system

Abstract

We provide the system. [Solution] A means for collecting historical information including the progress of a task and the actions of the person in charge, A means for learning a predictive model to predict the future progress of a task based on the aforementioned historical information, A means for identifying tasks that are likely to be delayed or have problems using the aforementioned predictive model, Means for generating alerts and suggested solutions regarding identified tasks, A means of notifying the project manager of the aforementioned alerts and suggestions, 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problems faced by project managers and companies are that they cannot anticipate the progress of tasks and the accompanying problems, and as a result, the entire project is delayed or the efficiency decreases. Existing methods focus on post-facto response, and there is a problem that proactive management is difficult. In particular, it is a major problem that the impact of task interdependencies and differences in the working styles of the persons in charge on the entire project cannot be evaluated and addressed in advance.

Means for Solving the Problems

[0005] This invention provides a means to collect historical information based on task progress and the actions of those responsible, and to analyze this information using a machine learning model, in order to improve the efficiency of project management. This means predicts future task progress and identifies tasks that may be delayed or problematic in advance. Furthermore, it enables proactive project management by notifying project managers of detected problems and proposing solutions. It also supports efficient project progress by suggesting resource reallocation and task schedule adjustments.

[0006] A "task" is a specific unit of work or activity set within a project, consisting of a work item with specific goals and deadlines to be achieved.

[0007] "Progress" refers to the extent to which a task or the entire project has been completed in accordance with the plan.

[0008] A "person in charge" is an individual or group responsible for carrying out a specific task or project.

[0009] "Historical information" refers to data collected in the past, including records of task progress, employee actions, and project outcomes.

[0010] A "predictive model" is a mathematical or statistical framework used to predict future events by analyzing past data.

[0011] "Delay" refers to a situation where a task or project falls behind its planned schedule.

[0012] An "alert" is a warning or cautionary message that is sent to the user when certain conditions are met.

[0013] A "solution" is a method or procedure proposed to improve or resolve a particular problem or issue.

[0014] "Resource reallocation" refers to the rearrangement of resources such as personnel, time, and equipment to help a task or project progress efficiently.

[0015] "Schedule adjustment" is the process of modifying the timeframes of planned tasks or projects to ensure they progress properly. [Brief explanation of the drawing]

[0016] [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] This 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 Example 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

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the labeled 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.

[0020] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is an AI system for supporting project management, aiming to prevent task delays and problems from occurring. The system functions by having a server collect historical information and using machine learning to predict future task progress.

[0038] Specifically, the server periodically retrieves data such as task progress and employee activity history from project management systems and databases. Next, the server preprocesses this data and prepares it for use in the model. This includes imputing missing data and normalization.

[0039] The server trains a predictive model based on pre-processed data. The trained model then takes new project data as input to predict the progress of future tasks. This prediction identifies potential delays and problems in the tasks.

[0040] The server alerts project managers about tasks that are likely to be delayed or problematic. These alerts include suggested solutions, such as resource reallocation or scheduling adjustments. This allows users to take appropriate action in advance.

[0041] For example, if a design team in a particular project has previously been supported by designers who tended to fall behind schedules, the server will store that data and predict the likelihood of a similar situation occurring in a new project. Based on this prediction, the server will issue alerts such as "The design team's schedule may fall behind schedule," helping users take preventative measures.

[0042] In this way, the present invention achieves increased efficiency in project management and improved risk management.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects past task progress, assignee information, and inter-project dependency data from project management systems and databases. It periodically retrieves the necessary data using APIs and SQL queries.

[0046] Step 2:

[0047] The server preprocesses the collected data. This includes imputing missing data, removing duplicates, and eliminating outliers. It also standardizes the data to prepare it for efficient training of predictive models.

[0048] Step 3:

[0049] The server splits the preprocessed dataset into training and test data. Using the training data, the server applies machine learning algorithms to build a model for predicting task progress.

[0050] Step 4:

[0051] The server evaluates the accuracy of the predictive model using test data. If necessary, it optimizes the model's accuracy by adjusting hyperparameters and other settings.

[0052] Step 5:

[0053] The server acquires real-time data from newly initiated projects and uses a trained predictive model to forecast the future progress of each task, identifying tasks that are likely to be delayed or are at high risk.

[0054] Step 6:

[0055] The server generates alert messages for tasks that are delayed or at risk. These alerts include suggestions for resolving the problem, such as adding resources or rescheduling the task.

[0056] Step 7:

[0057] The terminal displays alerts and suggestions via the project administrator's interface. The project administrator can receive this information and view the details.

[0058] Step 8:

[0059] Based on the displayed alerts and suggestions, the user consults with team members to determine feasible actions. These actions are then incorporated into the project plan to support the smooth progress of the project.

[0060] (Example 1)

[0061] 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."

[0062] In project management, delays in task progress and unexpected problems can occur, disrupting the overall schedule. Furthermore, planning without considering the activity history of assigned personnel carries risks. Effective measures are needed to prevent these problems.

[0063] 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.

[0064] In this invention, the server includes means for collecting historical information, means for preprocessing the historical information to impart missing data and normalize the data, and means for training a generative AI model using the preprocessed data to predict the progress of future tasks. This makes it possible to detect in advance the possibility of delays or problems occurring in the progress of future tasks and to take appropriate countermeasures.

[0065] "Historical information" refers to a collection of data regarding the progress of past tasks and the actions of the person in charge.

[0066] "Preprocessing" refers to processes such as imputing missing data and normalization that are performed to prepare collected data into a format suitable for analysis and model training.

[0067] A "generative AI model" is a model that uses machine learning algorithms to learn from data and is used for future predictions and classifications.

[0068] "Prediction" is the act of estimating the future progress of a task or the likelihood of problems occurring based on learned data.

[0069] An "alert" is a warning message sent to project managers when there is a high probability of task delays or problems occurring.

[0070] A "solution proposal" refers to a plan for reallocating resources or adjusting schedules that is presented as a countermeasure when delays or problems are anticipated.

[0071] This invention is an AI system that prevents task delays and problems in project management. The server collects historical information from project management systems and databases, and obtains data including task progress and the activity history of assigned personnel.

[0072] The server preprocesses this data by imputing missing data and normalizing it. For example, if data is missing, it fills in the missing portion with the mean, or it performs normalization to unify the data range. This prepares the data for use in generative AI models.

[0073] The server uses the pre-processed data to train a generative AI model. This training utilizes machine learning algorithms such as random forests and neural networks. The trained model helps predict the progress of future tasks using new project data. This allows the server to identify tasks that are likely to experience delays or problems.

[0074] The server generates alerts regarding identified tasks and notifies the user. These alerts include suggestions for solutions such as resource reallocation and scheduling adjustments. Based on this information, the user can take appropriate action in advance.

[0075] For example, in a project involving a designer who has a history of falling behind schedules, the server uses this historical information to predict the risk of delays and generates an alert such as, "The design team's schedule may fall behind schedule." Users who receive this alert can then adjust resources or revise the schedule.

[0076] An example of a prompt to input into the generating AI model is: "Train the model to predict project task delays and generate alerts and suggested solutions for tasks that are likely to cause problems." In this way, users can improve risk management and efficiency across the entire project.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server collects historical information from the project management system and database. Its input includes data such as task progress and the activity history of assigned personnel. This data collection may be done via APIs or using SQL queries. The output generates a raw dataset for use in the next step.

[0080] Step 2:

[0081] The server preprocesses the collected historical information. In this step, the raw dataset obtained in step 1 is used as input. Specifically, it performs actions such as imputing missing data and identifying and replacing outliers with appropriate values. It also normalizes the data to ensure that each data item has a unified scale. The output is preprocessed data formatted for use with generative AI models.

[0082] Step 3:

[0083] The server trains a generative AI model using preprocessed data. The input is the preprocessed data output in step 2. Specifically, it splits the data into training and test data and builds a model using algorithms such as random forests and neural networks. The output is the trained model used to predict future task progress.

[0084] Step 4:

[0085] The server uses this trained model to predict future task progress, taking new project data as input. The input is the latest task data related to the project. Specifically, the model is fed data and predicts potential task delays and problems. The output is a prediction that includes a ranking of each task's likelihood of delay and the reasons for these delays.

[0086] Step 5:

[0087] The server generates alerts for tasks that may experience delays or problems, based on the prediction results. The input used is the prediction results obtained in step 4. Specifically, it creates alert messages and suggests solutions such as resource reallocation and scheduling adjustments. The output consists of alerts and detailed solutions sent to project managers and stakeholders.

[0088] Step 6:

[0089] The user receives an alert from the server and considers the proposed solution. The input is the alert information sent in step 5. Specific actions include reallocating resources and reviewing the project schedule to implement the countermeasures. The output includes confirming that factors hindering the smooth progress of the project have been resolved and that tasks are proceeding as planned.

[0090] (Application Example 1)

[0091] 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."

[0092] In modern factories and production sites, numerous tasks are running simultaneously, making it difficult to manage the progress of each task. Furthermore, the risk of production delays due to machinery malfunctions is increasing. In this environment, there is a need for an efficient project management system that can prevent delays and problems and maximize productivity.

[0093] 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.

[0094] In this invention, the server includes means for collecting historical information including the progress of tasks and the actions of the person in charge; means for learning a predictive model for predicting the future progress of tasks based on the historical information; and means for monitoring the operating status of machinery and equipment in real time and predicting the progress of a specific job. This makes it possible to grasp the progress of each production task in real time and predict and notify delays and problems.

[0095] "Task progress" refers to information indicating the current progress or completion status of each task or project.

[0096] "Actions of the person in charge" refers to data that shows the specific tasks and decisions made by the person responsible for a particular task.

[0097] "Past information" refers to all information, including the history of tasks and the actions of personnel recorded in the past.

[0098] A "predictive model" is a computational model designed to predict future events or outcomes based on collected data.

[0099] "Operating status of machinery and equipment" refers to information that shows the current operating status and utilization rate of machinery and equipment in production facilities such as factories.

[0100] "Progress of a specific job" is an indicator that shows how far along a particular task or process is currently.

[0101] "Delay" refers to a situation where progress is behind schedule.

[0102] A "malfunction" refers to a state in which a machine or system does not operate as expected, resulting in an abnormality or failure.

[0103] A "warning" is information intended to notify and draw attention to anticipated risks or problems.

[0104] A "proposed solution" refers to specific actions or improvements recommended to avoid potential problems or risks.

[0105] To implement this invention, the server first collects data on the progress of tasks and the actions of personnel in factories and production sites. This utilizes sensor and log data, which is stored in an SQL database. The server uses AI single-board computers such as NVIDIA's Jetson Nano as hardware. The program is written in Python and uses Tensorflow® to train a predictive model.

[0106] The collected data is preprocessed using pandas and numpy. Preprocessing includes imputing missing values ​​and normalization. This data is then analyzed by machine learning models such as LSTM to predict the progress of future tasks. The server monitors the operating status of machinery and equipment in real time and generates alerts if the progress of a particular job is likely to fall behind schedule.

[0107] The user is notified of the prediction results and warnings. In response, the system proposes specific solutions, such as resource reallocation and task scheduling adjustments. These suggestions are then communicated to the user's device, enabling prompt action.

[0108] As a concrete example, if frequent malfunctions of a specific piece of equipment are detected from past data on an automotive parts assembly line, the system can use that data to make predictions and propose an early maintenance plan for that equipment. When using the generative AI model, the following prompt message is used: "Generate suggestions to minimize the risks associated with launching a new product line. Please provide advice based on past successes and failures that should be considered."

[0109] In this way, servers, terminals, and users work together to enable efficient project management and risk prediction.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server inputs task progress and assigned personnel actions, collected from sensor and log data, into an SQL database. This input includes work time, completion rate, and other data. Using this data, preprocessing such as missing value imputation and data normalization is performed using pandas and numpy, and a prepared dataset is output for the next step.

