system

Abstract

We provide the system. [Solution] A device for automatically collecting and integrating data, A device that uses a trained model to assess risk, A device that notifies and provides countermeasures when a risk is recognized, A device that visually displays information and prompts relevant parties to take action, A system that includes this.

Description

Technical Field

[0005] , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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] In project management in modern enterprises, it is a problem that project delays and budget overruns frequently occur. This results in wasteful consumption of resources and additional costs, threatening the competitiveness of the enterprise. To continuously solve this problem, a mechanism is required to monitor the progress of the project in real time, predict delay risks in advance, and respond quickly.

Means for Solving the Problems

[0005] This invention solves the above problems by providing a system that automatically collects and integrates information. Specifically, it has means to detect risks using a generated model, and based on this, notify projects with a high risk of delay and propose specific countermeasures. Furthermore, the generated model utilizes a language model trained to analyze data from multiple modals, achieving more accurate risk analysis. In addition, this system visualizes risk information and encourages prompt decision-making and action through proposals to stakeholders. This improves the success rate of projects and contributes to improving the operational efficiency and reducing costs of companies.

[0006] "Means for automatically collecting and integrating information" refers to a function that automatically acquires project-related information from various data sources, converts it into a centrally manageable format, and aggregates it.

[0007] "Means for detecting risks using generated models" refers to a function that uses a trained artificial intelligence model to analyze and identify project risks such as delays from integrated data.

[0008] "A means of notifying and proposing countermeasures" refers to a function that issues real-time warnings to relevant parties in response to detected risks and presents improvement measures and specific countermeasures.

[0009] A "language model trained to analyze data from multiple modals" is a model trained using machine learning techniques for a specific purpose, enabling it to simultaneously analyze different data formats such as text, images, and numerical data.

[0010] "A means of visualizing risk information and prompting action from stakeholders through proposals" refers to a function that displays analyzed risk information in an easy-to-understand visual format, enabling stakeholders to quickly recognize it and providing specific instructions or proposals for necessary actions. [Brief explanation of the drawing]

[0011] [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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a 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.

[0015] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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.

[0017] 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).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] As an embodiment of the present invention, we describe an information system that monitors the progress of a project in real time and predicts delay risks. This system consists of a server, terminals, and users.

[0033] First, the server automatically collects data from multiple sources, such as project management tools, email servers, and IoT sensor systems. This functionality is achieved using APIs and IMAP protocols, allowing necessary data to be accumulated without interrupting the daily flow of information. For example, it periodically retrieves the progress of tasks in ongoing projects and the content of email communications.

[0034] Next, the collected data is integrated on the server. The ETL (Extract, Transform, Load) process is used to convert data acquired in different formats into a unified analysis format. During this process, missing data values ​​are imputed and outliers are detected, resulting in a highly accurate dataset.

[0035] Subsequently, the server uses this dataset to perform risk analysis using a trained multimodal AI model. The model simultaneously analyzes different data formats (such as text and numerical data) to detect and evaluate delay risks and budget anomalies in real time. For example, it can process all data to detect delay risks due to excessive resource consumption in a specific project.

[0036] If a risk is detected, an AI chatbot on the server immediately notifies relevant parties. This includes sending messages via email or chat tools to prompt users to take necessary actions. The AI ​​also supports rapid decision-making by including optimal countermeasures as suggestions. In specific cases, concrete suggestions may be provided, such as "reconsider resource allocation and adjust the priority of related tasks."

[0037] Ultimately, the device visualizes risk information for the user through a dashboard. Here, the user can review the overall project picture and decide on specific actions based on the suggested countermeasures. This system is expected to increase the project's success rate and reduce unnecessary costs.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server automatically collects data from project management tools, email systems, and IoT sensors. It uses APIs and IMAP protocols to retrieve task progress information, communication history, and environmental data.

[0041] Step 2:

[0042] The server integrates the collected data for centralized management. To handle different data formats (e.g., JSON, CSV, stream data), it performs necessary data transformations through an ETL process and stores the data in a database.

[0043] Step 3:

[0044] The server preprocesses the integrated data. It improves the reliability of the analysis by imputing missing values ​​and identifying and appropriately handling outliers.

[0045] Step 4:

[0046] The server inputs the prepared data into the AI ​​model and performs a risk analysis. The model specializes in analyzing multimodal data and generates a score that assesses the risk of project delays and budget overruns.

[0047] Step 5:

[0048] The server determines the project's risk level based on the analysis results and updates the information on the dashboard.

[0049] Step 6:

[0050] The AI ​​chatbot (on the server) notifies relevant parties of detected risks. For example, it provides information via email or chat tools so that users can quickly recognize the risks.

[0051] Step 7:

[0052] The AI ​​chatbot will offer specific countermeasures for risks, including advice on reallocating resources and changing task priorities based on the current situation.

[0053] Step 8:

[0054] The device displays risk information and suggested countermeasures to the user in a dashboard format. Based on this, the user makes decisions and plans specific actions.

[0055] Step 9:

[0056] Based on the system's suggestions, the user takes necessary actions (e.g., scheduling meetings with stakeholders or rescheduling tasks).

[0057] (Example 1)

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

[0059] In project management, it is crucial to monitor progress and resource usage in real time and to detect potential delays and budget anomalies early. However, traditional methods often involve manual information gathering and analysis, which is time-consuming and prone to human error. This makes timely risk response difficult and contributes to a lower project success rate. Therefore, there is a need for a system that manages risks efficiently and accurately and proposes countermeasures quickly.

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

[0061] In this invention, the server includes means for automatically acquiring and integrating information from a data source, means for analyzing risks using a trained multiform analysis model, and means for notifying when a risk is detected and generating action plans. This makes it possible to detect delay risks and budget anomalies in a project in real time and to quickly present appropriate countermeasures.

[0062] "Data source" refers to systems and devices that provide information, such as project management tools, email servers, and IoT sensors.

[0063] "Integration" is the process of converting data obtained from different formats and media into a format that allows for consistent analysis, and then aggregating it.

[0064] A "multiform analysis model" refers to a pre-trained generative AI model that can simultaneously analyze data in different formats (e.g., text data and numerical data).

[0065] Analyzing "risk" involves processing and analyzing data to identify and evaluate potential problems such as project delays and budget anomalies.

[0066] "Notification" refers to the act of communicating information or warnings to relevant parties, and specifically includes sending messages via email or chat tools.

[0067] "Generating action plans" is the process of proposing feasible countermeasures and improvement measures for the risks that have been identified.

[0068] "Visualization" refers to the process of visually displaying data and analysis results so that users can easily understand them and make decisions.

[0069] As an embodiment of the present invention, a real-time risk analysis system for project management will be described. This system consists of a server, terminals, and users.

[0070] The server is responsible for automatically acquiring and integrating information. Data sources include project management tools, email servers, and IoT sensors, and standard communication methods such as APIs and IMAP protocols are used to collect data from these sources. The server executes an ETL (Extract, Transform, Load) process to unify data formats, detect anomalies, and perform corrections to generate a dataset suitable for analysis.

[0071] The generated dataset is analyzed in real time by a pre-trained multiform analysis model. This model can process text and numerical data simultaneously and identify and evaluate risks such as project delays and budget anomalies. For example, a prompt such as "Project name: XYZ, Progress: 60%, Budget consumption: 80%, Please perform a risk assessment based on resource utilization and propose the optimal countermeasures" can be input to the AI ​​model, allowing for multi-stage analysis.

[0072] If a risk is detected, the server uses an AI chatbot to notify relevant parties. The notification, delivered via email or chat tools, includes the nature of the risk and suggested actions. Users can receive this information and take prompt action as needed.

[0073] This risk information is visualized on a dashboard on the device. Through the dashboard, users can intuitively understand the project's progress and risk assessment results, and consider specific actions based on the displayed information. This is expected to increase the project's success rate and reduce unnecessary costs.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects data from project management tools, mail servers, and IoT sensors. Specifically, it retrieves data using APIs and IMAP protocols. As input, it receives project task progress information and communication records, and as output, these datasets are accumulated on the server.

[0077] Step 2:

[0078] The server integrates the collected data through an ETL process. Specifically, it converts data in different formats into a single analytical format, imputes missing values, and detects and corrects outliers. The input is the dataset obtained in step 1, and the output is a cleaned, unified dataset.

[0079] Step 3:

[0080] The server takes a unified dataset as input and assesses risk based on a trained multiform analysis model. Specifically, it uses a generative AI model to execute prompt statements and perform risk assessments. For example, it might present a prompt statement such as "Assess the risk of project progress at 60% and budget consumption at 80%", and the output would be an assessment of delay risk and budget anomalies.

[0081] Step 4:

[0082] Based on the assessment results, the server uses an AI chatbot to send risk notifications to relevant parties. Specifically, it notifies them of the risk and proposed countermeasures via email or chat tools. The input is the risk assessment results from step 3, and the output is a notification message which is then distributed to the relevant parties.

[0083] Step 5:

[0084] The device visualizes risk information for the user on a dashboard. Specifically, it visually displays the risk assessment results, allowing users to intuitively understand the project's progress. The input is the notification content from step 4, and the output is graphs and risk indicators displayed on the dashboard.

[0085] (Application Example 1)

[0086] 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."

[0087] Construction projects often face unforeseen risks, delays, and cost overruns. These situations are major obstacles to project success. Therefore, an efficient system is needed to monitor project progress in real time and to quickly identify and address risks.

[0088] 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.

[0089] In this invention, the server includes a device for automatically collecting and integrating data, a device for evaluating risks using a trained model, and a device for notifying and providing countermeasures when a risk is recognized. This enables real-time monitoring of progress within a construction project and rapid detection and response to risks.

[0090] "Data" is a collection of information that forms the basis for project progress and risk assessment.

[0091] A "model" is a computational method trained to analyze collected data and assess risk.

[0092] "Risk" refers to factors that indicate the possibility of undesirable outcomes occurring, such as project delays or cost overruns.

[0093] "Notification" refers to a means of quickly communicating information to relevant parties when a risk is detected.

[0094] "Countermeasures" refer to specific actions proposed to address risks and ensure the smooth progress of the project.

[0095] A "device" is a physical or virtual mechanism used to collect, analyze, and notify data.

[0096] A "trained model" is an AI model that learns from a large amount of data tailored to a specific purpose and can perform risk assessments.

[0097] In the system for implementing this invention, a server plays a central role. The server first automatically collects sensor data from construction sites and information from project management tools. This data is sent to the server via the Flask API using Python. Data integration is performed using an ETL process with Apache® NiFi, generating a dataset in a unified format.

[0098] The terminals specifically refer to smartphones and smart glasses, and serve as interfaces for users to check project progress and risk analysis results. Data is transmitted from the server to the terminals and displayed on the dashboard in real time.

[0099] The pre-trained AI model running on the server is built with PyTorch and analyzes the collected data. The model is multimodal and can process text and numerical data simultaneously. If a risk is detected, the AI ​​chatbot notifies relevant parties via Flask and proposes specific countermeasures.

[0100] As a concrete example, if there is a possibility that the foundation work of a building at a construction site may be delayed due to weather conditions, the server analyzes weather data and progress data to assess the risk. Based on this, the AI ​​model makes specific suggestions, such as "plan to concentrate heavy machinery use on sunny days." This suggestion is immediately notified to the project manager via a chat tool.

[0101] Examples of prompt statements are as follows:

[0102] "Project Name: Bridge Construction, Current Progress: 60%, Unexpected Weather Changes: Heavy Rain, Required Resources: Heavy Machinery, What is the optimal solution you would propose?"

[0103] In this way, the system supports the efficient progress of projects by enabling servers, terminals, and users to work together, share information in real time, and manage risks.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server receives data collected from IoT sensors at construction sites and progress data from project management tools. The input consists of various data formats obtained from each data source. The server converts this data into a unified format and extracts the necessary information. During this process, missing data values ​​are imputed, and anomalies are detected and corrected.

[0107] Step 2:

[0108] The server uses Apache NiFi to process the data through an ETL process, generating a formatted dataset. The input is the data integrated in step 1, and the output is an analyzable dataset suitable for AI models. Specifically, the data is rearranged along a time axis, and the formatting of each item is standardized.

[0109] Step 3:

[0110] The server inputs the formatted dataset into a generative AI model trained with PyTorch to analyze the risks. The input is a unified dataset, and the output is an assessment of potential risks in the project. The model comprehensively analyzes various data to estimate the risk of delays and potential cost overruns.

