system

Abstract

We provide the system. [Solution] A means of automatically obtaining progress information from external sources, A means of dynamically re-evaluating the priority of tasks based on acquired progress information, A means of proposing the optimal resource allocation based on the priority of tasks and available resources, A means to analyze the impact of a problem when it occurs and automatically generate alternative solutions, A means of managing the progress and priority of multiple work machines in a factory environment, A means for optimizing and notifying resource allocation in real time based on the status of the work machine, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern enterprises, medium to large-scale project management involves multiple elements such as progress tracking, task prioritization, and optimal resource allocation that are intricately intertwined, making efficient management extremely difficult. Especially in a remote work environment, lack of communication becomes a problem, and the effort required to quickly respond to important information and changes in the situation significantly increases. As a result, there is a problem that the burden on project managers and team members increases, and the risk of project delays and failures rises.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a system that automatically acquires project progress information from external sources and dynamically re-evaluates work priorities based on that progress information. It also incorporates a means to propose optimal resource allocation based on work priorities and available resources. Furthermore, it has a function to analyze the impact of problems and automatically generate alternative solutions when problems occur. This automates and optimizes project management, supporting efficient operation. In addition, it includes a means to automatically create and distribute progress reports to stakeholders using natural language generation technology, and a function to learn from past project data to improve management accuracy in future projects. This reduces the burden on project managers and team members and increases the project success rate.

[0006] "Progress information" refers to data that shows how far a project or task has progressed, and includes the completion status, deadlines, and implementation status of tasks.

[0007] "External information sources" refer to external systems and services that provide data related to project management, such as platforms from which information can be obtained via APIs.

[0008] "Task priority" is an indicator that shows the importance and urgency of each task in a project, and is used to determine which tasks should be prioritized.

[0009] "Resources" refer to elements such as personnel, time, and budget available to carry out a project, and their optimal allocation supports the efficient management of the project.

[0010] "Dynamic re-evaluation" refers to a process of reviewing evaluations in real time or as needed, based on certain criteria and environmental conditions.

[0011] "Natural language generation technology" is a technology that allows computer systems to generate human language, making it possible to automatically generate reports and other documents.

[0012] "Learning" refers to the process by which an AI model uses past data to discover patterns and rules from experience and improve its performance.

[0013] "Automatically generating alternative plans" refers to the process by which a system automatically creates new action plans or strategies based on unforeseen circumstances. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The project management support system of this invention supports the efficient operation of projects by automating the acquisition of progress information, prioritization, optimization of resource allocation, and response to problems.

[0036] The server automatically retrieves progress information from APIs of project management tools and communication platforms. This allows for the aggregation of information on progress, task status, deadlines, and assigned personnel, making it possible to understand the latest project status. For example, it can analyze the completion status of tasks obtained from an external source and calculate the overall progress of the project.

[0037] The terminal dynamically evaluates and resets task priorities based on information provided by the server. By utilizing an AI model, it has the functionality to determine priorities considering task importance, deadlines, and dependencies, enabling optimal resource allocation. For example, it allows for a mechanism to prioritize resources for urgent tasks.

[0038] Users receive progress reports automatically generated by the system, which assists them in making necessary decisions. By utilizing natural language generation technology, information is provided in an easy-to-understand and well-organized manner, allowing for a smoother understanding of project progress. This significantly reduces the effort required for report creation.

[0039] Furthermore, the system aims to improve the accuracy of future project management through continuous learning using past project data. By accumulating data and using that information, the AI ​​improves the accuracy of project planning and problem prediction, thereby achieving more effective project management.

[0040] Furthermore, the system automatically generates countermeasures in the event of unexpected problems. The server quickly analyzes the impact of the problem and suggests alternative solutions, allowing users to take effective action at the appropriate time. For example, if a team member takes an unscheduled vacation, a task reassignment plan is immediately generated, making it possible to adjust the schedule to avoid impacting the project's progress.

[0041] In this way, the present invention is an excellent system that streamlines and automates project management, reduces the burden on project managers and team members, and increases the success rate of projects.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server retrieves project progress data and task information from project management tools and communication platforms using APIs. This process involves periodic HTTP requests to ensure that the latest status is available in real time.

[0045] Step 2:

[0046] The server analyzes the acquired data and evaluates the project's progress based on that analysis. This provides the foundational data needed to determine the progress and any delays in each task.

[0047] Step 3:

[0048] The device uses the analyzed progress data to dynamically re-evaluate task priorities using an AI model. It sets priorities to efficiently advance tasks by considering importance, urgency, and dependencies.

[0049] Step 4:

[0050] The server considers and proposes effective resource allocation based on the AI ​​model and current task priorities. This is an action to optimize the skills and work time of team members.

[0051] Step 5:

[0052] Users receive automatically generated progress reports via their devices, allowing them to stay up-to-date on the project and receive support for decision-making as needed. These reports are provided in an easy-to-read format using natural language generation technology.

[0053] Step 6:

[0054] The server analyzes the impact of unexpected problems and automatically generates countermeasures and alternative solutions. This process is extremely fast to ensure that it does not disrupt the project.

[0055] Step 7:

[0056] The server stores past project data, which the AI ​​system uses to learn and improve the model's accuracy. This enhances the predictive power and planning accuracy of future project management.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In project management, many tasks require manual collection of progress information, prioritization, and resource allocation, hindering efficient operation. Furthermore, impact analysis and alternative planning when problems arise are cumbersome and require rapid response. On the other hand, learning from vast amounts of historical data is insufficient, limiting the improvement of project management accuracy. We aim to solve these challenges efficiently and effectively.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for automatically acquiring progress information from an information processing device, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, and means for analyzing the impact of problems when they occur and automatically generating alternative solutions. This reduces manual work, improves the efficiency and accuracy of project management, and enables rapid response when problems occur.

[0062] "Progress information" refers to data regarding the current status of a project, the progress of tasks, deadlines, and assigned personnel.

[0063] An "information processing device" refers to a computing device used for collecting, processing, and analyzing data.

[0064] "Task priority" refers to the order in which tasks or work within a project are assigned, and is determined based on their importance and urgency.

[0065] "Resource allocation" refers to the act of assigning resources within a project, such as personnel, time, and equipment, to each task.

[0066] "Impact analysis in the event of a problem" refers to the process of evaluating the impact that unexpected events have on the entire project or individual tasks.

[0067] An "alternative plan" refers to a new solution that replaces the original plan when problems arise in the progress of a scheduled project or task.

[0068] "Natural language generation technology" refers to the technology that automatically creates human-readable text from data that computers can understand.

[0069] A "generative AI model" refers to an artificial intelligence model that has the ability to generate new texts or solutions based on user input or data.

[0070] A "prompt" refers to an instruction or question given to a generative AI model to obtain a specific output.

[0071] The project management support system according to the present invention is composed of a combination of various technologies in order to achieve efficiency and automation in project management.

[0072] The server automatically retrieves progress information from APIs of project management tools and communication platforms. Specifically, it uses APIs such as Jira and Slack to collect information. The server aggregates data such as the project status, task progress, and assigned personnel from these sources in JSON format and stores this data in a database.

[0073] The terminal uses an AI model based on progress information provided by the server to dynamically evaluate the priority of tasks. In this case, it leverages AI frameworks such as TENSORFLOW® and PyTorch to determine priorities that take into account the importance, deadlines, and dependencies of tasks. This allows the terminal to allocate resources optimally, prioritizing the allocation of necessary resources to high-priority tasks.

[0074] Users receive progress reports automatically generated by a generative AI model. The generative AI model creates the report based on prompts entered. A specific example of a prompt is, "Summarize the current project progress and suggest the next steps." Users can use this report to make decisions and understand the project's progress more quickly.

[0075] This system improves the efficiency of project management, enabling monitoring of project progress and rapid response to problems. By linking servers and terminals, it automates the entire process from data collection and analysis to report generation, significantly reducing the burden on users.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server connects to the APIs of project management tools and communication platforms to retrieve progress information. Authentication is performed using API keys as input, and project task data is collected. The specific data is obtained in JSON format and includes task status, assignee, deadline, etc. Storing this data in a database allows for tracking the latest project status.

[0079] Step 2:

[0080] The server aggregates the collected data and analyzes the progress. It uses task information from the database as input to calculate the progress of each task. It expresses completed and incomplete tasks as percentages and calculates the progress rate. As output, it visualizes the progress on a dashboard, providing stakeholders with the latest status.

[0081] Step 3:

[0082] The terminal dynamically evaluates task priority using progress information sent from the server. Inputs include progress data and project requirements. This information is processed by an AI model (e.g., TensorFlow) to analyze task urgency, importance, and dependencies, and calculate priority. The output includes determining the optimal resource allocation and assigning resources based on importance.

[0083] Step 4:

[0084] The user receives a progress report generated by a generative AI model. Using the prompt "Summarize the current project progress and suggest the next steps" as input, the generative AI creates a report in natural language. The output is a human-readable report containing project progress and improvement suggestions.

[0085] Step 5:

[0086] The server monitors problems that arise during project progress and automatically generates countermeasures when necessary. Its inputs include analysis of progress data, the scope of the problem's impact, and resource availability. Using this data, it evaluates the impact of the problem and immediately creates alternative solutions. Outputs include, for example, task reassignment, aiming to streamline project progress.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Efficiently managing machinery in modern factories is crucial, especially in complex manufacturing processes. However, centrally monitoring the progress and prioritization of machinery and dynamically optimizing resource allocation is difficult, often leading to inefficient work planning and decreased productivity. A system is needed to solve these problems and achieve efficient resource allocation and progress management.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for proposing the optimal resource allocation based on the priority of tasks and available resources, means for managing the progress status and priority of multiple work machines in a factory environment, and means for optimizing and notifying resource allocation in real time based on the status of the work machines. This makes it possible to efficiently manage work machines in a factory and optimize productivity.

[0092] "Progress information" refers to data that shows the progress and degree of completion of a task.

[0093] "External information sources" refer to information providers such as various databases and APIs used to collect information from outside the system.

[0094] "Task priority" is an indicator that shows the importance and urgency of each task, and serves as a basis for resource allocation.

[0095] "Resource allocation" refers to the efficient distribution of available personnel and equipment to various tasks.

[0096] An "alternative plan" refers to a new work plan or response method that modifies the original plan when a problem occurs.

[0097] The term "factory environment" refers to the physical and administrative settings in which production activities take place, including the locations where machinery and personnel operate.

[0098] "Working machinery" refers to mechanical devices within a factory that are tasked with performing specific operations.

[0099] "Real-time" refers to a unit of time in which information or data is collected and processed immediately, meaning there is virtually no delay.

[0100] "Optimization" refers to adjusting or improving conditions or constraints in order to obtain the maximum possible results under those conditions or constraints.

[0101] "Notification" refers to the act of a system informing a user or related device of specific information.

[0102] The system realizing this invention involves the coordinated operation of a server, terminals, and users to support the efficient management of work machines. The server periodically acquires progress information from various work machines installed in the factory from external sources and sensors and stores it in a database. This ensures that the progress of work is always managed in an up-to-date state.

[0103] The terminal dynamically re-evaluates task priorities using an AI model based on acquired progress information. This AI model is built using libraries such as scikit-learn and TensorFlow, and calculates priorities based on the importance and deadlines of each task. It also proposes the optimal resource allocation in real time, taking into account the available resources of the work machine, and notifies the user accordingly.

[0104] Users receive notifications from their devices on smartphones and tablets, enabling them to make necessary decisions and adjust their work accordingly. This allows for efficient use of resources within the factory, preventing delays and decreased productivity. Furthermore, progress reports are automatically generated using natural language generation technology, helping users quickly understand the situation.

[0105] For example, if an unscheduled shutdown occurs on a manufacturing line due to machine maintenance, the server immediately retrieves this information, recalculates the assignment of a replacement machine, and notifies the terminal. Based on this information, the user can take flexible countermeasures.

[0106] Examples of prompts for a generative AI model:

[0107] "Please provide a response plan for when a machine on the production line unexpectedly shuts down. Factors to consider include the availability of alternative machinery, the urgency of the task, and resource constraints."

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server collects progress information using sensor data from each machine in the factory and stores it in a database. This input includes information on machine operating status and production quantity. Based on this data, the server analyzes the progress and provides the latest progress information as output.

[0111] Step 2:

[0112] The terminal receives the latest progress information provided by the server and inputs it into the AI ​​model. This AI model uses scikit-learn to calculate priorities that take into account the importance, deadline, and current resource status of the tasks. This calculation outputs the optimal task priorities.