[0113] Step 2:

[0114] The server uses TensorFlow to train generative AI models, such as LSTM models, based on a preprocessed dataset. It analyzes past patterns based on the input data and trains the model to predict future task progress. The server then outputs this trained model.

[0115] Step 3:

[0116] The server uses a trained model to predict the future operating status of machinery and equipment, taking new real-time data as input. Based on the prediction, it calculates the likelihood of delays for specific jobs or the risk of machine malfunctions, and outputs warnings.

[0117] Step 4:

[0118] The terminal receives warnings from the server and notifies the user. The input includes predicted operational status and warning details. For display to the user, it outputs notification information along with suggested solutions.

[0119] Step 5:

[0120] The user reviews notifications from their device and, if necessary, reallocates resources or adjusts schedules. Based on this, they decide on specific actions and output them as system feedback.

[0121] Through this series of processes, the system enables efficient task management and the prediction of potential problems in the production environment.

[0122] 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.

[0123] This invention provides a system that combines an emotion engine with an AI system to support project management, enabling it to predict task delays and respond in a way that takes user emotions into account. This system allows project managers to proactively prevent task delays and risks while responding flexibly to users' emotional states.

[0124] Specifically, the server collects historical information, recording task progress and the actions of the assigned personnel. In addition, it uses an emotion engine to analyze user emotions and collect emotion data. This data may include user text communications and biometric information. The server uses this data to train machine learning models and predict future task progress.

[0125] The server generates alerts for potential delays or problems related to predicted tasks. The emotion engine adjusts the tone and content of these alerts based on the user's emotional state. For example, if the system detects that the user is stressed, the alert message will be delivered in a more considerate tone.

[0126] As an example, consider a situation where a user is managing multiple projects. The server analyzes project progress data and identifies a task that may be behind schedule. At the same time, if the emotion engine detects stress from the user's recent communications, the server sends a gentle alert message such as, "This task may be behind schedule. Don't worry, work with your team to find a solution."

[0127] Based on the displayed alerts and suggestions, users consider countermeasures and incorporate them into their plans. This process simultaneously improves the efficiency of project management and reduces user stress.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server collects task progress, employee activity history, and user text communication and biometric information from project management systems and databases. This allows it to obtain project history information and user sentiment data.

[0131] Step 2:

[0132] The server preprocesses the collected data. This includes imputing missing values, removing duplicates and noise, and using an emotion engine to analyze the user's emotional state and extract emotional information as numerical data.

[0133] Step 3:

[0134] The server trains a machine learning model based on a pre-processed dataset. Using historical data, it builds a model that can predict the future progress of each task. At this time, sentiment data is also incorporated into the model to consider the impact of emotional states on project progress.

[0135] Step 4:

[0136] The server uses real-time data from newly initiated projects to predict the future progress of each task using a trained predictive model, identifying tasks at risk of delays or problems. Sentimental data is incorporated into this process.

[0137] Step 5:

[0138] The server generates alert messages that take into account the user's emotional state regarding identified high-risk tasks. It adjusts the tone and suggestions of the messages based on feedback from the emotion engine.

[0139] Step 6:

[0140] The terminal notifies the project administrator of alert messages. Users can view the alerts and suggested actions through the project management software on the terminal.

[0141] Step 7:

[0142] Based on the alerts and suggestions received, users consult with the team to determine feasible countermeasures. This is then incorporated into the project plan to help ensure the project progresses smoothly.

[0143] In this way, the present invention enables risk prediction and responses that take into account user emotions in project management.

[0144] (Example 2)

[0145] 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".

[0146] In project management, while early detection of task delays and the presentation of appropriate countermeasures are required, communication that takes into account the emotional state of managers and stakeholders is often neglected. As a result, effective decision-making regarding schedule adjustments and risk mitigation is difficult, which can ultimately reduce the overall efficiency of the project.

[0147] 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.

[0148] In this invention, the server includes means for collecting historical information including the progress of a task and the activities of the person in charge; means for learning a predictive model for predicting the future progress of a task based on the historical information; and means including an emotion engine for analyzing the emotional state of the user. This enables the server to detect the risk of delays and problems in real time and to provide flexible responses and alerts that take the user's emotions into consideration.

[0149] "Task progress" refers to information indicating the stage to which each task within a project has been completed.

[0150] "Activities of the person in charge" refers to a record of the actions and efforts taken by the individual or team assigned to each task.

[0151] "Historical information" refers to a collection of data related to past task progress, the actions of those in charge, and project management.

[0152] A "predictive model" is a computational method used to predict the future state and risks of a task based on collected data.

[0153] An "emotion engine" is a technology that analyzes a user's emotional state from their text, voice, or biometric data.

[0154] An "alert" is a notification designed to draw the attention of users or project managers.

[0155] "Tone" refers to the style or atmosphere of expression in notifications and messages.

[0156] "Emotional state" refers to the emotional state or tendency that a user experiences at a particular time or in a particular situation.

[0157] A "proposed solution" refers to specific action guidelines or plans presented as a response to identified problems or risks.

[0158] This invention provides a system for supporting project management, comprising a server, an emotion engine, and a machine learning model. The server interacts with project management tools to collect historical information, including task progress and the activities of assigned personnel. The server also utilizes an emotion engine for sentiment analysis, analyzing the user's emotional state. This analysis considers text data from the user's emails and messages, as well as data from biometric devices.

[0159] The specific hardware used will be a general-purpose server machine and user terminals such as computers and smartphones. For software, a common management system widely used as a project management tool will be employed. For sentiment analysis, a general sentiment engine software will be used, and for machine learning models, frameworks such as TensorFlow and PyTorch will be employed.

[0160] The server uses this data to predict the future progress of tasks. Based on this prediction, it generates alerts for potential task delays or problems, but customizes the messages to be user-friendly. For example, if a user is under stress, the notification will be delivered in a considerate and gentle tone.

[0161] For example, consider a case where a user is managing multiple projects simultaneously. Based on historical information, the server might suggest that a particular task is likely to fall behind schedule. At the same time, if the server's emotion engine detects high stress levels from the user's recent emails, it might adjust the notification message to something like, "This task is likely to fall behind schedule. Don't worry, let's work with your team to find a solution."

[0162] Furthermore, an example of a prompt message in the AI ​​model generated by this system is, "If the user is feeling stressed, please express the delay notification message gently." This allows the user to receive appropriate information, reduce stress, and ensure the smooth progress of the project.

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

[0164] Step 1:

[0165] The server collects task progress and assignee activity history from the project management tool. It uses data provided by the project management tool API as input. The server stores this data in a database, accumulating it as task history information. The output is the stored history information data.

[0166] Step 2:

[0167] The server trains a machine learning model based on collected historical information. The input consists of task progress and historical data. The server uses this data to train a predictive model for future task progress. TensorFlow and PyTorch are used to build the model and improve prediction accuracy. The output is the trained predictive model.

[0168] Step 3:

[0169] The server uses an emotion engine to analyze the user's emotional state. It takes user text data and biometric information as input. The emotion engine analyzes this data and evaluates the user's emotional state. The output generated as a result of the analysis is data indicating the user's current emotional state.

[0170] Step 4:

[0171] The server identifies tasks at risk of delays or problems based on a predictive model and sentiment data. The input consists of a trained predictive model and analyzed sentiment data. The server processes this information to identify tasks where problems are predicted. The output is a list of identified problematic tasks.

[0172] Step 5:

[0173] The server generates alerts and adjusts their content based on the user's emotional state. The inputs are an identified task list and the user's emotional state. The server creates an alert message from this data, adjusting the tone and wording according to the user's state. The output is the optimized alert message.

[0174] Step 6:

[0175] The server notifies the user's device of the generated alert message. The input is the optimized alert message. The server sends this message to the user's PC or smartphone. The output is the alert message displayed on the user's device.

[0176] Step 7:

[0177] The user checks the alert message displayed on the device and takes appropriate action. The input is the user receiving the alert display on the device. Based on this, the user adjusts the project progress and communicates as needed. The output is the adjusted project plan and the actions taken.

[0178] (Application Example 2)

[0179] 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".

[0180] There is a need to simultaneously improve work efficiency on the factory floor and manage the emotional well-being of workers. Conventional systems have limitations in detecting task delays and problems early, and struggle to respond flexibly while considering the emotional state of workers. As a result, there are limitations to achieving both production process optimization and worker stress reduction.

[0181] 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.

[0182] In this invention, the server includes means for collecting historical data including the progress of a task and the actions of the person performing the task; means for learning a prediction system for predicting the future progress of a task based on the historical data; and means for identifying tasks that are likely to be delayed or have problems using the prediction system. This makes it possible to analyze the biometric information and voice data of workers and provide flexible warning messages that are tailored to their emotional state.

[0183] A "task" refers to an individual activity or task that must be performed in a specific job or work process.

[0184] "Progress status" refers to the state of how far a task or work has been completed.

[0185] "Implementer" refers to a person or device that has the specific role of carrying out and executing a task or operation.

[0186] "Past data" refers to information collected or recorded historically in the past.

[0187] A "predictive system" refers to an algorithm or model used to estimate future events or situations based on past data.

[0188] A "warning" refers to a notification or message intended to draw attention to a specific event or situation.

[0189] "Countermeasures" refer to the actions or solutions that should be taken in response to potential problems or delays.

[0190] "Emotional state" refers to the emotional response or condition that an individual experiences mentally at a particular moment.

[0191] "Biometric information" refers to data that indicates an individual's physical condition, including heart rate, blood pressure, and body temperature.

[0192] "Audio data" refers to digital information containing recorded speech, including spoken words and their characteristics.

[0193] The system to realize this application example is based primarily on a cloud infrastructure that includes servers, terminals, and robots to support the work. The server uses a program written in Python to collect real-time progress and worker data from the work site. The server acquires historical data to train a predictive system and runs an algorithm that uses this data to predict the progress of future tasks.

[0194] The prediction system incorporates a machine learning model using TensorFlow to identify potential delays. This allows for early identification of which tasks are likely to experience delays. The server uses the OpenCV library to analyze biometric and voice data acquired by the robot to determine the emotional state of the user. This allows the server to understand whether the user is experiencing stress and, if necessary, to adjust the tone of warning messages according to their emotional state.

[0195] For example, suppose a worker is performing a task on a production line when a malfunction in the equipment causes delays. If a robot detects high stress levels from the worker's biometric data, the server can display a considerate message such as, "Please check the status of this equipment. If necessary, please request support," thereby easing the worker's tension and encouraging efficient response.

[0196] An example of a prompt message utilizing the generative AI model is: "Design a Python script that instantly identifies the cause of production line delays, analyzes worker stress levels, and generates advice that enables implementers to take appropriate action." The goal is for the entire system to work together to improve work efficiency and worker well-being.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server collects real-time data on the progress of work at the site, as well as biometric and voice data from terminals and robots. The input data consists of work progress records and physiological data, which are temporarily stored on the server's storage. After the biometric and voice data are formatted, they are prepared to be sent to the analysis process.

[0200] Step 2:

[0201] The server inputs progress data into a machine learning model and predicts future task progress based on past data. At this point, the input is historical record data, which is processed by a TensorFlow-based model to predict which tasks are likely to be delayed. The output is a delay prediction associated with a specific task ID.

[0202] Step 3:

[0203] The server uses the OpenCV library to analyze biometric and audio data to estimate the user's emotional state. The input consists of the user's biometric signals and audio files. Based on this, a machine learning algorithm analyzes emotions and outputs a stress level assessment. Specifically, it identifies fatigue and high stress levels from heart rate and voice tone.

[0204] Step 4:

[0205] The server integrates predicted delay information with sentiment assessment results to generate appropriate warning messages. The input consists of delay prediction data and sentiment state assessment results. Based on prompts created using a generative AI model, the server outputs messages in an emotionally sensitive tone.