[0111] Step 4:

[0112] If a risk is detected, the server activates an AI chatbot via Flask to notify relevant parties. The input is the analysis results from step 3, and the output is risk information and specific countermeasures. The server sends this information via email or chat tools to prompt action from the project manager.

[0113] Step 5:

[0114] Users access information transmitted from the server via a dashboard using devices such as smartphones or smart glasses. Inputs include risk information and suggested countermeasures, while output is a real-time visualization of the project status. Based on this, users make decisions and take specific actions to adjust the project plan as needed.

[0115] 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.

[0116] As an embodiment of the present invention, we describe an information system that monitors project progress in real time, predicts delay risks, and provides adaptive support that takes user emotions into consideration. This system mainly consists of a server, terminals, and users.

[0117] First, the server automatically collects and integrates data from project management tools, email servers, and sensor systems. This centralizes task progress, team communication, and environmental data. After collecting the data, the server preprocesses it and formats it so that it is suitable for supplying to AI models.

[0118] Next, the server analyzes this integrated data using a trained multimodal AI model. This model has the ability to process different data formats simultaneously and detect project delays and budget risks. This allows for early detection of potential risks and prompts for action.

[0119] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the user's emotional state based on user feedback and behavioral data, and adjusts risk mitigation measures based on this analysis. For example, if the emotion engine determines that a user is in a high-stress state, the user may receive suggestions for measures to alleviate that stress. This reduces the user's mental burden and enables more effective project management.

[0120] When a risk is detected, an AI chatbot on the server notifies relevant parties and presents suggestions adjusted by an emotion engine. Notifications are sent via email or chat tools, providing an environment for immediate response. For example, it might suggest appropriate break times or resource reallocation to project members who are experiencing stress.

[0121] Ultimately, the terminal displays risk information and recommended countermeasures to the user via a dashboard. Based on this information, the user can decide on actions and implement measures to improve the project. The implementation of this system is expected to improve the accuracy and efficiency of project management, maximizing results.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server automatically collects data from project management tools, email systems, and sensor systems. This includes retrieving task progress, email communications, and environmental data from sensors by making API calls and using the IMAP protocol.

[0125] Step 2:

[0126] The server integrates the collected data. This process involves converting data in different formats (e.g., CSV files, JSON objects, real-time stream data) and storing it in a unified database. When data loss or anomalies are detected, appropriate completion or correction processes are performed.

[0127] Step 3:

[0128] The server supplies integrated data to the AI ​​model to perform risk assessments. The multimodal AI model uses this data to evaluate project delay risks and budget risks and generates a risk score for each project.

[0129] Step 4:

[0130] The server runs an emotion engine to analyze the user's emotional state. It uses email text analysis and user feedback data to determine the user's emotions and stress level.

[0131] Step 5:

[0132] The server combines risk assessment results with user sentiment data to design optimized risk mitigation strategies. For example, it might suggest prioritizing tasks or reallocating resources to teams with high-stress users.

[0133] Step 6:

[0134] The AI ​​chatbot (on the server) notifies relevant parties of the assessed risks and countermeasures. Notifications are sent via email or chat applications, enabling a rapid response.

[0135] Step 7:

[0136] The device displays a dashboard to the user, providing a visual overview of project risk information and proposed countermeasures. Based on this, the user plans the necessary actions and communicates with team members.

[0137] Step 8:

[0138] Users utilize the information on the dashboard to implement suggested measures. These actions include scheduling meetings, adjusting break times, and rescheduling tasks, contributing to project optimization.

[0139] (Example 2)

[0140] 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".

[0141] In project progress management and risk assessment, it is essential to collect and integrate accurate information in real time to identify potential problems early and take countermeasures. However, conventional systems have limitations in integrating information, analyzing diverse data formats, and providing responses that take emotional states into account. As a result, immediate action to prevent project delays and cost overruns has been difficult.

[0142] 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.

[0143] In this invention, the server includes means for automatically collecting and integrating information, means for preprocessing and formatting the collected information for analysis, means for detecting risks using an analyzable model of the generated data in various formats, means for analyzing the user's emotional state and adjusting suggestions based on that, and means for notifying the user when a risk is detected and proposing adjusted countermeasures. This enables real-time monitoring of project progress and potential risks, and allows for the provision of appropriate countermeasures based on the user's emotional state.

[0144] "Means for automatically collecting and integrating information" refers to a system in which a server acquires data from various information management systems and centrally consolidates this data.

[0145] "Means for preprocessing collected information and shaping it for analysis" refers to a mechanism that cleans and converts the format of data acquired by a server to make it easier to analyze.

[0146] "A means of detecting risk using a model capable of analyzing diverse data formats" refers to a mechanism that uses a trained code sequence model to analyze data in different formats and identify potential risks.

[0147] "A means of analyzing the user's emotional state and adjusting suggestions based on that" refers to a system where the server analyzes user feedback and behavioral data to evaluate the emotional state and then changes the content of risk mitigation measures accordingly.

[0148] "A means of notifying when a risk is detected and proposing adjusted countermeasures" refers to a system in which the server quickly notifies relevant parties of the discovered risk and presents adaptive countermeasures that take into account emotional states.

[0149] This invention is an information system that streamlines project management and enables early detection of risks. This system primarily consists of a server, terminals, and users.

[0150] The server automatically collects and integrates data from information management tools, communication systems, and environmental monitoring sensors. Specifically, it uses common database software in project management tools to aggregate data from mail servers and sensors and saves it in JSON or CSV format.

[0151] The collected data is preprocessed using programming languages ​​such as Python and R to prepare it for analysis. The server then uses a pre-trained multimodal generative AI model to analyze the data in multiple formats. This model utilizes natural language processing libraries (e.g., TENSORFLOW®) to identify potential delays and budget overruns.

[0152] Furthermore, the server incorporates an emotion engine that analyzes user email feedback and digital activity to understand the user's emotional state. Based on this, the system adjusts risk mitigation measures and suggests stress relief measures if the user is experiencing high stress levels.

[0153] The device displays risk information and recommended countermeasures to the user through a dashboard, allowing the user to decide on specific actions. The dashboard displays real-time graphs and heatmaps, allowing users to visually check the degree of risk and progress.

[0154] For example, suppose one member of an IT development project falls behind on a task. In this case, the system uses an AI model to immediately detect the risk of delay, and if the emotion engine detects that member is stressed, it suggests an appropriate break.

[0155] By utilizing this system, users can gain a highly accurate understanding of project progress and risks, enabling more effective project management.

[0156] The following are examples of prompt statements to be input into the generative AI model:

[0157] "Analyze the current status of the ongoing 'New Product Development' project and predict the risks of delays and budget overruns. Also, consider appropriate support measures based on the emotional state of the team members."

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The server initiates the process of collecting and integrating information. Specifically, it retrieves data from project management systems, communication systems, and sensor clusters via APIs. It accepts project task data, email sending and receiving logs, and environmental sensor data as input. This data is then stored as an integrated dataset in JSON or CSV format.

[0161] Step 2:

[0162] The server preprocesses the collected information. Specifically, it uses a Python script to perform processes such as noise reduction and missing value imputation, and to standardize the data format. The input is the dataset integrated in step 1, and the output is a clean, analyzable, standardized dataset.

[0163] Step 3:

[0164] The server leverages a generative AI model to analyze the preprocessed data. Here, a trained multimodal AI model is used to analyze different data formats simultaneously. The input is the standardized dataset created in step 2, and the output is the results of the delay risk and budget overrun risk assessment for each task.

[0165] Step 4:

[0166] The server uses an emotion engine to analyze user feedback and behavior and evaluate their emotional state. Inputs are user behavioral data such as email content and keystroke logs, and outputs are quantified results such as stress levels and satisfaction ratings.

[0167] Step 5:

[0168] The AI ​​chatbot on the server notifies relevant parties when a risk is detected. This utilizes notification functions via email and chat applications. The input consists of the risk assessment results from Step 3 and the sentiment assessment results from Step 4, while the output is a notification message including specific countermeasures.

[0169] Step 6:

[0170] The device visually displays risk information and recommended countermeasures to the user on a dashboard. Input is notification data from the server, and output is information presented to the user as risk trend graphs and specific improvement action plans.

[0171] (Application Example 2)

[0172] 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 device 14 will be referred to as the "terminal."

[0173] In modern project management, real-time monitoring of progress and risk management are essential. However, especially in complex and diverse projects such as construction, centralized information management and early detection of delay risks are often difficult. Furthermore, the emotional states of individual project members also affect project progress, but there is a lack of means to properly monitor and effectively address these factors. Therefore, a new system is needed to overcome these challenges and ensure smooth project progress.

[0174] 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.

[0175] In this invention, the server includes means for automatically collecting and integrating information, means for detecting risks using the generated model, and means for analyzing the user's emotional state and providing adaptive countermeasures. This makes it possible to detect project risks early and provide adaptive support tailored to the emotional state of individual project members.

[0176] "Means for automatically collecting and integrating information" refers to technologies for automatically acquiring project-related data from diverse sources and organizing it into a single, integrated format.

[0177] "Means of detecting risks using generated models" refers to techniques that use AI models trained to analyze collected data to identify potential delays and obstacles in project progress.

[0178] "Means of analyzing users' emotional states and providing adaptive countermeasures" refers to technologies that analyze user feedback and behavioral data to evaluate emotions and then present specific support and countermeasures tailored to those states.

[0179] "A means of notifying and proposing countermeasures when a risk is detected" refers to a technology that quickly informs stakeholders of a risk when it is detected in a project and guides them toward appropriate countermeasures.

[0180] "Means of providing users with real-time information regarding project progress" refers to technologies that display information in real time so that users can immediately grasp the current status of the project and future risks.

[0181] The system of this invention is designed to support project management and consists mainly of a server, terminals, and users.

[0182] The server has the ability to automatically collect data from project management tools, email management systems, and various sensor systems. This data includes task progress, team conversations, and information about the work environment. After collection, the server preprocesses the data and converts it into a format suitable for analysis. This process uses Pandas as data processing software and leverages Azure® as the cloud service provider.

[0183] Next, the server analyzes the integrated data using a trained multimodal generative AI model. This AI model has the ability to process different data formats simultaneously to identify project delay risks and budget overrun risks. PyTorch is used for the analysis, and TensorFlow can also be utilized as needed. This allows the server to identify potential risks early and facilitate responses.

[0184] Furthermore, the system incorporates an emotion analysis function that evaluates the user's emotional state based on user feedback and behavioral data. Based on this information, it adjusts risk management measures for the user and provides appropriate support as needed. As an example of this emotion analysis function, if a user is determined to be in a high-stress state, the user will be offered suggestions for stress reduction.

[0185] When a risk is detected, an AI chatbot on the server notifies relevant stakeholders and provides tailored suggestions based on sentiment analysis. Email and chat tools are used as notification methods. For example, if a project member is experiencing stress, appropriate break times or reallocation of work resources will be suggested.

[0186] The device displays project risk information and recommended countermeasures to the user through a dashboard. This allows the user to make decisions based on the provided information and quickly take measures to improve the project.

[0187] For example, if an AI model detects that many workers are under high stress in a construction project, the app may automatically notify the project manager and suggest setting break times and optimizing work resources to reduce stress.

[0188] Examples of prompts to input into the generating AI model include: "Please suggest the main risks in the current construction project and specific measures to mitigate them."

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server automatically collects data from project management tools, email management systems, and sensor systems. The input is digital data from each source, and the output is an integrated dataset. The server centralizes the collected data using Pandas and filters out unnecessary data as needed.

[0192] Step 2:

[0193] The server preprocesses the integrated dataset and converts it into a format suitable for the generative AI model. The input to this process is a unified dataset, and the output is data formatted for model analysis. This includes specific actions such as data normalization and missing value imputation.

[0194] Step 3:

[0195] The server uses a multimodal generative AI model trained with PyTorch to analyze the formatted data. The input is pre-processed data, and the output is the risk detection result. Through this analysis, potential issues such as project delay risks and budget overruns are identified.

[0196] Step 4:

[0197] The server evaluates the user's emotional state based on user feedback and behavioral data. The input to this process is user-related data, and the output is an evaluation of the user's emotional state. Natural language processing and pattern recognition are performed using an emotion analysis engine.

[0198] Step 5:

[0199] When a risk is detected, the server proposes adaptively adjusted risk mitigation measures based on the emotional state and notifies relevant parties via an AI chatbot. The inputs are the risk detection results and the emotional state assessment results, while the output consists of the proposed measures and a notification message. Specific actions include generating notification emails and chat messages.

