system

Abstract

We provide the system. [Solution] In order to collect project progress information, a means of acquiring data from multiple data collection devices, A means of analyzing the acquired data in real time, A means of predicting risks associated with a specific task based on the analysis results, Means of providing notifications to stakeholders based on predictions, Means for providing a user interface for displaying notifications, A system that includes means for responding to user inquiries in real time.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Project management at a construction site is very complex and dynamic because multiple factors are intertwined. In particular, schedule management of the project, optimal allocation of resources, ensuring safety, and appropriate prediction of risks are required. However, it is difficult to integrally manage these elements in real time with current management methods, and as a result, waste of labor and materials and unexpected situations are likely to occur. In addition, rapid transmission of information and collection of feedback from the site are insufficient, often leading to delays in decision-making. There is a need for a system to improve such a situation and support efficient and safe project progress.

Means for Solving the Problems

[0005] This invention provides a system that comprehensively handles multiple factors related to project management. First, it collects real-time information from the project site from a data acquisition device and performs rapid data analysis based on this information. It has a means of predicting risks related to specific tasks using the results of this analysis. Furthermore, it notifies relevant parties of the predicted risk information, enabling a rapid response. It also provides a user-accessible user interface, allowing for information confirmation and real-time responses to inquiries. As a result, it enables precise monitoring and management of project progress, realizing a system that improves the success rate of projects while reducing waste.

[0006] A "data acquisition device" is a device, such as a sensor or drone, used to acquire various types of data from the field.

[0007] "Means of acquiring data" refers to the processes and technologies used to collect data from data acquisition devices and to process that data.

[0008] "Methods for real-time analysis" refer to processes and technologies that allow for the instantaneous analysis of acquired data, enabling a rapid understanding of the current situation and problems.

[0009] "Means of predicting risk" are techniques for inferring future dangers and challenges based on past data and current circumstances.

[0010] "Means of providing notifications" refers to technologies for communicating information and warnings based on analysis results to relevant parties.

[0011] A "user interface" is a screen or operating area that allows a system and a user to exchange information.

[0012] "Means of real-time response" refers to processes and technologies that allow for immediate responses and information provision in response to user inquiries and requests. [Brief explanation of the drawing]

[0013] [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]

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] The system of this invention is designed to efficiently manage projects at construction sites. The specific configuration of the system's operation is described below.

[0035] First, the server acquires data such as temperature, humidity, worker location information, and video from multiple sensors and drones installed on-site in real time. This data is used not only to monitor project progress but also to monitor safety and resource usage.

[0036] Next, the server analyzes this data. A combination of BIM (Building Information Modeling) data and sensor information is used to assess progress. This analysis detects discrepancies between the plan and actual progress. The server also uses machine learning models to learn from past data and predict future risks and problems. These predictions serve as important guidelines for preventing accidents on-site.

[0037] If the analysis identifies specific risks, the server automatically sends notifications to relevant parties. These notifications include the anticipated risks, their scope of impact, and recommended countermeasures. The notifications are delivered via email or a dedicated application, reaching relevant parties instantly.

[0038] The terminal provides an easy-to-use user interface that allows users to view information obtained from the server. Users can intuitively check project progress, resource allocation, and safety risk information. Furthermore, the terminal displays instant responses from an AI agent to user inquiries, providing rapid support for resolving project questions and problems.

[0039] For example, if a worker notices a shortage of materials in their assigned area, they can immediately inquire about the current material situation from their terminal. Based on the information provided by the terminal, the user can then quickly decide to order additional materials.

[0040] This system allows for a real-time overview of the entire project, reducing uncertainty and enabling efficient and safe project progress. In this way, the present invention promotes a significant improvement in management efficiency in the construction industry.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects data every second from various sensors and drones at the site. Sensors provide temperature, humidity, and worker location information, while drones collect overall site footage and detailed footage of specific areas.

[0044] Step 2:

[0045] The server preprocesses the retrieved data. This processing includes imputing missing data values, format conversion, and timestamp consistency. The preprocessed data is then stored in the database.

[0046] Step 3:

[0047] The server analyzes progress using BIM data and on-site sensor data. Specifically, it compares the planned schedule with actual work progress to detect delays and potential budget overruns.

[0048] Step 4:

[0049] The server runs a machine learning model to predict risks based on historical project data and field data. This model assesses safety risks by considering the on-site work environment and human factors.

[0050] Step 5:

[0051] If the server identifies risks based on the analysis and prediction results, it will generate a notification for the relevant project personnel. The notification will include the type of risk, the scope of its impact, and recommended countermeasures.

[0052] Step 6:

[0053] The terminal receives notifications from the server and displays them in the user interface. Through these notifications, users can immediately check the project status and consider necessary actions.

[0054] Step 7:

[0055] Users can make additional inquiries about the project via their device. The server responds to these inquiries in real time through an AI agent, providing the necessary information.

[0056] Step 8:

[0057] Users make quick decisions based on the information provided, such as implementing risk mitigation measures. They also send the obtained information and countermeasures to the system as feedback to improve the basis for future decision-making.

[0058] (Example 1)

[0059] 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."

[0060] Modern construction projects require monitoring progress, ensuring safety, and efficiently utilizing resources. However, effectively collecting, analyzing, and predicting multiple data points to prevent problems before they occur is challenging. Conventional technologies have limitations in prediction accuracy and real-time capabilities, making rapid response difficult.