[0113] Step 3:

[0114] The device calculates resource allocation to optimally distribute available resources based on priorities generated by the AI ​​model. The calculation results are notified to the user's smartphone in real time for the user to review. The notifications include specific work instructions and tasks that require adjustment.

[0115] Step 4:

[0116] Users receive notifications from their devices and make necessary adjustments within the factory. This includes, for example, changing the assignment of specific machinery or adding additional personnel. The user's decisions are fed back into the AI ​​model for prioritizing tasks in the next iteration.

[0117] Step 5:

[0118] The server continuously trains its AI model using user feedback and past operation data. This training process contributes to improving the accuracy of future task priorities and resource allocation. TensorFlow is used for data computation, continuously improving the model's accuracy.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention enables project management that takes into account the user's emotional state by incorporating an emotion engine into a project management support system. Specific embodiments are described below.

[0121] In addition to conventional progress data acquisition and analysis functions, the server implements an emotion engine to recognize the user's emotional state. The emotion engine captures emotional information from the user's facial expressions, voice tone, text input, etc., to evaluate and record the user's psychological state in real time.

[0122] The terminal simultaneously displays progress and sentiment information provided by the server, offering an interface for a comprehensive understanding of the project's current status. It also includes a function to adjust priorities based on sentiment information, supporting improved work efficiency and optimal allocation of personnel.

[0123] As a concrete example, during a team meeting, the server analyzes the participants' reactions and provides a sentiment report to their terminals after the meeting ends. Based on this report, suggestions are made to improve the flow of the next meeting. For example, if many members are experiencing stress, the cause will be considered and tasks will be redistributed accordingly.

[0124] Users can make better decisions by receiving emotion-based advice and feedback from the system while performing normal project management operations. This feedback is provided in an easy-to-understand manner using natural language generation technology, allowing users to proceed with projects while considering their emotional state.

[0125] Furthermore, after the project is completed, the server analyzes the collected emotional data and learns to improve future projects. This learning process will enable more sophisticated emotional recognition and adaptation in the next project.

[0126] This invention is expected to improve the efficiency of project management and enhance the emotional satisfaction of team members. This is particularly useful in environments where remote communication is prevalent.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server retrieves data from project management tools and communication platforms via APIs. This includes not only collecting task status, progress, assignee, and deadline information, but also simultaneously capturing user comments and reactions from meeting and chat logs.

[0130] Step 2:

[0131] The server analyzes the acquired data to understand the progress and uses an emotion engine to evaluate the user's emotional state. The emotion engine performs facial recognition and voice analysis, and executes a process to quantify emotions such as stress, satisfaction, and excitement.

[0132] Step 3:

[0133] The terminal receives progress and sentiment information transmitted from the server and displays it to the user in an integrated interface. This allows the user to intuitively understand the project's progress and the sentiment tendencies of the team members.

[0134] Step 4:

[0135] Users can use the emotional feedback provided by their device to re-evaluate communication with team members and prioritize tasks. For example, if a member is showing high stress levels, the user can make adjustments to reduce their workload.

[0136] Step 5:

[0137] The server generates appropriate countermeasures and alternatives based on the problems encountered and the emotional states of users and members. In doing so, it adjusts its approach to make suggestions that effectively motivate the team, taking their emotional states into account.

[0138] Step 6:

[0139] The terminal recommends a specific action plan to the user based on the countermeasures and alternatives suggested by the server. This recommendation takes emotional aspects into consideration and is provided in a format that supports the smooth progress of the project.

[0140] Step 7:

[0141] The server analyzes progress information and sentiment data collected during the project period as learning material, and uses this information as operational guidelines for the next project, thereby improving the accuracy of management.

[0142] This trend enables project management systems to achieve overall optimization, including emotional aspects, supporting more humane and effective project management.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0145] Traditional project management systems focus on collecting progress information and optimizing resource allocation, but they fail to grasp the user's psychological state in real time and consider the emotional factors that influence project progress. This can lead to decreased user satisfaction and efficiency. Furthermore, traditional systems standardize feedback and alternative proposals, lacking personalized suggestions tailored to individual user situations.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes means for automatically acquiring progress information from an information source, means for sentiment analysis for detecting and evaluating the user's psychological state, and means for dynamically re-evaluating the priority of tasks based on the acquired progress information and sentiment information. This enables decision-making in project management that takes into account the user's psychological state, thereby improving work efficiency and user satisfaction.

[0148] "Progress information" refers to data that shows the progress of a project or the degree of work completion, and is collected from external sources.

[0149] "Information source" refers to an external database or platform that provides progress information and other project-related data.

[0150] "User psychological state" refers to the emotions and psychological reactions that users feel in relation to the project, which can potentially influence the project's progress.

[0151] "Emotion analysis" refers to a technology that evaluates a user's emotions from facial expressions, voice, text, etc., and expresses them numerically or qualitatively.

[0152] "Dynamic reevaluation" refers to the process of reviewing the order and priorities of tasks based on newly collected data, taking into account the ever-changing circumstances.

[0153] "Resource allocation" refers to the method of optimally distributing and efficiently utilizing the human, material, and temporal resources available in a project.

[0154] An "alternative plan" is a flexible response or alternative approach to an existing plan when a problem arises.

[0155] "Natural language generation technology" refers to the technology that allows computers to generate text in a language that is easy for humans to understand, and is used for automatically creating progress reports and feedback.

[0156] "Learning methods" refer to the process of improving algorithms based on experience using past data to enhance accuracy in future projects.

[0157] In order to implement this invention, it is necessary for the server, terminal, and user to work together in cooperation. Specific embodiments are shown below.

[0158] The server is built on a cloud service and is a system that automatically retrieves progress information from various sources. These sources include, for example, project management tools and database systems, and data is retrieved via APIs. Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's facial expressions, voice, and text. Computer vision technology is used for facial expression analysis, speech recognition software for voice analysis, and natural language processing technology for text analysis. The results of the emotion analysis are recorded as numerical data and, in conjunction with the progress information, are used to re-evaluate the priority of tasks.

[0159] The terminal provides a user interface and is a tool for users to view progress and sentiment information received from the server. A dashboard is displayed on the terminal, allowing users to grasp the overall project picture through graphs and charts. Furthermore, the terminal incorporates a generative AI model, automatically generating progress reports and feedback using natural language generation technology and providing them to the user.

[0160] For example, if the server analyzes the emotional data of multiple participants during a team meeting and detects a high level of stress during the meeting, that information is sent to the terminal. The terminal can then display a real-time stress heatmap to the user and use a generative AI model to provide specific advice such as, "Please readjust the meeting agenda to reduce stress."

[0161] Users utilize this system to make decisions when managing projects. Based on progress and sentiment information provided through their devices, users can efficiently adjust task priorities and allocate resources optimally. They can also revise project plans based on feedback from the generative AI model.

[0162] As a concrete example, a prompt for the generating AI model might be: "Generate the emotional state of all members in the current project progress, and specific suggestions for improvement." This prompt allows the system to interactively respond to the user's needs.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server retrieves progress information from its sources. The input at this stage is raw data obtained from external project management tools and database APIs. The server executes API calls to retrieve project progress and task status. Data processing involves converting this data into a unified format and storing it in the database. The output is progress data organized chronologically.

[0166] Step 2:

[0167] The server collects user emotion data. Inputs include camera footage capturing the user's facial expressions, microphone data recording their voice, and the content of text messages. The server applies image analysis algorithms to extract emotions from facial expressions, uses speech recognition software to interpret voice tone, and analyzes the emotions in the text using natural language processing techniques. Data calculations generate a numerical emotion score, which is the output.

[0168] Step 3:

[0169] The terminal displays progress and sentiment information retrieved from the server on the user interface. At this stage, the input consists of progress and sentiment data provided by the server. The terminal converts this data into a visually easy-to-understand format and displays it as graphs and charts on the dashboard. Specifically, it also displays an overview of the members' sentiment states using sentiment heatmaps, etc. As output, it provides visual information that allows the user to understand the situation at a glance.

[0170] Step 4:

[0171] Based on the information displayed on the device, the user prompts a generative AI model to request feedback to support decision-making. An example input might be, "Please suggest topics to address in the next meeting and indicate actions based on the team's current sentiment." The generative AI model analyzes this prompt and uses pre-collected data to generate appropriate feedback. The output provides feedback that includes concrete suggestions the user can implement.

[0172] Step 5:

[0173] The server will learn from all the data after the project is completed. The input at this stage consists of all progress and sentiment data collected during the project. The server uses machine learning algorithms to detect patterns within the dataset and improve the accuracy of sentiment analysis and progress management. The output will be an improved algorithm for the next project. Specifically, the model will be updated, improving the overall response speed and accuracy of the system.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0176] In the interior environment of autonomous vehicles, there is a need to improve comfort based on passenger emotions. Therefore, there is a challenge in the lack of technology to provide appropriate environmental control that aligns with the psychological state of passengers.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for adapting the work environment using emotion recognition technology, and means for dynamically changing environmental settings considering the emotional state of passengers. This makes it possible to optimize the in-vehicle environment according to the emotional state of passengers.

[0179] "Progress information" refers to information in project management that shows the degree of completion and current status of each task or work process.

[0180] "External information sources" refer to data and resources provided from outside the system, and include information about project progress and work content.

[0181] "Dynamic re-evaluation" refers to updating and adapting evaluation criteria and content in real time in response to changes in circumstances and conditions.

[0182] "Resource allocation" is the process of assigning limited resources to each task or project in order to make the most optimal use of them.

[0183] "Emotion recognition technology" is a technology that analyzes a user's facial expressions and voice to determine their emotions and psychological state.

[0184] "Dynamically changing environment settings" refers to adjusting environmental conditions in real time according to the user's needs and circumstances at any given time.

[0185] "Adapting the work environment" means optimizing the physical and digital conditions of the work location and environment based on the user's psychological state and emotions.

[0186] To implement this invention, collaboration between a server, terminals, and users is necessary. The server first automatically acquires progress information from external sources, allowing for real-time monitoring of project progress. Furthermore, emotion recognition technology is used to collect and analyze emotional information from passengers' facial expressions and voices. Software such as OpenCV and Google® Face API is used for this analysis. This allows for an understanding of passengers' psychological states, enabling appropriate adjustments to the in-vehicle environment.

[0187] The terminal displays progress and sentiment information transmitted from the server, supporting users in making decisions based on this information. It also adjusts in-car environment settings, such as music and air conditioning, based on the user's sentiment. This allows passengers to enjoy their journey in a comfortable environment. Specifically, devices such as smart glasses and head-mounted displays are used as terminals, providing real-time feedback.

[0188] Users can smoothly manage projects based on real-time feedback and advice provided by the server and terminal. If the system detects that a passenger is experiencing stress, it will suggest playing relaxing music or adjusting the temperature. This allows passengers to have a more comfortable journey.

[0189] For example, if a passenger gets into a car after a meeting and a high level of stress is detected, the system will play calming music and set the air conditioning to a relaxing temperature.

[0190] Examples of prompt statements include the following:

[0191] "Please tell me how to suggest a relaxing in-car environment based on user sentiment data, with a particular focus on music and temperature settings."

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The server retrieves progress information from external sources. It uses project task information and progress data as input to analyze the project's progress. The analyzed data is used to evaluate the project's current status, and stakeholders are notified as needed.

[0195] Step 2:

[0196] The server analyzes passengers' emotions using emotion recognition technology. It uses passenger facial image data and audio data as input. OpenCV and the Google Face API are used to analyze this data and quantify the passengers' emotional states. This quantified emotional data is output and used in subsequent processing.

[0197] Step 3:

[0198] Emotional data is sent from the server to the terminal. Based on this data, the terminal proposes the optimal in-car environment settings for the passenger. It takes emotional data as input, selects music and adjusts the air conditioning settings, processes the results internally, and outputs adjustment suggestions.

[0199] Step 4:

[0200] The device uses a generative AI model to generate specific environmental adjustment suggestions for the user in natural language. It takes emotional data and suggested environmental settings as input and outputs feedback messages generated in natural language. These messages are presented to the user in an easily understandable format.

[0201] Step 5:

[0202] The user receives feedback from the device and follows suggestions for optimizing the in-car environment settings. Based on the user's feedback, the device implements the suggested settings and adjusts the in-car environment. This process allows the user to enjoy a comfortable journey.

