System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting task information of a user; means for receiving the task information and storing the task information in a database; means for analyzing the stored task information and operating a generation model for generating a schedule suitable for the user; means for notifying a terminal of the user of the generated schedule; and analysis means for summarizing task information received from a plurality of users and clarifying a problem of an entire organization.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern organizations, many tasks arise, often resulting in work delays and a decline in quality. However, it is difficult to communicate the organizational issues behind these problems to superiors, and as a result, the problems remain unresolved. In this environment, there is a need for a method to efficiently manage individual tasks and clarify the issues facing the organization as a whole. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: a means for a user to input their own task information; a means for receiving the task information and saving it in a database; a means for analyzing the saved task information and operating a generation model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule at their terminal; and an analysis means for aggregating task information received from multiple users and clarifying issues across the organization. Furthermore, by including a means for a user to input the reason why they are unable to perform a task and sending it together with the task information, and a means for generating specific improvement measures based on the analyzed data and notifying the user or administrator of the improvement measures, the system simultaneously improves the work efficiency of each user and visualizes and resolves issues across the organization.

[0006] "User" refers to an individual or organization that uses the system to input and manage their own task information.

[0007] "Task information" refers to data about the details of the specific tasks and work carried out by the user.

[0008] "Generative model" refers to an artificial intelligence model used to analyze a user's task information and generate appropriate schedules and improvement measures.

[0009] "Terminal" refers to a device (e.g., PC, smartphone, etc.) that a user uses to access the system and input / receive information.

[0010] "Database" refers to a storage device for storing and managing received task information and other related data.

[0011] "Analysis means" refers to the processes and technologies used to analyze received data, generate schedules suitable for users, and clarify organizational issues.

[0012] "Means for notification" refers to a method or function for communicating the generated schedule or improvement measures to a user or administrator.

[0013] "Saved task information" refers to all task information stored in the database.

[0014] "Schedule generation" refers to the process of calculating and generating a timetable for efficiently performing work based on the user's task information.

[0015] "Identifying issues" refers to the process of visualizing problems and areas requiring improvement across the entire organization through analysis.

[0016] "Improvement measures" refer to specific problem-solving methods proposed based on analyzed data. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] The present invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. This system mainly consists of the following components:

[0039] User task input method

[0040] Users enter their task information through a dedicated application on their device or through a web interface. Users can enter information such as task details, importance, deadline, current progress, and resources required to complete the task. Users can also enter reasons why they cannot complete the task (e.g., other higher-priority work, technical issues, lack of time, etc.).

[0041] A means of receiving and storing task information

[0042] The server receives task information and reasons for inability sent from the terminal in real time. After receiving, this data is stored in a database and used for subsequent analysis and schedule generation. The database has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[0043] How to operate generative AI models

[0044] The server inputs the task information stored in the database into a generative AI model. The generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. The model uses past data and common optimization algorithms to propose a plan that maximizes the user's work efficiency.

[0045] Schedule notification method

[0046] The server sends the schedule output from the generated AI model to the device. The device notifies the user and presents the new schedule in the form of a pop-up notification or alert. The user can review and approve the proposed schedule, and can also make adjustments as needed.

[0047] A means of clarifying issues across the organization

[0048] The server analyzes the task information collected from each user and the reasons why the task cannot be completed, and identifies issues across the organization. This is done using multivariate analysis and clustering techniques. Specifically, it identifies common obstacles and frequently occurring problem areas (e.g., times of day when complaints are frequently handled, or bottlenecks in specific processes, etc.).

[0049] Remediation generation and notification measures

[0050] The server generates specific improvement measures based on the analysis results. These improvement measures proposed by the generative AI model may include, for example, allocating a dedicated complaint handling team during specific time periods, reprioritizing work, or allocating additional resources. These improvement measures are notified to users and administrators via their devices.

[0051] Specific examples

[0052] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user also inputs the reason, "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. Next, a generative AI model analyzes the user's schedule and suggests a schedule such as, "Walk through complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to that schedule.

[0053] In this way, this system not only improves the work efficiency of the user, but also clarifies issues throughout the organization and proposes improvement measures, thereby improving overall work efficiency.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The user logs in to a dedicated application or web interface on their device and enters task information, including task details, importance, deadline, progress, required resources, etc. In addition, the user also enters the reason why they cannot perform the task.

[0057] Step 2:

[0058] The device sends the entered task information and the reason for it to the server. The data is encoded in a standard format (e.g., JSON, XML).

[0059] Step 3:

[0060] The server parses the task information and reason received from the device and stores it in a database, where each data item is properly indexed and managed for efficient search and retrieval.

[0061] Step 4:

[0062] The server inputs the task information stored in the database into a generative AI model, which uses natural language processing (NLP) to analyze the text and evaluate the task's priority, required resources, and relationship with other tasks.

[0063] Step 5:

[0064] The server generates a schedule specifically for the user based on the analysis results output by the AI ​​model. The schedule is designed as a timetable to optimize the user's work efficiency.

[0065] Step 6:

[0066] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar display, timeline display).

[0067] Step 7:

[0068] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[0069] Step 8:

[0070] The user can then work according to the proposed schedule, and can adjust or provide feedback as needed.

[0071] Step 9:

[0072] The server analyzes task information collected from multiple users and the reasons for their actions to identify common issues and problems. Multivariate analysis and clustering are used as analytical methods.

[0073] Step 10:

[0074] Based on the analysis, the server generates specific improvement measures, such as suggestions to set up dedicated complaint handling teams for specific time periods or to reprioritize tasks.

[0075] Step 11:

[0076] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[0077] Step 12:

[0078] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[0079] Example 1

[0080] 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."

[0081] In today's work environment, it is difficult for individual users to efficiently manage and execute tasks. In particular, when important, time-consuming tasks overlap with daily work, users often struggle with time management, resulting in a significant decline in work efficiency. Furthermore, it is difficult for the organization as a whole to grasp each user's work status and challenges, making it difficult to optimize resource allocation and achieve efficient work processes. To solve these problems, it is necessary to collect detailed task information for each user and present an optimal schedule based on that information. It is also important to identify issues across the organization and provide efficient solutions.

[0082] 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.

[0083] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for the generative AI model to analyze the user's task information using natural language processing technology and generate a schedule; a means for the generative AI model to generate a proposed schedule based on past data and an optimization algorithm; and a means for the user to confirm and approve the proposed schedule through the notification. This not only improves the efficiency of task management for individual users and business efficiency, but also clarifies issues across the organization and provides effective solutions.

[0084] "User" refers to an individual or corporation that uses this system to input and manage task information.

[0085] "Task information" is detailed information about a task entered by a user, and includes the specific task content, importance, deadline, progress, and resources for execution.

[0086] "Device" refers to the device used by the user to enter task information and view the generated schedule, including PCs, smartphones, tablets, etc.

[0087] "Server" refers to a computer system that processes task information received from users and operates generative AI models.

[0088] "Database" means a system for storing task information and related data received by the Server, including fast indexing and searching capabilities.

[0089] A "generative model" refers to an algorithm or machine learning model used to analyze a user's task information and generate an optimal schedule.

[0090] "Natural language processing technology" refers to technology that enables a generative model to analyze and understand text data such as user task information.

[0091] "Past data" refers to a user's past task information and execution history, as well as the organization's business data.

[0092] "Optimization algorithm" refers to the mathematical method or algorithm used by the generative model to create a schedule that maximizes the user's work efficiency.

[0093] "Notification" refers to a communication method for informing the user's terminal of the generated schedule and improvement measures.

[0094] "Analysis means" refers to the tools and methods used by the server to analyze aggregated task information and clarify issues across the entire organization.

[0095] "Improvement measures" refer to specific measures or plans proposed based on analyzed data to improve business efficiency or solve problems.

[0096] This invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. Specifically, it provides a series of processes in which users, servers, and terminals work together to collect and analyze task information, and generate and notify optimal schedules.

[0097] Users input their task information using a dedicated application on their device or a web interface. The input task information includes task details, importance, deadline, current progress, required resources, and reasons why the task cannot be completed (e.g., other high-priority work, technical issues, lack of time, etc.). The device then sends this information to the server in real time.

[0098] The server receives task information sent from the devices and stores it in a database. This database has high-speed indexing and search functions, allowing for efficient data storage and retrieval. Specifically, it is assumed that a relational database management system such as MySQL will be used.

[0099] The server then inputs the saved task information into a generative AI model. This generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. External services such as the Google Cloud Natural Language API can be used. The generative AI model uses past data and optimization algorithms to propose a plan that maximizes the user's work efficiency.

[0100] The generated schedule is sent from the server to the device, which then provides it to the user in the form of a pop-up notification or alert. The user can then review the proposed schedule and approve it or make adjustments as necessary.

[0101] The server then analyzes the task information collected from each user and the reasons for inexecution, and performs analysis to clarify issues across the organization. For example, it uses Python's SciPy library to perform multivariate analysis and clustering to identify common obstacles and frequently occurring problem areas.

[0102] Based on the analysis results, the server generates specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The generated remedial measures are notified to the user or administrator via the terminal.

[0103] Specific examples

[0104] For example, a user in the product development department inputs the task "Write a proposal for a new product" and the reason "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. The generative AI model then analyzes this information and generates a schedule such as "Deal with complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to the schedule.

[0105] Example prompt sentence:

[0106] The user inputs the task "Create a proposal for a new product" and notes that they cannot find time to work on it due to a customer complaint. The generative AI model analyzes this and suggests a schedule that allows time to create the proposal after the complaint has been handled.

[0107] As described above, the present invention is a system that makes task management more efficient for each user, improves work efficiency, and also clarifies issues across the entire organization and provides effective solutions.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] The user enters task information. The user accesses a dedicated application on the device or a web interface and enters task information such as "Create a proposal for a new product," as well as the importance, deadline, progress, and reason for inability to execute (e.g., due to a customer complaint). The entered data is sent from the device to the server in JSON format.

[0111] Input: Task information (task name, importance, deadline, progress, reason for inability)

[0112] Output: JSON format task information (device → server)

[0113] Step 2:

[0114] The server receives task information. The server receives task information in JSON format sent from the device in real time and records it in a log. The received data is analyzed and saved in a database. This database is implemented using MySQL and has high-speed indexing and search functions.

[0115] Input: Task information in JSON format

[0116] Output: Task information stored in a database

[0117] Step 3:

[0118] The generative AI model analyzes task information. The server retrieves the task information from the database and passes it to the generative AI model. The generative AI model uses the Google Cloud Natural Language API to analyze the task information using natural language processing technology. Based on past data and an optimization algorithm, it generates an optimal schedule for the user. At this time, a specific algorithm is used to propose a schedule that maximizes the user's work efficiency.

[0119] Input: Task information retrieved from the database

[0120] Output: Generated schedule

[0121] Step 4:

[0122] The generated schedule is notified to the user. The server sends the schedule received from the generative AI model to the user's device. The device presents this schedule to the user in the form of a pop-up notification or alert. The user reviews the proposed schedule and approves or adjusts it as necessary.

[0123] Input: Generated schedule

[0124] Output: Schedule displayed on the terminal

[0125] Step 5:

[0126] The server analyzes issues across the entire organization. It retrieves aggregated task information from each user and the reasons for inexecution from a database, and performs multivariate analysis and clustering using tools such as Python's SciPy. This identifies common obstacles and frequently occurring problem areas.

[0127] Input: Aggregate task information retrieved from the database

[0128] Output: Identification of issues across the organization

[0129] Step 6:

[0130] The server generates and notifies improvement measures. Based on the analysis results, the server uses a generative AI model to generate specific improvement measures. These may include assigning a dedicated complaint handling team to a specific time period, reprioritizing work, or allocating additional resources. The generated improvement measures are notified to users and administrators via their devices.

[0131] Input: Identification of issues across the organization

[0132] Output: Remediation measures communicated to users and administrators

[0133] As described above, at each step, appropriate data processing and calculations are performed based on the input data, and the resulting output is passed on to the next step, ensuring that the entire system functions smoothly.

[0134] (Application example 1)

[0135] 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."

[0136] Conventional task management systems generate schedules based on task information entered by users, but they are unable to reflect those schedules on industrial machines. Furthermore, there are limited means for clarifying issues across the organization, and generating specific improvement measures takes time and effort. Furthermore, there is no mechanism for providing appropriate prompts when using generative AI models, which can lead to a decrease in the accuracy of schedule generation.

[0137] 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.

[0138] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for reflecting the results on industrial machines to improve work efficiency; and a means for inputting prompt statements for generating the schedule into the generative AI model. This not only enables efficient user task management and schedule generation, but also enables the generated schedule to be reflected on industrial machines to improve work efficiency. Furthermore, providing appropriate prompt statements improves the accuracy of schedule generation using the generative AI model.

[0139] "User" refers to an individual or organizational member who uses the system to enter and manage task information.

[0140] "Task information" refers to information entered by the user, such as task details, importance, deadline, progress, and reasons why the task cannot be performed.

[0141] "Database" refers to a storage system that stores task information received from users and has high-speed indexing and searching capabilities.

[0142] "Generative Model" refers to an artificial intelligence model used to analyze stored task information and generate a schedule appropriate for the user.

[0143] "Terminal" refers to a computer device or smart device that a user uses to input task information and check the generated schedule.

[0144] "Analysis means" refers to an analysis method or technology used to aggregate task information received from multiple users and clarify issues across the entire organization.

[0145] "Industrial machinery" refers to automated equipment, robots, and other mechanical devices used in factories and industrial sites.

[0146] A "prompt" refers to preprocessed text data or instructions to be input into a generative AI model.

[0147] "Generative AI model" refers to the machine learning algorithms and artificial intelligence techniques used to analyze text data and generate schedules.

[0148] This invention is a system that allows users to input their own task information and use a generative AI model to improve work efficiency. This system is configured as follows.

[0149] First, a means is needed for users to input task information. This can be done using devices such as smartphones or PCs. Users can enter task details, importance, deadlines, progress, resources required to complete the task, and reasons why a task cannot be completed through a dedicated application or web interface.

[0150] The server then receives the task information and stores it in a database with sophisticated indexing and searching capabilities for efficient data storage and retrieval.

[0151] The saved task information is analyzed by the server. Software (e.g., OpenAI GPT-3 API) is used to operate the generative AI model. The generative AI model analyzes the user's task information and generates an optimal schedule. At this time, a prompt sentence is input to the generative AI model. An example of a prompt sentence is shown below.

[0152] Task Information:

[0153] Assembly of Part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Delay in delivery of parts)

[0154] Based on the details of this task, please suggest the most efficient schedule possible.

[0155] The generated schedule is sent from the server to the user's device. The schedule is presented to the user in the form of a pop-up notification or alert. The user can review the proposed schedule and make adjustments as necessary.

[0156] The server also provides a means for generating schedules that are reflected in industrial machines, thereby further improving work efficiency.

[0157] Furthermore, the server aggregates task information received from multiple users and has analytical tools to clarify issues across the organization. Specifically, it uses multivariate analysis and clustering techniques to identify common obstacles and frequently occurring problem areas.

[0158] Based on this information, specific remedial measures can be generated and communicated to users and administrators, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources.

[0159] In this way, the present invention not only improves the work efficiency of the user, but also contributes to improving the work of the entire organization.

[0160] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0161] Step 1:

[0162] The user enters their task information into the device. Using a dedicated application or a web interface, the user enters task details, importance, deadline, progress, and, if necessary, reasons why the task cannot be completed. The entered task information is saved on the device in a data format such as JSON.

[0163] Step 2:

[0164] The device sends task information to the server. The device then sends the entered task information to the server in real time. The sent task information includes task details, importance, deadline, progress, and reasons for inability to complete the task. The server receives this information and stores it in a database. The database has a high-speed indexing function, enabling efficient data storage and retrieval.

[0165] Step 3:

[0166] The server analyzes the received task information. The server retrieves the task information stored in the database and generates a prompt to input into the generative AI model. The prompt contains the instructions necessary to generate a schedule based on the task information. For example, it could be in the format "Task information: - Assemble part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Late delivery of parts) Please propose the most efficient schedule possible based on the details of this task."

[0167] Step 4:

[0168] A generative AI model analyzes the prompts and generates an optimal schedule. The server uses a generative AI model (for example, OpenAI GPT-3 API) to generate a schedule based on the input prompts. This generative AI model uses natural language processing technology, past data, and optimization algorithms to generate a schedule for efficiently managing the user's tasks.

[0169] Step 5:

[0170] The server notifies the user's device of the generated schedule. The generated schedule is sent from the server to the user's device. The device displays the generated schedule to the user in the form of a pop-up notification or alert. The user can check the displayed schedule and adjust it as necessary.

[0171] Step 6:

[0172] The server aggregates task information and clarifies the issues facing the entire organization. The server aggregates task information received from multiple users and uses multivariate analysis and clustering techniques to clarify the issues facing the entire organization. Specifically, it identifies common obstacles and frequently occurring problem areas.