[0061] 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.

[0062] In this invention, the server includes means for acquiring environmental information and worker location information from a data collection device, means for integrating the acquired information with building information and performing progress evaluation, and means for predicting risks based on past data using a machine learning model. This enables accurate real-time understanding of project progress, highly accurate prediction of future risks, and rapid response.

[0063] "Data acquisition device" refers to hardware or software used to acquire various types of environmental information and worker location information.

[0064] "Environmental information" refers to information indicating environmental conditions at the site, such as temperature, humidity, and light intensity.

[0065] "Worker location information" refers to information indicating the worker's current location, obtained using GPS or other location measurement methods.

[0066] "Architectural information" refers to information about the design, structure, and process of an architectural project, provided based on building information modeling.

[0067] "Progress evaluation" refers to the process of analyzing project progress by comparing the planned schedule with the actual progress.

[0068] A "machine learning model" refers to an algorithm or mechanism that learns from past data and predicts results based on new data.

[0069] "Risk prediction" refers to the process of predicting potential problems and challenges that may occur in the future, based on collected data and analysis results.

[0070] A "generative AI model" is a type of artificial intelligence used in natural language processing and data analysis, and refers to a model that generates optimal prompt sentences and other similar statements.

[0071] A "prompt sentence" refers to an instruction or question that is input into an artificial intelligence model and is used to guide the model's response.

[0072] This invention is a system designed to streamline the management of construction projects, and it performs risk management by acquiring information in real time using multiple data collection devices, and then analyzing and predicting based on that information.

[0073] The server acquires data such as temperature, humidity, worker location information, and video footage from data collection devices such as sensors and drones installed at the construction site. This data is stored in a dedicated database and integrated with building information. Building Information Modeling (BIM) is used for integration, and the progress of the project is evaluated in combination with sensor information.

[0074] The server also uses machine learning models to analyze historical data and predict future risks. These machine learning models also function as generative AI models, generating optimal prompts to respond to new data patterns. An example of a generated prompt might be: "We want to understand the progress on-site and future risks in real time. Please suggest the best course of action based on the current data."

[0075] If the analysis results identify specific risks, the server automatically sends notifications to relevant parties regarding the nature of the risks and the necessary countermeasures. These notifications are delivered quickly via email or application.

[0076] The terminal features a user interface that intuitively displays information provided by the server. Users can use this interface to quickly and reliably check project progress, resource allocation information, safety risks, and more. The terminal also displays real-time responses from an AI agent using a generated AI model, responding to user inquiries in real time.

[0077] If a worker notices a shortage of materials in their assigned area, they can immediately inquire about the material status from their terminal, and based on that information, they can quickly decide to order additional materials.

[0078] This system allows users to grasp the overall picture of a project in real time, thereby reducing uncertainty in project progress and enabling efficient and safe management. In this way, the system of the present invention significantly promotes improved efficiency in project management in the construction industry.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server acquires environmental information and worker location data in real time from sensors and drones placed at the construction site. Inputs include temperature and humidity data from sensors, GPS location information, and drone footage. This data is stored in a database and converted into a format usable for subsequent analysis.

[0082] Step 2:

[0083] The server integrates the acquired data with the building information model and evaluates the project's progress. Sensor data and BIM data are used as input in this step. Data integration allows for a comparison of site conditions with design data, enabling the detection of deviations from the plan. The output is a current progress evaluation report.

[0084] Step 3:

[0085] The server uses a machine learning model to analyze data and predict risks. Inputs include historical progress data and environmental factor information. The machine learning model learns from the historical data and performs calculations to predict future risks and problems. The output is a risk prediction report and recommended countermeasures.

[0086] Step 4:

[0087] The server utilizes a generative AI model to generate optimal prompt messages and notifies stakeholders of the prediction results. A risk prediction report is provided as input. The generated prompt messages allow stakeholders to easily understand specific risks and their countermeasures. Notifications are sent via email or a dedicated app.

[0088] Step 5:

[0089] The terminal displays information from the server on a user interface for user review. Inputs include notifications and risk information from the server. The terminal visually displays information in a dashboard format and provides real-time AI agent responses to user inquiries. Outputs include user-friendly information displays and immediate responses.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] In managing construction projects, various challenges exist, including delays in progress, resource shortages, and safety issues. These challenges can hinder project success, requiring real-time information management and rapid response. However, traditional methods have struggled to resolve these challenges quickly and efficiently. Therefore, a system capable of immediate situation assessment and response on-site is necessary.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes means for obtaining information from multiple information gathering devices to acquire the progress of a project, means for immediately analyzing the acquired information, and means for predicting potential hazards associated with a specific task based on the analysis results. This makes it possible to efficiently manage the progress of a construction project, monitor safety, and manage resources.

[0095] "Project progress" refers to the current progress of a construction project and the completion status of each stage.

[0096] An "information gathering device" refers to a device used to monitor environmental parameters, worker locations, and the conditions of a work zone.

[0097] "Means of immediate analysis" refers to methods and devices for analyzing collected information in real time and quickly understanding the current situation.

[0098] "Potential hazards" refer to predicting problems that could hinder the success of a construction project, such as delays in progress or safety risks.

[0099] A "human-machine interaction interface" refers to an interface that allows users to visually confirm and manipulate information, thereby improving usability.