[0206] Step 5:

[0207] The server sends the generated warning message to the user's terminal. The user receives the warning message on their terminal and reviews the displayed suggestions and notifications. The input here is the generated warning message, and the output is the visual feedback on the user's terminal. Based on the notification, the user considers the following work guidelines.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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".

[0224] This invention is an AI system for supporting project management, aiming to prevent task delays and problems from occurring. The system functions by having a server collect historical information and using machine learning to predict future task progress.

[0225] Specifically, the server periodically retrieves data such as task progress and employee activity history from project management systems and databases. Next, the server preprocesses this data and prepares it for use in the model. This includes imputing missing data and normalization.

[0226] The server trains a predictive model based on pre-processed data. The trained model then takes new project data as input to predict the progress of future tasks. This prediction identifies potential delays and problems in the tasks.

[0227] The server alerts project managers about tasks that are likely to be delayed or problematic. These alerts include suggested solutions, such as resource reallocation or scheduling adjustments. This allows users to take appropriate action in advance.

[0228] For example, if a design team in a particular project has previously been supported by designers who tended to fall behind schedules, the server will store that data and predict the likelihood of a similar situation occurring in a new project. Based on this prediction, the server will issue alerts such as "The design team's schedule may fall behind schedule," helping users take preventative measures.

[0229] In this way, the present invention achieves increased efficiency in project management and improved risk management.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server collects past task progress, assignee information, and inter-project dependency data from project management systems and databases. It periodically retrieves the necessary data using APIs and SQL queries.

[0233] Step 2:

[0234] The server preprocesses the collected data. This includes imputing missing data, removing duplicates, and eliminating outliers. It also standardizes the data to prepare it for efficient training of predictive models.

[0235] Step 3:

[0236] The server splits the preprocessed dataset into training and test data. Using the training data, the server applies machine learning algorithms to build a model for predicting task progress.

[0237] Step 4:

[0238] The server evaluates the accuracy of the predictive model using test data. If necessary, it optimizes the model's accuracy by adjusting hyperparameters and other settings.

[0239] Step 5:

[0240] The server acquires real-time data from newly initiated projects and uses a trained predictive model to forecast the future progress of each task, identifying tasks that are likely to be delayed or are at high risk.

[0241] Step 6:

[0242] The server generates alert messages for tasks that are delayed or at risk. These alerts include suggestions for resolving the problem, such as adding resources or rescheduling the task.

[0243] Step 7:

[0244] The terminal displays alerts and suggestions via the project administrator's interface. The project administrator can receive this information and view the details.

[0245] Step 8:

[0246] Based on the displayed alerts and suggestions, the user consults with team members to determine feasible actions. These actions are then incorporated into the project plan to support the smooth progress of the project.

[0247] (Example 1)

[0248] 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."

[0249] In project management, delays in task progress and unexpected problems can occur, disrupting the overall schedule. Furthermore, planning without considering the activity history of assigned personnel carries risks. Effective measures are needed to prevent these problems.

[0250] 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.

[0251] In this invention, the server includes means for collecting historical information, means for preprocessing the historical information to impart missing data and normalize the data, and means for training a generative AI model using the preprocessed data to predict the progress of future tasks. This makes it possible to detect in advance the possibility of delays or problems occurring in the progress of future tasks and to take appropriate countermeasures.

[0252] "Historical information" refers to a collection of data regarding the progress of past tasks and the actions of the person in charge.

[0253] "Preprocessing" refers to processes such as imputing missing data and normalization that are performed to prepare collected data into a format suitable for analysis and model training.

[0254] A "generative AI model" is a model that uses machine learning algorithms to learn from data and is used for future predictions and classifications.

[0255] "Prediction" is the act of estimating the future progress of a task or the likelihood of problems occurring based on learned data.

[0256] An "alert" is a warning message sent to project managers when there is a high probability of task delays or problems occurring.

[0257] A "solution proposal" refers to a plan for reallocating resources or adjusting schedules that is presented as a countermeasure when delays or problems are anticipated.

[0258] This invention is an AI system that prevents task delays and problems in project management. The server collects historical information from project management systems and databases, and obtains data including task progress and the activity history of assigned personnel.

[0259] The server preprocesses this data by imputing missing data and normalizing it. For example, if data is missing, it fills in the missing portion with the mean, or it performs normalization to unify the data range. This prepares the data for use in generative AI models.

[0260] The server uses the pre-processed data to train a generative AI model. This training utilizes machine learning algorithms such as random forests and neural networks. The trained model helps predict the progress of future tasks using new project data. This allows the server to identify tasks that are likely to experience delays or problems.

[0261] The server generates alerts regarding identified tasks and notifies the user. These alerts include suggestions for solutions such as resource reallocation and scheduling adjustments. Based on this information, the user can take appropriate action in advance.

[0262] For example, in a project involving a designer who has a history of falling behind schedules, the server uses this historical information to predict the risk of delays and generates an alert such as, "The design team's schedule may fall behind schedule." Users who receive this alert can then adjust resources or revise the schedule.

[0263] An example of a prompt to input into the generating AI model is: "Train the model to predict project task delays and generate alerts and suggested solutions for tasks that are likely to cause problems." In this way, users can improve risk management and efficiency across the entire project.

[0264] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0265] Step 1:

[0266] The server collects historical information from the project management system and database. Its input includes data such as task progress and the activity history of assigned personnel. This data collection may be done via APIs or using SQL queries. The output generates a raw dataset for use in the next step.

[0267] Step 2:

[0268] The server preprocesses the collected historical information. In this step, the raw dataset obtained in step 1 is used as input. Specifically, it performs actions such as imputing missing data and identifying and replacing outliers with appropriate values. It also normalizes the data to ensure that each data item has a unified scale. The output is preprocessed data formatted for use with generative AI models.

[0269] Step 3:

[0270] The server trains a generative AI model using preprocessed data. The input is the preprocessed data output in step 2. Specifically, it splits the data into training and test data and builds a model using algorithms such as random forests and neural networks. The output is the trained model used to predict future task progress.

[0271] Step 4:

[0272] The server uses this trained model to predict future task progress, taking new project data as input. The input is the latest task data related to the project. Specifically, the model is fed data and predicts potential task delays and problems. The output is a prediction that includes a ranking of each task's likelihood of delay and the reasons for these delays.

[0273] Step 5:

[0274] The server generates alerts for tasks that may experience delays or problems, based on the prediction results. The input used is the prediction results obtained in step 4. Specifically, it creates alert messages and suggests solutions such as resource reallocation and scheduling adjustments. The output consists of alerts and detailed solutions sent to project managers and stakeholders.

[0275] Step 6:

[0276] The user receives an alert from the server and considers the proposed solution. The input is the alert information sent in step 5. Specific actions include reallocating resources and reviewing the project schedule to implement the countermeasures. The output includes confirming that factors hindering the smooth progress of the project have been resolved and that tasks are proceeding as planned.

[0277] (Application Example 1)

[0278] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0279] In modern factories and production sites, a large number of tasks are carried out simultaneously, making it difficult to manage the progress of each task. In addition, the risk of production delays due to malfunctions in machinery and equipment is also increasing. In such an environment, an efficient project management system is required to prevent delays and problems in advance and maximize productivity.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0281] In this invention, the server includes means for collecting past information including the progress of tasks and the actions of the persons in charge, means for learning a prediction model for predicting the future progress of tasks based on the past information, and means for monitoring the operating status of machinery and equipment in real time and predicting the progress of specific jobs. As a result, it becomes possible to grasp the progress of each task in production in real time and predict and notify delays and malfunctions.

[0282] The "progress of a task" is information indicating the current progress and completion degree of each work or operation.

[0283] The "actions of the person in charge" are data indicating the specific operations and decisions made by the person responsible for a certain task.

[0284] The "past information" is the entire information including the history of tasks and the actions of the persons in charge recorded in the past.

[0285] The "prediction model" is a calculation model designed to infer future events and results based on the collected data.

[0286] "The operating status of mechanical equipment" refers to information indicating the current operating state and operating rate of machines and devices in production facilities such as factories.

[0287] "The progress of a specific job" is an indicator showing how far a specific task or process has progressed currently.

[0288] "Delay" refers to a state where progress is behind the scheduled schedule.

[0289] "Defect" means that the machine or system does not operate as expected and an abnormality or failure has occurred.

[0290] "Warning" is information for notifying predicted risks and problems in advance and prompting attention.

[0291] "Proposal of solutions" refers to specific action plans and improvement measures recommended to avoid possible problems and risks.

[0292] To implement this invention, first, the server collects the progress of tasks and the actions of the persons in charge at the factory or production site. For this, sensors and log data are used and stored in an SQL database. The server uses an AI single-board computer such as NVIDIA's Jetson Nano as hardware. The program is written in Python, and a prediction model is learned using TensorFlow.

[0293] The collected data is preprocessed using pandas and numpy. The preprocessing includes filling in missing values and normalizing the data. This data is analyzed by a machine learning model such as LSTM to predict the progress of future tasks. The server monitors the operating status of mechanical equipment in real time and generates a warning if the progress of a specific job may be delayed from the plan.

[0294] The user is notified of the prediction results and warnings. In response, the system proposes specific solutions, such as resource reallocation and task scheduling adjustments. These suggestions are then communicated to the user's device, enabling prompt action.

[0295] As a concrete example, if frequent malfunctions of a specific piece of equipment are detected from past data on an automotive parts assembly line, the system can use that data to make predictions and propose an early maintenance plan for that equipment. When using the generative AI model, the following prompt message is used: "Generate suggestions to minimize the risks associated with launching a new product line. Please provide advice based on past successes and failures that should be considered."

[0296] In this way, servers, terminals, and users work together to enable efficient project management and risk prediction.

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] The server inputs task progress and assigned personnel actions, collected from sensor and log data, into an SQL database. This input includes work time, completion rate, and other data. Using this data, preprocessing such as missing value imputation and data normalization is performed using pandas and numpy, and a prepared dataset is output for the next step.

[0300] Step 2:

[0301] The server uses TensorFlow to train generative AI models, such as LSTM models, based on a preprocessed dataset. It analyzes past patterns based on the input data and trains the model to predict future task progress. The server then outputs this trained model.

[0302] Step 3:

[0303] The server uses the trained model to predict the future operating status of the operating machinery and equipment with new real-time data as input. Based on the prediction, it calculates the possibility of a specific job being delayed and the risk of machine malfunctions, and outputs the generation of warnings.

[0304] Step 4:

[0305] The terminal obtains the warnings from the server and notifies the user. The input includes the prediction results of the operating status and the content of the warnings. It outputs as notification information with suggestions for solutions for display to the user.

[0306] Step 5:

[0307] The user checks the notification content from the terminal and performs resource reallocation or schedule adjustment as necessary. Based on this, specific actions are determined and output as system feedback.

[0308] Through this series of processes, the system realizes efficient management of tasks and foresight of potential problems in the production site.

[0309] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0310] The present invention is a system that combines an emotion engine with an AI system for supporting project management, enabling prediction of task delays and responses considering the user's emotions. With this system, project managers can prevent task delays and risks in advance and can make flexible responses according to the user's emotional state.

[0311] Specifically, the server collects historical information, recording task progress and the actions of the assigned personnel. In addition, it uses an emotion engine to analyze user emotions and collect emotion data. This data may include user text communications and biometric information. The server uses this data to train machine learning models and predict future task progress.

[0312] The server generates alerts for potential delays or problems related to predicted tasks. The emotion engine adjusts the tone and content of these alerts based on the user's emotional state. For example, if the system detects that the user is stressed, the alert message will be delivered in a more considerate tone.