[0173] Step 7:

[0174] The server generates remedial measures and notifies the user or administrator. Based on the analysis results, the generative AI model proposes specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The remedial measures are then notified to the user or administrator and applied.

[0175] 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.

[0176] This invention relates to a system that allows users to input and manage their own task information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves the quality and efficiency of work by recognizing the user's emotional state and providing corresponding schedules and improvement measures.

[0177] User task input method

[0178] Users input task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[0179] Emotion Engine

[0180] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[0181] Means for receiving and storing task information and emotion data

[0182] The server receives task information and emotion data sent from the devices. This data is stored in a database for subsequent analysis and schedule generation. The database has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[0183] How to operate generative AI models

[0184] The server inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate task priority, required resources, and relationships with other tasks. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0185] Schedule notification method

[0186] The server generates a schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to assign intensive tasks.

[0187] A means of clarifying issues across the organization

[0188] The server analyzes the task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[0189] Remediation generation and notification measures

[0190] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated complaint handling team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[0191] Specific examples

[0192] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user inputs the reason "I can't concentrate on writing the proposal because I have to deal with customer complaints" and the emotion "I'm feeling stressed because of the complaints." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light tasks and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[0193] In this way, this system improves work efficiency while taking into account the user's emotional state, and by clarifying issues across the entire organization, it is possible to achieve optimal business operations.

[0194] The processing flow will be explained below.

[0195] Step 1:

[0196] Users log in to a dedicated application or web interface on their device and enter task information and their emotional state. Task information includes task details, importance, deadline, progress, required resources, etc. Emotional states include stress, fatigue, motivation, etc.

[0197] Step 2:

[0198] The device sends the entered task information, emotional state, and the reason why the task cannot be performed to the server. The data is encoded in a standard format (e.g., JSON, XML).

[0199] Step 3:

[0200] The server receives the task information, emotional state, and reasons for preventing task execution sent from the terminal, and stores these data in a database, where each data is appropriately indexed.

[0201] Step 4:

[0202] The server inputs the task information and emotion data stored in the database into the generative AI model and emotion engine, which then analyzes the emotional state using natural language processing and machine learning algorithms.

[0203] Step 5:

[0204] The generative AI model evaluates task priority, required resources, and relationships with other tasks, and combines this with emotional state data obtained from the emotion engine to generate a schedule that adapts to the user's emotional state.

[0205] Step 6:

[0206] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar view, timeline view). The schedule that reflects the emotional state may include, for example, rest periods to reduce stress and small tasks to increase motivation.

[0207] Step 7:

[0208] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[0209] Step 8:

[0210] The user follows the proposed schedule and can adjust or provide feedback as needed. The user can also report their feelings and progress on the task to the system.

[0211] Step 9:

[0212] The server analyzes task information, emotional data, and feedback collected from multiple users to clarify issues across the organization. Multivariate analysis and clustering are used as analytical methods. This allows common issues and problems to be identified (e.g., emotional fluctuations at specific times of the day, the emotional load of specific tasks, etc.).

[0213] Step 10:

[0214] The server generates specific improvement measures based on the analysis results. The generative AI model and emotion engine work together to suggest improvement measures such as assigning dedicated complaint handling teams to specific times, reprioritizing work, or providing additional resources or rest periods.

[0215] Step 11:

[0216] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[0217] Step 12:

[0218] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[0219] Example 2

[0220] 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."

[0221] Conventional task management systems simply manage task information without considering the user's emotional state. This can lead to a decline in work efficiency due to stress and fluctuations in motivation. It is also difficult to identify issues across the organization, making it difficult to propose specific improvement measures quickly and effectively.

[0222] 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.

[0223] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and saving it in a storage device; a means for analyzing the saved task information and the user's emotional state and using a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule to their information terminal; an analysis means for aggregating task information and emotional data received from multiple users and clarifying issues across the organization; a means for inputting a reason why a user cannot perform a task and sending it together with the task information; and a means for generating specific countermeasures based on the analyzed data and notifying the user or administrator of the countermeasures. This enables optimal task management that takes into account the user's emotional state, rapid clarification of issues across the organization, and proposals for specific improvements.

[0224] "User" means a person who uses the system to enter and manage their work information.

[0225] "Task information" is data including detailed task information, importance, deadline, progress, required resources, and reasons why a task cannot be performed.

[0226] An "information terminal" is an electronic device used by a user, such as a personal computer, smartphone, or tablet.

[0227] A "memory device" is a database or storage device for saving received data.

[0228] "Emotional state" refers to a user's psychological or emotional state, such as stress level, fatigue level, and motivation level.

[0229] A "generative model" is an algorithm or machine learning model that analyzes input data and generates a schedule that is appropriate for the user.

[0230] A "schedule" is a planner created by a generative model that includes the user's tasks and schedule.

[0231] The "analysis means" refers to a method or tool for analyzing issues across an entire organization using work information and emotion data received from multiple users.

[0232] "Specific measures" are initiatives proposed based on the analysis results, such as reprioritizing work, assigning dedicated teams, adding resources, and providing rest periods.

[0233] The present invention relates to a system that allows users to input and manage their own work information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves work quality and efficiency by recognizing the user's emotional state and providing corresponding schedules and improvement measures. An embodiment of the present invention is described below.

[0234] User's job information input method

[0235] Users enter task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[0236] Emotion Engine

[0237] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[0238] Means for receiving and storing work information and emotional data

[0239] The server receives the task information and emotion data sent from the device. This data is stored in a storage device for subsequent analysis and schedule generation. The storage device has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[0240] How to operate generative AI models

[0241] The server inputs the stored work information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0242] Calendar notification methods

[0243] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to allocate intensive work.

[0244] A means of clarifying issues across the organization

[0245] The server analyzes the work information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[0246] Remediation generation and notification measures

[0247] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated response team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[0248] Specific examples

[0249] For example, suppose a user in a product development department inputs the task of "writing a proposal for a new product." The user enters the reason that "I can't concentrate on writing the proposal because I have to deal with customers," and the emotion that "I'm feeling stressed by dealing with them." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light work and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[0250] Example prompt sentence:

[0251] "Write a Python script that generates an optimal schedule based on task information and emotion data entered by a user in a task management system."

[0252] In this way, the system of the present invention improves business efficiency while taking into account the emotional state of the user, and by clarifying the issues facing the entire organization, it is possible to achieve optimal business operations.

[0253] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0254] Step 1:

[0255] Users input task information through a dedicated application on their device or a web interface, including details of the task, its importance, deadline, progress, required resources, reasons for not being able to perform the task, and current feelings (e.g., stress, fatigue, lack of motivation).

[0256] Specific operation: The user opens a dedicated application and enters information such as "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," "Lack of materials resources," and "Unable to concentrate on customer support. Stressful."

[0257] Input: User-entered task information and emotion data.

[0258] Output: Data sent from the device to the server.

[0259] Step 2:

[0260] The device sends the user's input and voice data in real time to the emotion engine, which uses natural language processing (NLP) and machine learning algorithms to analyze the user's emotional state and transmits it to the server as an emotion code.

[0261] Specific operation: The device sends text information such as "I can't concentrate on dealing with customers. I'm stressed" to the emotion engine, which then codes this as "high stress."

[0262] Input: User text information or voice data.

[0263] Output: Parsed emotion code.

[0264] Step 3:

[0265] The server receives the task information and emotion data sent from the device and stores it in a storage device. The stored data is used for subsequent analysis and schedule generation. The storage device has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[0266] Specific operation: The server receives the data "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," and "High stress," and stores it in the database.

[0267] Input: Task information and emotion data received from the terminal.

[0268] Output: Data stored in the database.

[0269] Step 4:

[0270] The server inputs the stored work information and emotional data into a generative AI model, which then performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. It also takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0271] Specific operation: The server inputs the job information of "writing a proposal for a new product" and the emotional data of "high stress" into the generative AI model, and the model begins analysis.

[0272] Input: Job information and emotion data stored in a database.

[0273] Output: The generated calendar.

[0274] Step 5:

[0275] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The generated schedule is adjusted to reflect the user's emotional state.

[0276] Specific operation: Based on the analysis results of the generated AI model, the server generates a schedule that "allocates light tasks and breaks in the morning, and focuses on creating proposals in the afternoon," and notifies the user's device of this.

[0277] Input: Analysis results from a generative AI model.

[0278] Output: Calendar notified to the device.

[0279] Step 6:

[0280] The server analyzes the work information and emotion data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems.

[0281] Specific operation: The server performs multivariate analysis of data collected from all users and identifies a common issue: "Customer service in the morning increases stress overall."

[0282] Input: Aggregated job information and emotion data.

[0283] Output: Analysis of issues across the organization.

[0284] Step 7:

[0285] The server generates specific improvement measures based on the analysis results and notifies the user or administrator via the device. The generative AI model and emotion engine work together to propose improvement measures such as "assigning a dedicated customer support team in the morning" or "changing work priorities."

[0286] Specific operation: The server generates "establishment of a dedicated team to handle complaints in the morning" as a remedial measure and notifies the user and administrator terminals of this.

[0287] Input: Results of an analysis of issues across the organization.

[0288] Output: Specific improvement measures.

[0289] This concludes the explanation of the process flow of this system, broken down into specific processing steps. Using this system enables efficient task management that takes into account the user's emotional state, and enables quick and effective solutions to issues across the organization.

[0290] (Application example 2)

[0291] 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."

[0292] In modern factory environments, efficient management of tasks performed by robots and appropriate assignment of work schedules that take into account their emotional states are required. Conventional systems have difficulty integrating the management of task information and the emotional states of robots to provide optimal schedules, which can result in reduced productivity and the accumulation of stress. To solve this problem, a system that integrates the input and management of task information, the analysis of emotional states, and appropriate task assignment is required.

[0293] 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.

[0294] In this invention, the server includes a means for users to input their own task information, a means for receiving the task information and saving it in a database, a means for analyzing the saved task information and operating a generation model to generate a schedule suitable for the user, a means for notifying the generated schedule to the user's terminal, a means for notifying the schedule to a robot that executes the schedule, and an analysis means for aggregating task information received from multiple users and clarifying issues across the organization. This enables efficient management of tasks handled by robots and appropriate allocation of work schedules that take emotional states into account.

[0295] A "user" is someone who uses the system to input and manage task information.

[0296] "Task information" is information such as task details, importance, deadline, current progress, and required resources entered by the user.

[0297] The "input means" refers to a means by which a user inputs task information through a dedicated application on a terminal or a web interface.

[0298] The "receiving means" is a means by which the system receives task information input by the user.

[0299] A "database" is a structured data storage system for storing received task information and emotion data.

[0300] The "analysis means" is a means for performing data analysis based on the saved task information and emotion data to generate a schedule suitable for the user.

[0301] A "generative model" is an algorithm or AI model that generates optimal schedules and improvement measures based on received task information and emotional data.

[0302] The "notification means" is a means for notifying the generated schedule to the user's terminal or the robot.

[0303] A "terminal" is an electronic device that a user uses to input task information and receive a generated schedule.

[0304] A "robot" is an automated machine that operates in a factory to perform specific tasks.

[0305] The "aggregation means" is a means for centralizing, integrating and managing task information received from a plurality of users.

[0306] "Issues across the organization" are problems or matters requiring improvement that are common across the organization and are discovered based on task information collected from multiple users.

[0307] In the system for realizing this application example, the program is configured as follows.

[0308] First, the user inputs task information. This task information is input through a dedicated application or web interface on the user's device. The device receives the input task information and sends it to the server. Specifically, the input information includes task details, importance, deadline, current progress, required resources, reasons for not being able to complete the task, and current emotional state (e.g., stress, fatigue, lack of motivation, etc.).

[0309] The server receives task information and emotion data sent from the devices and stores them in a database, which is designed for efficient data storage and retrieval with fast indexing and search capabilities.

[0310] The server then inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis using natural language processing (NLP) algorithms such as OpenAI's GPT-4 to evaluate the task's priority, required resources, and its relationship with other tasks. At the same time, it generates a schedule adapted to the user's emotional state based on the emotional data. For example, if the task details are "Assemble part A" and the emotional state is "Stressed due to a lack of parts," the generative AI model analyzes this and proposes an optimal task schedule.

[0311] The generated schedule is sent from the server to the user's terminal. The schedule is also sent to the robots in the factory. Specifically, the schedule is sent to the robots via an HTTP POST request using a robot API (e.g., Robot Operating System (ROS)).

[0312] The server analyzes task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used for the analysis to identify common issues and problems. Based on the analysis results, the generative AI model and emotion engine generate specific improvement measures, which are then notified to users and managers. For example, the server can suggest appropriate rest periods or the allocation of dedicated teams to address emotional fluctuations during specific time periods or the emotional load of specific tasks.

[0313] As a specific example, if the task details are "assembling part A" and the emotional state is "stressed due to a lack of parts," this information is input into the generative AI model, and a prompt sentence is generated as follows:

[0314] Emotional state analyzed: Stress due to parts shortage

[0315] Sentiment analysis results:

[0316]

[0317] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[0318] Proposed schedule:

[0319] This prompt text is input into a generative AI model, and an optimal schedule is generated and notified based on the analysis results, enabling task management and efficient operation within the factory.

[0320] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0321] Step 1:

[0322] The user enters task information.

[0323] Input: The user uses a dedicated application on the device or a web interface to input task details, importance, deadline, current progress, required resources, and emotional state (e.g., stress, fatigue, lack of motivation).

[0324] Operation: The entered information is sent to the terminal and forwarded to the server.

[0325] Step 2:

[0326] The server receives the task information and stores it in a database.

[0327] Input: Task information and emotion data sent from the device.

[0328] Data processing / data calculation: The server analyzes the received information and converts it into a format that can be stored in the database.

[0329] How it works: Data is stored in a database with fast indexing and searching capabilities.

[0330] Output: Saved task information and emotion data.

[0331] Step 3:

[0332] The server inputs the stored task information and emotion data into the generative AI model.

[0333] Input: Task information and emotion data stored in a database.

[0334] Data processing / data calculation: Generative AI models use natural language processing (NLP) algorithms to analyze text and assess task priority, required resources, and relationships with other tasks, while also analyzing sentiment data.

[0335] Operation:

[0336] If the task details are "Assemble part A" and the emotional state is "Stressed due to missing parts," generate the following prompt:

[0337] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[0338] Proposed schedule:

[0339] This prompt sentence is fed into a generative AI model to generate an optimal schedule.

[0340] Output: The generated schedule.

[0341] Step 4:

[0342] The server notifies the user's terminal of the generated schedule.

[0343] Input: The generated schedule.

[0344] Data processing / data calculation: Converts schedule data into a format that is easy for users to understand.

[0345] Operation:

[0346] The server transmits the generated schedule to the user's terminal via the notification means.

[0347] The terminal displays the received schedule.

[0348] Output: The schedule notified to the user.

[0349] Step 5:

[0350] The server notifies the robot of the generated schedule.

[0351] Input: The generated schedule.

[0352] Data processing / data calculation: Converts schedule data into a format that can be executed by the robot.

[0353] How it works: A schedule is sent to a robot via the Robots API via an HTTP POST request.

[0354] Output: The schedule notified to the robot.

[0355] Step 6:

[0356] The server analyzes task information aggregated from multiple users and clarifies issues across the organization.

[0357] Input: Task information and emotion data collected from multiple users.

[0358] Data processing / data calculation: Analyze data using multivariate analysis and clustering techniques to identify common issues and problems.

[0359] How it works: Based on the analysis results, issues across the organization are clarified and a report is generated.

[0360] Output: Clarified organization-wide challenges.

[0361] Step 7:

[0362] The server generates specific remedial measures based on the analyzed data and notifies the user or administrator of the remedial measures.

[0363] Input: Data after analysis and results of generative AI models.

[0364] Data processing / data calculation: Generate specific improvement measures based on the analysis results and create notification content.

[0365] Operation:

[0366] Improvement measures are proposed using a generative AI model and notified to administrators and users via notification means.

[0367] Output: Specific remediation measures communicated to the user or administrator.

[0368] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0369] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0370] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0371] [Second embodiment]

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

[0373] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0374] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0375] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0376] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0377] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0378] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0379] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0380] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0381] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0382] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0383] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0384] The present invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. This system mainly consists of the following components:

[0385] User task input method

[0386] Users enter their task information through a dedicated application on their device or through a web interface. Users can enter information such as task details, importance, deadline, current progress, and resources required to complete the task. Users can also enter reasons why they cannot complete the task (e.g., other higher-priority work, technical issues, lack of time, etc.).

[0387] A means of receiving and storing task information

[0388] The server receives task information and reasons for inability sent from the terminal in real time. After receiving, this data is stored in a database and used for subsequent analysis and schedule generation. The database has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[0389] How to operate generative AI models

[0390] The server inputs the task information stored in the database into a generative AI model. The generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. The model uses past data and common optimization algorithms to propose a plan that maximizes the user's work efficiency.