[0100] "Current resource status" refers to information indicating the availability and quantity of materials, personnel, equipment, etc., used in the project.

[0101] "Means of quickly making additional arrangements" refers to methods and processes for immediately taking action to secure necessary resources without delay.

[0102] The system implementing this invention is designed to streamline project management in construction projects. The server instantly collects and analyzes data obtained from multiple information gathering devices. These devices include sensors that monitor environmental parameters, worker locations, and work zone conditions. The server analyzes the acquired data in real time using machine learning models to predict project progress and potential hazards. Based on this analysis, the server automatically sends notifications to relevant parties if it detects signs of potential hazards. These notifications are displayed through a human-machine interaction interface, allowing users to immediately take action against the risks.

[0103] Users can check the current status of resources through their terminals and quickly make additional arrangements. This system supports quick and accurate decision-making and promotes project success.

[0104] As a concrete example, at a construction site, if a temperature rise exceeding a set standard is detected, the server can immediately analyze this information and issue a warning to workers to maintain a safe working environment. It is also possible to utilize a generated AI model to suggest the most appropriate countermeasures.

[0105] As an example of a prompt, we will use "Proposal for a method to analyze progress in real time from sensor data at a construction site."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server receives real-time data on temperature, humidity, worker locations, and work zone conditions from multiple data collection devices on-site. Inputs include various sensor data, and output is a formatted dataset. This data is converted to the required format using a sensor API and sent to the server.

[0109] Step 2:

[0110] The server immediately analyzes the received data. Here, the input is the formatted dataset obtained in step 1, and the output is the current project progress and predicted risk indicators of potential hazards obtained through the analysis. The data is analyzed using a machine learning model, and the risk is assessed in comparison with historical data.

[0111] Step 3:

[0112] The server automatically generates notifications to stakeholders based on the analysis results. The input is the risk indicator calculated in step 2, and the output is a warning message to the stakeholders. Specifically, the warning message is sent to the stakeholders' terminals using an email system or notification API.

[0113] Step 4:

[0114] The terminal displays received notifications to the user through a human-machine interaction interface. Input is messages from email or a notification API, and output is a warning display on the user interface. The user can review this and understand the actions to take in response to specific risks.

[0115] Step 5:

[0116] Users can check the current status of resources via their terminal. Input is the latest resource information from the server, and output is a dashboard showing the resource status. This allows users to identify depleted resources and quickly arrange for additional resources as needed.

[0117] 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.

[0118] The system of this invention is designed to improve efficiency and safety in project management at construction sites. Furthermore, the system incorporates an emotion engine to take the user's psychological state into consideration, thereby improving overall usability.

[0119] First, the server centrally collects diverse data from the field. This includes temperature, humidity, worker location information obtained through sensors, and video data of the work area obtained using drones. This data is organized and stored within the server.

[0120] After data collection, the server analyzes it in real time. In particular, machine learning models are used to scrutinize on-site risks and potential project delays. If any problems or risks related to work progress are discovered during this process, notifications are immediately sent to the relevant parties.

[0121] Next, the emotion engine analyzes the user's voice and facial expressions. The device collects this data and sends it to the emotion engine to evaluate the user's psychological state. This engine determines the user's stress level and concentration level, and adjusts notification content and response methods based on the results.

[0122] For example, if the server determines that a user is experiencing stress, it may change the tone of notifications to a more relaxing one and provide simplified guides and support messages as needed. This allows users to understand the situation more easily and work more efficiently.

[0123] Users can easily access the system through their devices to obtain necessary information and make inquiries. The system responds to user questions in real time and provides appropriate information.

[0124] In this way, a system incorporating an emotion engine not only accurately grasps the progress of a project but also takes into account the user's psychological state, supporting the smooth execution of tasks. This invention functions as a new means of improving on-site safety and work efficiency.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server periodically collects temperature, humidity, worker location information, and video data obtained from on-site sensors and drones. This data is transmitted to the server via the network and stored in a primary database.

[0128] Step 2:

[0129] The server preprocesses the collected raw data. This process involves imputing missing values ​​and unifying data in different formats. This preprocessing prepares the data for subsequent analysis.

[0130] Step 3:

[0131] The server performs real-time analysis using pre-processed data. It utilizes machine learning models to predict potential risks and delays on-site based on historical data patterns. The analysis results are used to generate alerts regarding safety and progress.

[0132] Step 4:

[0133] The emotion engine collects user voice and facial expression data via the device. This data is used to assess the stress levels and level of concentration the user is experiencing in relation to the project.

[0134] Step 5:

[0135] The server adjusts the content and tone of notifications based on the user's emotional state, as assessed by the emotion engine. For example, if the user is experiencing a high stress level, the notification will be phrased more gently and include additional supportive information.

[0136] Step 6:

[0137] The device displays personalized notifications to the user. These notifications include on-site progress and risk information, helping the user take necessary actions quickly.

[0138] Step 7:

[0139] Users can make additional inquiries to the system through their terminal. For example, if they ask for details about specific risks or recommended countermeasures, the server will respond immediately using an AI agent and provide relevant information.

[0140] Step 8:

[0141] Based on the necessary information, users decide on on-site response measures. For example, if an emergency evacuation is necessary, they immediately issue an evacuation order. The feedback obtained at this time is stored in the system's database and used to predict future risks.