[0313] As an example, consider a situation where a user is managing multiple projects. The server analyzes project progress data and identifies a task that may be behind schedule. At the same time, if the emotion engine detects stress from the user's recent communications, the server sends a gentle alert message such as, "This task may be behind schedule. Don't worry, work with your team to find a solution."

[0314] Based on the displayed alerts and suggestions, users consider countermeasures and incorporate them into their plans. This process simultaneously improves the efficiency of project management and reduces user stress.

[0315] The following describes the processing flow.

[0316] Step 1:

[0317] The server collects task progress, employee activity history, and user text communication and biometric information from project management systems and databases. This allows it to obtain project history information and user sentiment data.

[0318] Step 2:

[0319] The server preprocesses the collected data. This includes imputing missing values, removing duplicates and noise, and using an emotion engine to analyze the user's emotional state and extract emotional information as numerical data.

[0320] Step 3:

[0321] The server trains a machine learning model based on a pre-processed dataset. Using historical data, it builds a model that can predict the future progress of each task. At this time, sentiment data is also incorporated into the model to consider the impact of emotional states on project progress.

[0322] Step 4:

[0323] The server uses real-time data from newly initiated projects to predict the future progress of each task using a trained predictive model, identifying tasks at risk of delays or problems. Sentimental data is incorporated into this process.

[0324] Step 5:

[0325] The server generates alert messages that take into account the user's emotional state regarding identified high-risk tasks. It adjusts the tone and suggestions of the messages based on feedback from the emotion engine.

[0326] Step 6:

[0327] The terminal notifies the project administrator of alert messages. Users can view the alerts and suggested actions through the project management software on the terminal.

[0328] Step 7:

[0329] Based on the alerts and suggestions received, users consult with the team to determine feasible countermeasures. This is then incorporated into the project plan to help ensure the project progresses smoothly.

[0330] In this way, the present invention enables risk prediction and responses that take into account user emotions in project management.

[0331] (Example 2)

[0332] 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".

[0333] In project management, while early detection of task delays and the presentation of appropriate countermeasures are required, communication that takes into account the emotional state of managers and stakeholders is often neglected. As a result, effective decision-making regarding schedule adjustments and risk mitigation is difficult, which can ultimately reduce the overall efficiency of the project.

[0334] 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.

[0335] In this invention, the server includes means for collecting historical information including the progress of a task and the activities of the person in charge; means for learning a predictive model for predicting the future progress of a task based on the historical information; and means including an emotion engine for analyzing the emotional state of the user. This enables the server to detect the risk of delays and problems in real time and to provide flexible responses and alerts that take the user's emotions into consideration.

[0336] "Task progress" refers to information indicating the stage to which each task within a project has been completed.

[0337] "Activities of the person in charge" refers to a record of the actions and efforts taken by the individual or team assigned to each task.

[0338] "Historical information" refers to a collection of data related to past task progress, the actions of those in charge, and project management.

[0339] A "predictive model" is a computational method used to predict the future state and risks of a task based on collected data.

[0340] An "emotion engine" is a technology that analyzes a user's emotional state from their text, voice, or biometric data.

[0341] An "alert" is a notification designed to draw the attention of users or project managers.

[0342] "Tone" refers to the style or atmosphere of expression in notifications and messages.

[0343] "Emotional state" refers to the emotional state or tendency that a user experiences at a particular time or in a particular situation.

[0344] A "proposed solution" refers to specific action guidelines or plans presented as a response to identified problems or risks.

[0345] This invention provides a system for supporting project management, comprising a server, an emotion engine, and a machine learning model. The server interacts with project management tools to collect historical information, including task progress and the activities of assigned personnel. The server also utilizes an emotion engine for sentiment analysis, analyzing the user's emotional state. This analysis considers text data from the user's emails and messages, as well as data from biometric devices.

[0346] The specific hardware used will be a general-purpose server machine and user terminals such as computers and smartphones. For software, a common management system widely used as a project management tool will be employed. For sentiment analysis, a general sentiment engine software will be used, and for machine learning models, frameworks such as TensorFlow and PyTorch will be employed.

[0347] The server uses this data to predict the future progress of tasks. Based on this prediction, it generates alerts for potential task delays or problems, but customizes the messages to be user-friendly. For example, if a user is under stress, the notification will be delivered in a considerate and gentle tone.

[0348] For example, consider a case where a user is managing multiple projects simultaneously. Based on historical information, the server might suggest that a particular task is likely to fall behind schedule. At the same time, if the server's emotion engine detects high stress levels from the user's recent emails, it might adjust the notification message to something like, "This task is likely to fall behind schedule. Don't worry, let's work with your team to find a solution."

[0349] Furthermore, an example of a prompt message in the AI ​​model generated by this system is, "If the user is feeling stressed, please express the delay notification message gently." This allows the user to receive appropriate information, reduce stress, and ensure the smooth progress of the project.

[0350] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0351] Step 1:

[0352] The server collects task progress and assignee activity history from the project management tool. It uses data provided by the project management tool API as input. The server stores this data in a database, accumulating it as task history information. The output is the stored history information data.

[0353] Step 2:

[0354] The server trains a machine learning model based on collected historical information. The input consists of task progress and historical data. The server uses this data to train a predictive model for future task progress. TensorFlow and PyTorch are used to build the model and improve prediction accuracy. The output is the trained predictive model.

[0355] Step 3:

[0356] The server uses an emotion engine to analyze the user's emotional state. It takes user text data and biometric information as input. The emotion engine analyzes this data and evaluates the user's emotional state. The output generated as a result of the analysis is data indicating the user's current emotional state.

[0357] Step 4:

[0358] The server identifies tasks at risk of delays or problems based on a predictive model and sentiment data. The input consists of a trained predictive model and analyzed sentiment data. The server processes this information to identify tasks where problems are predicted. The output is a list of identified problematic tasks.

[0359] Step 5:

[0360] The server generates alerts and adjusts their content based on the user's emotional state. The inputs are an identified task list and the user's emotional state. The server creates an alert message from this data, adjusting the tone and wording according to the user's state. The output is the optimized alert message.

[0361] Step 6:

[0362] The server notifies the user's device of the generated alert message. The input is the optimized alert message. The server sends this message to the user's PC or smartphone. The output is the alert message displayed on the user's device.

[0363] Step 7:

[0364] The user checks the alert message displayed on the device and takes appropriate action. The input is the user receiving the alert display on the device. Based on this, the user adjusts the project progress and communicates as needed. The output is the adjusted project plan and the actions taken.

[0365] (Application Example 2)

[0366] 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."

[0367] There is a need to simultaneously improve work efficiency on the factory floor and manage the emotional well-being of workers. Conventional systems have limitations in detecting task delays and problems early, and struggle to respond flexibly while considering the emotional state of workers. As a result, there are limitations to achieving both production process optimization and worker stress reduction.

[0368] 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.

[0369] In this invention, the server includes means for collecting historical data including the progress of a task and the actions of the person performing it; means for learning a prediction system for predicting the future progress of a task based on the historical data; and means for identifying tasks that are likely to be delayed or have problems using the prediction system. This makes it possible to analyze the biometric information and voice data of workers and provide flexible warning messages that are tailored to their emotional state.

[0370] A "task" refers to an individual activity or task that must be performed in a specific job or work process.

[0371] "Progress status" refers to the state of how far a task or work has been completed.

[0372] "Implementer" refers to a person or device that has the specific role of carrying out and executing a task or operation.

[0373] "Past data" refers to information collected or recorded historically in the past.

[0374] A "predictive system" refers to an algorithm or model used to estimate future events or situations based on past data.

[0375] A "warning" refers to a notification or message intended to draw attention to a specific event or situation.

[0376] "Countermeasures" refer to the actions or solutions that should be taken in response to potential problems or delays.

[0377] "Emotional state" refers to the emotional response or condition that an individual experiences mentally at a particular moment.

[0378] "Biometric information" refers to data that indicates an individual's physical condition, including heart rate, blood pressure, and body temperature.

[0379] "Audio data" refers to digital information containing recorded speech, including spoken words and their characteristics.

[0380] The system to realize this application example is based primarily on a cloud infrastructure that includes servers, terminals, and robots to support the work. The server uses a program written in Python to collect real-time progress and worker data from the work site. The server acquires historical data to train a predictive system and runs an algorithm that uses this data to predict the progress of future tasks.

[0381] The prediction system incorporates a machine learning model using TensorFlow to identify potential delays. This allows for early identification of which tasks are likely to experience delays. The server uses the OpenCV library to analyze biometric and voice data acquired by the robot to determine the emotional state of the user. This allows the server to understand whether the user is experiencing stress and, if necessary, to adjust the tone of warning messages according to their emotional state.

[0382] For example, suppose a worker is performing a task on a production line when a malfunction in the equipment causes delays. If a robot detects high stress levels from the worker's biometric data, the server can display a considerate message such as, "Please check the status of this equipment. If necessary, please request support," thereby easing the worker's tension and encouraging efficient response.

[0383] An example of a prompt message utilizing the generative AI model is: "Design a Python script that instantly identifies the cause of production line delays, analyzes worker stress levels, and generates advice that enables implementers to take appropriate action." The goal is for the entire system to work together to improve work efficiency and worker well-being.

[0384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0385] Step 1:

[0386] The server collects real-time data on the progress of work at the site, as well as biometric and voice data from terminals and robots. The input data consists of work progress records and physiological data, which are temporarily stored on the server's storage. After the biometric and voice data are formatted, they are prepared to be sent to the analysis process.

[0387] Step 2:

[0388] The server inputs progress data into a machine learning model and predicts future task progress based on past data. At this point, the input is historical record data, which is processed by a TensorFlow-based model to predict which tasks are likely to be delayed. The output is a delay prediction associated with a specific task ID.

[0389] Step 3:

[0390] The server uses the OpenCV library to analyze biometric and audio data to estimate the user's emotional state. The input consists of the user's biometric signals and audio files. Based on this, a machine learning algorithm analyzes emotions and outputs a stress level assessment. Specifically, it identifies fatigue and high stress levels from heart rate and voice tone.

[0391] Step 4:

[0392] The server integrates predicted delay information with sentiment assessment results to generate appropriate warning messages. The input consists of delay prediction data and sentiment state assessment results. Based on prompts created using a generative AI model, the server outputs messages in an emotionally sensitive tone.

[0393] Step 5:

[0394] The server sends the generated warning message to the user's terminal. The user receives the warning message on their terminal and reviews the displayed suggestions and notifications. The input here is the generated warning message, and the output is the visual feedback on the user's terminal. Based on the notification, the user considers the following work guidelines.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] [Third Embodiment]

[0399] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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".

[0411] This invention is an AI system for supporting project management, aiming to prevent task delays and problems from occurring. The system functions by having a server collect historical information and using machine learning to predict future task progress.

[0412] Specifically, the server periodically retrieves data such as task progress and employee activity history from project management systems and databases. Next, the server preprocesses this data and prepares it for use in the model. This includes imputing missing data and normalization.

[0413] The server trains a predictive model based on pre-processed data. The trained model then takes new project data as input to predict the progress of future tasks. This prediction identifies potential delays and problems in the tasks.

[0414] The server alerts project managers about tasks that are likely to be delayed or problematic. These alerts include suggested solutions, such as resource reallocation or scheduling adjustments. This allows users to take appropriate action in advance.

[0415] For example, if a design team in a particular project has previously been supported by designers who tended to fall behind schedules, the server will store that data and predict the likelihood of a similar situation occurring in a new project. Based on this prediction, the server will issue alerts such as "The design team's schedule may fall behind schedule," helping users take preventative measures.

[0416] In this way, the present invention achieves increased efficiency in project management and improved risk management.

[0417] The following describes the processing flow.

[0418] Step 1:

[0419] The server collects past task progress, assignee information, and inter-project dependency data from project management systems and databases. It periodically retrieves the necessary data using APIs and SQL queries.