[0200] Step 6:

[0201] The terminal displays project risk information and recommended countermeasures to the user through a dashboard. The input for this process is notification data from the server, and the output is visual information provided to the user. The terminal visualizes the data and generates graphs and charts to help the user easily understand the situation.

[0202] Step 7:

[0203] Users decide on actions for the project based on the information provided on the dashboard. The input for this process is the visualized information displayed on the terminal, and the output is the specific actions taken by the user. Users adjust the project plan according to the suggestions, leading to more effective management.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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".

[0220] As an embodiment of the present invention, we describe an information system that monitors the progress of a project in real time and predicts delay risks. This system consists of a server, terminals, and users.

[0221] First, the server automatically collects data from multiple sources, such as project management tools, email servers, and IoT sensor systems. This functionality is achieved using APIs and IMAP protocols, allowing necessary data to be accumulated without interrupting the daily flow of information. For example, it periodically retrieves the progress of tasks in ongoing projects and the content of email communications.

[0222] Next, the collected data is integrated on the server. The ETL (Extract, Transform, Load) process is used to convert data acquired in different formats into a unified analysis format. During this process, missing data values ​​are imputed and outliers are detected, resulting in a highly accurate dataset.

[0223] Subsequently, the server uses this dataset to perform risk analysis using a trained multimodal AI model. The model simultaneously analyzes different data formats (such as text and numerical data) to detect and evaluate delay risks and budget anomalies in real time. For example, it can process all data to detect delay risks due to excessive resource consumption in a specific project.

[0224] If a risk is detected, an AI chatbot on the server immediately notifies relevant parties. This includes sending messages via email or chat tools to prompt users to take necessary actions. The AI ​​also supports rapid decision-making by including optimal countermeasures as suggestions. In specific cases, concrete suggestions may be provided, such as "reconsider resource allocation and adjust the priority of related tasks."

[0225] Ultimately, the device visualizes risk information for the user through a dashboard. Here, the user can review the overall project picture and decide on specific actions based on the suggested countermeasures. This system is expected to increase the project's success rate and reduce unnecessary costs.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The server automatically collects data from project management tools, email systems, and IoT sensors. It uses APIs and IMAP protocols to retrieve task progress information, communication history, and environmental data.

[0229] Step 2:

[0230] The server integrates the collected data for centralized management. To handle different data formats (e.g., JSON, CSV, stream data), it performs necessary data transformations through an ETL process and stores the data in a database.

[0231] Step 3:

[0232] The server preprocesses the integrated data. It improves the reliability of the analysis by imputing missing values ​​and identifying and appropriately handling outliers.

[0233] Step 4:

[0234] The server inputs the prepared data into the AI ​​model and performs a risk analysis. The model specializes in analyzing multimodal data and generates a score that assesses the risk of project delays and budget overruns.

[0235] Step 5:

[0236] The server determines the project's risk level based on the analysis results and updates the information on the dashboard.

[0237] Step 6:

[0238] The AI ​​chatbot (on the server) notifies relevant parties of detected risks. For example, it provides information via email or chat tools so that users can quickly recognize the risks.

[0239] Step 7:

[0240] The AI ​​chatbot will offer specific countermeasures for risks, including advice on reallocating resources and changing task priorities based on the current situation.

[0241] Step 8:

[0242] The device displays risk information and suggested countermeasures to the user in a dashboard format. Based on this, the user makes decisions and plans specific actions.

[0243] Step 9:

[0244] Based on the system's suggestions, the user takes necessary actions (e.g., scheduling meetings with stakeholders or rescheduling tasks).

[0245] (Example 1)

[0246] 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".

[0247] In project management, it is crucial to monitor progress and resource usage in real time and to detect potential delays and budget anomalies early. However, traditional methods often involve manual information gathering and analysis, which is time-consuming and prone to human error. This makes timely risk response difficult and contributes to a lower project success rate. Therefore, there is a need for a system that manages risks efficiently and accurately and proposes countermeasures quickly.

[0248] 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.

[0249] In this invention, the server includes means for automatically acquiring and integrating information from a data source, means for analyzing risks using a trained multiform analysis model, and means for notifying when a risk is detected and generating action plans. This makes it possible to detect delay risks and budget anomalies in a project in real time and to quickly present appropriate countermeasures.

[0250] "Data source" refers to systems and devices that provide information, such as project management tools, email servers, and IoT sensors.

[0251] "Integration" is the process of converting data obtained from different formats and media into a format that allows for consistent analysis, and then aggregating it.

[0252] A "multiform analysis model" refers to a pre-trained generative AI model that can simultaneously analyze data in different formats (e.g., text data and numerical data).

[0253] Analyzing "risk" involves processing and analyzing data to identify and evaluate potential problems such as project delays and budget anomalies.

[0254] "Notification" refers to the act of communicating information or warnings to relevant parties, and specifically includes sending messages via email or chat tools.

[0255] "Generating action plans" is the process of proposing feasible countermeasures and improvement measures for the risks that have been identified.

[0256] "Visualization" refers to the process of visually displaying data and analysis results so that users can easily understand them and make decisions.

[0257] As an embodiment of the present invention, a real-time risk analysis system for project management will be described. This system consists of a server, terminals, and users.

[0258] The server is responsible for automatically acquiring and integrating information. Data sources include project management tools, email servers, and IoT sensors, and standard communication methods such as APIs and IMAP protocols are used to collect data from these sources. The server executes an ETL (Extract, Transform, Load) process to unify data formats, detect anomalies, and perform corrections to generate a dataset suitable for analysis.

[0259] The generated dataset is analyzed in real time by a pre-trained multiform analysis model. This model can process text and numerical data simultaneously and identify and evaluate risks such as project delays and budget anomalies. For example, a prompt such as "Project name: XYZ, Progress: 60%, Budget consumption: 80%, Please perform a risk assessment based on resource utilization and propose the optimal countermeasures" can be input to the AI ​​model, allowing for multi-stage analysis.

[0260] If a risk is detected, the server uses an AI chatbot to notify relevant parties. The notification, delivered via email or chat tools, includes the nature of the risk and suggested actions. Users can receive this information and take prompt action as needed.

[0261] This risk information is visualized on a dashboard on the device. Through the dashboard, users can intuitively understand the project's progress and risk assessment results, and consider specific actions based on the displayed information. This is expected to increase the project's success rate and reduce unnecessary costs.

[0262] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0263] Step 1:

[0264] The server collects data from project management tools, mail servers, and IoT sensors. Specifically, it retrieves data using APIs and IMAP protocols. As input, it receives project task progress information and communication records, and as output, these datasets are accumulated on the server.

[0265] Step 2:

[0266] The server integrates the collected data through an ETL process. Specifically, it converts data in different formats into a single analytical format, imputes missing values, and detects and corrects outliers. The input is the dataset obtained in step 1, and the output is a cleaned, unified dataset.

[0267] Step 3:

[0268] The server takes a unified dataset as input and assesses risk based on a trained multiform analysis model. Specifically, it uses a generative AI model to execute prompt statements and perform risk assessments. For example, it might present a prompt statement such as "Assess the risk of project progress at 60% and budget consumption at 80%", and the output would be an assessment of delay risk and budget anomalies.

[0269] Step 4:

[0270] Based on the assessment results, the server uses an AI chatbot to send risk notifications to relevant parties. Specifically, it notifies them of the risk and proposed countermeasures via email or chat tools. The input is the risk assessment results from step 3, and the output is a notification message which is then distributed to the relevant parties.

[0271] Step 5:

[0272] The device visualizes risk information for the user on a dashboard. Specifically, it visually displays the risk assessment results, allowing users to intuitively understand the project's progress. The input is the notification content from step 4, and the output is graphs and risk indicators displayed on the dashboard.

[0273] (Application Example 1)

[0274] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] Construction projects often face unforeseen risks, delays, and cost overruns. These situations are major obstacles to project success. Therefore, an efficient system is needed to monitor project progress in real time and to quickly identify and address risks.

[0276] 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.

[0277] In this invention, the server includes a device for automatically collecting and integrating data, a device for evaluating risks using a trained model, and a device for notifying and providing countermeasures when a risk is recognized. This enables real-time monitoring of progress within a construction project and rapid detection and response to risks.

[0278] "Data" is a collection of information that forms the basis for project progress and risk assessment.

[0279] A "model" is a computational method trained to analyze collected data and assess risk.

[0280] "Risk" refers to factors that indicate the possibility of undesirable outcomes occurring, such as project delays or cost overruns.

[0281] A "notification" is a means to promptly convey such information to relevant parties when a risk is detected.

[0282] A "countermeasure" is a specific action proposed to address risks and facilitate the smooth progress of the project.

[0283] An "apparatus" is a physical or virtual mechanism used for data collection, analysis, and notification.

[0284] A "trained model" is an AI model that has learned based on a large amount of data for a specific purpose and can perform risk assessment.

[0285] In the system for implementing this invention, the server plays a central role. The server first automatically collects sensor data from the construction site and information from the project management tool. This data is sent to the server via the Flask API using Python. The integration of the data is performed by an ETL process using Apache NiFi, and a dataset is generated in a unified format.

[0286] The terminal specifically refers to a smartphone or smart glasses and is an interface for the user to check the progress of the project and the results of risk analysis. The data is sent from the server to the terminal and displayed on the dashboard in real time.

[0287] The trained AI model operating on the server is built with PyTorch and analyzes the collected data. The model is multimodal and can process text and numerical data simultaneously. When a risk is detected, the AI chatbot notifies the relevant parties through Flask and proposes specific countermeasures.

[0288] As a concrete example, if there is a possibility that the foundation work of a building at a construction site may be delayed due to weather conditions, the server analyzes weather data and progress data to assess the risk. Based on this, the AI ​​model makes specific suggestions, such as "plan to concentrate heavy machinery use on sunny days." This suggestion is immediately notified to the project manager via a chat tool.

[0289] Examples of prompt statements are as follows:

[0290] "Project Name: Bridge Construction, Current Progress: 60%, Unexpected Weather Changes: Heavy Rain, Required Resources: Heavy Machinery, What is the optimal solution you would propose?"

[0291] In this way, the system supports the efficient progress of projects by enabling servers, terminals, and users to work together, share information in real time, and manage risks.

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

[0293] Step 1:

[0294] The server receives data collected from IoT sensors at construction sites and progress data from project management tools. The input consists of various data formats obtained from each data source. The server converts this data into a unified format and extracts the necessary information. During this process, missing data values ​​are imputed, and anomalies are detected and corrected.

[0295] Step 2:

[0296] The server uses Apache NiFi to process the data through an ETL process, generating a formatted dataset. The input is the data integrated in step 1, and the output is an analyzable dataset suitable for AI models. Specifically, the data is rearranged along a time axis, and the formatting of each item is standardized.

[0297] Step 3:

[0298] The server inputs the formatted dataset into a generative AI model trained with PyTorch to analyze the risks. The input is a unified dataset, and the output is an assessment of potential risks in the project. The model comprehensively analyzes various data to estimate the risk of delays and potential cost overruns.

[0299] Step 4:

[0300] If a risk is detected, the server activates an AI chatbot via Flask to notify relevant parties. The input is the analysis results from step 3, and the output is risk information and specific countermeasures. The server sends this information via email or chat tools to prompt action from the project manager.

[0301] Step 5:

[0302] Users access information transmitted from the server via a dashboard using devices such as smartphones or smart glasses. Inputs include risk information and suggested countermeasures, while output is a real-time visualization of the project status. Based on this, users make decisions and take specific actions to adjust the project plan as needed.

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

[0304] As an embodiment of the present invention, we describe an information system that monitors project progress in real time, predicts delay risks, and provides adaptive support that takes user emotions into consideration. This system mainly consists of a server, terminals, and users.

[0305] First, the server automatically collects data from the project management tool, mail server, and sensor system and integrates it. This unifies the progress of tasks, communication content between teams, environmental data, etc. After collecting the data, the server preprocesses the data and formats it into a state suitable for feeding into the AI model.

[0306] Next, the server analyzes these integrated data using a trained multimodal AI model. This model has the ability to process different forms of data simultaneously and detect risks such as project delays and budget risks. This enables early discovery of potential risks and prompts responses.

[0307] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the emotional state from user feedback, behavioral data, etc., and adjusts risk response measures based on this. For example, if the emotion engine determines that a user is in a high-stress state, measures to reduce stress may be proposed to that user. This reduces the mental burden on the user and realizes more effective project management.