[0391] Schedule notification method

[0392] The server sends the schedule output from the generated AI model to the device. The device notifies the user and presents the new schedule in the form of a pop-up notification or alert. The user can review and approve the proposed schedule, and can also make adjustments as needed.

[0393] A means of clarifying issues across the organization

[0394] The server analyzes the task information collected from each user and the reasons why the task cannot be completed, and identifies issues across the organization. This is done using multivariate analysis and clustering techniques. Specifically, it identifies common obstacles and frequently occurring problem areas (e.g., times of day when complaints are frequently handled, or bottlenecks in specific processes, etc.).

[0395] Remediation generation and notification measures

[0396] The server generates specific improvement measures based on the analysis results. These improvement measures proposed by the generative AI model may include, for example, allocating a dedicated complaint handling team during specific time periods, reprioritizing work, or allocating additional resources. These improvement measures are notified to users and administrators via their devices.

[0397] Specific examples

[0398] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user also inputs the reason, "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. Next, a generative AI model analyzes the user's schedule and suggests a schedule such as, "Walk through complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to that schedule.

[0399] In this way, this system not only improves the work efficiency of the user, but also clarifies issues throughout the organization and proposes improvement measures, thereby improving overall work efficiency.

[0400] The processing flow will be explained below.

[0401] Step 1:

[0402] The user logs in to a dedicated application or web interface on their device and enters task information, including task details, importance, deadline, progress, required resources, etc. In addition, the user also enters the reason why they cannot perform the task.

[0403] Step 2:

[0404] The device sends the entered task information and the reason for it to the server. The data is encoded in a standard format (e.g., JSON, XML).

[0405] Step 3:

[0406] The server parses the task information and reason received from the device and stores it in a database, where each data item is properly indexed and managed for efficient search and retrieval.

[0407] Step 4:

[0408] The server inputs the task information stored in the database into a generative AI model, which uses natural language processing (NLP) to analyze the text and evaluate the task's priority, required resources, and relationship with other tasks.

[0409] Step 5:

[0410] The server generates a schedule specifically for the user based on the analysis results output by the AI ​​model. The schedule is designed as a timetable to optimize the user's work efficiency.

[0411] Step 6:

[0412] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar display, timeline display).

[0413] Step 7:

[0414] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[0415] Step 8:

[0416] The user can then work according to the proposed schedule, and can adjust or provide feedback as needed.

[0417] Step 9:

[0418] The server analyzes task information collected from multiple users and the reasons for their actions to identify common issues and problems. Multivariate analysis and clustering are used as analytical methods.

[0419] Step 10:

[0420] Based on the analysis, the server generates specific improvement measures, such as suggestions to set up dedicated complaint handling teams for specific time periods or to reprioritize tasks.

[0421] Step 11:

[0422] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[0423] Step 12:

[0424] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[0425] Example 1

[0426] 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."

[0427] In today's work environment, it is difficult for individual users to efficiently manage and execute tasks. In particular, when important, time-consuming tasks overlap with daily work, users often struggle with time management, resulting in a significant decline in work efficiency. Furthermore, it is difficult for the organization as a whole to grasp each user's work status and challenges, making it difficult to optimize resource allocation and achieve efficient work processes. To solve these problems, it is necessary to collect detailed task information for each user and present an optimal schedule based on that information. It is also important to identify issues across the organization and provide efficient solutions.

[0428] 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.

[0429] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for the generative AI model to analyze the user's task information using natural language processing technology and generate a schedule; a means for the generative AI model to generate a proposed schedule based on past data and an optimization algorithm; and a means for the user to confirm and approve the proposed schedule through the notification. This not only improves the efficiency of task management for individual users and business efficiency, but also clarifies issues across the organization and provides effective solutions.

[0430] "User" refers to an individual or corporation that uses this system to input and manage task information.

[0431] "Task information" is detailed information about a task entered by a user, and includes the specific task content, importance, deadline, progress, and resources for execution.

[0432] "Device" refers to the device used by the user to enter task information and view the generated schedule, including PCs, smartphones, tablets, etc.

[0433] "Server" refers to a computer system that processes task information received from users and operates generative AI models.

[0434] "Database" means a system for storing task information and related data received by the Server, including fast indexing and searching capabilities.

[0435] A "generative model" refers to an algorithm or machine learning model used to analyze a user's task information and generate an optimal schedule.

[0436] "Natural language processing technology" refers to technology that enables a generative model to analyze and understand text data such as user task information.

[0437] "Past data" refers to a user's past task information and execution history, as well as the organization's business data.

[0438] "Optimization algorithm" refers to the mathematical method or algorithm used by the generative model to create a schedule that maximizes the user's work efficiency.

[0439] "Notification" refers to a communication method for informing the user's terminal of the generated schedule and improvement measures.

[0440] "Analysis means" refers to the tools and methods used by the server to analyze aggregated task information and clarify issues across the entire organization.

[0441] "Improvement measures" refer to specific measures or plans proposed based on analyzed data to improve business efficiency or solve problems.

[0442] This invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. Specifically, it provides a series of processes in which users, servers, and terminals work together to collect and analyze task information, and generate and notify optimal schedules.

[0443] Users input their task information using a dedicated application on their device or a web interface. The input task information includes task details, importance, deadline, current progress, required resources, and reasons why the task cannot be completed (e.g., other high-priority work, technical issues, lack of time, etc.). The device then sends this information to the server in real time.

[0444] The server receives task information sent from the devices and stores it in a database. This database has high-speed indexing and search functions, allowing for efficient data storage and retrieval. Specifically, it is assumed that a relational database management system such as MySQL will be used.

[0445] The server then inputs the saved task information into a generative AI model. This generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. External services such as the Google Cloud Natural Language API can be used. The generative AI model uses past data and optimization algorithms to propose a plan that maximizes the user's work efficiency.

[0446] The generated schedule is sent from the server to the device, which then provides it to the user in the form of a pop-up notification or alert. The user can then review the proposed schedule and approve it or make adjustments as necessary.

[0447] The server then analyzes the task information collected from each user and the reasons for inexecution, and performs analysis to clarify issues across the organization. For example, it uses Python's SciPy library to perform multivariate analysis and clustering to identify common obstacles and frequently occurring problem areas.

[0448] Based on the analysis results, the server generates specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The generated remedial measures are notified to the user or administrator via the terminal.

[0449] Specific examples

[0450] For example, a user in the product development department inputs the task "Write a proposal for a new product" and the reason "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. The generative AI model then analyzes this information and generates a schedule such as "Deal with complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to the schedule.

[0451] Example prompt sentence:

[0452] The user inputs the task "Create a proposal for a new product" and notes that they cannot find time to work on it due to a customer complaint. The generative AI model analyzes this and suggests a schedule that allows time to create the proposal after the complaint has been handled.

[0453] As described above, the present invention is a system that makes task management more efficient for each user, improves work efficiency, and also clarifies issues across the entire organization and provides effective solutions.

[0454] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0455] Step 1:

[0456] The user enters task information. The user accesses a dedicated application on the device or a web interface and enters task information such as "Create a proposal for a new product," as well as the importance, deadline, progress, and reason for inability to execute (e.g., due to a customer complaint). The entered data is sent from the device to the server in JSON format.

[0457] Input: Task information (task name, importance, deadline, progress, reason for inability)

[0458] Output: JSON format task information (device → server)

[0459] Step 2:

[0460] The server receives task information. The server receives task information in JSON format sent from the device in real time and records it in a log. The received data is analyzed and saved in a database. This database is implemented using MySQL and has high-speed indexing and search functions.

[0461] Input: Task information in JSON format

[0462] Output: Task information stored in a database

[0463] Step 3:

[0464] The generative AI model analyzes task information. The server retrieves the task information from the database and passes it to the generative AI model. The generative AI model uses the Google Cloud Natural Language API to analyze the task information using natural language processing technology. Based on past data and an optimization algorithm, it generates an optimal schedule for the user. At this time, a specific algorithm is used to propose a schedule that maximizes the user's work efficiency.

[0465] Input: Task information retrieved from the database

[0466] Output: Generated schedule

[0467] Step 4:

[0468] The generated schedule is notified to the user. The server sends the schedule received from the generative AI model to the user's device. The device presents this schedule to the user in the form of a pop-up notification or alert. The user reviews the proposed schedule and approves or adjusts it as necessary.

[0469] Input: Generated schedule

[0470] Output: Schedule displayed on the terminal

[0471] Step 5:

[0472] The server analyzes issues across the entire organization. It retrieves aggregated task information from each user and the reasons for inexecution from a database, and performs multivariate analysis and clustering using tools such as Python's SciPy. This identifies common obstacles and frequently occurring problem areas.

[0473] Input: Aggregate task information retrieved from the database

[0474] Output: Identification of issues across the organization

[0475] Step 6:

[0476] The server generates and notifies improvement measures. Based on the analysis results, the server uses a generative AI model to generate specific improvement measures. These may include assigning a dedicated complaint handling team to a specific time period, reprioritizing work, or allocating additional resources. The generated improvement measures are notified to users and administrators via their devices.

[0477] Input: Identification of issues across the organization

[0478] Output: Remediation measures communicated to users and administrators

[0479] As described above, at each step, appropriate data processing and calculations are performed based on the input data, and the resulting output is passed on to the next step, ensuring that the entire system functions smoothly.

[0480] (Application example 1)

[0481] 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."

[0482] Conventional task management systems generate schedules based on task information entered by users, but they are unable to reflect those schedules on industrial machines. Furthermore, there are limited means for clarifying issues across the organization, and generating specific improvement measures takes time and effort. Furthermore, there is no mechanism for providing appropriate prompts when using generative AI models, which can lead to a decrease in the accuracy of schedule generation.

[0483] 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.

[0484] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for reflecting the results on industrial machines to improve work efficiency; and a means for inputting prompt statements for generating the schedule into the generative AI model. This not only enables efficient user task management and schedule generation, but also enables the generated schedule to be reflected on industrial machines to improve work efficiency. Furthermore, providing appropriate prompt statements improves the accuracy of schedule generation using the generative AI model.

[0485] "User" refers to an individual or organizational member who uses the system to enter and manage task information.

[0486] "Task information" refers to information entered by the user, such as task details, importance, deadline, progress, and reasons why the task cannot be performed.

[0487] "Database" refers to a storage system that stores task information received from users and has high-speed indexing and searching capabilities.

[0488] "Generative Model" refers to an artificial intelligence model used to analyze stored task information and generate a schedule appropriate for the user.

[0489] "Terminal" refers to a computer device or smart device that a user uses to input task information and check the generated schedule.

[0490] "Analysis means" refers to an analysis method or technology used to aggregate task information received from multiple users and clarify issues across the entire organization.

[0491] "Industrial machinery" refers to automated equipment, robots, and other mechanical devices used in factories and industrial sites.

[0492] A "prompt" refers to preprocessed text data or instructions to be input into a generative AI model.

[0493] "Generative AI model" refers to the machine learning algorithms and artificial intelligence techniques used to analyze text data and generate schedules.

[0494] This invention is a system that allows users to input their own task information and use a generative AI model to improve work efficiency. This system is configured as follows.

[0495] First, a means is needed for users to input task information. This can be done using devices such as smartphones or PCs. Users can enter task details, importance, deadlines, progress, resources required to complete the task, and reasons why a task cannot be completed through a dedicated application or web interface.

[0496] The server then receives the task information and stores it in a database with sophisticated indexing and searching capabilities for efficient data storage and retrieval.

[0497] The saved task information is analyzed by the server. Software (e.g., OpenAI GPT-3 API) is used to operate the generative AI model. The generative AI model analyzes the user's task information and generates an optimal schedule. At this time, a prompt sentence is input to the generative AI model. An example of a prompt sentence is shown below.

[0498] Task Information:

[0499] Assembly of Part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Delay in delivery of parts)

[0500] Based on the details of this task, please suggest the most efficient schedule possible.

[0501] The generated schedule is sent from the server to the user's device. The schedule is presented to the user in the form of a pop-up notification or alert. The user can review the proposed schedule and make adjustments as necessary.

[0502] The server also provides a means for generating schedules that are reflected in industrial machines, thereby further improving work efficiency.

[0503] Furthermore, the server aggregates task information received from multiple users and has analytical tools to clarify issues across the organization. Specifically, it uses multivariate analysis and clustering techniques to identify common obstacles and frequently occurring problem areas.

[0504] Based on this information, specific remedial measures can be generated and communicated to users and administrators, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources.

[0505] In this way, the present invention not only improves the work efficiency of the user, but also contributes to improving the work of the entire organization.

[0506] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0507] Step 1:

[0508] The user enters their task information into the device. Using a dedicated application or a web interface, the user enters task details, importance, deadline, progress, and, if necessary, reasons why the task cannot be completed. The entered task information is saved on the device in a data format such as JSON.

[0509] Step 2:

[0510] The device sends task information to the server. The device then sends the entered task information to the server in real time. The sent task information includes task details, importance, deadline, progress, and reasons for inability to complete the task. The server receives this information and stores it in a database. The database has a high-speed indexing function, enabling efficient data storage and retrieval.

[0511] Step 3:

[0512] The server analyzes the received task information. The server retrieves the task information stored in the database and generates a prompt to input into the generative AI model. The prompt contains the instructions necessary to generate a schedule based on the task information. For example, it could be in the format "Task information: - Assemble part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Late delivery of parts) Please propose the most efficient schedule possible based on the details of this task."

[0513] Step 4:

[0514] A generative AI model analyzes the prompts and generates an optimal schedule. The server uses a generative AI model (for example, OpenAI GPT-3 API) to generate a schedule based on the input prompts. This generative AI model uses natural language processing technology, past data, and optimization algorithms to generate a schedule for efficiently managing the user's tasks.

[0515] Step 5:

[0516] The server notifies the user's device of the generated schedule. The generated schedule is sent from the server to the user's device. The device displays the generated schedule to the user in the form of a pop-up notification or alert. The user can check the displayed schedule and adjust it as necessary.

[0517] Step 6:

[0518] The server aggregates task information and clarifies the issues facing the entire organization. The server aggregates task information received from multiple users and uses multivariate analysis and clustering techniques to clarify the issues facing the entire organization. Specifically, it identifies common obstacles and frequently occurring problem areas.

[0519] Step 7:

[0520] The server generates remedial measures and notifies the user or administrator. Based on the analysis results, the generative AI model proposes specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The remedial measures are then notified to the user or administrator and applied.

[0521] 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.

[0522] This invention relates to a system that allows users to input and manage their own task information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves the quality and efficiency of work by recognizing the user's emotional state and providing corresponding schedules and improvement measures.

[0523] User task input method

[0524] Users input task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[0525] Emotion Engine

[0526] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[0527] Means for receiving and storing task information and emotion data

[0528] The server receives task information and emotion data sent from the devices. This data is stored in a database for subsequent analysis and schedule generation. The database has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[0529] How to operate generative AI models

[0530] The server inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate task priority, required resources, and relationships with other tasks. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0531] Schedule notification method

[0532] The server generates a schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to assign intensive tasks.

[0533] A means of clarifying issues across the organization

[0534] The server analyzes the task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[0535] Remediation generation and notification measures

[0536] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated complaint handling team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[0537] Specific examples

[0538] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user inputs the reason "I can't concentrate on writing the proposal because I have to deal with customer complaints" and the emotion "I'm feeling stressed because of the complaints." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light tasks and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[0539] In this way, this system improves work efficiency while taking into account the user's emotional state, and by clarifying issues across the entire organization, it is possible to achieve optimal business operations.

[0540] The processing flow will be explained below.

[0541] Step 1:

[0542] Users log in to a dedicated application or web interface on their device and enter task information and their emotional state. Task information includes task details, importance, deadline, progress, required resources, etc. Emotional states include stress, fatigue, motivation, etc.

[0543] Step 2:

[0544] The device sends the entered task information, emotional state, and the reason why the task cannot be performed to the server. The data is encoded in a standard format (e.g., JSON, XML).

[0545] Step 3:

[0546] The server receives the task information, emotional state, and reasons for preventing task execution sent from the terminal, and stores these data in a database, where each data is appropriately indexed.

[0547] Step 4:

[0548] The server inputs the task information and emotion data stored in the database into the generative AI model and emotion engine, which then analyzes the emotional state using natural language processing and machine learning algorithms.

[0549] Step 5:

[0550] The generative AI model evaluates task priority, required resources, and relationships with other tasks, and combines this with emotional state data obtained from the emotion engine to generate a schedule that adapts to the user's emotional state.

[0551] Step 6:

[0552] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar view, timeline view). The schedule that reflects the emotional state may include, for example, rest periods to reduce stress and small tasks to increase motivation.

