." The output is the analyzed, categorized schedule information.

[1535] Step 4:

[1536] Recognize emotional information.

[1537] The server uses an emotion engine to recognize user emotions from schedule information and related data. Categorized schedule information is required as input. Using a machine learning model, the server generates emotion tags such as "stress," "satisfaction," and "anxiety." The output is schedule information with emotion tags.

[1538] Step 5:

[1539] Summarize your work hours.

[1540] The server summarizes working hours based on categorized schedule information. It requires schedule information with emotion tags as input. The server calculates the total time for each category and integrates the associated emotion tags. The output is the summarized working hours and emotion information.

[1541] Step 6:

[1542] Display the results.

[1543] The server displays summarized task time and emotion information. The input required is summarized task time and emotion information. The server formats this in graphs and tables, generating an interface that users can intuitively understand. The output is visualized data.

[1544] This allows users to understand their schedule and emotional state at a glance, enabling more efficient time management and mental health management.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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).

[1552] 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.

[1553] 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."

[1554] 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.

[1555] 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).

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1561] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1562] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1563] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1564] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1565] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1566] The following is further disclosed regarding the above embodiment.

[1567] (Claim 1)

[1568] means for authenticating user information;

[1569] a means for obtaining schedule information;

[1570] A means of analyzing and categorizing the acquired schedule information;

[1571] A means to summarize work hours based on the analysis results,

[1572] a means for displaying the summarized results;

[1573] A system including:

[1574] (Claim 2)

[1575] 10. The system of claim 1, further comprising means for obtaining the user's schedule information via a calendar API.

[1576] (Claim 3)

[1577] 2. The system according to claim 1, further comprising means for analyzing the acquired schedule information based on natural language processing.

[1578] "Example 1"

[1579] (Claim 1)

[1580] means for authenticating user information;

[1581] a means for obtaining schedule information;

[1582] A means of analyzing and categorizing the acquired schedule information;

[1583] A means to summarize work hours based on the analysis results,

[1584] a means for displaying the summarized results;

[1585] A means for analyzing schedule information using natural language processing technology;

[1586] A means for aggregating the acquired schedule information as summary information for multiple periods;

[1587] a means for visually displaying the summary information;

[1588] A system including:

[1589] (Claim 2)

[1590] 10. The system of claim 1, further comprising means for obtaining the user's schedule information via a calendar API.

[1591] (Claim 3)

[1592] 2. The system according to claim 1, further comprising means for analyzing the acquired schedule information based on natural language processing.

[1593] "Application Example 1"

[1594] (Claim 1)

[1595] means for authenticating user information;

[1596] a means for obtaining schedule information;

[1597] A means of analyzing and categorizing the acquired schedule information;

[1598] A means to summarize work hours based on the analysis results,

[1599] a means for displaying the summarized results;

[1600] A means for managing work schedules within a factory and calculating the total time for each work category;

[1601] a means to be installed on a robot in a factory;

[1602] A system including:

[1603] (Claim 2)

[1604] 10. The system of claim 1, further comprising means for obtaining the user's schedule information via a calendar API.

[1605] (Claim 3)

[1606] 2. The system according to claim 1, further comprising means for analyzing the acquired schedule information based on natural language processing.

[1607] "Example 2: Combining Emotion Engines"

[1608] (Claim 1)

[1609] means for authenticating user information;

[1610] a means for obtaining schedule information;

[1611] A means of analyzing and categorizing the acquired schedule information;

[1612] A means to summarize work hours based on the analysis results,

[1613] means for recognizing a user's emotional state and generating an emotion tag;

[1614] a means for displaying the summarized results together with the sentiment tag;

[1615] A system including:

[1616] (Claim 2)

[1617] 10. The system of claim 1, further comprising means for obtaining the user's schedule information via a calendar API.

[1618] (Claim 3)

[1619] 2. The system according to claim 1, further comprising means for analyzing the acquired schedule information based on natural language processing.

[1620] "Application example 2 when combining emotion engines"

[1621] (Claim 1)

[1622] means for authenticating user information;

[1623] a means for obtaining schedule information;

[1624] A means of analyzing and categorizing the acquired schedule information;

[1625] A means to summarize work hours based on categorized schedule information,

[1626] A means of integrating emotional information into summarized work time;

[1627] a means for displaying the summary result and the emotion information;

[1628] A system including:

[1629] (Claim 2)

[1630] 10. The system of claim 1, further comprising means for obtaining the user's schedule information via a calendar API.

[1631] (Claim 3)

[1632] 2. The system according to claim 1, further comprising means for analyzing the acquired schedule information based on natural language processing. [Explanation of symbols]

[1633] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for authenticating user information; a means for obtaining schedule information; A means of analyzing and categorizing the acquired schedule information; A means to summarize work hours based on the analysis results, a means for displaying the summarized results; A system including:

2. 2. The system of claim 1, further comprising means for obtaining the user's schedule information via a calendar API.

3. 2. The system according to claim 1, further comprising means for analyzing the acquired schedule information based on natural language processing.

Images