[0308] When a risk is detected, the AI chatbot on the server notifies the relevant parties and presents proposals adjusted by the emotion engine. The notification is sent using email or chat tools, providing an environment for immediate response. For example, suitable break times or reallocation of resources may be proposed to project members feeling stressed.

[0309] Finally, the terminal displays risk information and recommended countermeasures to the user through a dashboard. The user can make decisions based on these and take measures to improve the project. By introducing this system, the accuracy and efficiency of project management can be improved, and maximization of results can be expected.

[0310] The following explains the processing flow.

[0311] Step 1:

[0312] The server automatically collects data from project management tools, email systems, and sensor systems. This includes retrieving task progress, email communications, and environmental data from sensors by making API calls and using the IMAP protocol.

[0313] Step 2:

[0314] The server integrates the collected data. This process involves converting data in different formats (e.g., CSV files, JSON objects, real-time stream data) and storing it in a unified database. When data loss or anomalies are detected, appropriate completion or correction processes are performed.

[0315] Step 3:

[0316] The server supplies integrated data to the AI ​​model to perform risk assessments. The multimodal AI model uses this data to evaluate project delay risks and budget risks and generates a risk score for each project.

[0317] Step 4:

[0318] The server runs an emotion engine to analyze the user's emotional state. It uses email text analysis and user feedback data to determine the user's emotions and stress level.

[0319] Step 5:

[0320] The server combines risk assessment results with user sentiment data to design optimized risk mitigation strategies. For example, it might suggest prioritizing tasks or reallocating resources to teams with high-stress users.

[0321] Step 6:

[0322] The AI ​​chatbot (on the server) notifies relevant parties of the assessed risks and countermeasures. Notifications are sent via email or chat applications, enabling a rapid response.

[0323] Step 7:

[0324] The device displays a dashboard to the user, providing a visual overview of project risk information and proposed countermeasures. Based on this, the user plans the necessary actions and communicates with team members.

[0325] Step 8:

[0326] Users utilize the information on the dashboard to implement suggested measures. These actions include scheduling meetings, adjusting break times, and rescheduling tasks, contributing to project optimization.

[0327] (Example 2)

[0328] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0329] In project progress management and risk assessment, it is essential to collect and integrate accurate information in real time to identify potential problems early and take countermeasures. However, conventional systems have limitations in integrating information, analyzing diverse data formats, and providing responses that take emotional states into account. As a result, immediate action to prevent project delays and cost overruns has been difficult.

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

[0331] In this invention, the server includes means for automatically collecting and integrating information, means for preprocessing and formatting the collected information for analysis, means for detecting risks using an analyzable model of the generated data in various formats, means for analyzing the user's emotional state and adjusting suggestions based on that, and means for notifying the user when a risk is detected and proposing adjusted countermeasures. This enables real-time monitoring of project progress and potential risks, and allows for the provision of appropriate countermeasures based on the user's emotional state.

[0332] "Means for automatically collecting and integrating information" refers to a system in which a server acquires data from various information management systems and centrally consolidates this data.

[0333] "Means for preprocessing collected information and shaping it for analysis" refers to a mechanism that cleans and converts the format of data acquired by a server to make it easier to analyze.

[0334] "A means of detecting risk using a model capable of analyzing diverse data formats" refers to a mechanism that uses a trained code sequence model to analyze data in different formats and identify potential risks.

[0335] "A means of analyzing the user's emotional state and adjusting suggestions based on that" refers to a system where the server analyzes user feedback and behavioral data to evaluate the emotional state and then changes the content of risk mitigation measures accordingly.

[0336] "A means of notifying when a risk is detected and proposing adjusted countermeasures" refers to a system in which the server quickly notifies relevant parties of the discovered risk and presents adaptive countermeasures that take into account emotional states.

[0337] This invention is an information system that streamlines project management and enables early detection of risks. This system primarily consists of a server, terminals, and users.

[0338] The server automatically collects and integrates data from information management tools, communication systems, and environmental monitoring sensors. Specifically, it uses common database software in project management tools to aggregate data from mail servers and sensors and saves it in JSON or CSV format.

[0339] The collected data is preprocessed using programming languages ​​such as Python and R to prepare it for analysis. The server then uses a pre-trained multimodal generative AI model to analyze the data in multiple formats. This model utilizes natural language processing libraries (e.g., TensorFlow) to identify potential delays and budget overruns.

[0340] Furthermore, the server incorporates an emotion engine that analyzes user email feedback and digital activity to understand the user's emotional state. Based on this, the system adjusts risk mitigation measures and suggests stress relief measures if the user is experiencing high stress levels.

[0341] The device displays risk information and recommended countermeasures to the user through a dashboard, allowing the user to decide on specific actions. The dashboard displays real-time graphs and heatmaps, allowing users to visually check the degree of risk and progress.

[0342] For example, suppose one member of an IT development project falls behind on a task. In this case, the system uses an AI model to immediately detect the risk of delay, and if the emotion engine detects that member is stressed, it suggests an appropriate break.

[0343] By utilizing this system, users can gain a highly accurate understanding of project progress and risks, enabling more effective project management.

[0344] The following are examples of prompt statements to be input into the generative AI model:

[0345] "Analyze the current status of the ongoing 'New Product Development' project and predict the risks of delays and budget overruns. Also, consider appropriate support measures based on the emotional state of the team members."

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The server initiates the process of collecting and integrating information. Specifically, it retrieves data from project management systems, communication systems, and sensor clusters via APIs. It accepts project task data, email sending and receiving logs, and environmental sensor data as input. This data is then stored as an integrated dataset in JSON or CSV format.

[0349] Step 2:

[0350] The server preprocesses the collected information. Specifically, it uses a Python script to perform processes such as noise reduction and missing value imputation, and to standardize the data format. The input is the dataset integrated in step 1, and the output is a clean, analyzable, standardized dataset.

[0351] Step 3:

[0352] The server leverages a generative AI model to analyze the preprocessed data. Here, a trained multimodal AI model is used to analyze different data formats simultaneously. The input is the standardized dataset created in step 2, and the output is the results of the delay risk and budget overrun risk assessment for each task.

[0353] Step 4:

[0354] The server uses an emotion engine to analyze user feedback and behavior and evaluate their emotional state. Inputs are user behavioral data such as email content and keystroke logs, and outputs are quantified results such as stress levels and satisfaction ratings.

[0355] Step 5:

[0356] The AI ​​chatbot on the server notifies relevant parties when a risk is detected. This utilizes notification functions via email and chat applications. The input consists of the risk assessment results from Step 3 and the sentiment assessment results from Step 4, while the output is a notification message including specific countermeasures.

[0357] Step 6:

[0358] The device visually displays risk information and recommended countermeasures to the user on a dashboard. Input is notification data from the server, and output is information presented to the user as risk trend graphs and specific improvement action plans.

[0359] (Application Example 2)

[0360] 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."

[0361] In modern project management, real-time monitoring of progress and risk management are essential. However, especially in complex and diverse projects such as construction, centralized information management and early detection of delay risks are often difficult. Furthermore, the emotional states of individual project members also affect project progress, but there is a lack of means to properly monitor and effectively address these factors. Therefore, a new system is needed to overcome these challenges and ensure smooth project progress.

[0362] 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.

[0363] In this invention, the server includes means for automatically collecting and integrating information, means for detecting risks using the generated model, and means for analyzing the user's emotional state and providing adaptive countermeasures. This makes it possible to detect project risks early and provide adaptive support tailored to the emotional state of individual project members.

[0364] "Means for automatically collecting and integrating information" refers to technologies for automatically acquiring project-related data from diverse sources and organizing it into a single, integrated format.

[0365] "Means of detecting risks using generated models" refers to techniques that use AI models trained to analyze collected data to identify potential delays and obstacles in project progress.

[0366] "Means of analyzing users' emotional states and providing adaptive countermeasures" refers to technologies that analyze user feedback and behavioral data to evaluate emotions and then present specific support and countermeasures tailored to those states.

[0367] "A means of notifying and proposing countermeasures when a risk is detected" refers to a technology that quickly informs stakeholders of a risk when it is detected in a project and guides them toward appropriate countermeasures.

[0368] "Means of providing users with real-time information regarding project progress" refers to technologies that display information in real time so that users can immediately grasp the current status of the project and future risks.

[0369] The system of this invention is designed to support project management and consists mainly of a server, terminals, and users.

[0370] The server has the ability to automatically collect data from project management tools, email management systems, and various sensor systems. This data includes task progress, team conversations, and information about the work environment. After collection, the server preprocesses the data and converts it into a format suitable for analysis. This process uses Pandas as data processing software and Azure as the cloud service provider.

[0371] Next, the server analyzes the integrated data using a trained multimodal generative AI model. This AI model has the ability to process different data formats simultaneously to identify project delay risks and budget overrun risks. PyTorch is used for the analysis, and TensorFlow can also be utilized as needed. This allows the server to identify potential risks early and facilitate responses.

[0372] Furthermore, the system incorporates an emotion analysis function that evaluates the user's emotional state based on user feedback and behavioral data. Based on this information, it adjusts risk management measures for the user and provides appropriate support as needed. As an example of this emotion analysis function, if a user is determined to be in a high-stress state, the user will be offered suggestions for stress reduction.

[0373] When a risk is detected, an AI chatbot on the server notifies relevant stakeholders and provides tailored suggestions based on sentiment analysis. Email and chat tools are used as notification methods. For example, if a project member is experiencing stress, appropriate break times or reallocation of work resources will be suggested.

[0374] The device displays project risk information and recommended countermeasures to the user through a dashboard. This allows the user to make decisions based on the provided information and quickly take measures to improve the project.

[0375] For example, if an AI model detects that many workers are under high stress in a construction project, the app may automatically notify the project manager and suggest setting break times and optimizing work resources to reduce stress.

[0376] Examples of prompts to input into the generating AI model include: "Please suggest the main risks in the current construction project and specific measures to mitigate them."

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The server automatically collects data from project management tools, email management systems, and sensor systems. The input is digital data from each source, and the output is an integrated dataset. The server centralizes the collected data using Pandas and filters out unnecessary data as needed.

[0380] Step 2:

[0381] The server preprocesses the integrated dataset and converts it into a format suitable for the generative AI model. The input to this process is a unified dataset, and the output is data formatted for model analysis. This includes specific actions such as data normalization and missing value imputation.

[0382] Step 3:

[0383] The server uses a multimodal generative AI model trained with PyTorch to analyze the formatted data. The input is pre-processed data, and the output is the risk detection result. Through this analysis, potential issues such as project delay risks and budget overruns are identified.

[0384] Step 4:

[0385] The server evaluates the user's emotional state based on user feedback and behavioral data. The input to this process is user-related data, and the output is an evaluation of the user's emotional state. Natural language processing and pattern recognition are performed using an emotion analysis engine.

[0386] Step 5:

[0387] When a risk is detected, the server proposes adaptively adjusted risk mitigation measures based on the emotional state and notifies relevant parties via an AI chatbot. The inputs are the risk detection results and the emotional state assessment results, while the output consists of the proposed measures and a notification message. Specific actions include generating notification emails and chat messages.

[0388] Step 6:

[0389] The terminal displays project risk information and recommended countermeasures to the user through a dashboard. The input for this process is notification data from the server, and the output is visual information provided to the user. The terminal visualizes the data and generates graphs and charts to help the user easily understand the situation.

[0390] Step 7:

[0391] Users decide on actions for the project based on the information provided on the dashboard. The input for this process is the visualized information displayed on the terminal, and the output is the specific actions taken by the user. Users adjust the project plan according to the suggestions, leading to more effective management.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] [Third Embodiment]

[0396] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0397] 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.

[0398] 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).

[0399] 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.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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".

[0408] As an embodiment of the present invention, we describe an information system that monitors the progress of a project in real time and predicts delay risks. This system consists of a server, terminals, and users.

[0409] First, the server automatically collects data from multiple sources, such as project management tools, email servers, and IoT sensor systems. This functionality is achieved using APIs and IMAP protocols, allowing necessary data to be accumulated without interrupting the daily flow of information. For example, it periodically retrieves the progress of tasks in ongoing projects and the content of email communications.

[0410] Next, the collected data is integrated on the server. The ETL (Extract, Transform, Load) process is used to convert data acquired in different formats into a unified analysis format. During this process, missing data values ​​are imputed and outliers are detected, resulting in a highly accurate dataset.

[0411] Subsequently, the server uses this dataset to perform risk analysis using a trained multimodal AI model. The model simultaneously analyzes different data formats (such as text and numerical data) to detect and evaluate delay risks and budget anomalies in real time. For example, it can process all data to detect delay risks due to excessive resource consumption in a specific project.