[0553] Step 7:

[0554] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[0555] Step 8:

[0556] The user follows the proposed schedule and can adjust or provide feedback as needed. The user can also report their feelings and progress on the task to the system.

[0557] Step 9:

[0558] The server analyzes task information, emotional data, and feedback collected from multiple users to clarify issues across the organization. Multivariate analysis and clustering are used as analytical methods. This allows common issues and problems to be identified (e.g., emotional fluctuations at specific times of the day, the emotional load of specific tasks, etc.).

[0559] Step 10:

[0560] The server generates specific improvement measures based on the analysis results. The generative AI model and emotion engine work together to suggest improvement measures such as assigning dedicated complaint handling teams to specific times, reprioritizing work, or providing additional resources or rest periods.

[0561] Step 11:

[0562] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[0563] Step 12:

[0564] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[0565] Example 2

[0566] 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."

[0567] Conventional task management systems simply manage task information without considering the user's emotional state. This can lead to a decline in work efficiency due to stress and fluctuations in motivation. It is also difficult to identify issues across the organization, making it difficult to propose specific improvement measures quickly and effectively.

[0568] 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.

[0569] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and saving it in a storage device; a means for analyzing the saved task information and the user's emotional state and using a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule to their information terminal; an analysis means for aggregating task information and emotional data received from multiple users and clarifying issues across the organization; a means for inputting a reason why a user cannot perform a task and sending it together with the task information; and a means for generating specific countermeasures based on the analyzed data and notifying the user or administrator of the countermeasures. This enables optimal task management that takes into account the user's emotional state, rapid clarification of issues across the organization, and proposals for specific improvements.

[0570] "User" means a person who uses the system to enter and manage their work information.

[0571] "Task information" is data including detailed task information, importance, deadline, progress, required resources, and reasons why a task cannot be performed.

[0572] An "information terminal" is an electronic device used by a user, such as a personal computer, smartphone, or tablet.

[0573] A "memory device" is a database or storage device for saving received data.

[0574] "Emotional state" refers to a user's psychological or emotional state, such as stress level, fatigue level, and motivation level.

[0575] A "generative model" is an algorithm or machine learning model that analyzes input data and generates a schedule that is appropriate for the user.

[0576] A "schedule" is a planner created by a generative model that includes the user's tasks and schedule.

[0577] The "analysis means" refers to a method or tool for analyzing issues across an entire organization using work information and emotion data received from multiple users.

[0578] "Specific measures" are initiatives proposed based on the analysis results, such as reprioritizing work, assigning dedicated teams, adding resources, and providing rest periods.

[0579] The present invention relates to a system that allows users to input and manage their own work information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves work quality and efficiency by recognizing the user's emotional state and providing corresponding schedules and improvement measures. An embodiment of the present invention is described below.

[0580] User's job information input method

[0581] Users enter task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[0582] Emotion Engine

[0583] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[0584] Means for receiving and storing work information and emotional data

[0585] The server receives the task information and emotion data sent from the device. This data is stored in a storage device for subsequent analysis and schedule generation. The storage device has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[0586] How to operate generative AI models

[0587] The server inputs the stored work information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0588] Calendar notification methods

[0589] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to allocate intensive work.

[0590] A means of clarifying issues across the organization

[0591] The server analyzes the work information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[0592] Remediation generation and notification measures

[0593] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated response team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[0594] Specific examples

[0595] For example, suppose a user in a product development department inputs the task of "writing a proposal for a new product." The user enters the reason that "I can't concentrate on writing the proposal because I have to deal with customers," and the emotion that "I'm feeling stressed by dealing with them." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light work and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[0596] Example prompt sentence:

[0597] "Write a Python script that generates an optimal schedule based on task information and emotion data entered by a user in a task management system."

[0598] In this way, the system of the present invention improves business efficiency while taking into account the emotional state of the user, and by clarifying the issues facing the entire organization, it is possible to achieve optimal business operations.

[0599] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0600] Step 1:

[0601] Users input task information through a dedicated application on their device or a web interface, including details of the task, its importance, deadline, progress, required resources, reasons for not being able to perform the task, and current feelings (e.g., stress, fatigue, lack of motivation).

[0602] Specific operation: The user opens a dedicated application and enters information such as "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," "Lack of materials resources," and "Unable to concentrate on customer support. Stressful."

[0603] Input: User-entered task information and emotion data.

[0604] Output: Data sent from the device to the server.

[0605] Step 2:

[0606] The device sends the user's input and voice data in real time to the emotion engine, which uses natural language processing (NLP) and machine learning algorithms to analyze the user's emotional state and transmits it to the server as an emotion code.

[0607] Specific operation: The device sends text information such as "I can't concentrate on dealing with customers. I'm stressed" to the emotion engine, which then codes this as "high stress."

[0608] Input: User text information or voice data.

[0609] Output: Parsed emotion code.

[0610] Step 3:

[0611] The server receives the task information and emotion data sent from the device and stores it in a storage device. The stored data is used for subsequent analysis and schedule generation. The storage device has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[0612] Specific operation: The server receives the data "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," and "High stress," and stores it in the database.

[0613] Input: Task information and emotion data received from the terminal.

[0614] Output: Data stored in the database.

[0615] Step 4:

[0616] The server inputs the stored work information and emotional data into a generative AI model, which then performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. It also takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0617] Specific operation: The server inputs the job information of "writing a proposal for a new product" and the emotional data of "high stress" into the generative AI model, and the model begins analysis.

[0618] Input: Job information and emotion data stored in a database.

[0619] Output: The generated calendar.

[0620] Step 5:

[0621] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The generated schedule is adjusted to reflect the user's emotional state.

[0622] Specific operation: Based on the analysis results of the generated AI model, the server generates a schedule that "allocates light tasks and breaks in the morning, and focuses on creating proposals in the afternoon," and notifies the user's device of this.

[0623] Input: Analysis results from a generative AI model.

[0624] Output: Calendar notified to the device.

[0625] Step 6:

[0626] The server analyzes the work information and emotion data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems.

[0627] Specific operation: The server performs multivariate analysis of data collected from all users and identifies a common issue: "Customer service in the morning increases stress overall."

[0628] Input: Aggregated job information and emotion data.

[0629] Output: Analysis of issues across the organization.

[0630] Step 7:

[0631] The server generates specific improvement measures based on the analysis results and notifies the user or administrator via the device. The generative AI model and emotion engine work together to propose improvement measures such as "assigning a dedicated customer support team in the morning" or "changing work priorities."

[0632] Specific operation: The server generates "establishment of a dedicated team to handle complaints in the morning" as a remedial measure and notifies the user and administrator terminals of this.

[0633] Input: Results of an analysis of issues across the organization.

[0634] Output: Specific improvement measures.

[0635] This concludes the explanation of the process flow of this system, broken down into specific processing steps. Using this system enables efficient task management that takes into account the user's emotional state, and enables quick and effective solutions to issues across the organization.

[0636] (Application example 2)

[0637] 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."

[0638] In modern factory environments, efficient management of tasks performed by robots and appropriate assignment of work schedules that take into account their emotional states are required. Conventional systems have difficulty integrating the management of task information and the emotional states of robots to provide optimal schedules, which can result in reduced productivity and the accumulation of stress. To solve this problem, a system that integrates the input and management of task information, the analysis of emotional states, and appropriate task assignment is required.

[0639] 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.

[0640] In this invention, the server includes a means for users to input their own task information, a means for receiving the task information and saving it in a database, a means for analyzing the saved task information and operating a generation model to generate a schedule suitable for the user, a means for notifying the generated schedule to the user's terminal, a means for notifying the schedule to a robot that executes the schedule, and an analysis means for aggregating task information received from multiple users and clarifying issues across the organization. This enables efficient management of tasks handled by robots and appropriate allocation of work schedules that take emotional states into account.

[0641] A "user" is someone who uses the system to input and manage task information.

[0642] "Task information" is information such as task details, importance, deadline, current progress, and required resources entered by the user.

[0643] The "input means" refers to a means by which a user inputs task information through a dedicated application on a terminal or a web interface.

[0644] The "receiving means" is a means by which the system receives task information input by the user.

[0645] A "database" is a structured data storage system for storing received task information and emotion data.

[0646] The "analysis means" is a means for performing data analysis based on the saved task information and emotion data to generate a schedule suitable for the user.

[0647] A "generative model" is an algorithm or AI model that generates optimal schedules and improvement measures based on received task information and emotional data.

[0648] The "notification means" is a means for notifying the generated schedule to the user's terminal or the robot.

[0649] A "terminal" is an electronic device that a user uses to input task information and receive a generated schedule.

[0650] A "robot" is an automated machine that operates in a factory to perform specific tasks.

[0651] The "aggregation means" is a means for centralizing, integrating and managing task information received from a plurality of users.

[0652] "Issues across the organization" are problems or matters requiring improvement that are common across the organization and are discovered based on task information collected from multiple users.

[0653] In the system for realizing this application example, the program is configured as follows.

[0654] First, the user inputs task information. This task information is input through a dedicated application or web interface on the user's device. The device receives the input task information and sends it to the server. Specifically, the input information includes task details, importance, deadline, current progress, required resources, reasons for not being able to complete the task, and current emotional state (e.g., stress, fatigue, lack of motivation, etc.).

[0655] The server receives task information and emotion data sent from the devices and stores them in a database, which is designed for efficient data storage and retrieval with fast indexing and search capabilities.

[0656] The server then inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis using natural language processing (NLP) algorithms such as OpenAI's GPT-4 to evaluate the task's priority, required resources, and its relationship with other tasks. At the same time, it generates a schedule adapted to the user's emotional state based on the emotional data. For example, if the task details are "Assemble part A" and the emotional state is "Stressed due to a lack of parts," the generative AI model analyzes this and proposes an optimal task schedule.

[0657] The generated schedule is sent from the server to the user's terminal. The schedule is also sent to the robots in the factory. Specifically, the schedule is sent to the robots via an HTTP POST request using a robot API (e.g., Robot Operating System (ROS)).

[0658] The server analyzes task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used for the analysis to identify common issues and problems. Based on the analysis results, the generative AI model and emotion engine generate specific improvement measures, which are then notified to users and managers. For example, the server can suggest appropriate rest periods or the allocation of dedicated teams to address emotional fluctuations during specific time periods or the emotional load of specific tasks.

[0659] As a specific example, if the task details are "assembling part A" and the emotional state is "stressed due to a lack of parts," this information is input into the generative AI model, and a prompt sentence is generated as follows:

[0660] Emotional state analyzed: Stress due to parts shortage

[0661] Sentiment analysis results:

[0662]

[0663] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[0664] Proposed schedule:

[0665] This prompt text is input into a generative AI model, and an optimal schedule is generated and notified based on the analysis results, enabling task management and efficient operation within the factory.

[0666] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0667] Step 1:

[0668] The user enters task information.

[0669] Input: The user uses a dedicated application on the device or a web interface to input task details, importance, deadline, current progress, required resources, and emotional state (e.g., stress, fatigue, lack of motivation).

[0670] Operation: The entered information is sent to the terminal and forwarded to the server.

[0671] Step 2:

[0672] The server receives the task information and stores it in a database.

[0673] Input: Task information and emotion data sent from the device.

[0674] Data processing / data calculation: The server analyzes the received information and converts it into a format that can be stored in the database.

[0675] How it works: Data is stored in a database with fast indexing and searching capabilities.

[0676] Output: Saved task information and emotion data.

[0677] Step 3:

[0678] The server inputs the stored task information and emotion data into the generative AI model.

[0679] Input: Task information and emotion data stored in a database.

[0680] Data processing / data calculation: Generative AI models use natural language processing (NLP) algorithms to analyze text and assess task priority, required resources, and relationships with other tasks, while also analyzing sentiment data.

[0681] Operation:

[0682] If the task details are "Assemble part A" and the emotional state is "Stressed due to missing parts," generate the following prompt:

[0683] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[0684] Proposed schedule:

[0685] This prompt sentence is fed into a generative AI model to generate an optimal schedule.

[0686] Output: The generated schedule.

[0687] Step 4:

[0688] The server notifies the user's terminal of the generated schedule.

[0689] Input: The generated schedule.

[0690] Data processing / data calculation: Converts schedule data into a format that is easy for users to understand.

[0691] Operation:

[0692] The server transmits the generated schedule to the user's terminal via the notification means.

[0693] The terminal displays the received schedule.

[0694] Output: The schedule notified to the user.

[0695] Step 5:

[0696] The server notifies the robot of the generated schedule.

[0697] Input: The generated schedule.

[0698] Data processing / data calculation: Converts schedule data into a format that can be executed by the robot.

[0699] How it works: A schedule is sent to a robot via the Robots API via an HTTP POST request.

[0700] Output: The schedule notified to the robot.

[0701] Step 6:

[0702] The server analyzes task information aggregated from multiple users and clarifies issues across the organization.

[0703] Input: Task information and emotion data collected from multiple users.

[0704] Data processing / data calculation: Analyze data using multivariate analysis and clustering techniques to identify common issues and problems.

[0705] How it works: Based on the analysis results, issues across the organization are clarified and a report is generated.

[0706] Output: Clarified organization-wide challenges.

[0707] Step 7:

[0708] The server generates specific remedial measures based on the analyzed data and notifies the user or administrator of the remedial measures.

[0709] Input: Data after analysis and results of generative AI models.

[0710] Data processing / data calculation: Generate specific improvement measures based on the analysis results and create notification content.

[0711] Operation:

[0712] Improvement measures are proposed using a generative AI model and notified to administrators and users via notification means.

[0713] Output: Specific remediation measures communicated to the user or administrator.

[0714] 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.

[0715] 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.

[0716] 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.

[0717] [Third embodiment]

[0718] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0719] 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.

[0720] 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).

[0721] 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.

[0722] 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.

[0723] 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).

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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."

[0730] The present invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. This system mainly consists of the following components:

[0731] User task input method

[0732] Users enter their task information through a dedicated application on their device or through a web interface. Users can enter information such as task details, importance, deadline, current progress, and resources required to complete the task. Users can also enter reasons why they cannot complete the task (e.g., other higher-priority work, technical issues, lack of time, etc.).

[0733] A means of receiving and storing task information

[0734] The server receives task information and reasons for inability sent from the terminal in real time. After receiving, this data is stored in a database and used for subsequent analysis and schedule generation. The database has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[0735] How to operate generative AI models

[0736] The server inputs the task information stored in the database into a generative AI model. The generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. The model uses past data and common optimization algorithms to propose a plan that maximizes the user's work efficiency.

[0737] Schedule notification method

[0738] The server sends the schedule output from the generated AI model to the device. The device notifies the user and presents the new schedule in the form of a pop-up notification or alert. The user can review and approve the proposed schedule, and can also make adjustments as needed.

[0739] A means of clarifying issues across the organization

[0740] The server analyzes the task information collected from each user and the reasons why the task cannot be completed, and identifies issues across the organization. This is done using multivariate analysis and clustering techniques. Specifically, it identifies common obstacles and frequently occurring problem areas (e.g., times of day when complaints are frequently handled, or bottlenecks in specific processes, etc.).

[0741] Remediation generation and notification measures

[0742] The server generates specific improvement measures based on the analysis results. These improvement measures proposed by the generative AI model may include, for example, allocating a dedicated complaint handling team during specific time periods, reprioritizing work, or allocating additional resources. These improvement measures are notified to users and administrators via their devices.

[0743] Specific examples

[0744] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user also inputs the reason, "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. Next, a generative AI model analyzes the user's schedule and suggests a schedule such as, "Walk through complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to that schedule.

[0745] In this way, this system not only improves the work efficiency of the user, but also clarifies issues throughout the organization and proposes improvement measures, thereby improving overall work efficiency.

[0746] The processing flow will be explained below.

[0747] Step 1:

[0748] The user logs in to a dedicated application or web interface on their device and enters task information, including task details, importance, deadline, progress, required resources, etc. In addition, the user also enters the reason why they cannot perform the task.

[0749] Step 2:

[0750] The device sends the entered task information and the reason for it to the server. The data is encoded in a standard format (e.g., JSON, XML).

[0751] Step 3:

[0752] The server parses the task information and reason received from the device and stores it in a database, where each data item is properly indexed and managed for efficient search and retrieval.

[0753] Step 4:

[0754] The server inputs the task information stored in the database into a generative AI model, which uses natural language processing (NLP) to analyze the text and evaluate the task's priority, required resources, and relationship with other tasks.

[0755] Step 5:

[0756] The server generates a schedule specifically for the user based on the analysis results output by the AI ​​model. The schedule is designed as a timetable to optimize the user's work efficiency.

[0757] Step 6:

[0758] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar display, timeline display).

[0759] Step 7:

[0760] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[0761] Step 8:

[0762] The user can then work according to the proposed schedule, and can adjust or provide feedback as needed.

[0763] Step 9:

[0764] The server analyzes task information collected from multiple users and the reasons for their actions to identify common issues and problems. Multivariate analysis and clustering are used as analytical methods.