[0420] Step 2:

[0421] The server preprocesses the collected data. This includes imputing missing data, removing duplicates, and eliminating outliers. It also standardizes the data to prepare it for efficient training of predictive models.

[0422] Step 3:

[0423] The server splits the preprocessed dataset into training and test data. Using the training data, the server applies machine learning algorithms to build a model for predicting task progress.

[0424] Step 4:

[0425] The server evaluates the accuracy of the predictive model using test data. If necessary, it optimizes the model's accuracy by adjusting hyperparameters and other settings.

[0426] Step 5:

[0427] The server acquires real-time data from newly initiated projects and uses a trained predictive model to forecast the future progress of each task, identifying tasks that are likely to be delayed or are at high risk.

[0428] Step 6:

[0429] The server generates alert messages for tasks that are delayed or at risk. These alerts include suggestions for resolving the problem, such as adding resources or rescheduling the task.

[0430] Step 7:

[0431] The terminal displays alerts and suggestions via the project administrator's interface. The project administrator can receive this information and view the details.

[0432] Step 8:

[0433] Based on the displayed alerts and suggestions, the user consults with team members to determine feasible actions. These actions are then incorporated into the project plan to support the smooth progress of the project.

[0434] (Example 1)

[0435] 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."

[0436] In project management, delays in task progress and unexpected problems can occur, disrupting the overall schedule. Furthermore, planning without considering the activity history of assigned personnel carries risks. Effective measures are needed to prevent these problems.

[0437] 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.

[0438] In this invention, the server includes means for collecting historical information, means for preprocessing the historical information to impart missing data and normalize the data, and means for training a generative AI model using the preprocessed data to predict the progress of future tasks. This makes it possible to detect in advance the possibility of delays or problems occurring in the progress of future tasks and to take appropriate countermeasures.

[0439] "Historical information" refers to a collection of data regarding the progress of past tasks and the actions of the person in charge.

[0440] "Preprocessing" refers to processes such as imputing missing data and normalization that are performed to prepare collected data into a format suitable for analysis and model training.

[0441] A "generative AI model" is a model that uses machine learning algorithms to learn from data and is used for future predictions and classifications.

[0442] "Prediction" is the act of estimating the future progress of a task or the likelihood of problems occurring based on learned data.

[0443] An "alert" is a warning message sent to project managers when there is a high probability of task delays or problems occurring.

[0444] A "solution proposal" refers to a plan for reallocating resources or adjusting schedules that is presented as a countermeasure when delays or problems are anticipated.

[0445] This invention is an AI system that prevents task delays and problems in project management. The server collects historical information from project management systems and databases, and obtains data including task progress and the activity history of assigned personnel.

[0446] The server preprocesses this data by imputing missing data and normalizing it. For example, if data is missing, it fills in the missing portion with the mean, or it performs normalization to unify the data range. This prepares the data for use in generative AI models.

[0447] The server uses the pre-processed data to train a generative AI model. This training utilizes machine learning algorithms such as random forests and neural networks. The trained model helps predict the progress of future tasks using new project data. This allows the server to identify tasks that are likely to experience delays or problems.

[0448] The server generates alerts regarding identified tasks and notifies the user. These alerts include suggestions for solutions such as resource reallocation and scheduling adjustments. Based on this information, the user can take appropriate action in advance.

[0449] For example, in a project involving a designer who has a history of falling behind schedules, the server uses this historical information to predict the risk of delays and generates an alert such as, "The design team's schedule may fall behind schedule." Users who receive this alert can then adjust resources or revise the schedule.

[0450] An example of a prompt to input into the generating AI model is: "Train the model to predict project task delays and generate alerts and suggested solutions for tasks that are likely to cause problems." In this way, users can improve risk management and efficiency across the entire project.

[0451] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0452] Step 1:

[0453] The server collects historical information from the project management system and database. Its input includes data such as task progress and the activity history of assigned personnel. This data collection may be done via APIs or using SQL queries. The output generates a raw dataset for use in the next step.

[0454] Step 2:

[0455] The server preprocesses the collected historical information. In this step, the raw dataset obtained in step 1 is used as input. Specifically, it performs actions such as imputing missing data and identifying and replacing outliers with appropriate values. It also normalizes the data to ensure that each data item has a unified scale. The output is preprocessed data formatted for use with generative AI models.

[0456] Step 3:

[0457] The server trains a generative AI model using preprocessed data. The input is the preprocessed data output in step 2. Specifically, it splits the data into training and test data and builds a model using algorithms such as random forests and neural networks. The output is the trained model used to predict future task progress.

[0458] Step 4:

[0459] The server uses this trained model to predict future task progress, taking new project data as input. The input is the latest task data related to the project. Specifically, the model is fed data and predicts potential task delays and problems. The output is a prediction that includes a ranking of each task's likelihood of delay and the reasons for these delays.

[0460] Step 5:

[0461] The server generates alerts for tasks that may experience delays or problems, based on the prediction results. The input used is the prediction results obtained in step 4. Specifically, it creates alert messages and suggests solutions such as resource reallocation and scheduling adjustments. The output consists of alerts and detailed solutions sent to project managers and stakeholders.

[0462] Step 6:

[0463] The user receives an alert from the server and considers the proposed solution. The input is the alert information sent in step 5. Specific actions include reallocating resources and reviewing the project schedule to implement the countermeasures. The output includes confirming that factors hindering the smooth progress of the project have been resolved and that tasks are proceeding as planned.

[0464] (Application Example 1)

[0465] 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."

[0466] In modern factories and production sites, numerous tasks are running simultaneously, making it difficult to manage the progress of each task. Furthermore, the risk of production delays due to machinery malfunctions is increasing. In this environment, there is a need for an efficient project management system that can prevent delays and problems and maximize productivity.

[0467] 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.

[0468] In this invention, the server includes means for collecting historical information including the progress of tasks and the actions of the person in charge; means for learning a predictive model for predicting the future progress of tasks based on the historical information; and means for monitoring the operating status of machinery and equipment in real time and predicting the progress of a specific job. This makes it possible to grasp the progress of each production task in real time and predict and notify delays and problems.

[0469] "Task progress" refers to information indicating the current progress or completion status of each task or project.

[0470] "Actions of the person in charge" refers to data that shows the specific tasks and decisions made by the person responsible for a particular task.

[0471] "Past information" refers to all information, including the history of tasks and the actions of personnel recorded in the past.

[0472] A "predictive model" is a computational model designed to predict future events or outcomes based on collected data.

[0473] "Operating status of machinery and equipment" refers to information that shows the current operating status and utilization rate of machinery and equipment in production facilities such as factories.

[0474] "Progress of a specific job" is an indicator that shows how far along a particular task or process is currently.

[0475] "Delay" refers to a situation where progress is behind schedule.

[0476] A "malfunction" refers to a state in which a machine or system does not operate as expected, resulting in an abnormality or failure.

[0477] A "warning" is information intended to notify and draw attention to anticipated risks or problems.

[0478] A "proposed solution" refers to specific actions or improvements recommended to avoid potential problems or risks.

[0479] To implement this invention, the server first collects data on the progress of tasks and the actions of personnel in factories and production sites. This utilizes sensor and log data, which is stored in an SQL database. The server uses AI single-board computers such as NVIDIA's Jetson Nano as hardware. The program is written in Python, and TensorFlow is used to train a predictive model.

[0480] The collected data is preprocessed using pandas and numpy. Preprocessing includes imputing missing values ​​and normalization. This data is then analyzed by machine learning models such as LSTM to predict the progress of future tasks. The server monitors the operating status of machinery and equipment in real time and generates alerts if the progress of a particular job is likely to fall behind schedule.

[0481] The user is notified of the prediction results and warnings. In response, the system proposes specific solutions, such as resource reallocation and task scheduling adjustments. These suggestions are then communicated to the user's device, enabling prompt action.

[0482] As a concrete example, if frequent malfunctions of a specific piece of equipment are detected from past data on an automotive parts assembly line, the system can use that data to make predictions and propose an early maintenance plan for that equipment. When using the generative AI model, the following prompt message is used: "Generate suggestions to minimize the risks associated with launching a new product line. Please provide advice based on past successes and failures that should be considered."

[0483] In this way, servers, terminals, and users work together to enable efficient project management and risk prediction.

[0484] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0485] Step 1:

[0486] The server inputs task progress and assigned personnel actions, collected from sensor and log data, into an SQL database. This input includes work time, completion rate, and other data. Using this data, preprocessing such as missing value imputation and data normalization is performed using pandas and numpy, and a prepared dataset is output for the next step.

[0487] Step 2:

[0488] The server uses TensorFlow to train generative AI models, such as LSTM models, based on a preprocessed dataset. It analyzes past patterns based on the input data and trains the model to predict future task progress. The server then outputs this trained model.

[0489] Step 3:

[0490] The server uses a trained model to predict the future operating status of machinery and equipment, taking new real-time data as input. Based on the prediction, it calculates the likelihood of delays for specific jobs or the risk of machine malfunctions, and outputs warnings.

[0491] Step 4:

[0492] The terminal receives warnings from the server and notifies the user. The input includes predicted operational status and warning details. For display to the user, it outputs notification information along with suggested solutions.

[0493] Step 5:

[0494] The user reviews notifications from their device and, if necessary, reallocates resources or adjusts schedules. Based on this, they decide on specific actions and output them as system feedback.

[0495] Through this series of processes, the system enables efficient task management and the prediction of potential problems in the production environment.

[0496] 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.

[0497] This invention provides a system that combines an emotion engine with an AI system to support project management, enabling it to predict task delays and respond in a way that takes user emotions into account. This system allows project managers to proactively prevent task delays and risks while responding flexibly to users' emotional states.

[0498] Specifically, the server collects historical information, recording task progress and the actions of the assigned personnel. In addition, it uses an emotion engine to analyze user emotions and collect emotion data. This data may include user text communications and biometric information. The server uses this data to train machine learning models and predict future task progress.

[0499] The server generates alerts for potential delays or problems related to predicted tasks. The emotion engine adjusts the tone and content of these alerts based on the user's emotional state. For example, if the system detects that the user is stressed, the alert message will be delivered in a more considerate tone.

[0500] As an example, consider a situation where a user is managing multiple projects. The server analyzes project progress data and identifies a task that may be behind schedule. At the same time, if the emotion engine detects stress from the user's recent communications, the server sends a gentle alert message such as, "This task may be behind schedule. Don't worry, work with your team to find a solution."

[0501] Based on the displayed alerts and suggestions, users consider countermeasures and incorporate them into their plans. This process simultaneously improves the efficiency of project management and reduces user stress.

[0502] The following describes the processing flow.

[0503] Step 1:

[0504] The server collects task progress, employee activity history, and user text communication and biometric information from project management systems and databases. This allows it to obtain project history information and user sentiment data.

[0505] Step 2:

[0506] The server preprocesses the collected data. This includes imputing missing values, removing duplicates and noise, and using an emotion engine to analyze the user's emotional state and extract emotional information as numerical data.

[0507] Step 3:

[0508] The server trains a machine learning model based on a pre-processed dataset. Using historical data, it builds a model that can predict the future progress of each task. In this process, sentiment data is also incorporated into the model to consider the impact of emotional states on project progress.

[0509] Step 4:

[0510] The server uses real-time data from newly initiated projects to predict the future progress of each task using a trained predictive model, identifying tasks at risk of delays or problems. Sentimental data is incorporated into this process.

[0511] Step 5:

[0512] The server generates alert messages that take into account the user's emotional state regarding identified high-risk tasks. It adjusts the tone and suggestions of the messages based on feedback from the emotion engine.

[0513] Step 6:

[0514] The terminal notifies the project administrator of alert messages. Users can view the alerts and suggested actions through the project management software on the terminal.

[0515] Step 7:

[0516] Based on the alerts and suggestions received, users consult with the team to determine feasible countermeasures. This is then incorporated into the project plan to help ensure the project progresses smoothly.