[0412] If a risk is detected, an AI chatbot on the server immediately notifies relevant parties. This includes sending messages via email or chat tools to prompt users to take necessary actions. The AI ​​also supports rapid decision-making by including optimal countermeasures as suggestions. In specific cases, concrete suggestions may be provided, such as "reconsider resource allocation and adjust the priority of related tasks."

[0413] Ultimately, the device visualizes risk information for the user through a dashboard. Here, the user can review the overall project picture and decide on specific actions based on the suggested countermeasures. This system is expected to increase the project's success rate and reduce unnecessary costs.

[0414] The following describes the processing flow.

[0415] Step 1:

[0416] The server automatically collects data from project management tools, email systems, and IoT sensors. It uses APIs and IMAP protocols to retrieve task progress information, communication history, and environmental data.

[0417] Step 2:

[0418] The server integrates the collected data for centralized management. To handle different data formats (e.g., JSON, CSV, stream data), it performs necessary data transformations through an ETL process and stores the data in a database.

[0419] Step 3:

[0420] The server preprocesses the integrated data. It improves the reliability of the analysis by imputing missing values ​​and identifying and appropriately handling outliers.

[0421] Step 4:

[0422] The server inputs the prepared data into the AI ​​model and performs a risk analysis. The model specializes in analyzing multimodal data and generates a score that assesses the risk of project delays and budget overruns.

[0423] Step 5:

[0424] The server determines the project's risk level based on the analysis results and updates the information on the dashboard.

[0425] Step 6:

[0426] The AI ​​chatbot (on the server) notifies relevant parties of detected risks. For example, it provides information via email or chat tools so that users can quickly recognize the risks.

[0427] Step 7:

[0428] The AI ​​chatbot will offer specific countermeasures for risks, including advice on reallocating resources and changing task priorities based on the current situation.

[0429] Step 8:

[0430] The device displays risk information and suggested countermeasures to the user in a dashboard format. Based on this, the user makes decisions and plans specific actions.

[0431] Step 9:

[0432] Based on the system's suggestions, the user takes necessary actions (e.g., scheduling meetings with stakeholders or rescheduling tasks).

[0433] (Example 1)

[0434] 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."

[0435] In project management, it is crucial to monitor progress and resource usage in real time and to detect potential delays and budget anomalies early. However, traditional methods often involve manual information gathering and analysis, which is time-consuming and prone to human error. This makes timely risk response difficult and contributes to a lower project success rate. Therefore, there is a need for a system that manages risks efficiently and accurately and proposes countermeasures quickly.

[0436] 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.

[0437] In this invention, the server includes means for automatically acquiring and integrating information from a data source, means for analyzing risks using a trained multiform analysis model, and means for notifying when a risk is detected and generating action plans. This makes it possible to detect delay risks and budget anomalies in a project in real time and to quickly present appropriate countermeasures.

[0438] "Data source" refers to systems and devices that provide information, such as project management tools, email servers, and IoT sensors.

[0439] "Integration" is the process of converting data obtained from different formats and media into a format that allows for consistent analysis, and then aggregating it.

[0440] A "multiform analysis model" refers to a pre-trained generative AI model that can simultaneously analyze data in different formats (e.g., text data and numerical data).

[0441] Analyzing "risk" involves processing and analyzing data to identify and evaluate potential problems such as project delays and budget anomalies.

[0442] "Notification" refers to the act of communicating information or warnings to relevant parties, and specifically includes sending messages via email or chat tools.

[0443] "Generating action plans" is the process of proposing feasible countermeasures and improvement measures for the risks that have been identified.

[0444] "Visualization" refers to the process of visually displaying data and analysis results so that users can easily understand them and make decisions.

[0445] As an embodiment of the present invention, a real-time risk analysis system for project management will be described. This system consists of a server, terminals, and users.

[0446] The server is responsible for automatically acquiring and integrating information. Data sources include project management tools, email servers, and IoT sensors, and standard communication methods such as APIs and IMAP protocols are used to collect data from these sources. The server executes an ETL (Extract, Transform, Load) process to unify data formats, detect anomalies, and perform corrections to generate a dataset suitable for analysis.

[0447] The generated dataset is analyzed in real time by a pre-trained multiform analysis model. This model can process text and numerical data simultaneously and identify and evaluate risks such as project delays and budget anomalies. For example, a prompt such as "Project name: XYZ, Progress: 60%, Budget consumption: 80%, Please perform a risk assessment based on resource utilization and propose the optimal countermeasures" can be input to the AI ​​model, allowing for multi-stage analysis.

[0448] If a risk is detected, the server uses an AI chatbot to notify relevant parties. The notification, delivered via email or chat tools, includes the nature of the risk and suggested actions. Users can receive this information and take prompt action as needed.

[0449] This risk information is visualized on a dashboard on the device. Through the dashboard, users can intuitively understand the project's progress and risk assessment results, and consider specific actions based on the displayed information. This is expected to increase the project's success rate and reduce unnecessary costs.

[0450] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0451] Step 1:

[0452] The server collects data from project management tools, mail servers, and IoT sensors. Specifically, it retrieves data using APIs and IMAP protocols. As input, it receives project task progress information and communication records, and as output, these datasets are accumulated on the server.

[0453] Step 2:

[0454] The server integrates the collected data through an ETL process. Specifically, it converts data in different formats into a single analytical format, imputes missing values, and detects and corrects outliers. The input is the dataset obtained in step 1, and the output is a cleaned, unified dataset.

[0455] Step 3:

[0456] The server takes a unified dataset as input and assesses risk based on a trained multiform analysis model. Specifically, it uses a generative AI model to execute prompt statements and perform risk assessments. For example, it might present a prompt statement such as "Assess the risk of project progress at 60% and budget consumption at 80%", and the output would be an assessment of delay risk and budget anomalies.

[0457] Step 4:

[0458] Based on the assessment results, the server uses an AI chatbot to send risk notifications to relevant parties. Specifically, it notifies them of the risk and proposed countermeasures via email or chat tools. The input is the risk assessment results from step 3, and the output is a notification message which is then distributed to the relevant parties.

[0459] Step 5:

[0460] The device visualizes risk information for the user on a dashboard. Specifically, it visually displays the risk assessment results, allowing users to intuitively understand the project's progress. The input is the notification content from step 4, and the output is graphs and risk indicators displayed on the dashboard.

[0461] (Application Example 1)

[0462] 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."

[0463] Construction projects often face unforeseen risks, delays, and cost overruns. These situations are major obstacles to project success. Therefore, an efficient system is needed to monitor project progress in real time and to quickly identify and address risks.

[0464] 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.

[0465] In this invention, the server includes a device for automatically collecting and integrating data, a device for evaluating risks using a trained model, and a device for notifying and providing countermeasures when a risk is recognized. This enables real-time monitoring of progress within a construction project and rapid detection and response to risks.

[0466] "Data" is a collection of information that forms the basis for project progress and risk assessment.

[0467] A "model" is a computational method trained to analyze collected data and assess risk.

[0468] "Risk" refers to factors that indicate the possibility of undesirable outcomes occurring, such as project delays or cost overruns.

[0469] "Notification" refers to a means of quickly communicating information to relevant parties when a risk is detected.

[0470] "Countermeasures" refer to specific actions proposed to address risks and ensure the smooth progress of the project.

[0471] A "device" is a physical or virtual mechanism used to collect, analyze, and notify data.

[0472] A "trained model" is an AI model that learns from a large amount of data tailored to a specific purpose and can perform risk assessments.

[0473] In the system for implementing this invention, a server plays a central role. The server first automatically collects sensor data from construction sites and information from project management tools. This data is sent to the server via the Flask API using Python. Data integration is performed using an ETL process with Apache NiFi, generating a dataset in a unified format.

[0474] The terminals specifically refer to smartphones and smart glasses, and serve as interfaces for users to check project progress and risk analysis results. Data is transmitted from the server to the terminals and displayed on the dashboard in real time.

[0475] The pre-trained AI model running on the server is built with PyTorch and analyzes the collected data. The model is multimodal and can process text and numerical data simultaneously. If a risk is detected, the AI ​​chatbot notifies relevant parties via Flask and proposes specific countermeasures.

[0476] As a concrete example, if there is a possibility that the foundation work of a building at a construction site may be delayed due to weather conditions, the server analyzes weather data and progress data to assess the risk. Based on this, the AI ​​model makes specific suggestions, such as "plan to concentrate heavy machinery use on sunny days." This suggestion is immediately notified to the project manager via a chat tool.

[0477] Examples of prompt statements are as follows:

[0478] "Project Name: Bridge Construction, Current Progress: 60%, Unexpected Weather Changes: Heavy Rain, Required Resources: Heavy Machinery, What is the optimal solution you would propose?"

[0479] In this way, the system supports the efficient progress of projects by enabling servers, terminals, and users to work together, share information in real time, and manage risks.

[0480] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0481] Step 1:

[0482] The server receives data collected from IoT sensors at construction sites and progress data from project management tools. The input consists of various data formats obtained from each data source. The server converts this data into a unified format and extracts the necessary information. During this process, missing data values ​​are imputed, and anomalies are detected and corrected.

[0483] Step 2:

[0484] The server uses Apache NiFi to process the data through an ETL process, generating a formatted dataset. The input is the data integrated in step 1, and the output is an analyzable dataset suitable for AI models. Specifically, the data is rearranged along a time axis, and the formatting of each item is standardized.

[0485] Step 3:

[0486] The server inputs the formatted dataset into a generative AI model trained with PyTorch to analyze the risks. The input is a unified dataset, and the output is an assessment of potential risks in the project. The model comprehensively analyzes various data to estimate the risk of delays and potential cost overruns.

[0487] Step 4:

[0488] If a risk is detected, the server activates an AI chatbot via Flask to notify relevant parties. The input is the analysis results from step 3, and the output is risk information and specific countermeasures. The server sends this information via email or chat tools to prompt action from the project manager.

[0489] Step 5:

[0490] Users access information transmitted from the server via a dashboard using devices such as smartphones or smart glasses. Inputs include risk information and suggested countermeasures, while output is a real-time visualization of the project status. Based on this, users make decisions and take specific actions to adjust the project plan as needed.

[0491] 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.

[0492] As an embodiment of the present invention, we describe an information system that monitors project progress in real time, predicts delay risks, and provides adaptive support that takes user emotions into consideration. This system mainly consists of a server, terminals, and users.

[0493] First, the server automatically collects and integrates data from project management tools, email servers, and sensor systems. This centralizes task progress, team communication, and environmental data. After collecting the data, the server preprocesses it and formats it so that it is suitable for supplying to AI models.

[0494] Next, the server analyzes this integrated data using a trained multimodal AI model. This model has the ability to process different data formats simultaneously and detect project delays and budget risks. This allows for early detection of potential risks and prompts for action.

[0495] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the user's emotional state based on user feedback and behavioral data, and adjusts risk mitigation measures based on this analysis. For example, if the emotion engine determines that a user is in a high-stress state, the user may receive suggestions for measures to alleviate that stress. This reduces the user's mental burden and enables more effective project management.

[0496] When a risk is detected, an AI chatbot on the server notifies relevant parties and presents suggestions adjusted by an emotion engine. Notifications are sent via email or chat tools, providing an environment for immediate response. For example, it might suggest appropriate break times or resource reallocation to project members who are experiencing stress.

[0497] Ultimately, the terminal displays risk information and recommended countermeasures to the user via a dashboard. Based on this information, the user can decide on actions and implement measures to improve the project. The implementation of this system is expected to improve the accuracy and efficiency of project management, maximizing results.

[0498] The following describes the processing flow.

[0499] Step 1:

[0500] The server automatically collects data from project management tools, email systems, and sensor systems. This includes retrieving task progress, email communications, and environmental data from sensors by making API calls and using the IMAP protocol.

[0501] Step 2:

[0502] The server integrates the collected data. This process involves converting data in different formats (e.g., CSV files, JSON objects, real-time stream data) and storing it in a unified database. When data loss or anomalies are detected, appropriate completion or correction processes are performed.

[0503] Step 3:

[0504] The server supplies integrated data to the AI ​​model to perform risk assessments. The multimodal AI model uses this data to evaluate project delay risks and budget risks and generates a risk score for each project.

[0505] Step 4:

[0506] The server runs an emotion engine to analyze the user's emotional state. It uses email text analysis and user feedback data to determine the user's emotions and stress level.