[0142] (Example 2)

[0143] 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".

[0144] In project management at construction sites and other locations, it is a challenging task to improve efficiency and safety while also considering the psychological state of workers. This requires not only real-time collection and analysis of diverse site information, but also risk management based on this information and responses tailored to the psychological state of workers. Conventional technologies have struggled to process and address these issues centrally, and optimizing notifications and responses, in particular, while considering the psychological state of workers, has been a significant challenge.

[0145] 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.

[0146] In this invention, the server includes means for acquiring information from multiple information gathering devices at a construction site, means for analyzing the acquired information in real time, and means for predicting hazards associated with specific tasks based on the analysis results. This makes it possible to manage projects efficiently and safely based on the situation at the site and the user's psychological state.

[0147] An "information gathering device" is a device used to detect environmental conditions, worker locations, and the state of the work area at a construction site.

[0148] "Real-time analysis" is a process where analysis is performed as soon as data is acquired, allowing results to be obtained immediately.

[0149] "Risk prediction" is the process of predicting potential risks and problems at a site in advance, based on analyzed data.

[0150] An "emotion analysis device" is a device used to evaluate a user's psychological state based on their voice and facial expressions.

[0151] A "user interface" is an interface used by users to access notification information or make inquiries.

[0152] "Machine learning technology" is a technique in which computers recognize patterns based on data and automatically learn from them.

[0153] This invention is designed as a system to improve efficiency and safety in project management at construction sites. Specifically, a server plays the role of comprehensively collecting a wide variety of data from the construction site. This information collection utilizes multiple detectors to understand environmental conditions such as temperature and humidity, worker location information, and the state of the work area. This data is organized by the server and stored in a database.

[0154] After collecting data, the server analyzes it in real time. It utilizes machine learning technologies such as the Python library TENSORFLOW® or Scikit-learn to predict potential hazards and delays at the site. Based on this analysis, the server sends notifications to relevant parties. These notifications are sent via email, SMS, or push notifications.

[0155] Furthermore, the device collects the worker's voice and facial expressions using a camera and microphone, and transmits the information to an emotion analysis device. The emotion analysis system uses open-source analysis tools (such as OpenFace and DeepFace) to determine the user's stress level and concentration level. On the other hand, if it is determined that the user is feeling psychologically burdened, the tone of the notification content is adjusted to help them relax.

[0156] Users obtain necessary information and make inquiries through a dedicated terminal. The system uses NLP technology to respond to user questions in real time and provide appropriate support.

[0157] As a concrete example, consider a situation at a construction site where a worker is experiencing stress. In this case, an emotion analysis device detects this state, and the server sends a notification in a gentle tone, such as "Don't push yourself too hard, take breaks when necessary," thereby reducing the worker's psychological burden.

[0158] Example of a prompt:

[0159] "Consider a system prompt that analyzes the safety and efficiency of the work environment based on real-time data from construction sites, and generates notifications that take into account the user's psychological state using an emotion engine."

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server collects data from sensors and drones at the construction site. It receives temperature, humidity, worker locations, and video data of the work area as input, and stores this data integrally in a database. Specifically, the server uses network communication with each device to send requests and retrieve data. The output is an organized dataset.

[0163] Step 2:

[0164] The server analyzes the collected data in real time. The input is the dataset saved in Step 1. The server uses Python's TensorFlow to run a machine learning model and perform data calculations to predict risks and determine potential delays. Specifically, it trains the model and generates predictions for new data. The output is the result of the risk assessment and progress prediction.

[0165] Step 3:

[0166] The server generates and sends notifications to stakeholders based on the analysis results. The input is the risk and progress information obtained in step 2. The server uses the SMTP protocol and notification API to send emails, SMS messages, and push notifications. Specifically, it customizes the content of the notifications and sends them according to the recipient list. The output is the sent notification message.

[0167] Step 4:

[0168] The terminal collects voice and facial expression data from the worker and transmits it to an emotion analysis device. The input is real-time voice and video data. The terminal uses its camera and microphone to preprocess this data for analysis by OpenFace or DeepFace. The psychological state is evaluated using features recognized as specific actions. The output is an assessment of the user's stress level and concentration level.

[0169] Step 5:

[0170] The server adjusts the notification content based on the sentiment analysis results. The input is the evaluation result of the sentiment analysis in step 4. A generative AI model is used to generate prompt messages that correspond to the user's psychological state. Specifically, it performs natural language generation based on a template to create a notification message. The output is a customized notification message.

[0171] Step 6:

[0172] Users access the system using a dedicated terminal to obtain information and make inquiries. The input is a question from the user. The system analyzes the question using natural language processing and generates and provides an appropriate answer using a chatbot function. The specific operation involves understanding the user's intent and selecting the most suitable information. The output is the answer provided to the user.

[0173] (Application Example 2)

[0174] 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."

[0175] Project management at construction sites demands improved efficiency and safety. However, conventional systems have struggled with real-time risk prediction and rapid notification to stakeholders. Furthermore, information provision does not take into account the psychological state of workers, making it highly likely that efficiency will decrease due to stress and distraction. New methods are needed to solve these problems.

[0176] 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.

[0177] In this invention, the server includes means for acquiring information from multiple data collection devices to obtain the progress of a project, means for analyzing the acquired information in real time, and means for predicting risks associated with a specific operation based on the analysis results. This makes it possible to grasp the progress on site, improve safety, and provide flexible notifications that take into account the user's psychological state.