[0517] In this way, the present invention enables risk prediction and responses that take into account user emotions in project management.

[0518] (Example 2)

[0519] 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."

[0520] In project management, while early detection of task delays and the presentation of appropriate countermeasures are required, communication that takes into account the emotional state of managers and stakeholders is often neglected. As a result, effective decision-making regarding schedule adjustments and risk mitigation is difficult, which can ultimately reduce the overall efficiency of the project.

[0521] 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.

[0522] In this invention, the server includes means for collecting historical information including the progress of a task and the activities of the person in charge; means for learning a predictive model for predicting the future progress of a task based on the historical information; and means including an emotion engine for analyzing the emotional state of the user. This enables the server to detect the risk of delays and problems in real time and to provide flexible responses and alerts that take the user's emotions into consideration.

[0523] "Task progress" refers to information indicating the stage to which each task within a project has been completed.

[0524] "Activities of the person in charge" refers to a record of the actions and efforts taken by the individual or team assigned to each task.

[0525] "Historical information" refers to a collection of data related to past task progress, the actions of those in charge, and project management.

[0526] A "predictive model" is a computational method used to predict the future state and risks of a task based on collected data.

[0527] An "emotion engine" is a technology that analyzes a user's emotional state from their text, voice, or biometric data.

[0528] An "alert" is a notification designed to draw the attention of users or project managers.

[0529] "Tone" refers to the style or atmosphere of expression in notifications and messages.

[0530] "Emotional state" refers to the emotional state or tendency that a user experiences at a particular time or in a particular situation.

[0531] A "proposed solution" refers to specific action guidelines or plans presented as a response to identified problems or risks.

[0532] This invention provides a system for supporting project management, comprising a server, an emotion engine, and a machine learning model. The server interacts with project management tools to collect historical information, including task progress and the activities of assigned personnel. The server also utilizes an emotion engine for sentiment analysis, analyzing the user's emotional state. This analysis considers text data from the user's emails and messages, as well as data from biometric devices.

[0533] The specific hardware used will be a general-purpose server machine and user terminals such as computers and smartphones. For software, a common management system widely used as a project management tool will be employed. For sentiment analysis, a general sentiment engine software will be used, and for machine learning models, frameworks such as TensorFlow and PyTorch will be employed.

[0534] The server uses this data to predict the future progress of tasks. Based on this prediction, it generates alerts for potential task delays or problems, but customizes the messages to be user-friendly. For example, if a user is under stress, the notification will be delivered in a considerate and gentle tone.

[0535] For example, consider a case where a user is managing multiple projects simultaneously. Based on historical information, the server might suggest that a particular task is likely to fall behind schedule. At the same time, if the server's emotion engine detects high stress levels from the user's recent emails, it might adjust the notification message to something like, "This task is likely to fall behind schedule. Don't worry, let's work with your team to find a solution."

[0536] Furthermore, an example of a prompt message in the AI ​​model generated by this system is, "If the user is feeling stressed, please express the delay notification message gently." This allows the user to receive appropriate information, reduce stress, and ensure the smooth progress of the project.

[0537] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0538] Step 1:

[0539] The server collects task progress and assignee activity history from the project management tool. It uses data provided by the project management tool API as input. The server stores this data in a database, accumulating it as task history information. The output is the stored history information data.

[0540] Step 2:

[0541] The server trains a machine learning model based on collected historical information. The input consists of task progress and historical data. The server uses this data to train a predictive model for future task progress. TensorFlow and PyTorch are used to build the model and improve prediction accuracy. The output is the trained predictive model.

[0542] Step 3:

[0543] The server uses an emotion engine to analyze the user's emotional state. It takes user text data and biometric information as input. The emotion engine analyzes this data and evaluates the user's emotional state. The output generated as a result of the analysis is data indicating the user's current emotional state.

[0544] Step 4:

[0545] The server identifies tasks at risk of delays or problems based on a predictive model and sentiment data. The input consists of a trained predictive model and analyzed sentiment data. The server processes this information to identify tasks where problems are predicted. The output is a list of identified problematic tasks.

[0546] Step 5:

[0547] The server generates alerts and adjusts their content based on the user's emotional state. The inputs are an identified task list and the user's emotional state. The server creates an alert message from this data, adjusting the tone and wording according to the user's state. The output is the optimized alert message.

[0548] Step 6:

[0549] The server notifies the user's device of the generated alert message. The input is the optimized alert message. The server sends this message to the user's PC or smartphone. The output is the alert message displayed on the user's device.

[0550] Step 7:

[0551] The user checks the alert message displayed on the device and takes appropriate action. The input is the user receiving the alert display on the device. Based on this, the user adjusts the project progress and communicates as needed. The output is the adjusted project plan and the actions taken.

[0552] (Application Example 2)

[0553] 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."

[0554] There is a need to simultaneously improve work efficiency on the factory floor and manage the emotional well-being of workers. Conventional systems have limitations in detecting task delays and problems early, and struggle to respond flexibly while considering the emotional state of workers. As a result, there are limitations to achieving both production process optimization and worker stress reduction.

[0555] 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.

[0556] In this invention, the server includes means for collecting historical data including the progress of a task and the actions of the person performing the task; means for learning a prediction system for predicting the future progress of a task based on the historical data; and means for identifying tasks that are likely to be delayed or have problems using the prediction system. This makes it possible to analyze the biometric information and voice data of workers and provide flexible warning messages that are tailored to their emotional state.

[0557] A "task" refers to an individual activity or task that must be performed in a specific job or work process.

[0558] "Progress status" refers to the state of how far a task or work has been completed.

[0559] "Implementer" refers to a person or device that has the specific role of carrying out and executing a task or operation.

[0560] "Past data" refers to information collected or recorded historically in the past.

[0561] A "predictive system" refers to an algorithm or model used to estimate future events or situations based on past data.

[0562] A "warning" refers to a notification or message intended to draw attention to a specific event or situation.

[0563] "Countermeasures" refer to the actions or solutions that should be taken in response to potential problems or delays.

[0564] "Emotional state" refers to the emotional response or condition that an individual experiences mentally at a particular moment.

[0565] "Biometric information" refers to data that indicates an individual's physical condition, including heart rate, blood pressure, and body temperature.

[0566] "Audio data" refers to digital information containing recorded speech, including spoken words and their characteristics.

[0567] The system to realize this application example is based primarily on a cloud infrastructure that includes servers, terminals, and robots to support the work. The server uses a program written in Python to collect real-time progress and worker data from the work site. The server acquires historical data to train a predictive system and runs an algorithm that uses this data to predict the progress of future tasks.

[0568] The prediction system incorporates a machine learning model using TensorFlow to identify potential delays. This allows for early identification of which tasks are likely to experience delays. The server uses the OpenCV library to analyze biometric and voice data acquired by the robot to determine the emotional state of the user. This allows the server to understand whether the user is experiencing stress and, if necessary, to adjust the tone of warning messages according to their emotional state.

[0569] For example, suppose a worker is performing a task on a production line when a malfunction in the equipment causes delays. If a robot detects high stress levels from the worker's biometric data, the server can display a considerate message such as, "Please check the status of this equipment. If necessary, please request support," thereby easing the worker's tension and encouraging efficient response.

[0570] An example of a prompt message utilizing the generative AI model is: "Design a Python script that instantly identifies the cause of production line delays, analyzes worker stress levels, and generates advice that enables implementers to take appropriate action." The goal is for the entire system to work together to improve work efficiency and worker well-being.

[0571] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0572] Step 1:

[0573] The server collects real-time data on the progress of work at the site, as well as biometric and voice data from terminals and robots. The input data consists of work progress records and physiological data, which are temporarily stored on the server's storage. After the biometric and voice data are formatted, they are prepared to be sent to the analysis process.

[0574] Step 2:

[0575] The server inputs progress data into a machine learning model and predicts future task progress based on past data. At this point, the input is historical record data, which is processed by a TensorFlow-based model to predict which tasks are likely to be delayed. The output is a delay prediction associated with a specific task ID.

[0576] Step 3:

[0577] The server uses the OpenCV library to analyze biometric and audio data to estimate the user's emotional state. The input consists of the user's biometric signals and audio files. Based on this, a machine learning algorithm analyzes emotions and outputs a stress level assessment. Specifically, it identifies fatigue and high stress levels from heart rate and voice tone.

[0578] Step 4:

[0579] The server integrates predicted delay information with sentiment assessment results to generate appropriate warning messages. The input consists of delay prediction data and sentiment state assessment results. Based on prompts created using a generative AI model, the server outputs messages in an emotionally sensitive tone.

[0580] Step 5:

[0581] The server sends the generated warning message to the user's terminal. The user receives the warning message on their terminal and reviews the displayed suggestions and notifications. The input here is the generated warning message, and the output is the visual feedback on the user's terminal. Based on the notification, the user considers the following work guidelines.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] [Fourth Embodiment]

[0586] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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".

[0599] This invention is an AI system for supporting project management, aiming to prevent task delays and problems from occurring. The system functions by having a server collect historical information and using machine learning to predict future task progress.

[0600] Specifically, the server periodically retrieves data such as task progress and employee activity history from project management systems and databases. Next, the server preprocesses this data and prepares it for use in the model. This includes imputing missing data and normalization.

[0601] The server trains a predictive model based on pre-processed data. The trained model then takes new project data as input to predict the progress of future tasks. This prediction identifies potential delays and problems in the tasks.

[0602] The server alerts project managers about tasks that are likely to be delayed or problematic. These alerts include suggested solutions, such as resource reallocation or scheduling adjustments. This allows users to take appropriate action in advance.

[0603] For example, if a design team in a particular project has previously been supported by designers who tended to fall behind schedules, the server will store that data and predict the likelihood of a similar situation occurring in a new project. Based on this prediction, the server will issue alerts such as "The design team's schedule may fall behind schedule," helping users take preventative measures.

[0604] In this way, the present invention achieves increased efficiency in project management and improved risk management.

[0605] The following describes the processing flow.

[0606] Step 1:

[0607] The server collects past task progress, assignee information, and inter-project dependency data from project management systems and databases. It periodically retrieves the necessary data using APIs and SQL queries.

[0608] Step 2:

[0609] The server preprocesses the collected data. This includes imputing missing data, removing duplicates, and eliminating outliers. It also standardizes the data to prepare it for efficient training of predictive models.

[0610] Step 3:

[0611] The server splits the preprocessed dataset into training and test data. Using the training data, the server applies machine learning algorithms to build a model for predicting task progress.

[0612] Step 4:

[0613] The server evaluates the accuracy of the predictive model using test data. If necessary, it optimizes the model's accuracy by adjusting hyperparameters and other settings.

[0614] Step 5:

[0615] The server acquires real-time data from newly initiated projects and uses a trained predictive model to forecast the future progress of each task, identifying tasks that are likely to be delayed or are at high risk.

[0616] Step 6:

[0617] The server generates alert messages for tasks that are delayed or at risk. These alerts include suggestions for resolving the problem, such as adding resources or rescheduling the task.

[0618] Step 7:

[0619] The terminal displays alerts and suggestions via the project administrator's interface. The project administrator can receive this information and view the details.

[0620] Step 8:

[0621] Based on the displayed alerts and suggestions, the user consults with team members to determine feasible actions. These actions are then incorporated into the project plan to support the smooth progress of the project.

[0622] (Example 1)

[0623] 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".

[0624] In project management, delays in task progress and unexpected problems can occur, disrupting the overall schedule. Furthermore, planning without considering the activity history of assigned personnel carries risks. Effective measures are needed to prevent these problems.

[0625] 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.

[0626] In this invention, the server includes means for collecting historical information, means for preprocessing the historical information to impart missing data and normalize the data, and means for training a generative AI model using the preprocessed data to predict the progress of future tasks. This makes it possible to detect in advance the possibility of delays or problems occurring in the progress of future tasks and to take appropriate countermeasures.