[0203] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0204] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0205] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0209] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0210] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0211] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0212] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0213] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0214] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0215] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0216] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0217] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0218] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0219] The project management support system of this invention supports the efficient operation of projects by automating the acquisition of progress information, prioritization, optimization of resource allocation, and response to problems.

[0220] The server automatically retrieves progress information from APIs of project management tools and communication platforms. This allows for the aggregation of information on progress, task status, deadlines, and assigned personnel, making it possible to understand the latest project status. For example, it can analyze the completion status of tasks obtained from an external source and calculate the overall progress of the project.

[0221] The terminal dynamically evaluates and resets task priorities based on information provided by the server. By utilizing an AI model, it has the functionality to determine priorities considering task importance, deadlines, and dependencies, enabling optimal resource allocation. For example, it allows for a mechanism to prioritize resources for urgent tasks.

[0222] Users receive progress reports automatically generated by the system, which assists them in making necessary decisions. By utilizing natural language generation technology, information is provided in an easy-to-understand and well-organized manner, allowing for a smoother understanding of project progress. This significantly reduces the effort required for report creation.

[0223] Furthermore, the system aims to improve the accuracy of future project management through continuous learning using past project data. By accumulating data and using that information, the AI ​​improves the accuracy of project planning and problem prediction, thereby achieving more effective project management.

[0224] Furthermore, the system automatically generates countermeasures in the event of unexpected problems. The server quickly analyzes the impact of the problem and suggests alternative solutions, allowing users to take effective action at the appropriate time. For example, if a team member takes an unscheduled vacation, a task reassignment plan is immediately generated, making it possible to adjust the schedule to avoid impacting the project's progress.

[0225] In this way, the present invention is an excellent system that streamlines and automates project management, reduces the burden on project managers and team members, and increases the success rate of projects.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The server retrieves project progress data and task information from project management tools and communication platforms using APIs. This process involves periodic HTTP requests to ensure that the latest status is available in real time.

[0229] Step 2:

[0230] The server analyzes the acquired data and evaluates the project's progress based on that analysis. This provides the foundational data needed to determine the progress and any delays in each task.

[0231] Step 3:

[0232] The device uses the analyzed progress data to dynamically re-evaluate task priorities using an AI model. It sets priorities to efficiently advance tasks by considering importance, urgency, and dependencies.

[0233] Step 4:

[0234] The server considers and proposes effective resource allocation based on the AI ​​model and current task priorities. This is an action to optimize the skills and work time of team members.

[0235] Step 5:

[0236] Users receive automatically generated progress reports via their devices, allowing them to stay up-to-date on the project and receive support for decision-making as needed. These reports are provided in an easy-to-read format using natural language generation technology.

[0237] Step 6:

[0238] The server analyzes the impact of unexpected problems and automatically generates countermeasures and alternative solutions. This process is extremely fast to ensure that it does not disrupt the project.

[0239] Step 7:

[0240] The server stores past project data, which the AI ​​system uses to learn and improve the model's accuracy. This enhances the predictive power and planning accuracy of future project management.

[0241] (Example 1)

[0242] Next, we will describe Example 1. 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".

[0243] In project management, many tasks require manual collection of progress information, prioritization, and resource allocation, hindering efficient operation. Furthermore, impact analysis and alternative planning when problems arise are cumbersome and require rapid response. On the other hand, learning from vast amounts of historical data is insufficient, limiting the improvement of project management accuracy. We aim to solve these challenges efficiently and effectively.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes means for automatically acquiring progress information from an information processing device, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, and means for analyzing the impact of problems when they occur and automatically generating alternative solutions. This reduces manual work, improves the efficiency and accuracy of project management, and enables rapid response when problems occur.

[0246] "Progress information" refers to data regarding the current status of a project, the progress of tasks, deadlines, and assigned personnel.

[0247] An "information processing device" refers to a computing device used for collecting, processing, and analyzing data.

[0248] "Task priority" refers to the order in which tasks or work within a project are assigned, and is determined based on their importance and urgency.

[0249] "Resource allocation" refers to the act of assigning resources within a project, such as personnel, time, and equipment, to each task.

[0250] "Impact analysis in the event of a problem" refers to the process of evaluating the impact that unexpected events have on the entire project or individual tasks.

[0251] An "alternative plan" refers to a new solution that replaces the original plan when problems arise in the progress of a scheduled project or task.

[0252] "Natural language generation technology" refers to the technology that automatically creates human-readable text from data that computers can understand.

[0253] A "generative AI model" refers to an artificial intelligence model that has the ability to generate new texts or solutions based on user input or data.

[0254] A "prompt" refers to an instruction or question given to a generative AI model to obtain a specific output.

[0255] The project management support system according to the present invention is composed of a combination of various technologies in order to achieve efficiency and automation in project management.

[0256] The server automatically retrieves progress information from APIs of project management tools and communication platforms. Specifically, it uses APIs such as Jira and Slack to collect information. The server aggregates data such as the project status, task progress, and assigned personnel from these sources in JSON format and stores this data in a database.

[0257] The terminal uses an AI model based on progress information provided by the server to dynamically evaluate the priority of tasks. In this case, it leverages AI frameworks such as TensorFlow and PyTorch to determine priorities that take into account the importance, deadlines, and dependencies of tasks. This allows the terminal to allocate resources optimally, prioritizing the allocation of necessary resources to high-priority tasks.

[0258] Users receive progress reports automatically generated by a generative AI model. The generative AI model creates the report based on prompts entered. A specific example of a prompt is, "Summarize the current project progress and suggest the next steps." Users can use this report to make decisions and understand the project's progress more quickly.

[0259] This system improves the efficiency of project management, enabling monitoring of project progress and rapid response to problems. By linking servers and terminals, it automates the entire process from data collection and analysis to report generation, significantly reducing the burden on users.

[0260] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0261] Step 1:

[0262] The server connects to the APIs of project management tools and communication platforms to retrieve progress information. Authentication is performed using API keys as input, and project task data is collected. The specific data is obtained in JSON format and includes task status, assignee, deadline, etc. Storing this data in a database allows for tracking the latest project status.

[0263] Step 2:

[0264] The server aggregates the collected data and analyzes the progress. It uses task information from the database as input to calculate the progress of each task. It expresses completed and incomplete tasks as percentages and calculates the progress rate. As output, it visualizes the progress on a dashboard, providing stakeholders with the latest status.

[0265] Step 3:

[0266] The terminal dynamically evaluates task priority using progress information sent from the server. Inputs include progress data and project requirements. This information is processed by an AI model (e.g., TensorFlow) to analyze task urgency, importance, and dependencies, and calculate priority. The output includes determining the optimal resource allocation and assigning resources based on importance.

[0267] Step 4:

[0268] The user receives a progress report generated by a generative AI model. Using the prompt "Summarize the current project progress and suggest the next steps" as input, the generative AI creates a report in natural language. The output is a human-readable report containing project progress and improvement suggestions.

[0269] Step 5:

[0270] The server monitors problems that arise during project progress and automatically generates countermeasures when necessary. Its inputs include analysis of progress data, the scope of the problem's impact, and resource availability. Using this data, it evaluates the impact of the problem and immediately creates alternative solutions. Outputs include, for example, task reassignment, aiming to streamline project progress.

[0271] (Application Example 1)

[0272] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] Efficiently managing machinery in modern factories is crucial, especially in complex manufacturing processes. However, centrally monitoring the progress and prioritization of machinery and dynamically optimizing resource allocation is difficult, often leading to inefficient work planning and decreased productivity. A system is needed to solve these problems and achieve efficient resource allocation and progress management.

[0274] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0275] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for proposing the optimal resource allocation based on the priority of tasks and available resources, means for managing the progress status and priority of multiple work machines in a factory environment, and means for optimizing and notifying resource allocation in real time based on the status of the work machines. This makes it possible to efficiently manage work machines in a factory and optimize productivity.

[0276] "Progress information" refers to data that shows the progress and degree of completion of a task.

[0277] "External information sources" refer to information providers such as various databases and APIs used to collect information from outside the system.

[0278] "Task priority" is an indicator that shows the importance and urgency of each task, and serves as a basis for resource allocation.

[0279] "Resource allocation" refers to the efficient distribution of available personnel and equipment to various tasks.

[0280] An "alternative plan" refers to a new work plan or response method that modifies the original plan when a problem occurs.

[0281] "Factory environment" refers to the physical and managerial settings where production activities are carried out, which is the place where working machines and personnel operate.

[0282] "Working machine" refers to a mechanical device responsible for performing specific tasks within a factory.

[0283] "Real-time" refers to a time unit in which information and data are collected and immediately processed, meaning that there is almost no delay.

[0284] "Optimization" means adjusting or improving conditions in order to obtain the maximum results under given conditions and constraints.

[0285] "Notification" refers to the act of the system informing a user or related devices of specific information.

[0286] The system for realizing this invention has each element of the server, terminal, and user operating in cooperation to assist in the efficient management of working machines. The server regularly obtains the progress information of various working machines installed in the factory from external information sources and sensors, and stores it in a database. As a result, the progress of work is always managed in the latest state.

[0287] Based on the obtained progress information, the terminal dynamically re-evaluates the priority of work using an AI model. This AI model is constructed using libraries such as scikit-learn and TensorFlow, and calculates the priority order according to the importance and deadline of each work. Also, considering the available resources of the working machine, it proposes an optimal resource allocation in real-time and notifies this to the user.

[0288] The user receives notifications from the terminal via a smartphone or tablet and makes necessary decisions and work adjustments. As a result, the resources within the factory can be efficiently utilized, preventing work delays and productivity decline. Furthermore, by utilizing natural language generation technology, an automatically generated progress report is provided to assist the user in quickly grasping the situation.

[0289] For example, if an unscheduled shutdown occurs on a manufacturing line due to machine maintenance, the server immediately retrieves this information, recalculates the assignment of a replacement machine, and notifies the terminal. Based on this information, the user can take flexible countermeasures.

[0290] Examples of prompts for a generative AI model:

[0291] "Please provide a response plan for when a machine on the production line unexpectedly shuts down. Factors to consider include the availability of alternative machinery, the urgency of the task, and resource constraints."

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The server collects progress information using sensor data from each machine in the factory and stores it in a database. This input includes information on machine operating status and production quantity. Based on this data, the server analyzes the progress and provides the latest progress information as output.

[0295] Step 2:

[0296] The terminal receives the latest progress information provided by the server and inputs it into the AI ​​model. This AI model uses scikit-learn to calculate priorities that take into account the importance, deadline, and current resource status of the tasks. This calculation outputs the optimal task priorities.

[0297] Step 3:

[0298] The device calculates resource allocation to optimally distribute available resources based on priorities generated by the AI ​​model. The calculation results are notified to the user's smartphone in real time for the user to review. The notifications include specific work instructions and tasks that require adjustment.

[0299] Step 4:

[0300] Users receive notifications from their devices and make necessary adjustments within the factory. This includes, for example, changing the assignment of specific machinery or adding additional personnel. The user's decisions are fed back into the AI ​​model for prioritizing tasks in the next iteration.

[0301] Step 5:

[0302] The server continuously trains its AI model using user feedback and past operation data. This training process contributes to improving the accuracy of future task priorities and resource allocation. TensorFlow is used for data computation, continuously improving the model's accuracy.

[0303] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0304] This invention enables project management that takes into account the user's emotional state by incorporating an emotion engine into a project management support system. Specific embodiments are described below.

[0305] In addition to conventional progress data acquisition and analysis functions, the server implements an emotion engine to recognize the user's emotional state. The emotion engine captures emotional information from the user's facial expressions, voice tone, text input, etc., to evaluate and record the user's psychological state in real time.

[0306] The terminal simultaneously displays progress and sentiment information provided by the server, offering an interface for a comprehensive understanding of the project's current status. It also includes a function to adjust priorities based on sentiment information, supporting improved work efficiency and optimal allocation of personnel.

[0307] As a specific example, during a team meeting, the server analyzes the reactions of participants, and after the meeting, provides an emotion report to the terminal. Based on this report, suggestions are made to improve the progress of the next meeting. For example, if there are many members feeling stressed, reallocation of tasks is considered taking into account the cause.

[0308] While performing normal project management operations, users can make better decisions by receiving emotion-based advice and feedback from the system. This feedback is provided in an easy-to-understand manner by natural language generation technology, and users can proceed with the project while considering the emotional state.

[0309] Furthermore, after the project is completed, the server analyzes the collected emotion data and learns to utilize it for future improvements. Through this learning process, it becomes possible to achieve more refined emotion recognition and adaptation in the next project.