[0765] Step 10:

[0766] Based on the analysis, the server generates specific improvement measures, such as suggestions to set up dedicated complaint handling teams for specific time periods or to reprioritize tasks.

[0767] Step 11:

[0768] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[0769] Step 12:

[0770] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[0771] Example 1

[0772] 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."

[0773] In today's work environment, it is difficult for individual users to efficiently manage and execute tasks. In particular, when important, time-consuming tasks overlap with daily work, users often struggle with time management, resulting in a significant decline in work efficiency. Furthermore, it is difficult for the organization as a whole to grasp each user's work status and challenges, making it difficult to optimize resource allocation and achieve efficient work processes. To solve these problems, it is necessary to collect detailed task information for each user and present an optimal schedule based on that information. It is also important to identify issues across the organization and provide efficient solutions.

[0774] 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.

[0775] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for the generative AI model to analyze the user's task information using natural language processing technology and generate a schedule; a means for the generative AI model to generate a proposed schedule based on past data and an optimization algorithm; and a means for the user to confirm and approve the proposed schedule through the notification. This not only improves the efficiency of task management for individual users and business efficiency, but also clarifies issues across the organization and provides effective solutions.

[0776] "User" refers to an individual or corporation that uses this system to input and manage task information.

[0777] "Task information" is detailed information about a task entered by a user, and includes the specific task content, importance, deadline, progress, and resources for execution.

[0778] "Device" refers to the device used by the user to enter task information and view the generated schedule, including PCs, smartphones, tablets, etc.

[0779] "Server" refers to a computer system that processes task information received from users and operates generative AI models.

[0780] "Database" means a system for storing task information and related data received by the Server, including fast indexing and searching capabilities.

[0781] A "generative model" refers to an algorithm or machine learning model used to analyze a user's task information and generate an optimal schedule.

[0782] "Natural language processing technology" refers to technology that enables a generative model to analyze and understand text data such as user task information.

[0783] "Past data" refers to a user's past task information and execution history, as well as the organization's business data.

[0784] "Optimization algorithm" refers to the mathematical method or algorithm used by the generative model to create a schedule that maximizes the user's work efficiency.

[0785] "Notification" refers to a communication method for informing the user's terminal of the generated schedule and improvement measures.

[0786] "Analysis means" refers to the tools and methods used by the server to analyze aggregated task information and clarify issues across the entire organization.

[0787] "Improvement measures" refer to specific measures or plans proposed based on analyzed data to improve business efficiency or solve problems.

[0788] This invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. Specifically, it provides a series of processes in which users, servers, and terminals work together to collect and analyze task information, and generate and notify optimal schedules.

[0789] Users input their task information using a dedicated application on their device or a web interface. The input task information includes task details, importance, deadline, current progress, required resources, and reasons why the task cannot be completed (e.g., other high-priority work, technical issues, lack of time, etc.). The device then sends this information to the server in real time.

[0790] The server receives task information sent from the devices and stores it in a database. This database has high-speed indexing and search functions, allowing for efficient data storage and retrieval. Specifically, it is assumed that a relational database management system such as MySQL will be used.

[0791] The server then inputs the saved task information into a generative AI model. This generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. External services such as the Google Cloud Natural Language API can be used. The generative AI model uses past data and optimization algorithms to propose a plan that maximizes the user's work efficiency.

[0792] The generated schedule is sent from the server to the device, which then provides it to the user in the form of a pop-up notification or alert. The user can then review the proposed schedule and approve it or make adjustments as necessary.

[0793] The server then analyzes the task information collected from each user and the reasons for inexecution, and performs analysis to clarify issues across the organization. For example, it uses Python's SciPy library to perform multivariate analysis and clustering to identify common obstacles and frequently occurring problem areas.

[0794] Based on the analysis results, the server generates specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The generated remedial measures are notified to the user or administrator via the terminal.

[0795] Specific examples

[0796] For example, a user in the product development department inputs the task "Write a proposal for a new product" and the reason "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. The generative AI model then analyzes this information and generates a schedule such as "Deal with complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to the schedule.

[0797] Example prompt sentence:

[0798] The user inputs the task "Create a proposal for a new product" and notes that they cannot find time to work on it due to a customer complaint. The generative AI model analyzes this and suggests a schedule that allows time to create the proposal after the complaint has been handled.

[0799] As described above, the present invention is a system that makes task management more efficient for each user, improves work efficiency, and also clarifies issues across the entire organization and provides effective solutions.

[0800] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0801] Step 1:

[0802] The user enters task information. The user accesses a dedicated application on the device or a web interface and enters task information such as "Create a proposal for a new product," as well as the importance, deadline, progress, and reason for inability to execute (e.g., due to a customer complaint). The entered data is sent from the device to the server in JSON format.

[0803] Input: Task information (task name, importance, deadline, progress, reason for inability)

[0804] Output: JSON format task information (device → server)

[0805] Step 2:

[0806] The server receives task information. The server receives task information in JSON format sent from the device in real time and records it in a log. The received data is analyzed and saved in a database. This database is implemented using MySQL and has high-speed indexing and search functions.

[0807] Input: Task information in JSON format

[0808] Output: Task information stored in a database

[0809] Step 3:

[0810] The generative AI model analyzes task information. The server retrieves the task information from the database and passes it to the generative AI model. The generative AI model uses the Google Cloud Natural Language API to analyze the task information using natural language processing technology. Based on past data and an optimization algorithm, it generates an optimal schedule for the user. At this time, a specific algorithm is used to propose a schedule that maximizes the user's work efficiency.

[0811] Input: Task information retrieved from the database

[0812] Output: Generated schedule

[0813] Step 4:

[0814] The generated schedule is notified to the user. The server sends the schedule received from the generative AI model to the user's device. The device presents this schedule to the user in the form of a pop-up notification or alert. The user reviews the proposed schedule and approves or adjusts it as necessary.

[0815] Input: Generated schedule

[0816] Output: Schedule displayed on the terminal

[0817] Step 5:

[0818] The server analyzes issues across the entire organization. It retrieves aggregated task information from each user and the reasons for inexecution from a database, and performs multivariate analysis and clustering using tools such as Python's SciPy. This identifies common obstacles and frequently occurring problem areas.

[0819] Input: Aggregate task information retrieved from the database

[0820] Output: Identification of issues across the organization

[0821] Step 6:

[0822] The server generates and notifies improvement measures. Based on the analysis results, the server uses a generative AI model to generate specific improvement measures. These may include assigning a dedicated complaint handling team to a specific time period, reprioritizing work, or allocating additional resources. The generated improvement measures are notified to users and administrators via their devices.

[0823] Input: Identification of issues across the organization

[0824] Output: Remediation measures communicated to users and administrators

[0825] As described above, at each step, appropriate data processing and calculations are performed based on the input data, and the resulting output is passed on to the next step, ensuring that the entire system functions smoothly.

[0826] (Application example 1)

[0827] 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."

[0828] Conventional task management systems generate schedules based on task information entered by users, but they are unable to reflect those schedules on industrial machines. Furthermore, there are limited means for clarifying issues across the organization, and generating specific improvement measures takes time and effort. Furthermore, there is no mechanism for providing appropriate prompts when using generative AI models, which can lead to a decrease in the accuracy of schedule generation.

[0829] 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.

[0830] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for reflecting the results on industrial machines to improve work efficiency; and a means for inputting prompt statements for generating the schedule into the generative AI model. This not only enables efficient user task management and schedule generation, but also enables the generated schedule to be reflected on industrial machines to improve work efficiency. Furthermore, providing appropriate prompt statements improves the accuracy of schedule generation using the generative AI model.

[0831] "User" refers to an individual or organizational member who uses the system to enter and manage task information.

[0832] "Task information" refers to information entered by the user, such as task details, importance, deadline, progress, and reasons why the task cannot be performed.

[0833] "Database" refers to a storage system that stores task information received from users and has high-speed indexing and searching capabilities.

[0834] "Generative Model" refers to an artificial intelligence model used to analyze stored task information and generate a schedule appropriate for the user.

[0835] "Terminal" refers to a computer device or smart device that a user uses to input task information and check the generated schedule.

[0836] "Analysis means" refers to an analysis method or technology used to aggregate task information received from multiple users and clarify issues across the entire organization.

[0837] "Industrial machinery" refers to automated equipment, robots, and other mechanical devices used in factories and industrial sites.

[0838] A "prompt" refers to preprocessed text data or instructions to be input into a generative AI model.

[0839] "Generative AI model" refers to the machine learning algorithms and artificial intelligence techniques used to analyze text data and generate schedules.

[0840] This invention is a system that allows users to input their own task information and use a generative AI model to improve work efficiency. This system is configured as follows.

[0841] First, a means is needed for users to input task information. This can be done using devices such as smartphones or PCs. Users can enter task details, importance, deadlines, progress, resources required to complete the task, and reasons why a task cannot be completed through a dedicated application or web interface.

[0842] The server then receives the task information and stores it in a database with sophisticated indexing and searching capabilities for efficient data storage and retrieval.

[0843] The saved task information is analyzed by the server. Software (e.g., OpenAI GPT-3 API) is used to operate the generative AI model. The generative AI model analyzes the user's task information and generates an optimal schedule. At this time, a prompt sentence is input to the generative AI model. An example of a prompt sentence is shown below.

[0844] Task Information:

[0845] Assembly of Part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Delay in delivery of parts)

[0846] Based on the details of this task, please suggest the most efficient schedule possible.

[0847] The generated schedule is sent from the server to the user's device. The schedule is presented to the user in the form of a pop-up notification or alert. The user can review the proposed schedule and make adjustments as necessary.

[0848] The server also provides a means for generating schedules that are reflected in industrial machines, thereby further improving work efficiency.

[0849] Furthermore, the server aggregates task information received from multiple users and has analytical tools to clarify issues across the organization. Specifically, it uses multivariate analysis and clustering techniques to identify common obstacles and frequently occurring problem areas.

[0850] Based on this information, specific remedial measures can be generated and communicated to users and administrators, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources.

[0851] In this way, the present invention not only improves the work efficiency of the user, but also contributes to improving the work of the entire organization.

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

[0853] Step 1:

[0854] The user enters their task information into the device. Using a dedicated application or a web interface, the user enters task details, importance, deadline, progress, and, if necessary, reasons why the task cannot be completed. The entered task information is saved on the device in a data format such as JSON.

[0855] Step 2:

[0856] The device sends task information to the server. The device then sends the entered task information to the server in real time. The sent task information includes task details, importance, deadline, progress, and reasons for inability to complete the task. The server receives this information and stores it in a database. The database has a high-speed indexing function, enabling efficient data storage and retrieval.

[0857] Step 3:

[0858] The server analyzes the received task information. The server retrieves the task information stored in the database and generates a prompt to input into the generative AI model. The prompt contains the instructions necessary to generate a schedule based on the task information. For example, it could be in the format "Task information: - Assemble part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Late delivery of parts) Please propose the most efficient schedule possible based on the details of this task."

[0859] Step 4:

[0860] A generative AI model analyzes the prompts and generates an optimal schedule. The server uses a generative AI model (for example, OpenAI GPT-3 API) to generate a schedule based on the input prompts. This generative AI model uses natural language processing technology, past data, and optimization algorithms to generate a schedule for efficiently managing the user's tasks.

[0861] Step 5:

[0862] The server notifies the user's device of the generated schedule. The generated schedule is sent from the server to the user's device. The device displays the generated schedule to the user in the form of a pop-up notification or alert. The user can check the displayed schedule and adjust it as necessary.

[0863] Step 6:

[0864] The server aggregates task information and clarifies the issues facing the entire organization. The server aggregates task information received from multiple users and uses multivariate analysis and clustering techniques to clarify the issues facing the entire organization. Specifically, it identifies common obstacles and frequently occurring problem areas.

[0865] Step 7:

[0866] The server generates remedial measures and notifies the user or administrator. Based on the analysis results, the generative AI model proposes specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The remedial measures are then notified to the user or administrator and applied.

[0867] 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.

[0868] This invention relates to a system that allows users to input and manage their own task information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves the quality and efficiency of work by recognizing the user's emotional state and providing corresponding schedules and improvement measures.

[0869] User task input method

[0870] Users input task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[0871] Emotion Engine

[0872] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[0873] Means for receiving and storing task information and emotion data

[0874] The server receives task information and emotion data sent from the devices. This data is stored in a database for subsequent analysis and schedule generation. The database has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[0875] How to operate generative AI models

[0876] The server inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate task priority, required resources, and relationships with other tasks. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0877] Schedule notification method

[0878] The server generates a schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to assign intensive tasks.

[0879] A means of clarifying issues across the organization

[0880] The server analyzes the task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[0881] Remediation generation and notification measures

[0882] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated complaint handling team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[0883] Specific examples

[0884] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user inputs the reason "I can't concentrate on writing the proposal because I have to deal with customer complaints" and the emotion "I'm feeling stressed because of the complaints." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light tasks and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[0885] In this way, this system improves work efficiency while taking into account the user's emotional state, and by clarifying issues across the entire organization, it is possible to achieve optimal business operations.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] Users log in to a dedicated application or web interface on their device and enter task information and their emotional state. Task information includes task details, importance, deadline, progress, required resources, etc. Emotional states include stress, fatigue, motivation, etc.

[0889] Step 2:

[0890] The device sends the entered task information, emotional state, and the reason why the task cannot be performed to the server. The data is encoded in a standard format (e.g., JSON, XML).

[0891] Step 3:

[0892] The server receives the task information, emotional state, and reasons for preventing task execution sent from the terminal, and stores these data in a database, where each data is appropriately indexed.

[0893] Step 4:

[0894] The server inputs the task information and emotion data stored in the database into the generative AI model and emotion engine, which then analyzes the emotional state using natural language processing and machine learning algorithms.

[0895] Step 5:

[0896] The generative AI model evaluates task priority, required resources, and relationships with other tasks, and combines this with emotional state data obtained from the emotion engine to generate a schedule that adapts to the user's emotional state.

[0897] Step 6:

[0898] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar view, timeline view). The schedule that reflects the emotional state may include, for example, rest periods to reduce stress and small tasks to increase motivation.

[0899] Step 7:

[0900] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[0901] Step 8:

[0902] The user follows the proposed schedule and can adjust or provide feedback as needed. The user can also report their feelings and progress on the task to the system.

[0903] Step 9:

[0904] The server analyzes task information, emotional data, and feedback collected from multiple users to clarify issues across the organization. Multivariate analysis and clustering are used as analytical methods. This allows common issues and problems to be identified (e.g., emotional fluctuations at specific times of the day, the emotional load of specific tasks, etc.).

[0905] Step 10:

[0906] The server generates specific improvement measures based on the analysis results. The generative AI model and emotion engine work together to suggest improvement measures such as assigning dedicated complaint handling teams to specific times, reprioritizing work, or providing additional resources or rest periods.

[0907] Step 11:

[0908] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[0909] Step 12:

[0910] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[0911] Example 2

[0912] 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."

[0913] Conventional task management systems simply manage task information without considering the user's emotional state. This can lead to a decline in work efficiency due to stress and fluctuations in motivation. It is also difficult to identify issues across the organization, making it difficult to propose specific improvement measures quickly and effectively.

[0914] 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.

[0915] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and saving it in a storage device; a means for analyzing the saved task information and the user's emotional state and using a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule to their information terminal; an analysis means for aggregating task information and emotional data received from multiple users and clarifying issues across the organization; a means for inputting a reason why a user cannot perform a task and sending it together with the task information; and a means for generating specific countermeasures based on the analyzed data and notifying the user or administrator of the countermeasures. This enables optimal task management that takes into account the user's emotional state, rapid clarification of issues across the organization, and proposals for specific improvements.

[0916] "User" means a person who uses the system to enter and manage their work information.

[0917] "Task information" is data including detailed task information, importance, deadline, progress, required resources, and reasons why a task cannot be performed.

[0918] An "information terminal" is an electronic device used by a user, such as a personal computer, smartphone, or tablet.

[0919] A "memory device" is a database or storage device for saving received data.

[0920] "Emotional state" refers to a user's psychological or emotional state, such as stress level, fatigue level, and motivation level.

[0921] A "generative model" is an algorithm or machine learning model that analyzes input data and generates a schedule that is appropriate for the user.

[0922] A "schedule" is a planner created by a generative model that includes the user's tasks and schedule.

[0923] The "analysis means" refers to a method or tool for analyzing issues across an entire organization using work information and emotion data received from multiple users.

[0924] "Specific measures" are initiatives proposed based on the analysis results, such as reprioritizing work, assigning dedicated teams, adding resources, and providing rest periods.

[0925] The present invention relates to a system that allows users to input and manage their own work information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves work quality and efficiency by recognizing the user's emotional state and providing corresponding schedules and improvement measures. An embodiment of the present invention is described below.