[0507] Step 5:

[0508] The server combines risk assessment results with user sentiment data to design optimized risk mitigation strategies. For example, it might suggest prioritizing tasks or reallocating resources to teams with high-stress users.

[0509] Step 6:

[0510] The AI ​​chatbot (on the server) notifies relevant parties of the assessed risks and countermeasures. Notifications are sent via email or chat applications, enabling a rapid response.

[0511] Step 7:

[0512] The device displays a dashboard to the user, providing a visual overview of project risk information and proposed countermeasures. Based on this, the user plans the necessary actions and communicates with team members.

[0513] Step 8:

[0514] Users utilize the information on the dashboard to implement suggested measures. These actions include scheduling meetings, adjusting break times, and rescheduling tasks, contributing to project optimization.

[0515] (Example 2)

[0516] 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."

[0517] In project progress management and risk assessment, it is essential to collect and integrate accurate information in real time to identify potential problems early and take countermeasures. However, conventional systems have limitations in integrating information, analyzing diverse data formats, and providing responses that take emotional states into account. As a result, immediate action to prevent project delays and cost overruns has been difficult.

[0518] 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.

[0519] In this invention, the server includes means for automatically collecting and integrating information, means for preprocessing and formatting the collected information for analysis, means for detecting risks using an analyzable model of the generated data in various formats, means for analyzing the user's emotional state and adjusting suggestions based on that, and means for notifying the user when a risk is detected and proposing adjusted countermeasures. This enables real-time monitoring of project progress and potential risks, and allows for the provision of appropriate countermeasures based on the user's emotional state.

[0520] "Means for automatically collecting and integrating information" refers to a system in which a server acquires data from various information management systems and centrally consolidates this data.

[0521] "Means for preprocessing collected information and shaping it for analysis" refers to a mechanism that cleans and converts the format of data acquired by a server to make it easier to analyze.

[0522] "A means of detecting risk using a model capable of analyzing diverse data formats" refers to a mechanism that uses a trained code sequence model to analyze data in different formats and identify potential risks.

[0523] "A means of analyzing the user's emotional state and adjusting suggestions based on that" refers to a system where the server analyzes user feedback and behavioral data to evaluate the emotional state and then changes the content of risk mitigation measures accordingly.

[0524] "A means of notifying when a risk is detected and proposing adjusted countermeasures" refers to a system in which the server quickly notifies relevant parties of the discovered risk and presents adaptive countermeasures that take into account emotional states.

[0525] This invention is an information system that streamlines project management and enables early detection of risks. This system primarily consists of a server, terminals, and users.

[0526] The server automatically collects and integrates data from information management tools, communication systems, and environmental monitoring sensors. Specifically, it uses common database software in project management tools to aggregate data from mail servers and sensors and saves it in JSON or CSV format.

[0527] The collected data is preprocessed using programming languages ​​such as Python and R to prepare it for analysis. The server then uses a pre-trained multimodal generative AI model to analyze the data in multiple formats. This model utilizes natural language processing libraries (e.g., TensorFlow) to identify potential delays and budget overruns.

[0528] Furthermore, the server incorporates an emotion engine that analyzes user email feedback and digital activity to understand the user's emotional state. Based on this, the system adjusts risk mitigation measures and suggests stress relief measures if the user is experiencing high stress levels.

[0529] The device displays risk information and recommended countermeasures to the user through a dashboard, allowing the user to decide on specific actions. The dashboard displays real-time graphs and heatmaps, allowing users to visually check the degree of risk and progress.

[0530] For example, suppose one member of an IT development project falls behind on a task. In this case, the system uses an AI model to immediately detect the risk of delay, and if the emotion engine detects that member is stressed, it suggests an appropriate break.

[0531] By utilizing this system, users can gain a highly accurate understanding of project progress and risks, enabling more effective project management.

[0532] The following are examples of prompt statements to be input into the generative AI model:

[0533] "Analyze the current status of the ongoing 'New Product Development' project and predict the risks of delays and budget overruns. Also, consider appropriate support measures based on the emotional state of the team members."

[0534] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0535] Step 1:

[0536] The server initiates the process of collecting and integrating information. Specifically, it retrieves data from project management systems, communication systems, and sensor clusters via APIs. It accepts project task data, email sending and receiving logs, and environmental sensor data as input. This data is then stored as an integrated dataset in JSON or CSV format.

[0537] Step 2:

[0538] The server preprocesses the collected information. Specifically, it uses a Python script to perform processes such as noise reduction and missing value imputation, and to standardize the data format. The input is the dataset integrated in step 1, and the output is a clean, analyzable, standardized dataset.

[0539] Step 3:

[0540] The server leverages a generative AI model to analyze the preprocessed data. Here, a trained multimodal AI model is used to analyze different data formats simultaneously. The input is the standardized dataset created in step 2, and the output is the results of the delay risk and budget overrun risk assessment for each task.

[0541] Step 4:

[0542] The server uses an emotion engine to analyze user feedback and behavior and evaluate their emotional state. Inputs are user behavioral data such as email content and keystroke logs, and outputs are quantified results such as stress levels and satisfaction ratings.

[0543] Step 5:

[0544] The AI ​​chatbot on the server notifies relevant parties when a risk is detected. This utilizes notification functions via email and chat applications. The input consists of the risk assessment results from Step 3 and the sentiment assessment results from Step 4, while the output is a notification message including specific countermeasures.

[0545] Step 6:

[0546] The device visually displays risk information and recommended countermeasures to the user on a dashboard. Input is notification data from the server, and output is information presented to the user as risk trend graphs and specific improvement action plans.

[0547] (Application Example 2)

[0548] 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."

[0549] In modern project management, real-time monitoring of progress and risk management are essential. However, especially in complex and diverse projects such as construction, centralized information management and early detection of delay risks are often difficult. Furthermore, the emotional states of individual project members also affect project progress, but there is a lack of means to properly monitor and effectively address these factors. Therefore, a new system is needed to overcome these challenges and ensure smooth project progress.

[0550] 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.

[0551] In this invention, the server includes means for automatically collecting and integrating information, means for detecting risks using the generated model, and means for analyzing the user's emotional state and providing adaptive countermeasures. This makes it possible to detect project risks early and provide adaptive support tailored to the emotional state of individual project members.

[0552] "Means for automatically collecting and integrating information" refers to technologies for automatically acquiring project-related data from diverse sources and organizing it into a single, integrated format.

[0553] "Means of detecting risks using generated models" refers to techniques that use AI models trained to analyze collected data to identify potential delays and obstacles in project progress.

[0554] "Means of analyzing users' emotional states and providing adaptive countermeasures" refers to technologies that analyze user feedback and behavioral data to evaluate emotions and then present specific support and countermeasures tailored to those states.

[0555] "A means of notifying and proposing countermeasures when a risk is detected" refers to a technology that quickly informs stakeholders of a risk when it is detected in a project and guides them toward appropriate countermeasures.

[0556] "Means of providing users with real-time information regarding project progress" refers to technologies that display information in real time so that users can immediately grasp the current status of the project and future risks.

[0557] The system of this invention is designed to support project management and consists mainly of a server, terminals, and users.

[0558] The server has the ability to automatically collect data from project management tools, email management systems, and various sensor systems. This data includes task progress, team conversations, and information about the work environment. After collection, the server preprocesses the data and converts it into a format suitable for analysis. This process uses Pandas as data processing software and Azure as the cloud service provider.

[0559] Next, the server analyzes the integrated data using a trained multimodal generative AI model. This AI model has the ability to process different data formats simultaneously to identify project delay risks and budget overrun risks. PyTorch is used for the analysis, and TensorFlow can also be utilized as needed. This allows the server to identify potential risks early and facilitate responses.

[0560] Furthermore, the system incorporates an emotion analysis function that evaluates the user's emotional state based on user feedback and behavioral data. Based on this information, it adjusts risk management measures for the user and provides appropriate support as needed. As an example of this emotion analysis function, if a user is determined to be in a high-stress state, the user will be offered suggestions for stress reduction.

[0561] When a risk is detected, an AI chatbot on the server notifies relevant stakeholders and provides tailored suggestions based on sentiment analysis. Email and chat tools are used as notification methods. For example, if a project member is experiencing stress, appropriate break times or reallocation of work resources will be suggested.

[0562] The device displays project risk information and recommended countermeasures to the user through a dashboard. This allows the user to make decisions based on the provided information and quickly take measures to improve the project.

[0563] For example, if an AI model detects that many workers are under high stress in a construction project, the app may automatically notify the project manager and suggest setting break times and optimizing work resources to reduce stress.

[0564] Examples of prompts to input into the generating AI model include: "Please suggest the main risks in the current construction project and specific measures to mitigate them."

[0565] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0566] Step 1:

[0567] The server automatically collects data from project management tools, email management systems, and sensor systems. The input is digital data from each source, and the output is an integrated dataset. The server centralizes the collected data using Pandas and filters out unnecessary data as needed.

[0568] Step 2:

[0569] The server preprocesses the integrated dataset and converts it into a format suitable for the generative AI model. The input to this process is a unified dataset, and the output is data formatted for model analysis. This includes specific actions such as data normalization and missing value imputation.

[0570] Step 3:

[0571] The server uses a multimodal generative AI model trained with PyTorch to analyze the formatted data. The input is pre-processed data, and the output is the risk detection result. Through this analysis, potential issues such as project delay risks and budget overruns are identified.

[0572] Step 4:

[0573] The server evaluates the user's emotional state based on user feedback and behavioral data. The input to this process is user-related data, and the output is an evaluation of the user's emotional state. Natural language processing and pattern recognition are performed using an emotion analysis engine.

[0574] Step 5:

[0575] When a risk is detected, the server proposes adaptively adjusted risk mitigation measures based on the emotional state and notifies relevant parties via an AI chatbot. The inputs are the risk detection results and the emotional state assessment results, while the output consists of the proposed measures and a notification message. Specific actions include generating notification emails and chat messages.

[0576] Step 6:

[0577] The terminal displays project risk information and recommended countermeasures to the user through a dashboard. The input for this process is notification data from the server, and the output is visual information provided to the user. The terminal visualizes the data and generates graphs and charts to help the user easily understand the situation.

[0578] Step 7:

[0579] Users decide on actions for the project based on the information provided on the dashboard. The input for this process is the visualized information displayed on the terminal, and the output is the specific actions taken by the user. Users adjust the project plan according to the suggestions, leading to more effective management.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] [Fourth Embodiment]

[0584] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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".

[0597] As an embodiment of the present invention, we describe an information system that monitors the progress of a project in real time and predicts delay risks. This system consists of a server, terminals, and users.

[0598] First, the server automatically collects data from multiple sources, such as project management tools, email servers, and IoT sensor systems. This functionality is achieved using APIs and IMAP protocols, allowing necessary data to be accumulated without interrupting the daily flow of information. For example, it periodically retrieves the progress of tasks in ongoing projects and the content of email communications.

[0599] Next, the collected data is integrated on the server. The ETL (Extract, Transform, Load) process is used to convert data acquired in different formats into a unified analysis format. During this process, missing data values ​​are imputed and outliers are detected, resulting in a highly accurate dataset.

[0600] Subsequently, the server uses this dataset to perform risk analysis using a trained multimodal AI model. The model simultaneously analyzes different data formats (such as text and numerical data) to detect and evaluate delay risks and budget anomalies in real time. For example, it can process all data to detect delay risks due to excessive resource consumption in a specific project.

[0601] If a risk is detected, an AI chatbot on the server immediately notifies relevant parties. This includes sending messages via email or chat tools to prompt users to take necessary actions. The AI ​​also supports rapid decision-making by including optimal countermeasures as suggestions. In specific cases, concrete suggestions may be provided, such as "reconsider resource allocation and adjust the priority of related tasks."

[0602] Ultimately, the device visualizes risk information for the user through a dashboard. Here, the user can review the overall project picture and decide on specific actions based on the suggested countermeasures. This system is expected to increase the project's success rate and reduce unnecessary costs.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] The server automatically collects data from project management tools, email systems, and IoT sensors. It uses APIs and IMAP protocols to retrieve task progress information, communication history, and environmental data.

[0606] Step 2:

[0607] The server integrates the collected data for centralized management. To handle different data formats (e.g., JSON, CSV, stream data), it performs necessary data transformations through an ETL process and stores the data in a database.

[0608] Step 3:

[0609] The server preprocesses the integrated data. It improves the reliability of the analysis by imputing missing values ​​and identifying and appropriately handling outliers.