[0310] According to the present invention, it can be expected that the efficiency of project management is improved and the satisfaction of members in terms of emotions is also improved. This is particularly useful in an environment centered on remote communication.

[0311] The following describes the process flow.

[0312] Step 1:

[0313] The server obtains data via an API from a project management tool or a communication platform. Here, not only information on the status, progress, assignees, and deadlines of tasks is collected, but also the speech and reactions of users are simultaneously captured from the records of meetings and chats.

[0314] Step 2:

[0315] The server analyzes the acquired data to understand the progress and uses an emotion engine to evaluate the user's emotional state. The emotion engine performs facial recognition and voice analysis, and executes a process to quantify emotions such as stress, satisfaction, and excitement.

[0316] Step 3:

[0317] The terminal receives progress and sentiment information transmitted from the server and displays it to the user in an integrated interface. This allows the user to intuitively understand the project's progress and the sentiment tendencies of the team members.

[0318] Step 4:

[0319] Users can use the emotional feedback provided by their device to re-evaluate communication with team members and prioritize tasks. For example, if a member is showing high stress levels, the user can make adjustments to reduce their workload.

[0320] Step 5:

[0321] The server generates appropriate countermeasures and alternatives based on the problems encountered and the emotional states of users and members. In doing so, it adjusts its approach to make suggestions that effectively motivate the team, taking their emotional states into account.

[0322] Step 6:

[0323] The terminal recommends a specific action plan to the user based on the countermeasures and alternatives suggested by the server. This recommendation takes emotional aspects into consideration and is provided in a format that supports the smooth progress of the project.

[0324] Step 7:

[0325] The server analyzes progress information and sentiment data collected during the project period as learning material, and uses this information as operational guidelines for the next project, thereby improving the accuracy of management.

[0326] This trend enables project management systems to achieve overall optimization, including emotional aspects, supporting more humane and effective project management.

[0327] (Example 2)

[0328] Next, we will describe Example 2. 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".

[0329] Traditional project management systems focus on collecting progress information and optimizing resource allocation, but they fail to grasp the user's psychological state in real time and consider the emotional factors that influence project progress. This can lead to decreased user satisfaction and efficiency. Furthermore, traditional systems standardize feedback and alternative proposals, lacking personalized suggestions tailored to individual user situations.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes means for automatically acquiring progress information from an information source, means for sentiment analysis for detecting and evaluating the user's psychological state, and means for dynamically re-evaluating the priority of tasks based on the acquired progress information and sentiment information. This enables decision-making in project management that takes into account the user's psychological state, thereby improving work efficiency and user satisfaction.

[0332] "Progress information" refers to data that shows the progress of a project or the degree of work completion, and is collected from external sources.

[0333] "Information source" refers to an external database or platform that provides progress information and other project-related data.

[0334] "User psychological state" refers to the emotions and psychological reactions that users feel in relation to the project, which can potentially influence the project's progress.

[0335] "Emotion analysis" refers to a technology that evaluates a user's emotions from facial expressions, voice, text, etc., and expresses them numerically or qualitatively.

[0336] "Dynamic reevaluation" refers to the process of reviewing the order and priorities of tasks based on newly collected data, taking into account the ever-changing circumstances.

[0337] "Resource allocation" refers to the method of optimally distributing and efficiently utilizing the human, material, and temporal resources available in a project.

[0338] An "alternative plan" is a flexible response or alternative approach to an existing plan when a problem arises.

[0339] "Natural language generation technology" refers to the technology that allows computers to generate text in a language that is easy for humans to understand, and is used for automatically creating progress reports and feedback.

[0340] "Learning methods" refer to the process of improving algorithms based on experience using past data to enhance accuracy in future projects.

[0341] In order to implement this invention, it is necessary for the server, terminal, and user to work together in cooperation. Specific embodiments are shown below.

[0342] The server is built on a cloud service and is a system that automatically retrieves progress information from various sources. These sources include, for example, project management tools and database systems, and data is retrieved via APIs. Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's facial expressions, voice, and text. Computer vision technology is used for facial expression analysis, speech recognition software for voice analysis, and natural language processing technology for text analysis. The results of the emotion analysis are recorded as numerical data and, in conjunction with the progress information, are used to re-evaluate the priority of tasks.

[0343] The terminal provides a user interface and is a tool for users to view progress and sentiment information received from the server. A dashboard is displayed on the terminal, allowing users to grasp the overall project picture through graphs and charts. Furthermore, the terminal incorporates a generative AI model, automatically generating progress reports and feedback using natural language generation technology and providing them to the user.

[0344] For example, if the server analyzes the emotional data of multiple participants during a team meeting and detects a high level of stress during the meeting, that information is sent to the terminal. The terminal can then display a real-time stress heatmap to the user and use a generative AI model to provide specific advice such as, "Please readjust the meeting agenda to reduce stress."

[0345] Users utilize this system to make decisions when managing projects. Based on progress and sentiment information provided through their devices, users can efficiently adjust task priorities and allocate resources optimally. They can also revise project plans based on feedback from the generative AI model.

[0346] As a concrete example, a prompt for the generating AI model might be: "Generate the emotional state of all members in the current project progress, and specific suggestions for improvement." This prompt allows the system to interactively respond to the user's needs.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The server retrieves progress information from its sources. The input at this stage is raw data obtained from external project management tools and database APIs. The server executes API calls to retrieve project progress and task status. Data processing involves converting this data into a unified format and storing it in the database. The output is progress data organized chronologically.

[0350] Step 2:

[0351] The server collects user emotion data. Inputs include camera footage capturing the user's facial expressions, microphone data recording their voice, and the content of text messages. The server applies image analysis algorithms to extract emotions from facial expressions, uses speech recognition software to interpret voice tone, and analyzes the emotions in the text using natural language processing techniques. Data calculations generate a numerical emotion score, which is the output.

[0352] Step 3:

[0353] The terminal displays progress and sentiment information retrieved from the server on the user interface. At this stage, the input consists of progress and sentiment data provided by the server. The terminal converts this data into a visually easy-to-understand format and displays it as graphs and charts on the dashboard. Specifically, it also displays an overview of the members' sentiment states using sentiment heatmaps, etc. As output, it provides visual information that allows the user to understand the situation at a glance.

[0354] Step 4:

[0355] Based on the information displayed on the device, the user prompts a generative AI model to request feedback to support decision-making. An example input might be, "Please suggest topics to address in the next meeting and indicate actions based on the team's current sentiment." The generative AI model analyzes this prompt and uses pre-collected data to generate appropriate feedback. The output provides feedback that includes concrete suggestions the user can implement.

[0356] Step 5:

[0357] The server will learn from all the data after the project is completed. The input at this stage consists of all progress and sentiment data collected during the project. The server uses machine learning algorithms to detect patterns within the dataset and improve the accuracy of sentiment analysis and progress management. The output will be an improved algorithm for the next project. Specifically, the model will be updated, improving the overall response speed and accuracy of the system.

[0358] (Application Example 2)

[0359] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0360] In the interior environment of autonomous vehicles, there is a need to improve comfort based on passenger emotions. Therefore, there is a challenge in the lack of technology to provide appropriate environmental control that aligns with the psychological state of passengers.

[0361] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0362] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for adapting the work environment using emotion recognition technology, and means for dynamically changing environmental settings considering the emotional state of passengers. This makes it possible to optimize the in-vehicle environment according to the emotional state of passengers.

[0363] "Progress information" refers to information in project management that shows the degree of completion and current status of each task or work process.

[0364] "External information sources" refer to data and resources provided from outside the system, and include information about project progress and work content.

[0365] "Dynamic re-evaluation" refers to updating and adapting evaluation criteria and content in real time in response to changes in circumstances and conditions.

[0366] "Resource allocation" is the process of assigning limited resources to each task or project in order to make the most optimal use of them.

[0367] "Emotion recognition technology" is a technology that analyzes a user's facial expressions and voice to determine their emotions and psychological state.

[0368] "Dynamically changing environment settings" refers to adjusting environmental conditions in real time according to the user's needs and circumstances at any given time.

[0369] "Adapting the work environment" means optimizing the physical and digital conditions of the work location and environment based on the user's psychological state and emotions.

[0370] To implement this invention, collaboration between a server, terminals, and users is necessary. The server first automatically acquires progress information from external sources, allowing for real-time monitoring of project progress. Furthermore, emotion recognition technology is used to collect and analyze emotional information from passengers' facial expressions and voices. Software such as OpenCV and Google Face API are used for this analysis. This allows for an understanding of passengers' psychological states, enabling appropriate adjustments to the in-vehicle environment.

[0371] The terminal displays progress and sentiment information transmitted from the server, supporting users in making decisions based on this information. It also adjusts in-car environment settings, such as music and air conditioning, based on the user's sentiment. This allows passengers to enjoy their journey in a comfortable environment. Specifically, devices such as smart glasses and head-mounted displays are used as terminals, providing real-time feedback.

[0372] Users can smoothly manage projects based on real-time feedback and advice provided by the server and terminal. If the system detects that a passenger is experiencing stress, it will suggest playing relaxing music or adjusting the temperature. This allows passengers to have a more comfortable journey.

[0373] For example, if a passenger gets into a car after a meeting and a high level of stress is detected, the system will play calming music and set the air conditioning to a relaxing temperature.

[0374] Examples of prompt statements include the following:

[0375] "Please tell me how to suggest a relaxing in-car environment based on user sentiment data, with a particular focus on music and temperature settings."

[0376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0377] Step 1:

[0378] The server retrieves progress information from external sources. It uses project task information and progress data as input to analyze the project's progress. The analyzed data is used to evaluate the project's current status, and stakeholders are notified as needed.

[0379] Step 2:

[0380] The server analyzes passengers' emotions using emotion recognition technology. It uses passenger facial image data and audio data as input. OpenCV and the Google Face API are used to analyze this data and quantify the passengers' emotional states. This quantified emotional data is output and used in subsequent processing.

[0381] Step 3:

[0382] Emotional data is sent from the server to the terminal. Based on this data, the terminal proposes the optimal in-car environment settings for the passenger. It takes emotional data as input, selects music and adjusts the air conditioning settings, processes the results internally, and outputs adjustment suggestions.

[0383] Step 4:

[0384] The device uses a generative AI model to generate specific environmental adjustment suggestions for the user in natural language. It takes emotional data and suggested environmental settings as input and outputs feedback messages generated in natural language. These messages are presented to the user in an easily understandable format.

[0385] Step 5:

[0386] The user receives feedback from the device and follows suggestions for optimizing the in-car environment settings. Based on the user's feedback, the device implements the suggested settings and adjusts the in-car environment. This process allows the user to enjoy a comfortable journey.

[0387] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0388] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0389] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0390] [Third Embodiment]

[0391] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0392] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0393] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0394] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0395] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0396] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0397] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0398] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0399] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0400] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0401] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0402] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0403] The project management support system of this invention supports the efficient operation of projects by automating the acquisition of progress information, prioritization, optimization of resource allocation, and response to problems.

[0404] The server automatically retrieves progress information from APIs of project management tools and communication platforms. This allows for the aggregation of information on progress, task status, deadlines, and assigned personnel, making it possible to understand the latest project status. For example, it can analyze the completion status of tasks obtained from an external source and calculate the overall progress of the project.

[0405] The terminal dynamically evaluates and resets task priorities based on information provided by the server. By utilizing an AI model, it has the functionality to determine priorities considering task importance, deadlines, and dependencies, enabling optimal resource allocation. For example, it allows for a mechanism to prioritize resources for urgent tasks.

[0406] Users receive progress reports automatically generated by the system, which assists them in making necessary decisions. By utilizing natural language generation technology, information is provided in an easy-to-understand and well-organized manner, allowing for a smoother understanding of project progress. This significantly reduces the effort required for report creation.

[0407] Furthermore, the system aims to improve the accuracy of future project management through continuous learning using past project data. By accumulating data and using that information, the AI ​​improves the accuracy of project planning and problem prediction, thereby achieving more effective project management.

[0408] Furthermore, the system automatically generates countermeasures in the event of unexpected problems. The server quickly analyzes the impact of the problem and suggests alternative solutions, allowing users to take effective action at the appropriate time. For example, if a team member takes an unscheduled vacation, a task reassignment plan is immediately generated, making it possible to adjust the schedule to avoid impacting the project's progress.