[0926] User's job information input method

[0927] Users enter task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[0928] Emotion Engine

[0929] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[0930] Means for receiving and storing work information and emotional data

[0931] The server receives the task information and emotion data sent from the device. This data is stored in a storage device for subsequent analysis and schedule generation. The storage device has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[0932] How to operate generative AI models

[0933] The server inputs the stored work information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0934] Calendar notification methods

[0935] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to allocate intensive work.

[0936] A means of clarifying issues across the organization

[0937] The server analyzes the work information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[0938] Remediation generation and notification measures

[0939] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated response team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[0940] Specific examples

[0941] For example, suppose a user in a product development department inputs the task of "writing a proposal for a new product." The user enters the reason that "I can't concentrate on writing the proposal because I have to deal with customers," and the emotion that "I'm feeling stressed by dealing with them." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light work and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[0942] Example prompt sentence:

[0943] "Write a Python script that generates an optimal schedule based on task information and emotion data entered by a user in a task management system."

[0944] In this way, the system of the present invention improves business efficiency while taking into account the emotional state of the user, and by clarifying the issues facing the entire organization, it is possible to achieve optimal business operations.

[0945] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0946] Step 1:

[0947] Users input task information through a dedicated application on their device or a web interface, including details of the task, its importance, deadline, progress, required resources, reasons for not being able to perform the task, and current feelings (e.g., stress, fatigue, lack of motivation).

[0948] Specific operation: The user opens a dedicated application and enters information such as "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," "Lack of materials resources," and "Unable to concentrate on customer support. Stressful."

[0949] Input: User-entered task information and emotion data.

[0950] Output: Data sent from the device to the server.

[0951] Step 2:

[0952] The device sends the user's input and voice data in real time to the emotion engine, which uses natural language processing (NLP) and machine learning algorithms to analyze the user's emotional state and transmits it to the server as an emotion code.

[0953] Specific operation: The device sends text information such as "I can't concentrate on dealing with customers. I'm stressed" to the emotion engine, which then codes this as "high stress."

[0954] Input: User text information or voice data.

[0955] Output: Parsed emotion code.

[0956] Step 3:

[0957] The server receives the task information and emotion data sent from the device and stores it in a storage device. The stored data is used for subsequent analysis and schedule generation. The storage device has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[0958] Specific operation: The server receives the data "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," and "High stress," and stores it in the database.

[0959] Input: Task information and emotion data received from the terminal.

[0960] Output: Data stored in the database.

[0961] Step 4:

[0962] The server inputs the stored work information and emotional data into a generative AI model, which then performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. It also takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[0963] Specific operation: The server inputs the job information of "writing a proposal for a new product" and the emotional data of "high stress" into the generative AI model, and the model begins analysis.

[0964] Input: Job information and emotion data stored in a database.

[0965] Output: The generated calendar.

[0966] Step 5:

[0967] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The generated schedule is adjusted to reflect the user's emotional state.

[0968] Specific operation: Based on the analysis results of the generated AI model, the server generates a schedule that "allocates light tasks and breaks in the morning, and focuses on creating proposals in the afternoon," and notifies the user's device of this.

[0969] Input: Analysis results from a generative AI model.

[0970] Output: Calendar notified to the device.

[0971] Step 6:

[0972] The server analyzes the work information and emotion data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems.

[0973] Specific operation: The server performs multivariate analysis of data collected from all users and identifies a common issue: "Customer service in the morning increases stress overall."

[0974] Input: Aggregated job information and emotion data.

[0975] Output: Analysis of issues across the organization.

[0976] Step 7:

[0977] The server generates specific improvement measures based on the analysis results and notifies the user or administrator via the device. The generative AI model and emotion engine work together to propose improvement measures such as "assigning a dedicated customer support team in the morning" or "changing work priorities."

[0978] Specific operation: The server generates "establishment of a dedicated team to handle complaints in the morning" as a remedial measure and notifies the user and administrator terminals of this.

[0979] Input: Results of an analysis of issues across the organization.

[0980] Output: Specific improvement measures.

[0981] This concludes the explanation of the process flow of this system, broken down into specific processing steps. Using this system enables efficient task management that takes into account the user's emotional state, and enables quick and effective solutions to issues across the organization.

[0982] (Application example 2)

[0983] 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."

[0984] In modern factory environments, efficient management of tasks performed by robots and appropriate assignment of work schedules that take into account their emotional states are required. Conventional systems have difficulty integrating the management of task information and the emotional states of robots to provide optimal schedules, which can result in reduced productivity and the accumulation of stress. To solve this problem, a system that integrates the input and management of task information, the analysis of emotional states, and appropriate task assignment is required.

[0985] 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.

[0986] In this invention, the server includes a means for users to input their own task information, a means for receiving the task information and saving it in a database, a means for analyzing the saved task information and operating a generation model to generate a schedule suitable for the user, a means for notifying the generated schedule to the user's terminal, a means for notifying the schedule to a robot that executes the schedule, and an analysis means for aggregating task information received from multiple users and clarifying issues across the organization. This enables efficient management of tasks handled by robots and appropriate allocation of work schedules that take emotional states into account.

[0987] A "user" is someone who uses the system to input and manage task information.

[0988] "Task information" is information such as task details, importance, deadline, current progress, and required resources entered by the user.

[0989] The "input means" refers to a means by which a user inputs task information through a dedicated application on a terminal or a web interface.

[0990] The "receiving means" is a means by which the system receives task information input by the user.

[0991] A "database" is a structured data storage system for storing received task information and emotion data.

[0992] The "analysis means" is a means for performing data analysis based on the saved task information and emotion data to generate a schedule suitable for the user.

[0993] A "generative model" is an algorithm or AI model that generates optimal schedules and improvement measures based on received task information and emotional data.

[0994] The "notification means" is a means for notifying the generated schedule to the user's terminal or the robot.

[0995] A "terminal" is an electronic device that a user uses to input task information and receive a generated schedule.

[0996] A "robot" is an automated machine that operates in a factory to perform specific tasks.

[0997] The "aggregation means" is a means for centralizing, integrating and managing task information received from a plurality of users.

[0998] "Issues across the organization" are problems or matters requiring improvement that are common across the organization and are discovered based on task information collected from multiple users.

[0999] In the system for realizing this application example, the program is configured as follows.

[1000] First, the user inputs task information. This task information is input through a dedicated application or web interface on the user's device. The device receives the input task information and sends it to the server. Specifically, the input information includes task details, importance, deadline, current progress, required resources, reasons for not being able to complete the task, and current emotional state (e.g., stress, fatigue, lack of motivation, etc.).

[1001] The server receives task information and emotion data sent from the devices and stores them in a database, which is designed for efficient data storage and retrieval with fast indexing and search capabilities.

[1002] The server then inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis using natural language processing (NLP) algorithms such as OpenAI's GPT-4 to evaluate the task's priority, required resources, and its relationship with other tasks. At the same time, it generates a schedule adapted to the user's emotional state based on the emotional data. For example, if the task details are "Assemble part A" and the emotional state is "Stressed due to a lack of parts," the generative AI model analyzes this and proposes an optimal task schedule.

[1003] The generated schedule is sent from the server to the user's terminal. The schedule is also sent to the robots in the factory. Specifically, the schedule is sent to the robots via an HTTP POST request using a robot API (e.g., Robot Operating System (ROS)).

[1004] The server analyzes task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used for the analysis to identify common issues and problems. Based on the analysis results, the generative AI model and emotion engine generate specific improvement measures, which are then notified to users and managers. For example, the server can suggest appropriate rest periods or the allocation of dedicated teams to address emotional fluctuations during specific time periods or the emotional load of specific tasks.

[1005] As a specific example, if the task details are "assembling part A" and the emotional state is "stressed due to a lack of parts," this information is input into the generative AI model, and a prompt sentence is generated as follows:

[1006] Emotional state analyzed: Stress due to parts shortage

[1007] Sentiment analysis results:

[1008]

[1009] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[1010] Proposed schedule:

[1011] This prompt text is input into a generative AI model, and an optimal schedule is generated and notified based on the analysis results, enabling task management and efficient operation within the factory.

[1012] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1013] Step 1:

[1014] The user enters task information.

[1015] Input: The user uses a dedicated application on the device or a web interface to input task details, importance, deadline, current progress, required resources, and emotional state (e.g., stress, fatigue, lack of motivation).

[1016] Operation: The entered information is sent to the terminal and forwarded to the server.

[1017] Step 2:

[1018] The server receives the task information and stores it in a database.

[1019] Input: Task information and emotion data sent from the device.

[1020] Data processing / data calculation: The server analyzes the received information and converts it into a format that can be stored in the database.

[1021] How it works: Data is stored in a database with fast indexing and searching capabilities.

[1022] Output: Saved task information and emotion data.

[1023] Step 3:

[1024] The server inputs the stored task information and emotion data into the generative AI model.

[1025] Input: Task information and emotion data stored in a database.

[1026] Data processing / data calculation: Generative AI models use natural language processing (NLP) algorithms to analyze text and assess task priority, required resources, and relationships with other tasks, while also analyzing sentiment data.

[1027] Operation:

[1028] If the task details are "Assemble part A" and the emotional state is "Stressed due to missing parts," generate the following prompt:

[1029] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[1030] Proposed schedule:

[1031] This prompt sentence is fed into a generative AI model to generate an optimal schedule.

[1032] Output: The generated schedule.

[1033] Step 4:

[1034] The server notifies the user's terminal of the generated schedule.

[1035] Input: The generated schedule.

[1036] Data processing / data calculation: Converts schedule data into a format that is easy for users to understand.

[1037] Operation:

[1038] The server transmits the generated schedule to the user's terminal via the notification means.

[1039] The terminal displays the received schedule.

[1040] Output: The schedule notified to the user.

[1041] Step 5:

[1042] The server notifies the robot of the generated schedule.

[1043] Input: The generated schedule.

[1044] Data processing / data calculation: Converts schedule data into a format that can be executed by the robot.

[1045] How it works: A schedule is sent to a robot via the Robots API via an HTTP POST request.

[1046] Output: The schedule notified to the robot.

[1047] Step 6:

[1048] The server analyzes task information aggregated from multiple users and clarifies issues across the organization.

[1049] Input: Task information and emotion data collected from multiple users.

[1050] Data processing / data calculation: Analyze data using multivariate analysis and clustering techniques to identify common issues and problems.

[1051] How it works: Based on the analysis results, issues across the organization are clarified and a report is generated.

[1052] Output: Clarified organization-wide challenges.

[1053] Step 7:

[1054] The server generates specific remedial measures based on the analyzed data and notifies the user or administrator of the remedial measures.

[1055] Input: Data after analysis and results of generative AI models.

[1056] Data processing / data calculation: Generate specific improvement measures based on the analysis results and create notification content.

[1057] Operation:

[1058] Improvement measures are proposed using a generative AI model and notified to administrators and users via notification means.

[1059] Output: Specific remediation measures communicated to the user or administrator.

[1060] 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.

[1061] 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.

[1062] 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.

[1063] [Fourth embodiment]

[1064] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1065] 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.

[1066] 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).

[1067] 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.

[1068] 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.

[1069] 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).

[1070] 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.

[1071] 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.

[1072] 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.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] 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."

[1077] The present invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. This system mainly consists of the following components:

[1078] User task input method

[1079] Users enter their task information through a dedicated application on their device or through a web interface. Users can enter information such as task details, importance, deadline, current progress, and resources required to complete the task. Users can also enter reasons why they cannot complete the task (e.g., other higher-priority work, technical issues, lack of time, etc.).

[1080] A means of receiving and storing task information

[1081] The server receives task information and reasons for inability sent from the terminal in real time. After receiving, this data is stored in a database and used for subsequent analysis and schedule generation. The database has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[1082] How to operate generative AI models

[1083] The server inputs the task information stored in the database into a generative AI model. The generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. The model uses past data and common optimization algorithms to propose a plan that maximizes the user's work efficiency.

[1084] Schedule notification method

[1085] The server sends the schedule output from the generated AI model to the device. The device notifies the user and presents the new schedule in the form of a pop-up notification or alert. The user can review and approve the proposed schedule, and can also make adjustments as needed.

[1086] A means of clarifying issues across the organization

[1087] The server analyzes the task information collected from each user and the reasons why the task cannot be completed, and identifies issues across the organization. This is done using multivariate analysis and clustering techniques. Specifically, it identifies common obstacles and frequently occurring problem areas (e.g., times of day when complaints are frequently handled, or bottlenecks in specific processes, etc.).

[1088] Remediation generation and notification measures

[1089] The server generates specific improvement measures based on the analysis results. These improvement measures proposed by the generative AI model may include, for example, allocating a dedicated complaint handling team during specific time periods, reprioritizing work, or allocating additional resources. These improvement measures are notified to users and administrators via their devices.

[1090] Specific examples

[1091] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user also inputs the reason, "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. Next, a generative AI model analyzes the user's schedule and suggests a schedule such as, "Walk through complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to that schedule.

[1092] In this way, this system not only improves the work efficiency of the user, but also clarifies issues throughout the organization and proposes improvement measures, thereby improving overall work efficiency.

[1093] The processing flow will be explained below.

[1094] Step 1:

[1095] The user logs in to a dedicated application or web interface on their device and enters task information, including task details, importance, deadline, progress, required resources, etc. In addition, the user also enters the reason why they cannot perform the task.

[1096] Step 2:

[1097] The device sends the entered task information and the reason for it to the server. The data is encoded in a standard format (e.g., JSON, XML).

[1098] Step 3:

[1099] The server parses the task information and reason received from the device and stores it in a database, where each data item is properly indexed and managed for efficient search and retrieval.

[1100] Step 4:

[1101] The server inputs the task information stored in the database into a generative AI model, which uses natural language processing (NLP) to analyze the text and evaluate the task's priority, required resources, and relationship with other tasks.

[1102] Step 5:

[1103] The server generates a schedule specifically for the user based on the analysis results output by the AI ​​model. The schedule is designed as a timetable to optimize the user's work efficiency.

[1104] Step 6:

[1105] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar display, timeline display).

[1106] Step 7:

[1107] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[1108] Step 8:

[1109] The user can then work according to the proposed schedule, and can adjust or provide feedback as needed.

[1110] Step 9:

[1111] The server analyzes task information collected from multiple users and the reasons for their actions to identify common issues and problems. Multivariate analysis and clustering are used as analytical methods.

[1112] Step 10:

[1113] Based on the analysis, the server generates specific improvement measures, such as suggestions to set up dedicated complaint handling teams for specific time periods or to reprioritize tasks.

[1114] Step 11:

[1115] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[1116] Step 12:

[1117] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[1118] Example 1

[1119] 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."

[1120] In today's work environment, it is difficult for individual users to efficiently manage and execute tasks. In particular, when important, time-consuming tasks overlap with daily work, users often struggle with time management, resulting in a significant decline in work efficiency. Furthermore, it is difficult for the organization as a whole to grasp each user's work status and challenges, making it difficult to optimize resource allocation and achieve efficient work processes. To solve these problems, it is necessary to collect detailed task information for each user and present an optimal schedule based on that information. It is also important to identify issues across the organization and provide efficient solutions.

[1121] 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.

[1122] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for the generative AI model to analyze the user's task information using natural language processing technology and generate a schedule; a means for the generative AI model to generate a proposed schedule based on past data and an optimization algorithm; and a means for the user to confirm and approve the proposed schedule through the notification. This not only improves the efficiency of task management for individual users and business efficiency, but also clarifies issues across the organization and provides effective solutions.

[1123] "User" refers to an individual or corporation that uses this system to input and manage task information.

[1124] "Task information" is detailed information about a task entered by a user, and includes the specific task content, importance, deadline, progress, and resources for execution.

[1125] "Device" refers to the device used by the user to enter task information and view the generated schedule, including PCs, smartphones, tablets, etc.

[1126] "Server" refers to a computer system that processes task information received from users and operates generative AI models.

[1127] "Database" means a system for storing task information and related data received by the Server, including fast indexing and searching capabilities.

[1128] A "generative model" refers to an algorithm or machine learning model used to analyze a user's task information and generate an optimal schedule.

[1129] "Natural language processing technology" refers to technology that enables a generative model to analyze and understand text data such as user task information.

[1130] "Past data" refers to a user's past task information and execution history, as well as the organization's business data.

[1131] "Optimization algorithm" refers to the mathematical method or algorithm used by the generative model to create a schedule that maximizes the user's work efficiency.

[1132] "Notification" refers to a communication method for informing the user's terminal of the generated schedule and improvement measures.

[1133] "Analysis means" refers to the tools and methods used by the server to analyze aggregated task information and clarify issues across the entire organization.

[1134] "Improvement measures" refer to specific measures or plans proposed based on analyzed data to improve business efficiency or solve problems.