[0627] "Historical information" refers to a collection of data regarding the progress of past tasks and the actions of the person in charge.

[0628] "Preprocessing" refers to processes such as imputing missing data and normalization that are performed to prepare collected data into a format suitable for analysis and model training.

[0629] A "generative AI model" is a model that uses machine learning algorithms to learn from data and is used for future predictions and classifications.

[0630] "Prediction" is the act of estimating the future progress of a task or the likelihood of problems occurring based on learned data.

[0631] An "alert" is a warning message sent to project managers when there is a high probability of task delays or problems occurring.

[0632] A "solution proposal" refers to a plan for reallocating resources or adjusting schedules that is presented as a countermeasure when delays or problems are anticipated.

[0633] This invention is an AI system that prevents task delays and problems in project management. The server collects historical information from project management systems and databases, and obtains data including task progress and the activity history of assigned personnel.

[0634] The server preprocesses this data by imputing missing data and normalizing it. For example, if data is missing, it fills in the missing portion with the mean, or it performs normalization to unify the data range. This prepares the data for use in generative AI models.

[0635] The server uses the pre-processed data to train a generative AI model. This training utilizes machine learning algorithms such as random forests and neural networks. The trained model helps predict the progress of future tasks using new project data. This allows the server to identify tasks that are likely to experience delays or problems.

[0636] The server generates alerts regarding identified tasks and notifies the user. These alerts include suggestions for solutions such as resource reallocation and scheduling adjustments. Based on this information, the user can take appropriate action in advance.

[0637] For example, in a project involving a designer who has a history of falling behind schedules, the server uses this historical information to predict the risk of delays and generates an alert such as, "The design team's schedule may fall behind schedule." Users who receive this alert can then adjust resources or revise the schedule.

[0638] An example of a prompt to input into the generating AI model is: "Train the model to predict project task delays and generate alerts and suggested solutions for tasks that are likely to cause problems." In this way, users can improve risk management and efficiency across the entire project.

[0639] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0640] Step 1:

[0641] The server collects historical information from the project management system and database. Its input includes data such as task progress and the activity history of assigned personnel. This data collection may be done via APIs or using SQL queries. The output generates a raw dataset for use in the next step.

[0642] Step 2:

[0643] The server preprocesses the collected historical information. In this step, the raw dataset obtained in step 1 is used as input. Specifically, it performs actions such as imputing missing data and identifying and replacing outliers with appropriate values. It also normalizes the data to ensure that each data item has a unified scale. The output is preprocessed data formatted for use with generative AI models.

[0644] Step 3:

[0645] The server trains a generative AI model using preprocessed data. The input is the preprocessed data output in step 2. Specifically, it splits the data into training and test data and builds a model using algorithms such as random forests and neural networks. The output is the trained model used to predict future task progress.

[0646] Step 4:

[0647] The server uses this trained model to predict future task progress, taking new project data as input. The input is the latest task data related to the project. Specifically, the model is fed data and predicts potential task delays and problems. The output is a prediction that includes a ranking of each task's likelihood of delay and the reasons for these delays.

[0648] Step 5:

[0649] The server generates alerts for tasks that may experience delays or problems, based on the prediction results. The input used is the prediction results obtained in step 4. Specifically, it creates alert messages and suggests solutions such as resource reallocation and scheduling adjustments. The output consists of alerts and detailed solutions sent to project managers and stakeholders.

[0650] Step 6:

[0651] The user receives an alert from the server and considers the proposed solution. The input is the alert information sent in step 5. Specific actions include reallocating resources and reviewing the project schedule to implement the countermeasures. The output includes confirming that factors hindering the smooth progress of the project have been resolved and that tasks are proceeding as planned.

[0652] (Application Example 1)

[0653] 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".

[0654] In modern factories and production sites, numerous tasks are running simultaneously, making it difficult to manage the progress of each task. Furthermore, the risk of production delays due to machinery malfunctions is increasing. In this environment, there is a need for an efficient project management system that can prevent delays and problems and maximize productivity.

[0655] 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.

[0656] In this invention, the server includes means for collecting historical information including the progress of tasks and the actions of the person in charge; means for learning a predictive model for predicting the future progress of tasks based on the historical information; and means for monitoring the operating status of machinery and equipment in real time and predicting the progress of a specific job. This makes it possible to grasp the progress of each production task in real time and predict and notify delays and problems.

[0657] "Task progress" refers to information indicating the current progress or completion status of each task or project.

[0658] "Actions of the person in charge" refers to data that shows the specific tasks and decisions made by the person responsible for a particular task.

[0659] "Past information" refers to all information, including the history of tasks and the actions of personnel recorded in the past.

[0660] A "predictive model" is a computational model designed to predict future events or outcomes based on collected data.

[0661] "Operating status of machinery and equipment" refers to information that shows the current operating status and utilization rate of machinery and equipment in production facilities such as factories.

[0662] "Progress of a specific job" is an indicator that shows how far along a particular task or process is currently.

[0663] "Delay" refers to a situation where progress is behind schedule.

[0664] A "malfunction" refers to a state in which a machine or system does not operate as expected, resulting in an abnormality or failure.

[0665] A "warning" is information intended to notify and draw attention to anticipated risks or problems.

[0666] A "proposed solution" refers to specific actions or improvements recommended to avoid potential problems or risks.

[0667] To implement this invention, the server first collects data on the progress of tasks and the actions of personnel in factories and production sites. This utilizes sensor and log data, which is stored in an SQL database. The server uses AI single-board computers such as NVIDIA's Jetson Nano as hardware. The program is written in Python, and TensorFlow is used to train a predictive model.

[0668] The collected data is preprocessed using pandas and numpy. Preprocessing includes imputing missing values ​​and normalization. This data is then analyzed by machine learning models such as LSTM to predict the progress of future tasks. The server monitors the operating status of machinery and equipment in real time and generates alerts if the progress of a particular job is likely to fall behind schedule.

[0669] The user is notified of the prediction results and warnings. In response, the system proposes specific solutions, such as resource reallocation and task scheduling adjustments. These suggestions are then communicated to the user's device, enabling prompt action.

[0670] As a concrete example, if frequent malfunctions of a specific piece of equipment are detected from past data on an automotive parts assembly line, the system can use that data to make predictions and propose an early maintenance plan for that equipment. When using the generative AI model, the following prompt message is used: "Generate suggestions to minimize the risks associated with launching a new product line. Please provide advice based on past successes and failures that should be considered."

[0671] In this way, servers, terminals, and users work together to enable efficient project management and risk prediction.

[0672] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0673] Step 1:

[0674] The server inputs task progress and assigned personnel actions, collected from sensor and log data, into an SQL database. This input includes work time, completion rate, and other data. Using this data, preprocessing such as missing value imputation and data normalization is performed using pandas and numpy, and a prepared dataset is output for the next step.

[0675] Step 2:

[0676] The server uses TensorFlow to train generative AI models, such as LSTM models, based on a preprocessed dataset. It analyzes past patterns based on the input data and trains the model to predict future task progress. The server then outputs this trained model.

[0677] Step 3:

[0678] The server uses a trained model to predict the future operating status of machinery and equipment, taking new real-time data as input. Based on the prediction, it calculates the likelihood of delays for specific jobs or the risk of machine malfunctions, and outputs warnings.

[0679] Step 4:

[0680] The terminal receives warnings from the server and notifies the user. The input includes predicted operational status and warning details. For display to the user, it outputs notification information along with suggested solutions.

[0681] Step 5:

[0682] The user reviews notifications from their device and, if necessary, reallocates resources or adjusts schedules. Based on this, they decide on specific actions and output them as system feedback.

[0683] Through this series of processes, the system enables efficient task management and the prediction of potential problems in the production environment.

[0684] 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.

[0685] This invention provides a system that combines an emotion engine with an AI system to support project management, enabling it to predict task delays and respond in a way that takes user emotions into account. This system allows project managers to proactively prevent task delays and risks while responding flexibly to users' emotional states.

[0686] Specifically, the server collects historical information, recording task progress and the actions of the assigned personnel. In addition, it uses an emotion engine to analyze user emotions and collect emotion data. This data may include user text communications and biometric information. The server uses this data to train machine learning models and predict future task progress.

[0687] The server generates alerts for potential delays or problems related to predicted tasks. The emotion engine adjusts the tone and content of these alerts based on the user's emotional state. For example, if the system detects that the user is stressed, the alert message will be delivered in a more considerate tone.

[0688] As an example, consider a situation where a user is managing multiple projects. The server analyzes project progress data and identifies a task that may be behind schedule. At the same time, if the emotion engine detects stress from the user's recent communications, the server sends a gentle alert message such as, "This task may be behind schedule. Don't worry, work with your team to find a solution."

[0689] Based on the displayed alerts and suggestions, users consider countermeasures and incorporate them into their plans. This process simultaneously improves the efficiency of project management and reduces user stress.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The server collects task progress, employee activity history, and user text communication and biometric information from project management systems and databases. This allows it to obtain project history information and user sentiment data.

[0693] Step 2:

[0694] The server preprocesses the collected data. This includes imputing missing values, removing duplicates and noise, and using an emotion engine to analyze the user's emotional state and extract emotional information as numerical data.

[0695] Step 3:

[0696] The server trains a machine learning model based on a pre-processed dataset. Using historical data, it builds a model that can predict the future progress of each task. At this time, sentiment data is also incorporated into the model to consider the impact of emotional states on project progress.

[0697] Step 4:

[0698] The server uses real-time data from newly initiated projects to predict the future progress of each task using a trained predictive model, identifying tasks at risk of delays or problems. Sentimental data is incorporated into this process.

[0699] Step 5:

[0700] The server generates alert messages that take into account the user's emotional state regarding identified high-risk tasks. It adjusts the tone and suggestions of the messages based on feedback from the emotion engine.

[0701] Step 6:

[0702] The terminal notifies the project administrator of alert messages. Users can view the alerts and suggested actions through the project management software on the terminal.

[0703] Step 7:

[0704] Based on the alerts and suggestions received, users consult with the team to determine feasible countermeasures. This is then incorporated into the project plan to help ensure the project progresses smoothly.

[0705] In this way, the present invention enables risk prediction and responses that take into account user emotions in project management.

[0706] (Example 2)

[0707] 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".

[0708] In project management, while early detection of task delays and the presentation of appropriate countermeasures are required, communication that takes into account the emotional state of managers and stakeholders is often neglected. As a result, effective decision-making regarding schedule adjustments and risk mitigation is difficult, which can ultimately reduce the overall efficiency of the project.

[0709] 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.

[0710] In this invention, the server includes means for collecting historical information including the progress of a task and the activities of the person in charge; means for learning a predictive model for predicting the future progress of a task based on the historical information; and means including an emotion engine for analyzing the emotional state of the user. This enables the server to detect the risk of delays and problems in real time and to provide flexible responses and alerts that take the user's emotions into consideration.

[0711] "Task progress" refers to information indicating the stage to which each task within a project has been completed.

[0712] "Activities of the person in charge" refers to a record of the actions and efforts taken by the individual or team assigned to each task.

[0713] "Historical information" refers to a collection of data related to past task progress, the actions of those in charge, and project management.

[0714] A "predictive model" is a computational method used to predict the future state and risks of a task based on collected data.

[0715] An "emotion engine" is a technology that analyzes a user's emotional state from their text, voice, or biometric data.

[0716] An "alert" is a notification designed to draw the attention of users or project managers.

[0717] "Tone" refers to the style or atmosphere of expression in notifications and messages.

[0718] "Emotional state" refers to the emotional state or tendency that a user experiences at a particular time or in a particular situation.

[0719] A "proposed solution" refers to specific action guidelines or plans presented as a response to identified problems or risks.