[0409] In this way, the present invention is an excellent system that streamlines and automates project management, reduces the burden on project managers and team members, and increases the success rate of projects.

[0410] The following describes the processing flow.

[0411] Step 1:

[0412] The server retrieves project progress data and task information from project management tools and communication platforms using APIs. This process involves periodic HTTP requests to ensure that the latest status is available in real time.

[0413] Step 2:

[0414] The server analyzes the acquired data and evaluates the project's progress based on that analysis. This provides the foundational data needed to determine the progress and any delays in each task.

[0415] Step 3:

[0416] The device uses the analyzed progress data to dynamically re-evaluate task priorities using an AI model. It sets priorities to efficiently advance tasks by considering importance, urgency, and dependencies.

[0417] Step 4:

[0418] The server considers and proposes effective resource allocation based on the AI ​​model and current task priorities. This is an action to optimize the skills and work time of team members.

[0419] Step 5:

[0420] Users receive automatically generated progress reports via their devices, allowing them to stay up-to-date on the project and receive support for decision-making as needed. These reports are provided in an easy-to-read format using natural language generation technology.

[0421] Step 6:

[0422] The server analyzes the impact of unexpected problems and automatically generates countermeasures and alternative solutions. This process is extremely fast to ensure that it does not disrupt the project.

[0423] Step 7:

[0424] The server stores past project data, which the AI ​​system uses to learn and improve the model's accuracy. This enhances the predictive power and planning accuracy of future project management.

[0425] (Example 1)

[0426] Next, we will describe Example 1. 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."

[0427] In project management, many tasks require manual collection of progress information, prioritization, and resource allocation, hindering efficient operation. Furthermore, impact analysis and alternative planning when problems arise are cumbersome and require rapid response. On the other hand, learning from vast amounts of historical data is insufficient, limiting the improvement of project management accuracy. We aim to solve these challenges efficiently and effectively.

[0428] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0429] In this invention, the server includes means for automatically acquiring progress information from an information processing device, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, and means for analyzing the impact of problems when they occur and automatically generating alternative solutions. This reduces manual work, improves the efficiency and accuracy of project management, and enables rapid response when problems occur.

[0430] "Progress information" refers to data regarding the current status of a project, the progress of tasks, deadlines, and assigned personnel.

[0431] An "information processing device" refers to a computing device used for collecting, processing, and analyzing data.

[0432] "Task priority" refers to the order in which tasks or work within a project are assigned, and is determined based on their importance and urgency.

[0433] "Resource allocation" refers to the act of assigning resources within a project, such as personnel, time, and equipment, to each task.

[0434] "Impact analysis in the event of a problem" refers to the process of evaluating the impact that unexpected events have on the entire project or individual tasks.

[0435] An "alternative plan" refers to a new solution that replaces the original plan when problems arise in the progress of a scheduled project or task.

[0436] "Natural language generation technology" refers to the technology that automatically creates human-readable text from data that computers can understand.

[0437] A "generative AI model" refers to an artificial intelligence model that has the ability to generate new texts or solutions based on user input or data.

[0438] A "prompt" refers to an instruction or question given to a generative AI model to obtain a specific output.

[0439] The project management support system according to the present invention is composed of a combination of various technologies in order to achieve efficiency and automation in project management.

[0440] The server automatically retrieves progress information from APIs of project management tools and communication platforms. Specifically, it uses APIs such as Jira and Slack to collect information. The server aggregates data such as the project status, task progress, and assigned personnel from these sources in JSON format and stores this data in a database.

[0441] The terminal uses an AI model based on progress information provided by the server to dynamically evaluate the priority of tasks. In this case, it leverages AI frameworks such as TensorFlow and PyTorch to determine priorities that take into account the importance, deadlines, and dependencies of tasks. This allows the terminal to allocate resources optimally, prioritizing the allocation of necessary resources to high-priority tasks.

[0442] Users receive progress reports automatically generated by a generative AI model. The generative AI model creates the report based on prompts entered. A specific example of a prompt is, "Summarize the current project progress and suggest the next steps." Users can use this report to make decisions and understand the project's progress more quickly.

[0443] This system improves the efficiency of project management, enabling monitoring of project progress and rapid response to problems. By linking servers and terminals, it automates the entire process from data collection and analysis to report generation, significantly reducing the burden on users.

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The server connects to the APIs of project management tools and communication platforms to retrieve progress information. Authentication is performed using API keys as input, and project task data is collected. The specific data is obtained in JSON format and includes task status, assignee, deadline, etc. Storing this data in a database allows for tracking the latest project status.

[0447] Step 2:

[0448] The server aggregates the collected data and analyzes the progress. It uses task information from the database as input to calculate the progress of each task. It expresses completed and incomplete tasks as percentages and calculates the progress rate. As output, it visualizes the progress on a dashboard, providing stakeholders with the latest status.

[0449] Step 3:

[0450] The terminal dynamically evaluates task priority using progress information sent from the server. Inputs include progress data and project requirements. This information is processed by an AI model (e.g., TensorFlow) to analyze task urgency, importance, and dependencies, and calculate priority. The output includes determining the optimal resource allocation and assigning resources based on importance.

[0451] Step 4:

[0452] The user receives a progress report generated by a generative AI model. Using the prompt "Summarize the current project progress and suggest the next steps" as input, the generative AI creates a report in natural language. The output is a human-readable report containing project progress and improvement suggestions.

[0453] Step 5:

[0454] The server monitors problems that arise during project progress and automatically generates countermeasures when necessary. Its inputs include analysis of progress data, the scope of the problem's impact, and resource availability. Using this data, it evaluates the impact of the problem and immediately creates alternative solutions. Outputs include, for example, task reassignment, aiming to streamline project progress.

[0455] (Application Example 1)

[0456] Next, we will explain Application Example 1. In the following explanation, 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."

[0457] Efficiently managing machinery in modern factories is crucial, especially in complex manufacturing processes. However, centrally monitoring the progress and prioritization of machinery and dynamically optimizing resource allocation is difficult, often leading to inefficient work planning and decreased productivity. A system is needed to solve these problems and achieve efficient resource allocation and progress management.

[0458] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0459] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for proposing the optimal resource allocation based on the priority of tasks and available resources, means for managing the progress status and priority of multiple work machines in a factory environment, and means for optimizing and notifying resource allocation in real time based on the status of the work machines. This makes it possible to efficiently manage work machines in a factory and optimize productivity.

[0460] "Progress information" refers to data that shows the progress and degree of completion of a task.

[0461] "External information sources" refer to information providers such as various databases and APIs used to collect information from outside the system.

[0462] "Task priority" is an indicator that shows the importance and urgency of each task, and serves as a basis for resource allocation.

[0463] "Resource allocation" refers to the efficient distribution of available personnel and equipment to various tasks.

[0464] An "alternative plan" refers to a new work plan or response method that modifies the original plan when a problem occurs.

[0465] The term "factory environment" refers to the physical and administrative settings in which production activities take place, including the locations where machinery and personnel operate.

[0466] "Working machinery" refers to mechanical devices within a factory that are tasked with performing specific operations.

[0467] "Real-time" refers to a unit of time in which information or data is collected and processed immediately, meaning there is virtually no delay.

[0468] "Optimization" refers to adjusting or improving conditions or constraints in order to obtain the maximum possible results under those conditions or constraints.

[0469] "Notification" refers to the act of a system informing a user or related device of specific information.

[0470] The system realizing this invention involves the coordinated operation of a server, terminals, and users to support the efficient management of work machines. The server periodically acquires progress information from various work machines installed in the factory from external sources and sensors and stores it in a database. This ensures that the progress of work is always managed in an up-to-date state.

[0471] The terminal dynamically re-evaluates task priorities using an AI model based on acquired progress information. This AI model is built using libraries such as scikit-learn and TensorFlow, and calculates priorities based on the importance and deadlines of each task. It also proposes the optimal resource allocation in real time, taking into account the available resources of the work machine, and notifies the user accordingly.

[0472] Users receive notifications from their devices on smartphones and tablets, enabling them to make necessary decisions and adjust their work accordingly. This allows for efficient use of resources within the factory, preventing delays and decreased productivity. Furthermore, progress reports are automatically generated using natural language generation technology, helping users quickly understand the situation.

[0473] For example, if an unscheduled shutdown occurs on a manufacturing line due to machine maintenance, the server immediately retrieves this information, recalculates the assignment of a replacement machine, and notifies the terminal. Based on this information, the user can take flexible countermeasures.

[0474] Examples of prompts for a generative AI model:

[0475] "Please provide a response plan for when a machine on the production line unexpectedly shuts down. Factors to consider include the availability of alternative machinery, the urgency of the task, and resource constraints."

[0476] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0477] Step 1:

[0478] The server collects progress information using sensor data from each machine in the factory and stores it in a database. This input includes information on machine operating status and production quantity. Based on this data, the server analyzes the progress and provides the latest progress information as output.

[0479] Step 2:

[0480] The terminal receives the latest progress information provided by the server and inputs it into the AI ​​model. This AI model uses scikit-learn to calculate priorities that take into account the importance, deadline, and current resource status of the tasks. This calculation outputs the optimal task priorities.

[0481] Step 3:

[0482] The device calculates resource allocation to optimally distribute available resources based on priorities generated by the AI ​​model. The calculation results are notified to the user's smartphone in real time for the user to review. The notifications include specific work instructions and tasks that require adjustment.

[0483] Step 4:

[0484] Users receive notifications from their devices and make necessary adjustments within the factory. This includes, for example, changing the assignment of specific machinery or adding additional personnel. The user's decisions are fed back into the AI ​​model for prioritizing tasks in the next iteration.

[0485] Step 5:

[0486] The server continuously trains its AI model using user feedback and past operation data. This training process contributes to improving the accuracy of future task priorities and resource allocation. TensorFlow is used for data computation, continuously improving the model's accuracy.

[0487] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0488] This invention enables project management that takes into account the user's emotional state by incorporating an emotion engine into a project management support system. Specific embodiments are described below.

[0489] In addition to conventional progress data acquisition and analysis functions, the server implements an emotion engine to recognize the user's emotional state. The emotion engine captures emotional information from the user's facial expressions, voice tone, text input, etc., to evaluate and record the user's psychological state in real time.

[0490] The terminal simultaneously displays progress and sentiment information provided by the server, offering an interface for a comprehensive understanding of the project's current status. It also includes a function to adjust priorities based on sentiment information, supporting improved work efficiency and optimal allocation of personnel.

[0491] As a concrete example, during a team meeting, the server analyzes the participants' reactions and provides a sentiment report to their terminals after the meeting ends. Based on this report, suggestions are made to improve the flow of the next meeting. For example, if many members are experiencing stress, the cause will be considered and tasks will be redistributed accordingly.

[0492] Users can make better decisions by receiving emotion-based advice and feedback from the system while performing normal project management operations. This feedback is provided in an easy-to-understand manner using natural language generation technology, allowing users to proceed with projects while considering their emotional state.

[0493] Furthermore, after the project is completed, the server analyzes the collected emotional data and learns to improve future projects. This learning process will enable more sophisticated emotional recognition and adaptation in the next project.

[0494] This invention is expected to improve the efficiency of project management and enhance the emotional satisfaction of team members. This is particularly useful in environments where remote communication is prevalent.

[0495] The following describes the processing flow.

[0496] Step 1:

[0497] The server retrieves data from project management tools and communication platforms via APIs. This includes not only collecting task status, progress, assignee, and deadline information, but also simultaneously capturing user comments and reactions from meeting and chat logs.

[0498] Step 2:

[0499] The server analyzes the acquired data to understand the progress and uses an emotion engine to evaluate the user's emotional state. The emotion engine performs facial recognition and voice analysis, and executes a process to quantify emotions such as stress, satisfaction, and excitement.

[0500] Step 3:

[0501] The terminal receives progress and sentiment information transmitted from the server and displays it to the user in an integrated interface. This allows the user to intuitively understand the project's progress and the sentiment tendencies of the team members.

[0502] Step 4:

[0503] Users can use the emotional feedback provided by their device to re-evaluate communication with team members and prioritize tasks. For example, if a member is showing high stress levels, the user can make adjustments to reduce their workload.

[0504] Step 5:

[0505] The server generates appropriate countermeasures and alternatives based on the problems encountered and the emotional states of users and members. In doing so, it adjusts its approach to make suggestions that effectively motivate the team, taking their emotional states into account.

[0506] Step 6:

[0507] The terminal recommends a specific action plan to the user based on the countermeasures and alternatives suggested by the server. This recommendation takes emotional aspects into consideration and is provided in a format that supports the smooth progress of the project.