[0178] "Project progress" refers to the status of work progress and the degree to which the schedule has been achieved at a construction site.

[0179] A "data acquisition device" is a device used to acquire environmental parameters and worker activity information, and may include sensors.

[0180] "Analysis results" refer to the results of real-time evaluation and prediction based on collected data.

[0181] "Specific operations" refers to the specific tasks or procedures performed at a construction site.

[0182] "Hazard" refers to any factor or condition that could potentially threaten safety at a construction site.

[0183] "Stakeholders" refers to individuals or organizations that play a crucial role in the project.

[0184] "Notifications" refer to information and warnings provided based on analysis results and predictions.

[0185] An "information display device" is a device used to display notifications and other necessary information to the user.

[0186] "Psychological state" refers to the mental condition of a worker, including their emotions, stress levels, and level of concentration.

[0187] The system of this invention is primarily intended to streamline project management and improve safety at construction sites. The specific configuration and procedures for operating this system are described below.

[0188] The server aggregates information from multiple data collection devices, including sensors that capture environmental parameters and worker movement data. The server also implements an artificial intelligence model for analyzing the data acquired in real time. This allows it to predict potential hazards on-site and provide notifications to relevant parties as needed.

[0189] The terminal is used to provide a user interface. Notifications and other important information are made visible to the user through this terminal. In addition, the terminal works in conjunction with an emotion engine that detects the worker's voice and facial expressions and analyzes their psychological state. This allows for the adjustment of notification content based on stress levels and concentration levels.

[0190] Users can interact with the system through their devices and receive important project information in real time. Furthermore, the system is equipped with a function to respond to user inquiries immediately.

[0191] For example, when a worker performing high-altitude work at a construction site uses this system, the emotion engine detects anxiety and tension. In this situation, the smart glasses provided by the device display messages encouraging relaxation, such as "Take a deep breath," and also visualize guidance on stretching techniques.

[0192] An example of a prompt message when using a generative AI model might be, "If the on-site temperature data exceeds 35 degrees Celsius, suggest ways to reduce worker stress." In this way, the entire system works together to improve on-site safety and work efficiency.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The server acquires information such as temperature, humidity, worker locations, and video of the work area from multiple data collection devices at the construction site. This data is input from sensors and drones and transmitted to the server. The server temporarily stores the received data in preparation for the next analysis step.

[0196] Step 2:

[0197] The server analyzes received environmental data and worker activity information in real time. This analysis uses a machine learning model to assess potential risks and delays based on the data. The data received as input is passed to the model, and the analysis results output risk predictions and potential delays.

[0198] Step 3:

[0199] The server prepares to provide notifications to relevant parties based on the analysis results. Specifically, it determines what kind of notification to issue for the predicted risks and selects the appropriate information. The selected notification is then output to the user via the terminal.

[0200] Step 4:

[0201] The device collects the user's voice and facial expressions to send to the emotion engine. This input data is used with speech recognition and image analysis technologies to evaluate the user's psychological state. Based on this data, the emotion engine determines the stress level and concentration level, and outputs the results as emotion analysis results.

[0202] Step 5:

[0203] The server adjusts pre-prepared notifications based on the sentiment analysis results. If the user's stress level is high, the notification content can be changed to a gentler tone and include messages to help the worker relax. This adjusted notification is output through the terminal.

[0204] Step 6:

[0205] Users receive real-time notifications through their devices and can view instructions and reports in a visual format. They can also interact with their devices to ask questions and request additional instructions. This ensures that users can continue working safely and efficiently, always based on the latest information.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] The system of this invention is designed to efficiently manage projects at construction sites. The specific configuration of the system's operation is described below.

[0223] First, the server acquires data such as temperature, humidity, worker location information, and video from multiple sensors and drones installed on-site in real time. This data is used not only to monitor project progress but also to monitor safety and resource usage.

[0224] Next, the server analyzes this data. A combination of BIM (Building Information Modeling) data and sensor information is used to assess progress. This analysis detects discrepancies between the plan and actual progress. The server also uses machine learning models to learn from past data and predict future risks and problems. These predictions serve as important guidelines for preventing accidents on-site.

[0225] If the analysis identifies specific risks, the server automatically sends notifications to relevant parties. These notifications include the anticipated risks, their scope of impact, and recommended countermeasures. The notifications are delivered via email or a dedicated application, reaching relevant parties instantly.

[0226] The terminal provides an easy-to-use user interface that allows users to view information obtained from the server. Users can intuitively check project progress, resource allocation, and safety risk information. Furthermore, the terminal displays instant responses from an AI agent to user inquiries, providing rapid support for resolving project questions and problems.

[0227] For example, if a worker notices a shortage of materials in their assigned area, they can immediately inquire about the current material situation from their terminal. Based on the information provided by the terminal, the user can then quickly decide to order additional materials.

[0228] This system allows for a real-time overview of the entire project, reducing uncertainty and enabling efficient and safe project progress. In this way, the present invention promotes a significant improvement in management efficiency in the construction industry.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The server collects data every second from various sensors and drones at the site. Sensors provide temperature, humidity, and worker location information, while drones collect overall site footage and detailed footage of specific areas.