[1135] This invention relates to a system that allows users to input and manage their own task information and utilizes a generative AI model to improve work efficiency. Specifically, it provides a series of processes in which users, servers, and terminals work together to collect and analyze task information, and generate and notify optimal schedules.

[1136] Users input their task information using a dedicated application on their device or a web interface. The input task information includes task details, importance, deadline, current progress, required resources, and reasons why the task cannot be completed (e.g., other high-priority work, technical issues, lack of time, etc.). The device then sends this information to the server in real time.

[1137] The server receives task information sent from the devices and stores it in a database. This database has high-speed indexing and search functions, allowing for efficient data storage and retrieval. Specifically, it is assumed that a relational database management system such as MySQL will be used.

[1138] The server then inputs the saved task information into a generative AI model. This generative AI model uses natural language processing (NLP) technology to analyze the text data and generate an appropriate schedule based on the user's work situation and requirements. External services such as the Google Cloud Natural Language API can be used. The generative AI model uses past data and optimization algorithms to propose a plan that maximizes the user's work efficiency.

[1139] The generated schedule is sent from the server to the device, which then provides it to the user in the form of a pop-up notification or alert. The user can then review the proposed schedule and approve it or make adjustments as necessary.

[1140] The server then analyzes the task information collected from each user and the reasons for inexecution, and performs analysis to clarify issues across the organization. For example, it uses Python's SciPy library to perform multivariate analysis and clustering to identify common obstacles and frequently occurring problem areas.

[1141] Based on the analysis results, the server generates specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The generated remedial measures are notified to the user or administrator via the terminal.

[1142] Specific examples

[1143] For example, a user in the product development department inputs the task "Write a proposal for a new product" and the reason "I can't concentrate on writing the proposal because I'm dealing with customer complaints." The server receives this information and stores it in a database. The generative AI model then analyzes this information and generates a schedule such as "Deal with complaints from 2:00 to 3:00 PM, then spend the next hour writing the proposal." The device displays this schedule to the user as a pop-up notification, and the user proceeds with their work according to the schedule.

[1144] Example prompt sentence:

[1145] The user inputs the task "Create a proposal for a new product" and notes that they cannot find time to work on it due to a customer complaint. The generative AI model analyzes this and suggests a schedule that allows time to create the proposal after the complaint has been handled.

[1146] As described above, the present invention is a system that makes task management more efficient for each user, improves work efficiency, and also clarifies issues across the entire organization and provides effective solutions.

[1147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1148] Step 1:

[1149] The user enters task information. The user accesses a dedicated application on the device or a web interface and enters task information such as "Create a proposal for a new product," as well as the importance, deadline, progress, and reason for inability to execute (e.g., due to a customer complaint). The entered data is sent from the device to the server in JSON format.

[1150] Input: Task information (task name, importance, deadline, progress, reason for inability)

[1151] Output: JSON format task information (device → server)

[1152] Step 2:

[1153] The server receives task information. The server receives task information in JSON format sent from the device in real time and records it in a log. The received data is analyzed and saved in a database. This database is implemented using MySQL and has high-speed indexing and search functions.

[1154] Input: Task information in JSON format

[1155] Output: Task information stored in a database

[1156] Step 3:

[1157] The generative AI model analyzes task information. The server retrieves the task information from the database and passes it to the generative AI model. The generative AI model uses the Google Cloud Natural Language API to analyze the task information using natural language processing technology. Based on past data and an optimization algorithm, it generates an optimal schedule for the user. At this time, a specific algorithm is used to propose a schedule that maximizes the user's work efficiency.

[1158] Input: Task information retrieved from the database

[1159] Output: Generated schedule

[1160] Step 4:

[1161] The generated schedule is notified to the user. The server sends the schedule received from the generative AI model to the user's device. The device presents this schedule to the user in the form of a pop-up notification or alert. The user reviews the proposed schedule and approves or adjusts it as necessary.

[1162] Input: Generated schedule

[1163] Output: Schedule displayed on the terminal

[1164] Step 5:

[1165] The server analyzes issues across the entire organization. It retrieves aggregated task information from each user and the reasons for inexecution from a database, and performs multivariate analysis and clustering using tools such as Python's SciPy. This identifies common obstacles and frequently occurring problem areas.

[1166] Input: Aggregate task information retrieved from the database

[1167] Output: Identification of issues across the organization

[1168] Step 6:

[1169] The server generates and notifies improvement measures. Based on the analysis results, the server uses a generative AI model to generate specific improvement measures. These may include assigning a dedicated complaint handling team to a specific time period, reprioritizing work, or allocating additional resources. The generated improvement measures are notified to users and administrators via their devices.

[1170] Input: Identification of issues across the organization

[1171] Output: Remediation measures communicated to users and administrators

[1172] As described above, at each step, appropriate data processing and calculations are performed based on the input data, and the resulting output is passed on to the next step, ensuring that the entire system functions smoothly.

[1173] (Application example 1)

[1174] 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."

[1175] Conventional task management systems generate schedules based on task information entered by users, but they are unable to reflect those schedules on industrial machines. Furthermore, there are limited means for clarifying issues across the organization, and generating specific improvement measures takes time and effort. Furthermore, there is no mechanism for providing appropriate prompts when using generative AI models, which can lead to a decrease in the accuracy of schedule generation.

[1176] 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.

[1177] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and storing it in a database; a means for analyzing the stored task information and operating a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule; an analysis means for aggregating task information received from multiple users and clarifying issues across the organization; a means for reflecting the results on industrial machines to improve work efficiency; and a means for inputting prompt statements for generating the schedule into the generative AI model. This not only enables efficient user task management and schedule generation, but also enables the generated schedule to be reflected on industrial machines to improve work efficiency. Furthermore, providing appropriate prompt statements improves the accuracy of schedule generation using the generative AI model.

[1178] "User" refers to an individual or organizational member who uses the system to enter and manage task information.

[1179] "Task information" refers to information entered by the user, such as task details, importance, deadline, progress, and reasons why the task cannot be performed.

[1180] "Database" refers to a storage system that stores task information received from users and has high-speed indexing and searching capabilities.

[1181] "Generative Model" refers to an artificial intelligence model used to analyze stored task information and generate a schedule appropriate for the user.

[1182] "Terminal" refers to a computer device or smart device that a user uses to input task information and check the generated schedule.

[1183] "Analysis means" refers to an analysis method or technology used to aggregate task information received from multiple users and clarify issues across the entire organization.

[1184] "Industrial machinery" refers to automated equipment, robots, and other mechanical devices used in factories and industrial sites.

[1185] A "prompt" refers to preprocessed text data or instructions to be input into a generative AI model.

[1186] "Generative AI model" refers to the machine learning algorithms and artificial intelligence techniques used to analyze text data and generate schedules.

[1187] This invention is a system that allows users to input their own task information and use a generative AI model to improve work efficiency. This system is configured as follows.

[1188] First, a means is needed for users to input task information. This can be done using devices such as smartphones or PCs. Users can enter task details, importance, deadlines, progress, resources required to complete the task, and reasons why a task cannot be completed through a dedicated application or web interface.

[1189] The server then receives the task information and stores it in a database with sophisticated indexing and searching capabilities for efficient data storage and retrieval.

[1190] The saved task information is analyzed by the server. Software (e.g., OpenAI GPT-3 API) is used to operate the generative AI model. The generative AI model analyzes the user's task information and generates an optimal schedule. At this time, a prompt sentence is input to the generative AI model. An example of a prompt sentence is shown below.

[1191] Task Information:

[1192] Assembly of Part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Delay in delivery of parts)

[1193] Based on the details of this task, please suggest the most efficient schedule possible.

[1194] The generated schedule is sent from the server to the user's device. The schedule is presented to the user in the form of a pop-up notification or alert. The user can review the proposed schedule and make adjustments as necessary.

[1195] The server also provides a means for generating schedules that are reflected in industrial machines, thereby further improving work efficiency.

[1196] Furthermore, the server aggregates task information received from multiple users and has analytical tools to clarify issues across the organization. Specifically, it uses multivariate analysis and clustering techniques to identify common obstacles and frequently occurring problem areas.

[1197] Based on this information, specific remedial measures can be generated and communicated to users and administrators, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources.

[1198] In this way, the present invention not only improves the work efficiency of the user, but also contributes to improving the work of the entire organization.

[1199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1200] Step 1:

[1201] The user enters their task information into the device. Using a dedicated application or a web interface, the user enters task details, importance, deadline, progress, and, if necessary, reasons why the task cannot be completed. The entered task information is saved on the device in a data format such as JSON.

[1202] Step 2:

[1203] The device sends task information to the server. The device then sends the entered task information to the server in real time. The sent task information includes task details, importance, deadline, progress, and reasons for inability to complete the task. The server receives this information and stores it in a database. The database has a high-speed indexing function, enabling efficient data storage and retrieval.

[1204] Step 3:

[1205] The server analyzes the received task information. The server retrieves the task information stored in the database and generates a prompt to input into the generative AI model. The prompt contains the instructions necessary to generate a schedule based on the task information. For example, it could be in the format "Task information: - Assemble part A (Priority: 3, Due: 2023-10-15 17:00, Reason: Late delivery of parts) Please propose the most efficient schedule possible based on the details of this task."

[1206] Step 4:

[1207] A generative AI model analyzes the prompts and generates an optimal schedule. The server uses a generative AI model (for example, OpenAI GPT-3 API) to generate a schedule based on the input prompts. This generative AI model uses natural language processing technology, past data, and optimization algorithms to generate a schedule for efficiently managing the user's tasks.

[1208] Step 5:

[1209] The server notifies the user's device of the generated schedule. The generated schedule is sent from the server to the user's device. The device displays the generated schedule to the user in the form of a pop-up notification or alert. The user can check the displayed schedule and adjust it as necessary.

[1210] Step 6:

[1211] The server aggregates task information and clarifies the issues facing the entire organization. The server aggregates task information received from multiple users and uses multivariate analysis and clustering techniques to clarify the issues facing the entire organization. Specifically, it identifies common obstacles and frequently occurring problem areas.

[1212] Step 7:

[1213] The server generates remedial measures and notifies the user or administrator. Based on the analysis results, the generative AI model proposes specific remedial measures, such as assigning a dedicated response team to a specific time period, reprioritizing work, or allocating additional resources. The remedial measures are then notified to the user or administrator and applied.

[1214] 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.

[1215] This invention relates to a system that allows users to input and manage their own task information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves the quality and efficiency of work by recognizing the user's emotional state and providing corresponding schedules and improvement measures.

[1216] User task input method

[1217] Users input task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[1218] Emotion Engine

[1219] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[1220] Means for receiving and storing task information and emotion data

[1221] The server receives task information and emotion data sent from the devices. This data is stored in a database for subsequent analysis and schedule generation. The database has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[1222] How to operate generative AI models

[1223] The server inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate task priority, required resources, and relationships with other tasks. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[1224] Schedule notification method

[1225] The server generates a schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to assign intensive tasks.

[1226] A means of clarifying issues across the organization

[1227] The server analyzes the task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[1228] Remediation generation and notification measures

[1229] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated complaint handling team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[1230] Specific examples

[1231] For example, suppose a user in a product development department inputs the task "Write a proposal for a new product." The user inputs the reason "I can't concentrate on writing the proposal because I have to deal with customer complaints" and the emotion "I'm feeling stressed because of the complaints." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light tasks and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[1232] In this way, this system improves work efficiency while taking into account the user's emotional state, and by clarifying issues across the entire organization, it is possible to achieve optimal business operations.

[1233] The processing flow will be explained below.

[1234] Step 1:

[1235] Users log in to a dedicated application or web interface on their device and enter task information and their emotional state. Task information includes task details, importance, deadline, progress, required resources, etc. Emotional states include stress, fatigue, motivation, etc.

[1236] Step 2:

[1237] The device sends the entered task information, emotional state, and the reason why the task cannot be performed to the server. The data is encoded in a standard format (e.g., JSON, XML).

[1238] Step 3:

[1239] The server receives the task information, emotional state, and reasons for preventing task execution sent from the terminal, and stores these data in a database, where each data is appropriately indexed.

[1240] Step 4:

[1241] The server inputs the task information and emotion data stored in the database into the generative AI model and emotion engine, which then analyzes the emotional state using natural language processing and machine learning algorithms.

[1242] Step 5:

[1243] The generative AI model evaluates task priority, required resources, and relationships with other tasks, and combines this with emotional state data obtained from the emotion engine to generate a schedule that adapts to the user's emotional state.

[1244] Step 6:

[1245] The server sends the generated schedule to the user's device. The schedule data is formatted in a format that is intuitively easy for the user to understand (e.g., calendar view, timeline view). The schedule that reflects the emotional state may include, for example, rest periods to reduce stress and small tasks to increase motivation.

[1246] Step 7:

[1247] The device notifies the user of the received schedule. Notifications are made in the form of pop-ups or alerts, allowing the user to confirm and approve the new schedule.

[1248] Step 8:

[1249] The user follows the proposed schedule and can adjust or provide feedback as needed. The user can also report their feelings and progress on the task to the system.

[1250] Step 9:

[1251] The server analyzes task information, emotional data, and feedback collected from multiple users to clarify issues across the organization. Multivariate analysis and clustering are used as analytical methods. This allows common issues and problems to be identified (e.g., emotional fluctuations at specific times of the day, the emotional load of specific tasks, etc.).

[1252] Step 10:

[1253] The server generates specific improvement measures based on the analysis results. The generative AI model and emotion engine work together to suggest improvement measures such as assigning dedicated complaint handling teams to specific times, reprioritizing work, or providing additional resources or rest periods.

[1254] Step 11:

[1255] The server documents the remediation actions generated and notifies the user or administrator, possibly in the form of a system alert or email.

[1256] Step 12:

[1257] Users and managers review the proposed improvements and implement them as needed, improving operational efficiency and optimizing overall organizational performance.

[1258] Example 2

[1259] 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."

[1260] Conventional task management systems simply manage task information without considering the user's emotional state. This can lead to a decline in work efficiency due to stress and fluctuations in motivation. It is also difficult to identify issues across the organization, making it difficult to propose specific improvement measures quickly and effectively.

[1261] 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.

[1262] In this invention, the server includes: a means for a user to input their own task information; a means for receiving the task information and saving it in a storage device; a means for analyzing the saved task information and the user's emotional state and using a generative model to generate a schedule suitable for the user; a means for notifying the user of the generated schedule to their information terminal; an analysis means for aggregating task information and emotional data received from multiple users and clarifying issues across the organization; a means for inputting a reason why a user cannot perform a task and sending it together with the task information; and a means for generating specific countermeasures based on the analyzed data and notifying the user or administrator of the countermeasures. This enables optimal task management that takes into account the user's emotional state, rapid clarification of issues across the organization, and proposals for specific improvements.

[1263] "User" means a person who uses the system to enter and manage their work information.

[1264] "Task information" is data including detailed task information, importance, deadline, progress, required resources, and reasons why a task cannot be performed.

[1265] An "information terminal" is an electronic device used by a user, such as a personal computer, smartphone, or tablet.

[1266] A "memory device" is a database or storage device for saving received data.

[1267] "Emotional state" refers to a user's psychological or emotional state, such as stress level, fatigue level, and motivation level.

[1268] A "generative model" is an algorithm or machine learning model that analyzes input data and generates a schedule that is appropriate for the user.

[1269] A "schedule" is a planner created by a generative model that includes the user's tasks and schedule.

[1270] The "analysis means" refers to a method or tool for analyzing issues across an entire organization using work information and emotion data received from multiple users.

[1271] "Specific measures" are initiatives proposed based on the analysis results, such as reprioritizing work, assigning dedicated teams, adding resources, and providing rest periods.

[1272] The present invention relates to a system that allows users to input and manage their own work information and improve work efficiency by utilizing a generative AI model and an emotion engine. This system improves work quality and efficiency by recognizing the user's emotional state and providing corresponding schedules and improvement measures. An embodiment of the present invention is described below.

[1273] User's job information input method

[1274] Users enter task information through a dedicated application on their device or a web interface. They can enter information such as task details, importance, deadline, current progress, and required resources. They can also enter reasons for not being able to complete the task and their current feelings (e.g., stress, fatigue, lack of motivation, etc.).

[1275] Emotion Engine

[1276] The device sends the user's input and voice in real time to the emotion engine, which analyzes their emotional state. The emotion engine uses natural language processing (NLP) and machine learning algorithms to identify the user's emotions, encode them, and send them to the server.

[1277] Means for receiving and storing work information and emotional data

[1278] The server receives the task information and emotion data sent from the device. This data is stored in a storage device for subsequent analysis and schedule generation. The storage device has high-speed indexing and search capabilities, allowing for efficient data storage and retrieval.

[1279] How to operate generative AI models

[1280] The server inputs the stored work information and emotional data into a generative AI model. The generative AI model performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. At the same time, it takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[1281] Calendar notification methods

[1282] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The schedule is adjusted to reflect the user's emotional state. For example, if stress is high, the schedule may be adjusted to increase rest time, or if motivation is high, the schedule may be adjusted to allocate intensive work.