[0508] Step 7:

[0509] The server analyzes progress information and sentiment data collected during the project period as learning material, and uses this information as operational guidelines for the next project, thereby improving the accuracy of management.

[0510] This trend enables project management systems to achieve overall optimization, including emotional aspects, supporting more humane and effective project management.

[0511] (Example 2)

[0512] Next, we will describe Example 2. 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."

[0513] Traditional project management systems focus on collecting progress information and optimizing resource allocation, but they fail to grasp the user's psychological state in real time and consider the emotional factors that influence project progress. This can lead to decreased user satisfaction and efficiency. Furthermore, traditional systems standardize feedback and alternative proposals, lacking personalized suggestions tailored to individual user situations.

[0514] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0515] In this invention, the server includes means for automatically acquiring progress information from an information source, means for sentiment analysis for detecting and evaluating the user's psychological state, and means for dynamically re-evaluating the priority of tasks based on the acquired progress information and sentiment information. This enables decision-making in project management that takes into account the user's psychological state, thereby improving work efficiency and user satisfaction.

[0516] "Progress information" refers to data that shows the progress of a project or the degree of work completion, and is collected from external sources.

[0517] "Information source" refers to an external database or platform that provides progress information and other project-related data.

[0518] "User psychological state" refers to the emotions and psychological reactions that users feel in relation to the project, which can potentially influence the project's progress.

[0519] "Emotion analysis" refers to a technology that evaluates a user's emotions from facial expressions, voice, text, etc., and expresses them numerically or qualitatively.

[0520] "Dynamic reevaluation" refers to the process of reviewing the order and priorities of tasks based on newly collected data, taking into account the ever-changing circumstances.

[0521] "Resource allocation" refers to the method of optimally distributing and efficiently utilizing the human, material, and temporal resources available in a project.

[0522] An "alternative plan" is a flexible response or alternative approach to an existing plan when a problem arises.

[0523] "Natural language generation technology" refers to the technology that allows computers to generate text in a language that is easy for humans to understand, and is used for automatically creating progress reports and feedback.

[0524] "Learning methods" refer to the process of improving algorithms based on experience using past data to enhance accuracy in future projects.

[0525] In order to implement this invention, it is necessary for the server, terminal, and user to work together in cooperation. Specific embodiments are shown below.

[0526] The server is built on a cloud service and is a system that automatically retrieves progress information from various sources. These sources include, for example, project management tools and database systems, and data is retrieved via APIs. Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's facial expressions, voice, and text. Computer vision technology is used for facial expression analysis, speech recognition software for voice analysis, and natural language processing technology for text analysis. The results of the emotion analysis are recorded as numerical data and, in conjunction with the progress information, are used to re-evaluate the priority of tasks.

[0527] The terminal provides a user interface and is a tool for users to view progress and sentiment information received from the server. A dashboard is displayed on the terminal, allowing users to grasp the overall project picture through graphs and charts. Furthermore, the terminal incorporates a generative AI model, automatically generating progress reports and feedback using natural language generation technology and providing them to the user.

[0528] For example, if the server analyzes the emotional data of multiple participants during a team meeting and detects a high level of stress during the meeting, that information is sent to the terminal. The terminal can then display a real-time stress heatmap to the user and use a generative AI model to provide specific advice such as, "Please readjust the meeting agenda to reduce stress."

[0529] Users utilize this system to make decisions when managing projects. Based on progress and sentiment information provided through their devices, users can efficiently adjust task priorities and allocate resources optimally. They can also revise project plans based on feedback from the generative AI model.

[0530] As a concrete example, a prompt for the generating AI model might be: "Generate the emotional state of all members in the current project progress, and specific suggestions for improvement." This prompt allows the system to interactively respond to the user's needs.

[0531] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0532] Step 1:

[0533] The server retrieves progress information from its sources. The input at this stage is raw data obtained from external project management tools and database APIs. The server executes API calls to retrieve project progress and task status. Data processing involves converting this data into a unified format and storing it in the database. The output is progress data organized chronologically.

[0534] Step 2:

[0535] The server collects user emotion data. Inputs include camera footage capturing the user's facial expressions, microphone data recording their voice, and the content of text messages. The server applies image analysis algorithms to extract emotions from facial expressions, uses speech recognition software to interpret voice tone, and analyzes the emotions in the text using natural language processing techniques. Data calculations generate a numerical emotion score, which is the output.

[0536] Step 3:

[0537] The terminal displays progress and sentiment information retrieved from the server on the user interface. At this stage, the input consists of progress and sentiment data provided by the server. The terminal converts this data into a visually easy-to-understand format and displays it as graphs and charts on the dashboard. Specifically, it also displays an overview of the members' sentiment states using sentiment heatmaps, etc. As output, it provides visual information that allows the user to understand the situation at a glance.

[0538] Step 4:

[0539] Based on the information displayed on the device, the user prompts a generative AI model to request feedback to support decision-making. An example input might be, "Please suggest topics to address in the next meeting and indicate actions based on the team's current sentiment." The generative AI model analyzes this prompt and uses pre-collected data to generate appropriate feedback. The output provides feedback that includes concrete suggestions the user can implement.

[0540] Step 5:

[0541] The server will learn from all the data after the project is completed. The input at this stage consists of all progress and sentiment data collected during the project. The server uses machine learning algorithms to detect patterns within the dataset and improve the accuracy of sentiment analysis and progress management. The output will be an improved algorithm for the next project. Specifically, the model will be updated, improving the overall response speed and accuracy of the system.

[0542] (Application Example 2)

[0543] Next, we will explain application example 2. In the following explanation, 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."

[0544] In the interior environment of autonomous vehicles, there is a need to improve comfort based on passenger emotions. Therefore, there is a challenge in the lack of technology to provide appropriate environmental control that aligns with the psychological state of passengers.

[0545] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0546] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for adapting the work environment using emotion recognition technology, and means for dynamically changing environmental settings considering the emotional state of passengers. This makes it possible to optimize the in-vehicle environment according to the emotional state of passengers.

[0547] "Progress information" refers to information in project management that shows the degree of completion and current status of each task or work process.

[0548] "External information sources" refer to data and resources provided from outside the system, and include information about project progress and work content.

[0549] "Dynamic re-evaluation" refers to updating and adapting evaluation criteria and content in real time in response to changes in circumstances and conditions.

[0550] "Resource allocation" is the process of assigning limited resources to each task or project in order to make the most optimal use of them.

[0551] "Emotion recognition technology" is a technology that analyzes a user's facial expressions and voice to determine their emotions and psychological state.

[0552] "Dynamically changing environment settings" refers to adjusting environmental conditions in real time according to the user's needs and circumstances at any given time.

[0553] "Adapting the work environment" means optimizing the physical and digital conditions of the work location and environment based on the user's psychological state and emotions.

[0554] To implement this invention, collaboration between a server, terminals, and users is necessary. The server first automatically acquires progress information from external sources, allowing for real-time monitoring of project progress. Furthermore, emotion recognition technology is used to collect and analyze emotional information from passengers' facial expressions and voices. Software such as OpenCV and Google Face API are used for this analysis. This allows for an understanding of passengers' psychological states, enabling appropriate adjustments to the in-vehicle environment.

[0555] The terminal displays progress and sentiment information transmitted from the server, supporting users in making decisions based on this information. It also adjusts in-car environment settings, such as music and air conditioning, based on the user's sentiment. This allows passengers to enjoy their journey in a comfortable environment. Specifically, devices such as smart glasses and head-mounted displays are used as terminals, providing real-time feedback.

[0556] Users can smoothly manage projects based on real-time feedback and advice provided by the server and terminal. If the system detects that a passenger is experiencing stress, it will suggest playing relaxing music or adjusting the temperature. This allows passengers to have a more comfortable journey.

[0557] For example, if a passenger gets into a car after a meeting and a high level of stress is detected, the system will play calming music and set the air conditioning to a relaxing temperature.

[0558] Examples of prompt statements include the following:

[0559] "Please tell me how to suggest a relaxing in-car environment based on user sentiment data, with a particular focus on music and temperature settings."

[0560] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0561] Step 1:

[0562] The server retrieves progress information from external sources. It uses project task information and progress data as input to analyze the project's progress. The analyzed data is used to evaluate the project's current status, and stakeholders are notified as needed.

[0563] Step 2:

[0564] The server analyzes passengers' emotions using emotion recognition technology. It uses passenger facial image data and audio data as input. OpenCV and the Google Face API are used to analyze this data and quantify the passengers' emotional states. This quantified emotional data is output and used in subsequent processing.

[0565] Step 3:

[0566] Emotional data is sent from the server to the terminal. Based on this data, the terminal proposes the optimal in-car environment settings for the passenger. It takes emotional data as input, selects music and adjusts the air conditioning settings, processes the results internally, and outputs adjustment suggestions.

[0567] Step 4:

[0568] The device uses a generative AI model to generate specific environmental adjustment suggestions for the user in natural language. It takes emotional data and suggested environmental settings as input and outputs feedback messages generated in natural language. These messages are presented to the user in an easily understandable format.

[0569] Step 5:

[0570] The user receives feedback from the device and follows suggestions for optimizing the in-car environment settings. Based on the user's feedback, the device implements the suggested settings and adjusts the in-car environment. This process allows the user to enjoy a comfortable journey.

[0571] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0572] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0573] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0574] [Fourth Embodiment]

[0575] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0576] As shown in Figure 7, the 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.

[0577] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0578] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0579] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0580] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0581] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0582] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0583] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0584] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0585] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0586] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0587] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0588] The project management support system of this invention supports the efficient operation of projects by automating the acquisition of progress information, prioritization, optimization of resource allocation, and response to problems.

[0589] The server automatically retrieves progress information from APIs of project management tools and communication platforms. This allows for the aggregation of information on progress, task status, deadlines, and assigned personnel, making it possible to understand the latest project status. For example, it can analyze the completion status of tasks obtained from an external source and calculate the overall progress of the project.

[0590] The terminal dynamically evaluates and resets task priorities based on information provided by the server. By utilizing an AI model, it has the functionality to determine priorities considering task importance, deadlines, and dependencies, enabling optimal resource allocation. For example, it allows for a mechanism to prioritize resources for urgent tasks.

[0591] Users receive progress reports automatically generated by the system, which assists them in making necessary decisions. By utilizing natural language generation technology, information is provided in an easy-to-understand and well-organized manner, allowing for a smoother understanding of project progress. This significantly reduces the effort required for report creation.

[0592] Furthermore, the system aims to improve the accuracy of future project management through continuous learning using past project data. By accumulating data and using that information, the AI ​​improves the accuracy of project planning and problem prediction, thereby achieving more effective project management.

[0593] Furthermore, the system automatically generates countermeasures in the event of unexpected problems. The server quickly analyzes the impact of the problem and suggests alternative solutions, allowing users to take effective action at the appropriate time. For example, if a team member takes an unscheduled vacation, a task reassignment plan is immediately generated, making it possible to adjust the schedule to avoid impacting the project's progress.

[0594] In this way, the present invention is an excellent system that streamlines and automates project management, reduces the burden on project managers and team members, and increases the success rate of projects.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The server retrieves project progress data and task information from project management tools and communication platforms using APIs. This process involves periodic HTTP requests to ensure that the latest status is available in real time.

[0598] Step 2:

[0599] The server analyzes the acquired data and evaluates the project's progress based on that analysis. This provides the foundational data needed to determine the progress and any delays in each task.

[0600] Step 3:

[0601] The device uses the analyzed progress data to dynamically re-evaluate task priorities using an AI model. It sets priorities to efficiently advance tasks by considering importance, urgency, and dependencies.

[0602] Step 4:

[0603] The server considers and proposes effective resource allocation based on the AI ​​model and current task priorities. This is an action to optimize the skills and work time of team members.

[0604] Step 5:

[0605] Users receive automatically generated progress reports via their devices, allowing them to stay up-to-date on the project and receive support for decision-making as needed. These reports are provided in an easy-to-read format using natural language generation technology.

[0606] Step 6:

[0607] The server analyzes the impact of unexpected problems and automatically generates countermeasures and alternative solutions. This process is extremely fast to ensure that it does not disrupt the project.

[0608] Step 7:

[0609] The server stores past project data, which the AI ​​system uses to learn and improve the model's accuracy. This enhances the predictive power and planning accuracy of future project management.