[0232] Step 2:

[0233] The server preprocesses the retrieved data. This processing includes imputing missing data values, format conversion, and timestamp consistency. The preprocessed data is then stored in the database.

[0234] Step 3:

[0235] The server analyzes progress using BIM data and on-site sensor data. Specifically, it compares the planned schedule with actual work progress to detect delays and potential budget overruns.

[0236] Step 4:

[0237] The server runs a machine learning model to predict risks based on historical project data and field data. This model assesses safety risks by considering the on-site work environment and human factors.

[0238] Step 5:

[0239] If the server identifies risks based on the analysis and prediction results, it will generate a notification for the relevant project personnel. The notification will include the type of risk, the scope of its impact, and recommended countermeasures.

[0240] Step 6:

[0241] The terminal receives notifications from the server and displays them in the user interface. Through these notifications, users can immediately check the project status and consider necessary actions.

[0242] Step 7:

[0243] Users can make additional inquiries about the project via their device. The server responds to these inquiries in real time through an AI agent, providing the necessary information.

[0244] Step 8:

[0245] Users make quick decisions based on the information provided, such as implementing risk mitigation measures. They also send the obtained information and countermeasures to the system as feedback to improve the basis for future decision-making.

[0246] (Example 1)

[0247] 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."

[0248] Modern construction projects require monitoring progress, ensuring safety, and efficiently utilizing resources. However, effectively collecting, analyzing, and predicting multiple data points to prevent problems before they occur is challenging. Conventional technologies have limitations in prediction accuracy and real-time capabilities, making rapid response difficult.

[0249] 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.

[0250] In this invention, the server includes means for acquiring environmental information and worker location information from a data collection device, means for integrating the acquired information with building information and performing progress evaluation, and means for predicting risks based on past data using a machine learning model. This enables accurate real-time understanding of project progress, highly accurate prediction of future risks, and rapid response.

[0251] "Data acquisition device" refers to hardware or software used to acquire various types of environmental information and worker location information.

[0252] "Environmental information" refers to information indicating environmental conditions at the site, such as temperature, humidity, and light intensity.

[0253] "Worker location information" refers to information indicating the worker's current location, obtained using GPS or other location measurement methods.

[0254] "Architectural information" refers to information about the design, structure, and process of an architectural project, provided based on building information modeling.

[0255] "Progress evaluation" refers to the process of analyzing project progress by comparing the planned schedule with the actual progress.

[0256] A "machine learning model" refers to an algorithm or mechanism that learns from past data and predicts results based on new data.

[0257] "Risk prediction" refers to the process of predicting potential problems and challenges that may occur in the future, based on collected data and analysis results.

[0258] A "generative AI model" is a type of artificial intelligence used in natural language processing and data analysis, and refers to a model that generates optimal prompt sentences and other similar statements.

[0259] A "prompt sentence" refers to an instruction or question that is input into an artificial intelligence model and is used to guide the model's response.

[0260] This invention is a system designed to streamline the management of construction projects, and it performs risk management by acquiring information in real time using multiple data collection devices, and then analyzing and predicting based on that information.

[0261] The server acquires data such as temperature, humidity, worker location information, and video footage from data collection devices such as sensors and drones installed at the construction site. This data is stored in a dedicated database and integrated with building information. Building Information Modeling (BIM) is used for integration, and the progress of the project is evaluated in combination with sensor information.

[0262] The server also uses machine learning models to analyze historical data and predict future risks. These machine learning models also function as generative AI models, generating optimal prompts to respond to new data patterns. An example of a generated prompt might be: "We want to understand the progress on-site and future risks in real time. Please suggest the best course of action based on the current data."

[0263] If the analysis results identify specific risks, the server automatically sends notifications to relevant parties regarding the nature of the risks and the necessary countermeasures. These notifications are delivered quickly via email or application.

[0264] The terminal features a user interface that intuitively displays information provided by the server. Users can use this interface to quickly and reliably check project progress, resource allocation information, safety risks, and more. The terminal also displays real-time responses from an AI agent using a generated AI model, responding to user inquiries in real time.

[0265] If a worker notices a shortage of materials in their assigned area, they can immediately inquire about the material status from their terminal, and based on that information, they can quickly decide to order additional materials.

[0266] This system allows users to grasp the overall picture of a project in real time, thereby reducing uncertainty in project progress and enabling efficient and safe management. In this way, the system of the present invention significantly promotes improved efficiency in project management in the construction industry.

[0267] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0268] Step 1:

[0269] The server acquires environmental information and worker location data in real time from sensors and drones placed at the construction site. Inputs include temperature and humidity data from sensors, GPS location information, and drone footage. This data is stored in a database and converted into a format usable for subsequent analysis.

[0270] Step 2:

[0271] The server integrates the acquired data with the building information model and evaluates the project's progress. Sensor data and BIM data are used as input in this step. Data integration allows for a comparison of site conditions with design data, enabling the detection of deviations from the plan. The output is a current progress evaluation report.

[0272] Step 3:

[0273] The server uses a machine learning model to analyze data and predict risks. Inputs include historical progress data and environmental factor information. The machine learning model learns from the historical data and performs calculations to predict future risks and problems. The output is a risk prediction report and recommended countermeasures.