[0610] Step 4:

[0611] The server inputs the prepared data into the AI ​​model and performs a risk analysis. The model specializes in analyzing multimodal data and generates a score that assesses the risk of project delays and budget overruns.

[0612] Step 5:

[0613] The server determines the project's risk level based on the analysis results and updates the information on the dashboard.

[0614] Step 6:

[0615] The AI ​​chatbot (on the server) notifies relevant parties of detected risks. For example, it provides information via email or chat tools so that users can quickly recognize the risks.

[0616] Step 7:

[0617] The AI ​​chatbot will offer specific countermeasures for risks, including advice on reallocating resources and changing task priorities based on the current situation.

[0618] Step 8:

[0619] The device displays risk information and suggested countermeasures to the user in a dashboard format. Based on this, the user makes decisions and plans specific actions.

[0620] Step 9:

[0621] Based on the system's suggestions, the user takes necessary actions (e.g., scheduling meetings with stakeholders or rescheduling tasks).

[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, it is crucial to monitor progress and resource usage in real time and to detect potential delays and budget anomalies early. However, traditional methods often involve manual information gathering and analysis, which is time-consuming and prone to human error. This makes timely risk response difficult and contributes to a lower project success rate. Therefore, there is a need for a system that manages risks efficiently and accurately and proposes countermeasures quickly.

[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 automatically acquiring and integrating information from a data source, means for analyzing risks using a trained multiform analysis model, and means for notifying when a risk is detected and generating action plans. This makes it possible to detect delay risks and budget anomalies in a project in real time and to quickly present appropriate countermeasures.

[0627] "Data source" refers to systems and devices that provide information, such as project management tools, email servers, and IoT sensors.

[0628] "Integration" is the process of converting data obtained from different formats and media into a format that allows for consistent analysis, and then aggregating it.

[0629] A "multiform analysis model" refers to a pre-trained generative AI model that can simultaneously analyze data in different formats (e.g., text data and numerical data).

[0630] Analyzing "risk" involves processing and analyzing data to identify and evaluate potential problems such as project delays and budget anomalies.

[0631] "Notification" refers to the act of communicating information or warnings to relevant parties, and specifically includes sending messages via email or chat tools.

[0632] "Generating action plans" is the process of proposing feasible countermeasures and improvement measures for the risks that have been identified.

[0633] "Visualization" refers to the process of visually displaying data and analysis results so that users can easily understand them and make decisions.

[0634] As an embodiment of the present invention, a real-time risk analysis system for project management will be described. This system consists of a server, terminals, and users.

[0635] The server is responsible for automatically acquiring and integrating information. Data sources include project management tools, email servers, and IoT sensors, and standard communication methods such as APIs and IMAP protocols are used to collect data from these sources. The server executes an ETL (Extract, Transform, Load) process to unify data formats, detect anomalies, and perform corrections to generate a dataset suitable for analysis.

[0636] The generated dataset is analyzed in real time by a pre-trained multiform analysis model. This model can process text and numerical data simultaneously and identify and evaluate risks such as project delays and budget anomalies. For example, a prompt such as "Project name: XYZ, Progress: 60%, Budget consumption: 80%, Please perform a risk assessment based on resource utilization and propose the optimal countermeasures" can be input to the AI ​​model, allowing for multi-stage analysis.

[0637] If a risk is detected, the server uses an AI chatbot to notify relevant parties. The notification, delivered via email or chat tools, includes the nature of the risk and suggested actions. Users can receive this information and take prompt action as needed.

[0638] This risk information is visualized on a dashboard on the device. Through the dashboard, users can intuitively understand the project's progress and risk assessment results, and consider specific actions based on the displayed information. This is expected to increase the project's success rate and reduce unnecessary costs.

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

[0640] Step 1:

[0641] The server collects data from project management tools, mail servers, and IoT sensors. Specifically, it retrieves data using APIs and IMAP protocols. As input, it receives project task progress information and communication records, and as output, these datasets are accumulated on the server.

[0642] Step 2:

[0643] The server integrates the collected data through an ETL process. Specifically, it converts data in different formats into a single analytical format, imputes missing values, and detects and corrects outliers. The input is the dataset obtained in step 1, and the output is a cleaned, unified dataset.

[0644] Step 3:

[0645] The server takes a unified dataset as input and assesses risk based on a trained multiform analysis model. Specifically, it uses a generative AI model to execute prompt statements and perform risk assessments. For example, it might present a prompt statement such as "Assess the risk of project progress at 60% and budget consumption at 80%", and the output would be an assessment of delay risk and budget anomalies.

[0646] Step 4:

[0647] Based on the assessment results, the server uses an AI chatbot to send risk notifications to relevant parties. Specifically, it notifies them of the risk and proposed countermeasures via email or chat tools. The input is the risk assessment results from step 3, and the output is a notification message which is then distributed to the relevant parties.

[0648] Step 5:

[0649] The device visualizes risk information for the user on a dashboard. Specifically, it visually displays the risk assessment results, allowing users to intuitively understand the project's progress. The input is the notification content from step 4, and the output is graphs and risk indicators displayed on the dashboard.

[0650] (Application Example 1)

[0651] 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".

[0652] Construction projects often face unforeseen risks, delays, and cost overruns. These situations are major obstacles to project success. Therefore, an efficient system is needed to monitor project progress in real time and to quickly identify and address risks.

[0653] 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.

[0654] In this invention, the server includes a device for automatically collecting and integrating data, a device for evaluating risks using a trained model, and a device for notifying and providing countermeasures when a risk is recognized. This enables real-time monitoring of progress within a construction project and rapid detection and response to risks.

[0655] "Data" is a collection of information that forms the basis for project progress and risk assessment.

[0656] A "model" is a computational method trained to analyze collected data and assess risk.

[0657] "Risk" refers to factors that indicate the possibility of undesirable outcomes occurring, such as project delays or cost overruns.

[0658] "Notification" refers to a means of quickly communicating information to relevant parties when a risk is detected.

[0659] "Countermeasures" refer to specific actions proposed to address risks and ensure the smooth progress of the project.

[0660] A "device" is a physical or virtual mechanism used to collect, analyze, and notify data.

[0661] A "trained model" is an AI model that learns from a large amount of data tailored to a specific purpose and can perform risk assessments.

[0662] In the system for implementing this invention, a server plays a central role. The server first automatically collects sensor data from construction sites and information from project management tools. This data is sent to the server via the Flask API using Python. Data integration is performed using an ETL process with Apache NiFi, generating a dataset in a unified format.

[0663] The terminals specifically refer to smartphones and smart glasses, and serve as interfaces for users to check project progress and risk analysis results. Data is transmitted from the server to the terminals and displayed on the dashboard in real time.

[0664] The pre-trained AI model running on the server is built with PyTorch and analyzes the collected data. The model is multimodal and can process text and numerical data simultaneously. If a risk is detected, the AI ​​chatbot notifies relevant parties via Flask and proposes specific countermeasures.

[0665] As a concrete example, if there is a possibility that the foundation work of a building at a construction site may be delayed due to weather conditions, the server analyzes weather data and progress data to assess the risk. Based on this, the AI ​​model makes specific suggestions, such as "plan to concentrate heavy machinery use on sunny days." This suggestion is immediately notified to the project manager via a chat tool.

[0666] Examples of prompt statements are as follows:

[0667] "Project Name: Bridge Construction, Current Progress: 60%, Unexpected Weather Changes: Heavy Rain, Required Resources: Heavy Machinery, What is the optimal solution you would propose?"

[0668] In this way, the system supports the efficient progress of projects by enabling servers, terminals, and users to work together, share information in real time, and manage risks.

[0669] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0670] Step 1:

[0671] The server receives data collected from IoT sensors at construction sites and progress data from project management tools. The input consists of various data formats obtained from each data source. The server converts this data into a unified format and extracts the necessary information. During this process, missing data values ​​are imputed, and anomalies are detected and corrected.

[0672] Step 2:

[0673] The server uses Apache NiFi to process the data through an ETL process, generating a formatted dataset. The input is the data integrated in step 1, and the output is an analyzable dataset suitable for AI models. Specifically, the data is rearranged along a time axis, and the formatting of each item is standardized.

[0674] Step 3:

[0675] The server inputs the formatted dataset into a generative AI model trained with PyTorch to analyze the risks. The input is a unified dataset, and the output is an assessment of potential risks in the project. The model comprehensively analyzes various data to estimate the risk of delays and potential cost overruns.

[0676] Step 4:

[0677] If a risk is detected, the server activates an AI chatbot via Flask to notify relevant parties. The input is the analysis results from step 3, and the output is risk information and specific countermeasures. The server sends this information via email or chat tools to prompt action from the project manager.

[0678] Step 5:

[0679] Users access information transmitted from the server via a dashboard using devices such as smartphones or smart glasses. Inputs include risk information and suggested countermeasures, while output is a real-time visualization of the project status. Based on this, users make decisions and take specific actions to adjust the project plan as needed.

[0680] 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.

[0681] As an embodiment of the present invention, we describe an information system that monitors project progress in real time, predicts delay risks, and provides adaptive support that takes user emotions into consideration. This system mainly consists of a server, terminals, and users.

[0682] First, the server automatically collects and integrates data from project management tools, email servers, and sensor systems. This centralizes task progress, team communication, and environmental data. After collecting the data, the server preprocesses it and formats it so that it is suitable for supplying to AI models.

[0683] Next, the server analyzes this integrated data using a trained multimodal AI model. This model has the ability to process different data formats simultaneously and detect project delays and budget risks. This allows for early detection of potential risks and prompts for action.

[0684] Furthermore, this system incorporates an emotion engine. The emotion engine analyzes the user's emotional state based on user feedback and behavioral data, and adjusts risk mitigation measures based on this analysis. For example, if the emotion engine determines that a user is in a high-stress state, the user may receive suggestions for measures to alleviate that stress. This reduces the user's mental burden and enables more effective project management.

[0685] When a risk is detected, an AI chatbot on the server notifies relevant parties and presents suggestions adjusted by an emotion engine. Notifications are sent via email or chat tools, providing an environment for immediate response. For example, it might suggest appropriate break times or resource reallocation to project members who are experiencing stress.

[0686] Ultimately, the terminal displays risk information and recommended countermeasures to the user via a dashboard. Based on this information, the user can decide on actions and implement measures to improve the project. The implementation of this system is expected to improve the accuracy and efficiency of project management, maximizing results.

[0687] The following describes the processing flow.

[0688] Step 1:

[0689] The server automatically collects data from project management tools, email systems, and sensor systems. This includes retrieving task progress, email communications, and environmental data from sensors by making API calls and using the IMAP protocol.

[0690] Step 2:

[0691] The server integrates the collected data. This process involves converting data in different formats (e.g., CSV files, JSON objects, real-time stream data) and storing it in a unified database. When data loss or anomalies are detected, appropriate completion or correction processes are performed.

[0692] Step 3:

[0693] The server supplies integrated data to the AI ​​model to perform risk assessments. The multimodal AI model uses this data to evaluate project delay risks and budget risks and generates a risk score for each project.

[0694] Step 4:

[0695] The server runs an emotion engine to analyze the user's emotional state. It uses email text analysis and user feedback data to determine the user's emotions and stress level.

[0696] Step 5:

[0697] The server combines risk assessment results with user sentiment data to design optimized risk mitigation strategies. For example, it might suggest prioritizing tasks or reallocating resources to teams with high-stress users.

[0698] Step 6:

[0699] The AI ​​chatbot (on the server) notifies relevant parties of the assessed risks and countermeasures. Notifications are sent via email or chat applications, enabling a rapid response.

[0700] Step 7:

[0701] The device displays a dashboard to the user, providing a visual overview of project risk information and proposed countermeasures. Based on this, the user plans the necessary actions and communicates with team members.

[0702] Step 8:

[0703] Users utilize the information on the dashboard to implement suggested measures. These actions include scheduling meetings, adjusting break times, and rescheduling tasks, contributing to project optimization.

[0704] (Example 2)

[0705] 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".

[0706] In project progress management and risk assessment, it is essential to collect and integrate accurate information in real time to identify potential problems early and take countermeasures. However, conventional systems have limitations in integrating information, analyzing diverse data formats, and providing responses that take emotional states into account. As a result, immediate action to prevent project delays and cost overruns has been difficult.

[0707] 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.