[0610] (Example 1)

[0611] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] In project management, many tasks require manual collection of progress information, prioritization, and resource allocation, hindering efficient operation. Furthermore, impact analysis and alternative planning when problems arise are cumbersome and require rapid response. On the other hand, learning from vast amounts of historical data is insufficient, limiting the improvement of project management accuracy. We aim to solve these challenges efficiently and effectively.

[0613] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0614] In this invention, the server includes means for automatically acquiring progress information from an information processing device, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, and means for analyzing the impact of problems when they occur and automatically generating alternative solutions. This reduces manual work, improves the efficiency and accuracy of project management, and enables rapid response when problems occur.

[0615] "Progress information" refers to data regarding the current status of a project, the progress of tasks, deadlines, and assigned personnel.

[0616] An "information processing device" refers to a computing device used for collecting, processing, and analyzing data.

[0617] "Task priority" refers to the order in which tasks or work within a project are assigned, and is determined based on their importance and urgency.

[0618] "Resource allocation" refers to the act of assigning resources within a project, such as personnel, time, and equipment, to each task.

[0619] "Impact analysis in the event of a problem" refers to the process of evaluating the impact that unexpected events have on the entire project or individual tasks.

[0620] An "alternative plan" refers to a new solution that replaces the original plan when problems arise in the progress of a scheduled project or task.

[0621] "Natural language generation technology" refers to the technology that automatically creates human-readable text from data that computers can understand.

[0622] A "generative AI model" refers to an artificial intelligence model that has the ability to generate new texts or solutions based on user input or data.

[0623] A "prompt" refers to an instruction or question given to a generative AI model to obtain a specific output.

[0624] The project management support system according to the present invention is composed of a combination of various technologies in order to achieve efficiency and automation in project management.

[0625] The server automatically retrieves progress information from APIs of project management tools and communication platforms. Specifically, it uses APIs such as Jira and Slack to collect information. The server aggregates data such as the project status, task progress, and assigned personnel from these sources in JSON format and stores this data in a database.

[0626] The terminal uses an AI model based on progress information provided by the server to dynamically evaluate the priority of tasks. In this case, it leverages AI frameworks such as TensorFlow and PyTorch to determine priorities that take into account the importance, deadlines, and dependencies of tasks. This allows the terminal to allocate resources optimally, prioritizing the allocation of necessary resources to high-priority tasks.

[0627] Users receive progress reports automatically generated by a generative AI model. The generative AI model creates the report based on prompts entered. A specific example of a prompt is, "Summarize the current project progress and suggest the next steps." Users can use this report to make decisions and understand the project's progress more quickly.

[0628] This system improves the efficiency of project management, enabling monitoring of project progress and rapid response to problems. By linking servers and terminals, it automates the entire process from data collection and analysis to report generation, significantly reducing the burden on users.

[0629] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0630] Step 1:

[0631] The server connects to the APIs of project management tools and communication platforms to retrieve progress information. Authentication is performed using API keys as input, and project task data is collected. The specific data is obtained in JSON format and includes task status, assignee, deadline, etc. Storing this data in a database allows for tracking the latest project status.

[0632] Step 2:

[0633] The server aggregates the collected data and analyzes the progress. It uses task information from the database as input to calculate the progress of each task. It expresses completed and incomplete tasks as percentages and calculates the progress rate. As output, it visualizes the progress on a dashboard, providing stakeholders with the latest status.

[0634] Step 3:

[0635] The terminal dynamically evaluates task priority using progress information sent from the server. Inputs include progress data and project requirements. This information is processed by an AI model (e.g., TensorFlow) to analyze task urgency, importance, and dependencies, and calculate priority. The output includes determining the optimal resource allocation and assigning resources based on importance.

[0636] Step 4:

[0637] The user receives a progress report generated by a generative AI model. Using the prompt "Summarize the current project progress and suggest the next steps" as input, the generative AI creates a report in natural language. The output is a human-readable report containing project progress and improvement suggestions.

[0638] Step 5:

[0639] The server monitors problems that arise during project progress and automatically generates countermeasures when necessary. Its inputs include analysis of progress data, the scope of the problem's impact, and resource availability. Using this data, it evaluates the impact of the problem and immediately creates alternative solutions. Outputs include, for example, task reassignment, aiming to streamline project progress.

[0640] (Application Example 1)

[0641] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] Efficiently managing machinery in modern factories is crucial, especially in complex manufacturing processes. However, centrally monitoring the progress and prioritization of machinery and dynamically optimizing resource allocation is difficult, often leading to inefficient work planning and decreased productivity. A system is needed to solve these problems and achieve efficient resource allocation and progress management.

[0643] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0644] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for proposing the optimal resource allocation based on the priority of tasks and available resources, means for managing the progress status and priority of multiple work machines in a factory environment, and means for optimizing and notifying resource allocation in real time based on the status of the work machines. This makes it possible to efficiently manage work machines in a factory and optimize productivity.

[0645] "Progress information" refers to data that shows the progress and degree of completion of a task.

[0646] "External information sources" refer to information providers such as various databases and APIs used to collect information from outside the system.

[0647] "Task priority" is an indicator that shows the importance and urgency of each task, and serves as a basis for resource allocation.

[0648] "Resource allocation" refers to the efficient distribution of available personnel and equipment to various tasks.

[0649] An "alternative plan" refers to a new work plan or response method that modifies the original plan when a problem occurs.

[0650] The term "factory environment" refers to the physical and administrative settings in which production activities take place, including the locations where machinery and personnel operate.

[0651] "Working machinery" refers to mechanical devices within a factory that are tasked with performing specific operations.

[0652] "Real-time" refers to a unit of time in which information or data is collected and processed immediately, meaning there is virtually no delay.

[0653] "Optimization" refers to adjusting or improving conditions or constraints in order to obtain the maximum possible results under those conditions or constraints.

[0654] "Notification" refers to the act of a system informing a user or related device of specific information.

[0655] The system realizing this invention involves the coordinated operation of a server, terminals, and users to support the efficient management of work machines. The server periodically acquires progress information from various work machines installed in the factory from external sources and sensors and stores it in a database. This ensures that the progress of work is always managed in an up-to-date state.

[0656] The terminal dynamically re-evaluates task priorities using an AI model based on acquired progress information. This AI model is built using libraries such as scikit-learn and TensorFlow, and calculates priorities based on the importance and deadlines of each task. It also proposes the optimal resource allocation in real time, taking into account the available resources of the work machine, and notifies the user accordingly.

[0657] Users receive notifications from their devices on smartphones and tablets, enabling them to make necessary decisions and adjust their work accordingly. This allows for efficient use of resources within the factory, preventing delays and decreased productivity. Furthermore, progress reports are automatically generated using natural language generation technology, helping users quickly understand the situation.

[0658] For example, if an unscheduled shutdown occurs on a manufacturing line due to machine maintenance, the server immediately retrieves this information, recalculates the assignment of a replacement machine, and notifies the terminal. Based on this information, the user can take flexible countermeasures.

[0659] Examples of prompts for a generative AI model:

[0660] "Please provide a response plan for when a machine on the production line unexpectedly shuts down. Factors to consider include the availability of alternative machinery, the urgency of the task, and resource constraints."

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] The server collects progress information using sensor data from each machine in the factory and stores it in a database. This input includes information on machine operating status and production quantity. Based on this data, the server analyzes the progress and provides the latest progress information as output.

[0664] Step 2:

[0665] The terminal receives the latest progress information provided by the server and inputs it into the AI ​​model. This AI model uses scikit-learn to calculate priorities that take into account the importance, deadline, and current resource status of the tasks. This calculation outputs the optimal task priorities.

[0666] Step 3:

[0667] The device calculates resource allocation to optimally distribute available resources based on priorities generated by the AI ​​model. The calculation results are notified to the user's smartphone in real time for the user to review. The notifications include specific work instructions and tasks that require adjustment.

[0668] Step 4:

[0669] Users receive notifications from their devices and make necessary adjustments within the factory. This includes, for example, changing the assignment of specific machinery or adding additional personnel. The user's decisions are fed back into the AI ​​model for prioritizing tasks in the next iteration.

[0670] Step 5:

[0671] The server continuously trains its AI model using user feedback and past operation data. This training process contributes to improving the accuracy of future task priorities and resource allocation. TensorFlow is used for data computation, continuously improving the model's accuracy.

[0672] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0673] This invention enables project management that takes into account the user's emotional state by incorporating an emotion engine into a project management support system. Specific embodiments are described below.

[0674] In addition to conventional progress data acquisition and analysis functions, the server implements an emotion engine to recognize the user's emotional state. The emotion engine captures emotional information from the user's facial expressions, voice tone, text input, etc., to evaluate and record the user's psychological state in real time.

[0675] The terminal simultaneously displays progress and sentiment information provided by the server, offering an interface for a comprehensive understanding of the project's current status. It also includes a function to adjust priorities based on sentiment information, supporting improved work efficiency and optimal allocation of personnel.

[0676] As a concrete example, during a team meeting, the server analyzes the participants' reactions and provides a sentiment report to their terminals after the meeting ends. Based on this report, suggestions are made to improve the flow of the next meeting. For example, if many members are experiencing stress, the cause will be considered and tasks will be redistributed accordingly.

[0677] Users can make better decisions by receiving emotion-based advice and feedback from the system while performing normal project management operations. This feedback is provided in an easy-to-understand manner using natural language generation technology, allowing users to proceed with projects while considering their emotional state.

[0678] Furthermore, after the project is completed, the server analyzes the collected emotional data and learns to improve future projects. This learning process will enable more sophisticated emotional recognition and adaptation in the next project.

[0679] This invention is expected to improve the efficiency of project management and enhance the emotional satisfaction of team members. This is particularly useful in environments where remote communication is prevalent.

[0680] The following describes the processing flow.

[0681] Step 1:

[0682] The server retrieves data from project management tools and communication platforms via APIs. This includes not only collecting task status, progress, assignee, and deadline information, but also simultaneously capturing user comments and reactions from meeting and chat logs.

[0683] Step 2:

[0684] The server analyzes the acquired data to understand the progress and uses an emotion engine to evaluate the user's emotional state. The emotion engine performs facial recognition and voice analysis, and executes a process to quantify emotions such as stress, satisfaction, and excitement.

[0685] Step 3:

[0686] The terminal receives progress and sentiment information transmitted from the server and displays it to the user in an integrated interface. This allows the user to intuitively understand the project's progress and the sentiment tendencies of the team members.

[0687] Step 4:

[0688] Users can use the emotional feedback provided by their device to re-evaluate communication with team members and prioritize tasks. For example, if a member is showing high stress levels, the user can make adjustments to reduce their workload.

[0689] Step 5:

[0690] The server generates appropriate countermeasures and alternatives based on the problems encountered and the emotional states of users and members. In doing so, it adjusts its approach to make suggestions that effectively motivate the team, taking their emotional states into account.

[0691] Step 6:

[0692] The terminal recommends a specific action plan to the user based on the countermeasures and alternatives suggested by the server. This recommendation takes emotional aspects into consideration and is provided in a format that supports the smooth progress of the project.

[0693] Step 7:

[0694] The server analyzes progress information and sentiment data collected during the project period as learning material, and uses this information as operational guidelines for the next project, thereby improving the accuracy of management.

[0695] This trend enables project management systems to achieve overall optimization, including emotional aspects, supporting more humane and effective project management.

[0696] (Example 2)

[0697] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] Traditional project management systems focus on collecting progress information and optimizing resource allocation, but they fail to grasp the user's psychological state in real time and consider the emotional factors that influence project progress. This can lead to decreased user satisfaction and efficiency. Furthermore, traditional systems standardize feedback and alternative proposals, lacking personalized suggestions tailored to individual user situations.

[0699] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0700] In this invention, the server includes means for automatically acquiring progress information from an information source, means for sentiment analysis for detecting and evaluating the user's psychological state, and means for dynamically re-evaluating the priority of tasks based on the acquired progress information and sentiment information. This enables decision-making in project management that takes into account the user's psychological state, thereby improving work efficiency and user satisfaction.

[0701] "Progress information" refers to data that shows the progress of a project or the degree of work completion, and is collected from external sources.

[0702] "Information source" refers to an external database or platform that provides progress information and other project-related data.

[0703] "User psychological state" refers to the emotions and psychological reactions that users feel in relation to the project, which can potentially influence the project's progress.

[0704] "Emotion analysis" refers to a technology that evaluates a user's emotions from facial expressions, voice, text, etc., and expresses them numerically or qualitatively.