[0274] Step 4:

[0275] The server utilizes a generative AI model to generate optimal prompt messages and notifies stakeholders of the prediction results. A risk prediction report is provided as input. The generated prompt messages allow stakeholders to easily understand specific risks and their countermeasures. Notifications are sent via email or a dedicated app.

[0276] Step 5:

[0277] The terminal displays information from the server on a user interface for user review. Inputs include notifications and risk information from the server. The terminal visually displays information in a dashboard format and provides real-time AI agent responses to user inquiries. Outputs include user-friendly information displays and immediate responses.

[0278] (Application Example 1)

[0279] 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."

[0280] In managing construction projects, various challenges exist, including delays in progress, resource shortages, and safety issues. These challenges can hinder project success, requiring real-time information management and rapid response. However, traditional methods have struggled to resolve these challenges quickly and efficiently. Therefore, a system capable of immediate situation assessment and response on-site is necessary.

[0281] 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.

[0282] In this invention, the server includes means for obtaining information from a plurality of information collection devices to acquire the progress status of a project, means for immediately analyzing the acquired information, and means for predicting potential risks related to specific operations based on the analysis results. Thereby, it becomes possible to efficiently perform progress management, safety monitoring, and resource management of a construction project.

[0283] The "progress status of the project" refers to the current progress degree of the construction project and the completion status of each process.

[0284] The "information collection device" refers to a device used to monitor environmental parameters, the location of workers, and the status of work zones.

[0285] The "means for immediately analyzing" refers to methods and devices for analyzing the collected information in real time to quickly grasp the current situation.

[0286] "Potential risks" refers to predicting problems that may impede the success of the project, such as delays in project progress and safety risks in a construction project.

[0287] The "human-machine interaction interface" refers to an interface for users to visually confirm and operate information, which improves user-friendliness.

[0288] The "current status of resources" refers to information indicating the available status and quantity of materials, personnel, equipment, etc. used in the project.

[0289] The "means for quickly making additional arrangements" refers to methods and processes for immediately executing actions to ensure the necessary resources without delay.

[0290] The system implementing this invention is designed to streamline project management in construction projects. The server instantly collects and analyzes data obtained from multiple information gathering devices. These devices include sensors that monitor environmental parameters, worker locations, and work zone conditions. The server analyzes the acquired data in real time using machine learning models to predict project progress and potential hazards. Based on this analysis, the server automatically sends notifications to relevant parties if it detects signs of potential hazards. These notifications are displayed through a human-machine interaction interface, allowing users to immediately take action against the risks.

[0291] Users can check the current status of resources through their terminals and quickly make additional arrangements. This system supports quick and accurate decision-making and promotes project success.

[0292] As a concrete example, at a construction site, if a temperature rise exceeding a set standard is detected, the server can immediately analyze this information and issue a warning to workers to maintain a safe working environment. It is also possible to utilize a generated AI model to suggest the most appropriate countermeasures.

[0293] As an example of a prompt, we will use "Proposal for a method to analyze progress in real time from sensor data at a construction site."

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The server receives real-time data on temperature, humidity, worker locations, and work zone conditions from multiple data collection devices on-site. Inputs include various sensor data, and output is a formatted dataset. This data is converted to the required format using a sensor API and sent to the server.

[0297] Step 2:

[0298] The server immediately analyzes the received data. Here, the input is the formatted dataset obtained in step 1, and the output is the current project progress and predicted risk indicators of potential hazards obtained through the analysis. The data is analyzed using a machine learning model, and the risk is assessed in comparison with historical data.

[0299] Step 3:

[0300] The server automatically generates notifications to stakeholders based on the analysis results. The input is the risk indicator calculated in step 2, and the output is a warning message to the stakeholders. Specifically, the warning message is sent to the stakeholders' terminals using an email system or notification API.

[0301] Step 4:

[0302] The terminal displays received notifications to the user through a human-machine interaction interface. Input is messages from email or a notification API, and output is a warning display on the user interface. The user can review this and understand the actions to take in response to specific risks.

[0303] Step 5:

[0304] Users can check the current status of resources via their terminal. Input is the latest resource information from the server, and output is a dashboard showing the resource status. This allows users to identify depleted resources and quickly arrange for additional resources as needed.

[0305] 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.

[0306] The system of the present invention is designed to improve efficiency and safety in project management at construction sites. Furthermore, this system incorporates an emotion engine and improves the overall usability by considering the psychological state of users.

[0307] First, the server centrally collects various data on-site. This includes temperature and humidity obtained through sensors, location information of workers, and video data of the work area obtained using drones. These data are sorted and stored within the server.

[0308] After data collection, the server analyzes it in real time. Particularly, it uses a machine learning model to examine risks on-site and the possibility of project delays. If problems or risks related to work progress are discovered during this process, notifications are immediately sent to relevant parties.

[0309] Next, the emotion engine analyzes the user's voice and expression. The terminal collects this data and transmits information to the emotion engine to evaluate the psychological state. This engine discriminates the user's stress level and concentration, and adjusts the notification content and response method based on the results.

[0310] For example, if a certain user is determined to be feeling stressed, the server changes the notification content to a relaxing tone or provides simplified guides and support messages as needed. As a result, the user can more easily understand the situation and proceed with work efficiently.

[0311] Users can easily access the system through the terminal to obtain necessary information or make inquiries. The system responds to the user's questions in real time and provides appropriate information.