[1283] A means of clarifying issues across the organization

[1284] The server analyzes the work information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems (e.g., emotional fluctuations during specific time periods, the emotional load of specific tasks, etc.).

[1285] Remediation generation and notification measures

[1286] The server generates specific improvement measures based on the analysis results. The improvement measures proposed by the generative AI model and emotion engine in collaboration include, for example, assigning a dedicated response team to specific time periods, reprioritizing work, or providing additional resources or rest periods. These improvement measures are notified to users and administrators via their devices.

[1287] Specific examples

[1288] For example, suppose a user in a product development department inputs the task of "writing a proposal for a new product." The user enters the reason that "I can't concentrate on writing the proposal because I have to deal with customers," and the emotion that "I'm feeling stressed by dealing with them." The server receives this information, and the generative AI model and emotion engine analyze it. As a result of the analysis, a schedule is generated that first suggests light work and breaks to reduce the user's stress, followed by time to write the proposal. The device notifies the user of this schedule, and the user proceeds with their work according to the new schedule.

[1289] Example prompt sentence:

[1290] "Write a Python script that generates an optimal schedule based on task information and emotion data entered by a user in a task management system."

[1291] In this way, the system of the present invention improves business efficiency while taking into account the emotional state of the user, and by clarifying the issues facing the entire organization, it is possible to achieve optimal business operations.

[1292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1293] Step 1:

[1294] Users input task information through a dedicated application on their device or a web interface, including details of the task, its importance, deadline, progress, required resources, reasons for not being able to perform the task, and current feelings (e.g., stress, fatigue, lack of motivation).

[1295] Specific operation: The user opens a dedicated application and enters information such as "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," "Lack of materials resources," and "Unable to concentrate on customer support. Stressful."

[1296] Input: User-entered task information and emotion data.

[1297] Output: Data sent from the device to the server.

[1298] Step 2:

[1299] The device sends the user's input and voice data in real time to the emotion engine, which uses natural language processing (NLP) and machine learning algorithms to analyze the user's emotional state and transmits it to the server as an emotion code.

[1300] Specific operation: The device sends text information such as "I can't concentrate on dealing with customers. I'm stressed" to the emotion engine, which then codes this as "high stress."

[1301] Input: User text information or voice data.

[1302] Output: Parsed emotion code.

[1303] Step 3:

[1304] The server receives the task information and emotion data sent from the device and stores it in a storage device. The stored data is used for subsequent analysis and schedule generation. The storage device has high-speed indexing and search functions, allowing for efficient data storage and retrieval.

[1305] Specific operation: The server receives the data "Create a proposal for a new product," "Important," "October 15, 2023," "50% progress," and "High stress," and stores it in the database.

[1306] Input: Task information and emotion data received from the terminal.

[1307] Output: Data stored in the database.

[1308] Step 4:

[1309] The server inputs the stored work information and emotional data into a generative AI model, which then performs text analysis based on natural language processing to evaluate the work's priority, required resources, and relationships with other work. It also takes the emotional data into account to generate a schedule that adapts to the user's emotional state.

[1310] Specific operation: The server inputs the job information of "writing a proposal for a new product" and the emotional data of "high stress" into the generative AI model, and the model begins analysis.

[1311] Input: Job information and emotion data stored in a database.

[1312] Output: The generated calendar.

[1313] Step 5:

[1314] The server generates a personalized schedule for the user based on the analysis results output by the generative AI model and sends it to the device. The generated schedule is adjusted to reflect the user's emotional state.

[1315] Specific operation: Based on the analysis results of the generated AI model, the server generates a schedule that "allocates light tasks and breaks in the morning, and focuses on creating proposals in the afternoon," and notifies the user's device of this.

[1316] Input: Analysis results from a generative AI model.

[1317] Output: Calendar notified to the device.

[1318] Step 6:

[1319] The server analyzes the work information and emotion data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used to identify common issues and problems.

[1320] Specific operation: The server performs multivariate analysis of data collected from all users and identifies a common issue: "Customer service in the morning increases stress overall."

[1321] Input: Aggregated job information and emotion data.

[1322] Output: Analysis of issues across the organization.

[1323] Step 7:

[1324] The server generates specific improvement measures based on the analysis results and notifies the user or administrator via the device. The generative AI model and emotion engine work together to propose improvement measures such as "assigning a dedicated customer support team in the morning" or "changing work priorities."

[1325] Specific operation: The server generates "establishment of a dedicated team to handle complaints in the morning" as a remedial measure and notifies the user and administrator terminals of this.

[1326] Input: Results of an analysis of issues across the organization.

[1327] Output: Specific improvement measures.

[1328] This concludes the explanation of the process flow of this system, broken down into specific processing steps. Using this system enables efficient task management that takes into account the user's emotional state, and enables quick and effective solutions to issues across the organization.

[1329] (Application example 2)

[1330] 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."

[1331] In modern factory environments, efficient management of tasks performed by robots and appropriate assignment of work schedules that take into account their emotional states are required. Conventional systems have difficulty integrating the management of task information and the emotional states of robots to provide optimal schedules, which can result in reduced productivity and the accumulation of stress. To solve this problem, a system that integrates the input and management of task information, the analysis of emotional states, and appropriate task assignment is required.

[1332] 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.

[1333] In this invention, the server includes a means for users to input their own task information, a means for receiving the task information and saving it in a database, a means for analyzing the saved task information and operating a generation model to generate a schedule suitable for the user, a means for notifying the generated schedule to the user's terminal, a means for notifying the schedule to a robot that executes the schedule, and an analysis means for aggregating task information received from multiple users and clarifying issues across the organization. This enables efficient management of tasks handled by robots and appropriate allocation of work schedules that take emotional states into account.

[1334] A "user" is someone who uses the system to input and manage task information.

[1335] "Task information" is information such as task details, importance, deadline, current progress, and required resources entered by the user.

[1336] The "input means" refers to a means by which a user inputs task information through a dedicated application on a terminal or a web interface.

[1337] The "receiving means" is a means by which the system receives task information input by the user.

[1338] A "database" is a structured data storage system for storing received task information and emotion data.

[1339] The "analysis means" is a means for performing data analysis based on the saved task information and emotion data to generate a schedule suitable for the user.

[1340] A "generative model" is an algorithm or AI model that generates optimal schedules and improvement measures based on received task information and emotional data.

[1341] The "notification means" is a means for notifying the generated schedule to the user's terminal or the robot.

[1342] A "terminal" is an electronic device that a user uses to input task information and receive a generated schedule.

[1343] A "robot" is an automated machine that operates in a factory to perform specific tasks.

[1344] The "aggregation means" is a means for centralizing, integrating and managing task information received from a plurality of users.

[1345] "Issues across the organization" are problems or matters requiring improvement that are common across the organization and are discovered based on task information collected from multiple users.

[1346] In the system for realizing this application example, the program is configured as follows.

[1347] First, the user inputs task information. This task information is input through a dedicated application or web interface on the user's device. The device receives the input task information and sends it to the server. Specifically, the input information includes task details, importance, deadline, current progress, required resources, reasons for not being able to complete the task, and current emotional state (e.g., stress, fatigue, lack of motivation, etc.).

[1348] The server receives task information and emotion data sent from the devices and stores them in a database, which is designed for efficient data storage and retrieval with fast indexing and search capabilities.

[1349] The server then inputs the stored task information and emotional data into a generative AI model. The generative AI model performs text analysis using natural language processing (NLP) algorithms such as OpenAI's GPT-4 to evaluate the task's priority, required resources, and its relationship with other tasks. At the same time, it generates a schedule adapted to the user's emotional state based on the emotional data. For example, if the task details are "Assemble part A" and the emotional state is "Stressed due to a lack of parts," the generative AI model analyzes this and proposes an optimal task schedule.

[1350] The generated schedule is sent from the server to the user's terminal. The schedule is also sent to the robots in the factory. Specifically, the schedule is sent to the robots via an HTTP POST request using a robot API (e.g., Robot Operating System (ROS)).

[1351] The server analyzes task information and emotional data collected from each user to clarify issues across the organization. Multivariate analysis and clustering techniques are used for the analysis to identify common issues and problems. Based on the analysis results, the generative AI model and emotion engine generate specific improvement measures, which are then notified to users and managers. For example, the server can suggest appropriate rest periods or the allocation of dedicated teams to address emotional fluctuations during specific time periods or the emotional load of specific tasks.

[1352] As a specific example, if the task details are "assembling part A" and the emotional state is "stressed due to a lack of parts," this information is input into the generative AI model, and a prompt sentence is generated as follows:

[1353] Emotional state analyzed: Stress due to parts shortage

[1354] Sentiment analysis results:

[1355]

[1356] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[1357] Proposed schedule:

[1358] This prompt text is input into a generative AI model, and an optimal schedule is generated and notified based on the analysis results, enabling task management and efficient operation within the factory.

[1359] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1360] Step 1:

[1361] The user enters task information.

[1362] Input: The user uses a dedicated application on the device or a web interface to input task details, importance, deadline, current progress, required resources, and emotional state (e.g., stress, fatigue, lack of motivation).

[1363] Operation: The entered information is sent to the terminal and forwarded to the server.

[1364] Step 2:

[1365] The server receives the task information and stores it in a database.

[1366] Input: Task information and emotion data sent from the device.

[1367] Data processing / data calculation: The server analyzes the received information and converts it into a format that can be stored in the database.

[1368] How it works: Data is stored in a database with fast indexing and searching capabilities.

[1369] Output: Saved task information and emotion data.

[1370] Step 3:

[1371] The server inputs the stored task information and emotion data into the generative AI model.

[1372] Input: Task information and emotion data stored in a database.

[1373] Data processing / data calculation: Generative AI models use natural language processing (NLP) algorithms to analyze text and assess task priority, required resources, and relationships with other tasks, while also analyzing sentiment data.

[1374] Operation:

[1375] If the task details are "Assemble part A" and the emotional state is "Stressed due to missing parts," generate the following prompt:

[1376] Task details: Assemble part A, Priority: High, Deadline: 2023-10-05, Current status: In progress, Sentiment analysis: Stress due to parts shortage

[1377] Proposed schedule:

[1378] This prompt sentence is fed into a generative AI model to generate an optimal schedule.

[1379] Output: The generated schedule.

[1380] Step 4:

[1381] The server notifies the user's terminal of the generated schedule.

[1382] Input: The generated schedule.

[1383] Data processing / data calculation: Converts schedule data into a format that is easy for users to understand.

[1384] Operation:

[1385] The server transmits the generated schedule to the user's terminal via the notification means.

[1386] The terminal displays the received schedule.

[1387] Output: The schedule notified to the user.

[1388] Step 5:

[1389] The server notifies the robot of the generated schedule.

[1390] Input: The generated schedule.

[1391] Data processing / data calculation: Converts schedule data into a format that can be executed by the robot.

[1392] How it works: A schedule is sent to a robot via the Robots API via an HTTP POST request.

[1393] Output: The schedule notified to the robot.

[1394] Step 6:

[1395] The server analyzes task information aggregated from multiple users and clarifies issues across the organization.

[1396] Input: Task information and emotion data collected from multiple users.

[1397] Data processing / data calculation: Analyze data using multivariate analysis and clustering techniques to identify common issues and problems.

[1398] How it works: Based on the analysis results, issues across the organization are clarified and a report is generated.

[1399] Output: Clarified organization-wide challenges.

[1400] Step 7:

[1401] The server generates specific remedial measures based on the analyzed data and notifies the user or administrator of the remedial measures.

[1402] Input: Data after analysis and results of generative AI models.

[1403] Data processing / data calculation: Generate specific improvement measures based on the analysis results and create notification content.

[1404] Operation:

[1405] Improvement measures are proposed using a generative AI model and notified to administrators and users via notification means.

[1406] Output: Specific remediation measures communicated to the user or administrator.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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.

[1411] 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.

[1412] 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.

[1413] 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).

[1414] 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.

[1415] 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."

[1416] 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.

[1417] 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).

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] The following is further disclosed regarding the above embodiment.

[1429] (Claim 1)

[1430] a means for users to input their task information;

[1431] means for receiving the task information and storing it in a database;

[1432] means for analyzing the stored task information and operating a generation model for generating a schedule suitable for the user;

[1433] means for notifying a user terminal of the generated schedule;

[1434] A system that aggregates task information received from multiple users and includes analytical means for clarifying issues across the organization.

[1435] (Claim 2)

[1436] 2. The system according to claim 1, further comprising means for allowing a user to input a reason why the user is unable to perform a task and to transmit the input together with the task information.

[1437] (Claim 3)

[1438] 2. The system according to claim 1, further comprising means for generating specific remedial measures based on the analyzed data and notifying the remedial measures to a user or an administrator.

[1439] "Example 1"

[1440] (Claim 1)

[1441] a means for users to input their task information;

[1442] means for receiving the task information and storing it in a database;

[1443] means for analyzing the stored task information and operating a generation model for generating a schedule suitable for the user;

[1444] means for notifying a user terminal of the generated schedule;

[1445] An analytical method for aggregating task information received from multiple users and clarifying issues across the organization;

[1446] A means for the generative AI model to analyze user task information using natural language processing technology and generate a schedule;

[1447] A means for the generative AI model to generate a proposed schedule based on historical data and an optimization algorithm;

[1448] a means for the user to review and approve the proposed schedule through a notification;

[1449] A system including:

[1450] (Claim 2)

[1451] 2. The system according to claim 1, further comprising means for allowing a user to input a reason why the user is unable to perform a task and to transmit the input together with the task information.

[1452] (Claim 3)

[1453] 2. The system according to claim 1, further comprising means for generating specific remedial measures based on the analyzed data and notifying the remedial measures to a user or an administrator.

[1454] "Application Example 1"

[1455] (Claim 1)

[1456] a means for users to input their task information;

[1457] means for receiving the task information and storing it in a database;

[1458] means for analyzing the stored task information and operating a generation model for generating a schedule suitable for the user;

[1459] means for notifying a user terminal of the generated schedule;

[1460] An analytical method for aggregating task information received from multiple users and clarifying issues across the organization;

[1461] Measures to improve work efficiency reflected in industrial machinery,

[1462] a means for inputting a prompt sentence for generating the schedule into a generative AI model;

[1463] A system including:

[1464] (Claim 2)

[1465] 2. The system according to claim 1, further comprising means for allowing a user to input a reason why the user is unable to perform a task and to transmit the input together with the task information.

[1466] (Claim 3)

[1467] 2. The system according to claim 1, further comprising means for generating specific remedial measures based on the analyzed data and notifying the remedial measures to a user or an administrator.

[1468] "Example 2: Combining Emotion Engines"

[1469] (Claim 1)

[1470] a means for users to input their job information;

[1471] means for receiving the job information and storing it in a storage device;

[1472] means for analyzing the stored task information and the user's emotional state and operating a generative model to generate a schedule suitable for the user;

[1473] means for notifying the user's information terminal of the generated schedule;

[1474] A system that includes analytical means for aggregating work information and emotion data received from multiple users and clarifying issues across the organization.

[1475] (Claim 2)

[1476] 2. The system according to claim 1, further comprising means for allowing a user to input a reason why the user is unable to perform a task and to transmit the input together with the task information.

[1477] (Claim 3)

[1478] 2. The system according to claim 1, further comprising means for generating specific countermeasures based on the analyzed data and notifying a user or an administrator of the countermeasures.

[1479] "Application example 2 when combining emotion engines"

[1480] (Claim 1)

[1481] a means for users to input their task information;

[1482] means for receiving the task information and storing it in a database;

[1483] means for analyzing the stored task information and operating a generation model for generating a schedule suitable for the user;

[1484] means for notifying a user terminal of the generated schedule;

[1485] means for notifying a robot that executes the schedule;

[1486] A system that aggregates task information received from multiple users and includes analytical means for clarifying issues across the organization.

[1487] (Claim 2)

[1488] 2. The system according to claim 1, further comprising means for allowing a user to input a reason why the user is unable to perform a task and to transmit the input together with the task information.

[1489] (Claim 3)

[1490] 2. The system according to claim 1, further comprising means for generating specific remedial measures based on the analyzed data and notifying the remedial measures to a user or an administrator. [Explanation of symbols]

[1491] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for users to input their task information; means for receiving the task information and storing it in a database; means for analyzing the stored task information and operating a generation model for generating a schedule suitable for the user; means for notifying a user terminal of the generated schedule; A system that aggregates task information received from multiple users and includes analytical means for clarifying issues across the organization.

2. 2. The system of claim 1, further comprising means for allowing a user to input a reason why the user cannot perform a task and transmit the input together with the task information.

3. The system according to claim 1 , further comprising means for generating specific remedial measures based on the analyzed data and notifying a user or administrator of the remedial measures.

Images