[0705] "Dynamic reevaluation" refers to the process of reviewing the order and priorities of tasks based on newly collected data, taking into account the ever-changing circumstances.

[0706] "Resource allocation" refers to the method of optimally distributing and efficiently utilizing the human, material, and temporal resources available in a project.

[0707] An "alternative plan" is a flexible response or alternative approach to an existing plan when a problem arises.

[0708] "Natural language generation technology" refers to the technology that allows computers to generate text in a language that is easy for humans to understand, and is used for automatically creating progress reports and feedback.

[0709] "Learning methods" refer to the process of improving algorithms based on experience using past data to enhance accuracy in future projects.

[0710] In order to implement this invention, it is necessary for the server, terminal, and user to work together in cooperation. Specific embodiments are shown below.

[0711] The server is built on a cloud service and is a system that automatically retrieves progress information from various sources. These sources include, for example, project management tools and database systems, and data is retrieved via APIs. Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's facial expressions, voice, and text. Computer vision technology is used for facial expression analysis, speech recognition software for voice analysis, and natural language processing technology for text analysis. The results of the emotion analysis are recorded as numerical data and, in conjunction with the progress information, are used to re-evaluate the priority of tasks.

[0712] The terminal provides a user interface and is a tool for users to view progress and sentiment information received from the server. A dashboard is displayed on the terminal, allowing users to grasp the overall project picture through graphs and charts. Furthermore, the terminal incorporates a generative AI model, automatically generating progress reports and feedback using natural language generation technology and providing them to the user.

[0713] For example, if the server analyzes the emotional data of multiple participants during a team meeting and detects a high level of stress during the meeting, that information is sent to the terminal. The terminal can then display a real-time stress heatmap to the user and use a generative AI model to provide specific advice such as, "Please readjust the meeting agenda to reduce stress."

[0714] Users utilize this system to make decisions when managing projects. Based on progress and sentiment information provided through their devices, users can efficiently adjust task priorities and allocate resources optimally. They can also revise project plans based on feedback from the generative AI model.

[0715] As a concrete example, a prompt for the generating AI model might be: "Generate the emotional state of all members in the current project progress, and specific suggestions for improvement." This prompt allows the system to interactively respond to the user's needs.

[0716] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0717] Step 1:

[0718] The server retrieves progress information from its sources. The input at this stage is raw data obtained from external project management tools and database APIs. The server executes API calls to retrieve project progress and task status. Data processing involves converting this data into a unified format and storing it in the database. The output is progress data organized chronologically.

[0719] Step 2:

[0720] The server collects user emotion data. Inputs include camera footage capturing the user's facial expressions, microphone data recording their voice, and the content of text messages. The server applies image analysis algorithms to extract emotions from facial expressions, uses speech recognition software to interpret voice tone, and analyzes the emotions in the text using natural language processing techniques. Data calculations generate a numerical emotion score, which is the output.

[0721] Step 3:

[0722] The terminal displays progress and sentiment information retrieved from the server on the user interface. At this stage, the input consists of progress and sentiment data provided by the server. The terminal converts this data into a visually easy-to-understand format and displays it as graphs and charts on the dashboard. Specifically, it also displays an overview of the members' sentiment states using sentiment heatmaps, etc. As output, it provides visual information that allows the user to understand the situation at a glance.

[0723] Step 4:

[0724] Based on the information displayed on the device, the user prompts a generative AI model to request feedback to support decision-making. An example input might be, "Please suggest topics to address in the next meeting and indicate actions based on the team's current sentiment." The generative AI model analyzes this prompt and uses pre-collected data to generate appropriate feedback. The output provides feedback that includes concrete suggestions the user can implement.

[0725] Step 5:

[0726] The server will learn from all the data after the project is completed. The input at this stage consists of all progress and sentiment data collected during the project. The server uses machine learning algorithms to detect patterns within the dataset and improve the accuracy of sentiment analysis and progress management. The output will be an improved algorithm for the next project. Specifically, the model will be updated, improving the overall response speed and accuracy of the system.

[0727] (Application Example 2)

[0728] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0729] In the interior environment of autonomous vehicles, there is a need to improve comfort based on passenger emotions. Therefore, there is a challenge in the lack of technology to provide appropriate environmental control that aligns with the psychological state of passengers.

[0730] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0731] In this invention, the server includes means for automatically acquiring progress information from an external information source, means for dynamically re-evaluating the priority of tasks based on the acquired progress information, means for adapting the work environment using emotion recognition technology, and means for dynamically changing environmental settings considering the emotional state of passengers. This makes it possible to optimize the in-vehicle environment according to the emotional state of passengers.

[0732] "Progress information" refers to information in project management that shows the degree of completion and current status of each task or work process.

[0733] "External information sources" refer to data and resources provided from outside the system, and include information about project progress and work content.

[0734] "Dynamic re-evaluation" refers to updating and adapting evaluation criteria and content in real time in response to changes in circumstances and conditions.

[0735] "Resource allocation" is the process of assigning limited resources to each task or project in order to make the most optimal use of them.

[0736] "Emotion recognition technology" is a technology that analyzes a user's facial expressions and voice to determine their emotions and psychological state.

[0737] "Dynamically changing environment settings" refers to adjusting environmental conditions in real time according to the user's needs and circumstances at any given time.

[0738] "Adapting the work environment" means optimizing the physical and digital conditions of the work location and environment based on the user's psychological state and emotions.

[0739] To implement this invention, collaboration between a server, terminals, and users is necessary. The server first automatically acquires progress information from external sources, allowing for real-time monitoring of project progress. Furthermore, emotion recognition technology is used to collect and analyze emotional information from passengers' facial expressions and voices. Software such as OpenCV and Google Face API are used for this analysis. This allows for an understanding of passengers' psychological states, enabling appropriate adjustments to the in-vehicle environment.

[0740] The terminal displays progress and sentiment information transmitted from the server, supporting users in making decisions based on this information. It also adjusts in-car environment settings, such as music and air conditioning, based on the user's sentiment. This allows passengers to enjoy their journey in a comfortable environment. Specifically, devices such as smart glasses and head-mounted displays are used as terminals, providing real-time feedback.

[0741] Users can smoothly manage projects based on real-time feedback and advice provided by the server and terminal. If the system detects that a passenger is experiencing stress, it will suggest playing relaxing music or adjusting the temperature. This allows passengers to have a more comfortable journey.

[0742] For example, if a passenger gets into a car after a meeting and a high level of stress is detected, the system will play calming music and set the air conditioning to a relaxing temperature.

[0743] Examples of prompt statements include the following:

[0744] "Please tell me how to suggest a relaxing in-car environment based on user sentiment data, with a particular focus on music and temperature settings."

[0745] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0746] Step 1:

[0747] The server retrieves progress information from external sources. It uses project task information and progress data as input to analyze the project's progress. The analyzed data is used to evaluate the project's current status, and stakeholders are notified as needed.

[0748] Step 2:

[0749] The server analyzes passengers' emotions using emotion recognition technology. It uses passenger facial image data and audio data as input. OpenCV and the Google Face API are used to analyze this data and quantify the passengers' emotional states. This quantified emotional data is output and used in subsequent processing.

[0750] Step 3:

[0751] Emotional data is sent from the server to the terminal. Based on this data, the terminal proposes the optimal in-car environment settings for the passenger. It takes emotional data as input, selects music and adjusts the air conditioning settings, processes the results internally, and outputs adjustment suggestions.

[0752] Step 4:

[0753] The device uses a generative AI model to generate specific environmental adjustment suggestions for the user in natural language. It takes emotional data and suggested environmental settings as input and outputs feedback messages generated in natural language. These messages are presented to the user in an easily understandable format.

[0754] Step 5:

[0755] The user receives feedback from the device and follows suggestions for optimizing the in-car environment settings. Based on the user's feedback, the device implements the suggested settings and adjusts the in-car environment. This process allows the user to enjoy a comfortable journey.

[0756] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0757] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0758] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0759] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0760] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0761] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0762] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0763] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0764] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0765] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0766] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0767] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0768] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0769] 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.

[0770] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0771] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0772] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0773] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0774] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0775] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0776] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0777] The following is further disclosed regarding the embodiments described above.

[0778] (Claim 1)

[0779] A means of automatically obtaining progress information from external sources,

[0780] A means of dynamically re-evaluating the priority of tasks based on acquired progress information,

[0781] A means of proposing the optimal resource allocation based on the priority of tasks and available resources,

[0782] A system that includes means for analyzing the impact of a problem when it occurs and automatically generating alternative solutions.

[0783] (Claim 2)

[0784] The system according to claim 1, which automatically generates progress reports using natural language generation technology and distributes them to relevant parties.

[0785] (Claim 3)

[0786] The system according to claim 1, comprising a learning means for learning from past project data to improve management accuracy in the next project.

[0787] "Example 1"

[0788] (Claim 1)

[0789] A means of automatically acquiring progress information from an information processing device,

[0790] A means of dynamically re-evaluating the priority of tasks based on acquired progress information,

[0791] A means of proposing the optimal resource allocation based on the priority of tasks and available resources,

[0792] A means of improving management accuracy through continuous learning using historical data,

[0793] A system that includes means for analyzing the impact of a problem when it occurs and automatically generating alternative solutions.

[0794] (Claim 2)

[0795] The system according to claim 1, which automatically generates progress reports using natural language generation technology and distributes them to relevant parties.

[0796] (Claim 3)

[0797] The system according to claim 1, which generates a report from a prompt sentence using a generative AI model.

[0798] "Application Example 1"

[0799] (Claim 1)

[0800] A means of automatically obtaining progress information from external sources,

[0801] A means of dynamically re-evaluating the priority of tasks based on acquired progress information,

[0802] A means of proposing the optimal resource allocation based on the priority of tasks and available resources,

[0803] A means to analyze the impact of a problem when it occurs and automatically generate alternative solutions,

[0804] A means of managing the progress and priority of multiple work machines in a factory environment,

[0805] A means of optimizing and notifying resource allocation in real time based on the status of the work machine.

[0806] A system that includes this.

[0807] (Claim 2)

[0808] The system according to claim 1, which automatically generates progress reports using natural language generation technology and distributes them to relevant parties.

[0809] (Claim 3)

[0810] The system according to claim 1, comprising a learning means for learning from past operation data and improving the accuracy of management in the next operation.

[0811] "Example 2 of combining an emotion engine"

[0812] (Claim 1)

[0813] A means of automatically obtaining progress information from the source,

[0814] A means of emotion analysis for detecting and evaluating the psychological state of users,

[0815] A means for dynamically re-evaluating the priority of tasks based on acquired progress information and sentiment information,

[0816] A means of proposing the optimal resource allocation based on the priority of tasks and available resources,

[0817] A system that includes means for analyzing the impact of a problem when it occurs and automatically generating alternative solutions.

[0818] (Claim 2)

[0819] The system according to claim 1, which automatically generates progress reports and emotion-based feedback using natural language generation technology and provides them to relevant parties.

[0820] (Claim 3)

[0821] The system according to claim 1, comprising a learning means for learning using past project data and sentiment data to improve management accuracy and sentiment analysis accuracy in the next project.

[0822] "Application example 2 when combining with an emotional engine"

[0823] (Claim 1)

[0824] A means of automatically obtaining progress information from external sources,

[0825] A means of dynamically re-evaluating the priority of tasks based on acquired progress information,

[0826] A means of proposing the optimal resource allocation based on the priority of tasks and available resources,

[0827] A means of adapting the work environment using emotion recognition technology,

[0828] A system that includes means for dynamically changing environmental settings to take into account the emotional state of passengers.

[0829] (Claim 2)

[0830] The system according to claim 1, which automatically generates progress reports using natural language generation technology and distributes them to relevant parties.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising a learning means for learning from past project data to improve management accuracy in the next project. [Explanation of symbols]

[0833] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically obtaining progress information from external sources, A means of dynamically re-evaluating the priority of tasks based on acquired progress information, A means of proposing the optimal resource allocation based on the priority of tasks and available resources, A means to analyze the impact of a problem when it occurs and automatically generate alternative solutions, A means of managing the progress and priority of multiple work machines in a factory environment, A means for optimizing and notifying resource allocation in real time based on the status of the work machine, A system that includes this.

2. The system according to claim 1, which automatically generates progress reports using natural language generation technology and distributes them to relevant parties.

3. The system according to claim 1, comprising a learning means for learning from past operation data and improving the accuracy of management in the next operation.

Images