[0720] This invention provides a system for supporting project management, comprising a server, an emotion engine, and a machine learning model. The server interacts with project management tools to collect historical information, including task progress and the activities of assigned personnel. The server also utilizes an emotion engine for sentiment analysis, analyzing the user's emotional state. This analysis considers text data from the user's emails and messages, as well as data from biometric devices.

[0721] The specific hardware used will be a general-purpose server machine and user terminals such as computers and smartphones. For software, a common management system widely used as a project management tool will be employed. For sentiment analysis, a general sentiment engine software will be used, and for machine learning models, frameworks such as TensorFlow and PyTorch will be employed.

[0722] The server uses this data to predict the future progress of tasks. Based on this prediction, it generates alerts for potential task delays or problems, but customizes the messages to be user-friendly. For example, if a user is under stress, the notification will be delivered in a considerate and gentle tone.

[0723] For example, consider a case where a user is managing multiple projects simultaneously. Based on historical information, the server might suggest that a particular task is likely to fall behind schedule. At the same time, if the server's emotion engine detects high stress levels from the user's recent emails, it might adjust the notification message to something like, "This task is likely to fall behind schedule. Don't worry, let's work with your team to find a solution."

[0724] Furthermore, an example of a prompt message in the AI ​​model generated by this system is, "If the user is feeling stressed, please express the delay notification message gently." This allows the user to receive appropriate information, reduce stress, and ensure the smooth progress of the project.

[0725] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0726] Step 1:

[0727] The server collects task progress and assignee activity history from the project management tool. It uses data provided by the project management tool API as input. The server stores this data in a database, accumulating it as task history information. The output is the stored history information data.

[0728] Step 2:

[0729] The server trains a machine learning model based on collected historical information. The input consists of task progress and historical data. The server uses this data to train a predictive model for future task progress. TensorFlow and PyTorch are used to build the model and improve prediction accuracy. The output is the trained predictive model.

[0730] Step 3:

[0731] The server uses an emotion engine to analyze the user's emotional state. It takes user text data and biometric information as input. The emotion engine analyzes this data and evaluates the user's emotional state. The output generated as a result of the analysis is data indicating the user's current emotional state.

[0732] Step 4:

[0733] The server identifies tasks at risk of delays or problems based on a predictive model and sentiment data. The input consists of a trained predictive model and analyzed sentiment data. The server processes this information to identify tasks where problems are predicted. The output is a list of identified problematic tasks.

[0734] Step 5:

[0735] The server generates alerts and adjusts their content based on the user's emotional state. The inputs are an identified task list and the user's emotional state. The server creates an alert message from this data, adjusting the tone and wording according to the user's state. The output is the optimized alert message.

[0736] Step 6:

[0737] The server notifies the user's device of the generated alert message. The input is the optimized alert message. The server sends this message to the user's PC or smartphone. The output is the alert message displayed on the user's device.

[0738] Step 7:

[0739] The user checks the alert message displayed on the device and takes appropriate action. The input is the user receiving the alert display on the device. Based on this, the user adjusts the project progress and communicates as needed. The output is the adjusted project plan and the actions taken.

[0740] (Application Example 2)

[0741] 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".

[0742] There is a need to simultaneously improve work efficiency on the factory floor and manage the emotional well-being of workers. Conventional systems have limitations in detecting task delays and problems early, and struggle to respond flexibly while considering the emotional state of workers. As a result, there are limitations to achieving both production process optimization and worker stress reduction.

[0743] 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.

[0744] In this invention, the server includes means for collecting historical data including the progress of a task and the actions of the person performing it; means for learning a prediction system for predicting the future progress of a task based on the historical data; and means for identifying tasks that are likely to be delayed or have problems using the prediction system. This makes it possible to analyze the biometric information and voice data of workers and provide flexible warning messages that are tailored to their emotional state.

[0745] A "task" refers to an individual activity or task that must be performed in a specific job or work process.

[0746] "Progress status" refers to the state of how far a task or work has been completed.

[0747] "Implementer" refers to a person or device that has the specific role of carrying out and executing a task or operation.

[0748] "Past data" refers to information collected or recorded historically in the past.

[0749] A "predictive system" refers to an algorithm or model used to estimate future events or situations based on past data.

[0750] A "warning" refers to a notification or message intended to draw attention to a specific event or situation.

[0751] "Countermeasures" refer to the actions or solutions that should be taken in response to potential problems or delays.

[0752] "Emotional state" refers to the emotional response or condition that an individual experiences mentally at a particular moment.

[0753] "Biometric information" refers to data that indicates an individual's physical condition, including heart rate, blood pressure, and body temperature.

[0754] "Audio data" refers to digital information containing recorded speech, including spoken words and their characteristics.

[0755] The system to realize this application example is based primarily on a cloud infrastructure that includes servers, terminals, and robots to support the work. The server uses a program written in Python to collect real-time progress and worker data from the work site. The server acquires historical data to train a predictive system and runs an algorithm that uses this data to predict the progress of future tasks.

[0756] The prediction system incorporates a machine learning model using TensorFlow to identify potential delays. This allows for early identification of which tasks are likely to experience delays. The server uses the OpenCV library to analyze biometric and voice data acquired by the robot to determine the emotional state of the user. This allows the server to understand whether the user is experiencing stress and, if necessary, to adjust the tone of warning messages according to their emotional state.

[0757] For example, suppose a worker is performing a task on a production line when a malfunction in the equipment causes delays. If a robot detects high stress levels from the worker's biometric data, the server can display a considerate message such as, "Please check the status of this equipment. If necessary, please request support," thereby easing the worker's tension and encouraging efficient response.

[0758] An example of a prompt message utilizing the generative AI model is: "Design a Python script that instantly identifies the cause of production line delays, analyzes worker stress levels, and generates advice that enables implementers to take appropriate action." The goal is for the entire system to work together to improve work efficiency and worker well-being.

[0759] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0760] Step 1:

[0761] The server collects real-time data on the progress of work at the site, as well as biometric and voice data from terminals and robots. The input data consists of work progress records and physiological data, which are temporarily stored on the server's storage. After the biometric and voice data are formatted, they are prepared to be sent to the analysis process.

[0762] Step 2:

[0763] The server inputs progress data into a machine learning model and predicts future task progress based on past data. At this point, the input is historical record data, which is processed by a TensorFlow-based model to predict which tasks are likely to be delayed. The output is a delay prediction associated with a specific task ID.

[0764] Step 3:

[0765] The server uses the OpenCV library to analyze biometric and audio data to estimate the user's emotional state. The input consists of the user's biometric signals and audio files. Based on this, a machine learning algorithm analyzes emotions and outputs a stress level assessment. Specifically, it identifies fatigue and high stress levels from heart rate and voice tone.

[0766] Step 4:

[0767] The server integrates predicted delay information with sentiment assessment results to generate appropriate warning messages. The input consists of delay prediction data and sentiment state assessment results. Based on prompts created using a generative AI model, the server outputs messages in an emotionally sensitive tone.

[0768] Step 5:

[0769] The server sends the generated warning message to the user's terminal. The user receives the warning message on their terminal and reviews the displayed suggestions and notifications. The input here is the generated warning message, and the output is the visual feedback on the user's terminal. Based on the notification, the user considers the following work guidelines.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] The following is further disclosed regarding the embodiments described above.

[0792] (Claim 1)

[0793] A means for collecting historical information including the progress of a task and the actions of the person in charge,

[0794] A means for learning a predictive model to predict the future progress of a task based on the aforementioned historical information,

[0795] A means for identifying tasks that are likely to be delayed or have problems using the aforementioned predictive model,

[0796] Means for generating alerts and suggested solutions regarding identified tasks,

[0797] A means of notifying the project manager of the aforementioned alerts and suggestions,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, which identifies and removes duplicate or incomplete data from historical information.

[0801] (Claim 3)

[0802] The system according to claim 1, wherein the proposed solution includes resource redistribution or task scheduling.

[0803] "Example 1"

[0804] (Claim 1)

[0805] Means for collecting historical information,

[0806] The means for preprocessing the aforementioned historical information, imputing missing data, and normalizing the data,

[0807] A method for training a generative AI model using preprocessed data and predicting the progress of future tasks,

[0808] A means for identifying tasks that are likely to experience delays or problems using the aforementioned generation AI model,

[0809] A means for generating alerts and suggested solutions regarding identified tasks, and for suggesting resource redistribution and scheduling adjustments,

[0810] Means for notifying the user of the aforementioned alerts and suggestions,

[0811] A system that includes this.

[0812] (Claim 2)

[0813] The system according to claim 1, which identifies and removes duplicate or incomplete data from historical information.

[0814] (Claim 3)

[0815] The system according to claim 1, wherein the proposed solution includes resource redistribution or task scheduling.

[0816] "Application Example 1"

[0817] (Claim 1)

[0818] A means of collecting historical information, including the progress of the task and the actions of the person in charge,

[0819] A means for learning a predictive model to predict the future progress of a task based on the aforementioned past information,

[0820] A means for identifying tasks that are likely to be delayed or have problems using the aforementioned predictive model,

[0821] Means for generating warnings and suggested solutions regarding identified tasks,

[0822] Means for notifying the work manager of the aforementioned warnings and suggestions,

[0823] A means of monitoring the operating status of machinery and equipment in real time and predicting the progress of a specific job,

[0824] A method for predicting malfunctions in specific equipment based on past data and notifying administrators,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1 for identifying and removing duplicate or incomplete data from past information.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the proposed solution includes the redistribution of resources or the scheduling of work.

[0830] "Example 2 of combining an emotion engine"

[0831] (Claim 1)

[0832] A means for collecting historical information including the progress of a task and the activities of the person in charge,

[0833] A means for learning a predictive model to predict the future progress of a task based on the aforementioned historical information,

[0834] A means including an emotion engine for analyzing the user's emotional state,

[0835] A means for identifying tasks that are likely to be delayed or experience problems based on the aforementioned predictive model and emotional state, and for generating alerts,

[0836] A means for adjusting the tone and content of the aforementioned alert according to the user's emotional state,

[0837] A means of notifying the project manager of the aforementioned alerts and proposed countermeasures,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1 for identifying and removing duplicate or incomplete data from historical information and sentiment data.

[0841] (Claim 3)

[0842] The system according to claim 1, wherein the proposed solution includes resource redistribution or adjustment of task time planning.

[0843] "Application example 2 when combining with an emotional engine"

[0844] (Claim 1)

[0845] A means of collecting historical data including the progress of the task and the actions of the person performing it,

[0846] A means for learning a prediction system for predicting the future progress of a task based on the aforementioned past data,

[0847] Means for identifying tasks that are likely to be delayed or have problems using the aforementioned prediction system,

[0848] Means for generating warnings and suggested countermeasures regarding identified tasks,

[0849] Means for notifying the work manager of the aforementioned warnings and suggestions,

[0850] A method for a robot to analyze biometric information and voice data to determine the emotions of a worker,

[0851] A means of adjusting the tone of warning messages based on the emotional state of the worker,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1 for identifying and removing duplicate or incomplete data from historical data.

[0855] (Claim 3)

[0856] The system according to claim 1, wherein the proposed countermeasures include resource redistribution or task time management. [Explanation of Symbols]

[0857] 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 for collecting historical information including the progress of a task and the actions of the person in charge, A means for learning a predictive model to predict the future progress of a task based on the aforementioned historical information, A means for identifying tasks that are likely to be delayed or have problems using the aforementioned predictive model, Means for generating alerts and suggested solutions regarding identified tasks, A means of notifying the project manager of the aforementioned alerts and suggestions, A system that includes this.

2. The system according to claim 1, which identifies and removes duplicate or incomplete data from historical information.

3. The system according to claim 1, wherein the proposed solution includes resource redistribution or task scheduling.

Images