[0708] In this invention, the server includes means for automatically collecting and integrating information, means for preprocessing and formatting the collected information for analysis, means for detecting risks using an analyzable model of the generated data in various formats, means for analyzing the user's emotional state and adjusting suggestions based on that, and means for notifying the user when a risk is detected and proposing adjusted countermeasures. This enables real-time monitoring of project progress and potential risks, and allows for the provision of appropriate countermeasures based on the user's emotional state.

[0709] "Means for automatically collecting and integrating information" refers to a system in which a server acquires data from various information management systems and centrally consolidates this data.

[0710] "Means for preprocessing collected information and shaping it for analysis" refers to a mechanism that cleans and converts the format of data acquired by a server to make it easier to analyze.

[0711] "A means of detecting risk using a model capable of analyzing diverse data formats" refers to a mechanism that uses a trained code sequence model to analyze data in different formats and identify potential risks.

[0712] "A means of analyzing the user's emotional state and adjusting suggestions based on that" refers to a system where the server analyzes user feedback and behavioral data to evaluate the emotional state and then changes the content of risk mitigation measures accordingly.

[0713] "A means of notifying when a risk is detected and proposing adjusted countermeasures" refers to a system in which the server quickly notifies relevant parties of the discovered risk and presents adaptive countermeasures that take into account emotional states.

[0714] This invention is an information system that streamlines project management and enables early detection of risks. This system primarily consists of a server, terminals, and users.

[0715] The server automatically collects and integrates data from information management tools, communication systems, and environmental monitoring sensors. Specifically, it uses common database software in project management tools to aggregate data from mail servers and sensors and saves it in JSON or CSV format.

[0716] The collected data is preprocessed using programming languages ​​such as Python and R to prepare it for analysis. The server then uses a pre-trained multimodal generative AI model to analyze the data in multiple formats. This model utilizes natural language processing libraries (e.g., TensorFlow) to identify potential delays and budget overruns.

[0717] Furthermore, the server incorporates an emotion engine that analyzes user email feedback and digital activity to understand the user's emotional state. Based on this, the system adjusts risk mitigation measures and suggests stress relief measures if the user is experiencing high stress levels.

[0718] The device displays risk information and recommended countermeasures to the user through a dashboard, allowing the user to decide on specific actions. The dashboard displays real-time graphs and heatmaps, allowing users to visually check the degree of risk and progress.

[0719] For example, suppose one member of an IT development project falls behind on a task. In this case, the system uses an AI model to immediately detect the risk of delay, and if the emotion engine detects that member is stressed, it suggests an appropriate break.

[0720] By utilizing this system, users can gain a highly accurate understanding of project progress and risks, enabling more effective project management.

[0721] The following are examples of prompt statements to be input into the generative AI model:

[0722] "Analyze the current status of the ongoing 'New Product Development' project and predict the risks of delays and budget overruns. Also, consider appropriate support measures based on the emotional state of the team members."

[0723] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0724] Step 1:

[0725] The server initiates the process of collecting and integrating information. Specifically, it retrieves data from project management systems, communication systems, and sensor clusters via APIs. It accepts project task data, email sending and receiving logs, and environmental sensor data as input. This data is then stored as an integrated dataset in JSON or CSV format.

[0726] Step 2:

[0727] The server preprocesses the collected information. Specifically, it uses a Python script to perform processes such as noise reduction and missing value imputation, and to standardize the data format. The input is the dataset integrated in step 1, and the output is a clean, analyzable, standardized dataset.

[0728] Step 3:

[0729] The server leverages a generative AI model to analyze the preprocessed data. Here, a trained multimodal AI model is used to analyze different data formats simultaneously. The input is the standardized dataset created in step 2, and the output is the results of the delay risk and budget overrun risk assessment for each task.

[0730] Step 4:

[0731] The server uses an emotion engine to analyze user feedback and behavior and evaluate their emotional state. Inputs are user behavioral data such as email content and keystroke logs, and outputs are quantified results such as stress levels and satisfaction ratings.

[0732] Step 5:

[0733] The AI ​​chatbot on the server notifies relevant parties when a risk is detected. This utilizes notification functions via email and chat applications. The input consists of the risk assessment results from Step 3 and the sentiment assessment results from Step 4, while the output is a notification message including specific countermeasures.

[0734] Step 6:

[0735] The device visually displays risk information and recommended countermeasures to the user on a dashboard. Input is notification data from the server, and output is information presented to the user as risk trend graphs and specific improvement action plans.

[0736] (Application Example 2)

[0737] 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".

[0738] In modern project management, real-time monitoring of progress and risk management are essential. However, especially in complex and diverse projects such as construction, centralized information management and early detection of delay risks are often difficult. Furthermore, the emotional states of individual project members also affect project progress, but there is a lack of means to properly monitor and effectively address these factors. Therefore, a new system is needed to overcome these challenges and ensure smooth project progress.

[0739] 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.

[0740] In this invention, the server includes means for automatically collecting and integrating information, means for detecting risks using the generated model, and means for analyzing the user's emotional state and providing adaptive countermeasures. This makes it possible to detect project risks early and provide adaptive support tailored to the emotional state of individual project members.

[0741] "Means for automatically collecting and integrating information" refers to technologies for automatically acquiring project-related data from diverse sources and organizing it into a single, integrated format.

[0742] "Means of detecting risks using generated models" refers to techniques that use AI models trained to analyze collected data to identify potential delays and obstacles in project progress.

[0743] "Means of analyzing users' emotional states and providing adaptive countermeasures" refers to technologies that analyze user feedback and behavioral data to evaluate emotions and then present specific support and countermeasures tailored to those states.

[0744] "A means of notifying and proposing countermeasures when a risk is detected" refers to a technology that quickly informs stakeholders of a risk when it is detected in a project and guides them toward appropriate countermeasures.

[0745] "Means of providing users with real-time information regarding project progress" refers to technologies that display information in real time so that users can immediately grasp the current status of the project and future risks.

[0746] The system of this invention is designed to support project management and consists mainly of a server, terminals, and users.

[0747] The server has the ability to automatically collect data from project management tools, email management systems, and various sensor systems. This data includes task progress, team conversations, and information about the work environment. After collection, the server preprocesses the data and converts it into a format suitable for analysis. This process uses Pandas as data processing software and Azure as the cloud service provider.

[0748] Next, the server analyzes the integrated data using a trained multimodal generative AI model. This AI model has the ability to process different data formats simultaneously to identify project delay risks and budget overrun risks. PyTorch is used for the analysis, and TensorFlow can also be utilized as needed. This allows the server to identify potential risks early and facilitate responses.

[0749] Furthermore, the system incorporates an emotion analysis function that evaluates the user's emotional state based on user feedback and behavioral data. Based on this information, it adjusts risk management measures for the user and provides appropriate support as needed. As an example of this emotion analysis function, if a user is determined to be in a high-stress state, the user will be offered suggestions for stress reduction.

[0750] When a risk is detected, an AI chatbot on the server notifies relevant stakeholders and provides tailored suggestions based on sentiment analysis. Email and chat tools are used as notification methods. For example, if a project member is experiencing stress, appropriate break times or reallocation of work resources will be suggested.

[0751] The device displays project risk information and recommended countermeasures to the user through a dashboard. This allows the user to make decisions based on the provided information and quickly take measures to improve the project.

[0752] For example, if an AI model detects that many workers are under high stress in a construction project, the app may automatically notify the project manager and suggest setting break times and optimizing work resources to reduce stress.

[0753] Examples of prompts to input into the generating AI model include: "Please suggest the main risks in the current construction project and specific measures to mitigate them."

[0754] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0755] Step 1:

[0756] The server automatically collects data from project management tools, email management systems, and sensor systems. The input is digital data from each source, and the output is an integrated dataset. The server centralizes the collected data using Pandas and filters out unnecessary data as needed.

[0757] Step 2:

[0758] The server preprocesses the integrated dataset and converts it into a format suitable for the generative AI model. The input to this process is a unified dataset, and the output is data formatted for model analysis. This includes specific actions such as data normalization and missing value imputation.

[0759] Step 3:

[0760] The server uses a multimodal generative AI model trained with PyTorch to analyze the formatted data. The input is pre-processed data, and the output is the risk detection result. Through this analysis, potential issues such as project delay risks and budget overruns are identified.

[0761] Step 4:

[0762] The server evaluates the user's emotional state based on user feedback and behavioral data. The input to this process is user-related data, and the output is an evaluation of the user's emotional state. Natural language processing and pattern recognition are performed using an emotion analysis engine.

[0763] Step 5:

[0764] When a risk is detected, the server proposes adaptively adjusted risk mitigation measures based on the emotional state and notifies relevant parties via an AI chatbot. The inputs are the risk detection results and the emotional state assessment results, while the output consists of the proposed measures and a notification message. Specific actions include generating notification emails and chat messages.

[0765] Step 6:

[0766] The terminal displays project risk information and recommended countermeasures to the user through a dashboard. The input for this process is notification data from the server, and the output is visual information provided to the user. The terminal visualizes the data and generates graphs and charts to help the user easily understand the situation.

[0767] Step 7:

[0768] Users decide on actions for the project based on the information provided on the dashboard. The input for this process is the visualized information displayed on the terminal, and the output is the specific actions taken by the user. Users adjust the project plan according to the suggestions, leading to more effective management.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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."

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] The following is further disclosed regarding the embodiments described above.

[0791] (Claim 1)

[0792] Means for automatically collecting and integrating information,

[0793] A means of detecting risk using the generated model,

[0794] A means of notifying when a risk is detected and proposing countermeasures,

[0795] A system that includes this.

[0796] (Claim 2)

[0797] The system according to claim 1, comprising a generated model and a language model trained to analyze data from multiple modals.

[0798] (Claim 3)

[0799] The system according to claim 1, further comprising means for visualizing risk information and prompting stakeholders to take action through proposals.

[0800] "Example 1"

[0801] (Claim 1)

[0802] A means of automatically acquiring and integrating information from data sources,

[0803] A means of analyzing risk using a pre-trained multiform analysis model,

[0804] A means of notifying when a risk is detected and generating a plan of action,

[0805] A means of visualizing risk information and action plans on the user's terminal,

[0806] A system that includes this.

[0807] (Claim 2)

[0808] The system according to claim 1, comprising a generative AI model trained to analyze information in different forms using a multiform analysis model.

[0809] (Claim 3)

[0810] The system according to claim 1, further comprising means for visualizing risk information and encouraging stakeholders to take action through action plans.

[0811] "Application Example 1"

[0812] (Claim 1)

[0813] A device for automatically collecting and integrating data,

[0814] A device that uses a trained model to assess risk,

[0815] A device that notifies and provides countermeasures when a risk is recognized,

[0816] A device that visually displays information and prompts relevant parties to take action,

[0817] A system that includes this.

[0818] (Claim 2)

[0819] The system according to claim 1, comprising a generated model, a language model trained to analyze data from multiple sources.

[0820] (Claim 3)

[0821] The system according to claim 1, which provides an indication of delay risk or cost overrun.

[0822] "Example 2 of combining an emotion engine"

[0823] (Claim 1)

[0824] Means for automatically collecting and integrating information,

[0825] A means for preprocessing and formatting the collected information for analysis,

[0826] A means of detecting risk using a model capable of analyzing the generated data in various formats,

[0827] A means of analyzing the user's emotional state and adjusting suggestions based on that,

[0828] A means of notifying when a risk is detected and proposing adjusted countermeasures,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, wherein the generated model includes a code sequence model trained to analyze data from multiple information formats.

[0832] (Claim 3)

[0833] The system according to claim 1, further comprising a means for visualizing risk information and prompting stakeholders to take action through proposals.

[0834] "Application example 2 when combining with an emotional engine"

[0835] (Claim 1)

[0836] Means for automatically collecting and integrating information,

[0837] A means of detecting risk using the generated model,

[0838] A means of analyzing the user's emotional state and providing adaptive countermeasures,

[0839] A means of notifying when a risk is detected and proposing countermeasures,

[0840] A means of providing users with real-time information regarding project progress,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, comprising a generated model and a language model trained to analyze data from multiple modals.

[0844] (Claim 3)

[0845] The system according to claim 1, further comprising means for visualizing risk information and prompting stakeholders to take action through suggestions based on the user's emotional state. [Explanation of Symbols]

[0846] 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 device for automatically collecting and integrating data, A device that uses a trained model to assess risk, A device that notifies and provides countermeasures when a risk is recognized, A device that visually displays information and prompts relevant parties to take action, A system that includes this.

2. The system according to claim 1, comprising a generated model, a language model trained to analyze data from multiple sources.

3. The system according to claim 1, which provides an indication of delay risk and cost overrun.

Images