[0312] In this way, a system incorporating an emotion engine not only accurately grasps the progress of a project but also takes into account the user's psychological state, supporting the smooth execution of tasks. This invention functions as a new means of improving on-site safety and work efficiency.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The server periodically collects temperature, humidity, worker location information, and video data obtained from on-site sensors and drones. This data is transmitted to the server via the network and stored in a primary database.

[0316] Step 2:

[0317] The server preprocesses the collected raw data. This process involves imputing missing values ​​and unifying data in different formats. This preprocessing prepares the data for subsequent analysis.

[0318] Step 3:

[0319] The server performs real-time analysis using pre-processed data. It utilizes machine learning models to predict potential risks and delays on-site based on historical data patterns. The analysis results are used to generate alerts regarding safety and progress.

[0320] Step 4:

[0321] The emotion engine collects user voice and facial expression data via the device. This data is used to assess the stress levels and level of concentration the user is experiencing in relation to the project.

[0322] Step 5:

[0323] The server adjusts the content and tone of notifications based on the user's emotional state, as assessed by the emotion engine. For example, if the user is experiencing a high stress level, the notification will be phrased more gently and include additional supportive information.

[0324] Step 6:

[0325] The device displays personalized notifications to the user. These notifications include on-site progress and risk information, helping the user take necessary actions quickly.

[0326] Step 7:

[0327] Users can make additional inquiries to the system through their terminal. For example, if they ask for details about specific risks or recommended countermeasures, the server will respond immediately using an AI agent and provide relevant information.

[0328] Step 8:

[0329] Based on the necessary information, users decide on on-site response measures. For example, if an emergency evacuation is necessary, they immediately issue an evacuation order. The feedback obtained at this time is stored in the system's database and used to predict future risks.

[0330] (Example 2)

[0331] 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".

[0332] In project management at construction sites and other locations, it is a challenging task to improve efficiency and safety while also considering the psychological state of workers. This requires not only real-time collection and analysis of diverse site information, but also risk management based on this information and responses tailored to the psychological state of workers. Conventional technologies have struggled to process and address these issues centrally, and optimizing notifications and responses, in particular, while considering the psychological state of workers, has been a significant challenge.

[0333] 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.

[0334] In this invention, the server includes means for acquiring information from multiple information gathering devices at a construction site, means for analyzing the acquired information in real time, and means for predicting hazards associated with specific tasks based on the analysis results. This makes it possible to manage projects efficiently and safely based on the situation at the site and the user's psychological state.

[0335] An "information gathering device" is a device used to detect environmental conditions, worker locations, and the state of the work area at a construction site.

[0336] "Real-time analysis" is a process where analysis is performed as soon as data is acquired, allowing results to be obtained immediately.

[0337] "Risk prediction" is the process of predicting potential risks and problems at a site in advance, based on analyzed data.

[0338] An "emotion analysis device" is a device used to evaluate a user's psychological state based on their voice and facial expressions.

[0339] A "user interface" is an interface used by users to access notification information or make inquiries.

[0340] "Machine learning technology" is a technique in which computers recognize patterns based on data and automatically learn from them.

[0341] This invention is designed as a system to improve efficiency and safety in project management at construction sites. Specifically, a server plays the role of comprehensively collecting a wide variety of data from the construction site. This information collection utilizes multiple detectors to understand environmental conditions such as temperature and humidity, worker location information, and the state of the work area. This data is organized by the server and stored in a database.

[0342] After collecting data, the server analyzes it in real time. It utilizes machine learning techniques such as Python libraries TensorFlow or Scikit-learn to predict potential hazards and delays in the field. Based on this analysis, the server sends notifications to relevant parties. These notifications are sent via email, SMS, or push notifications.

[0343] Furthermore, the device collects the worker's voice and facial expressions using a camera and microphone, and transmits the information to an emotion analysis device. The emotion analysis system uses open-source analysis tools (such as OpenFace and DeepFace) to determine the user's stress level and concentration level. On the other hand, if it is determined that the user is feeling psychologically burdened, the tone of the notification content is adjusted to help them relax.

[0344] Users obtain necessary information and make inquiries through a dedicated terminal. The system uses NLP technology to respond to user questions in real time and provide appropriate support.

[0345] As a concrete example, consider a situation at a construction site where a worker is experiencing stress. In this case, an emotion analysis device detects this state, and the server sends a notification in a gentle tone, such as "Don't push yourself too hard, take breaks when necessary," thereby reducing the worker's psychological burden.

[0346] Example of a prompt:

[0347] "Consider a system prompt that analyzes the safety and efficiency of the work environment based on real-time data from construction sites, and generates notifications that take into account the user's psychological state using an emotion engine."

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] The server collects data from sensors and drones at the construction site. It receives temperature, humidity, worker locations, and video data of the work area as input, and stores this data integrally in a database. Specifically, the server uses network communication with each device to send requests and retrieve data. The output is an organized dataset.

[0351] Step 2:

[0352] The server analyzes the collected data in real time. The input is the dataset saved in Step 1. The server uses Python's TensorFlow to run a machine learning model and perform data calculations to predict risks and determine potential delays. Specifically, it trains the model and generates predictions for new data. The output is the result of the risk assessment and progress prediction.

[0353] Step 3:

[0354] The server generates and sends notifications to stakeholders based on the analysis results. The input is the risk and progress information obtained in step 2. The server uses the SMTP protocol and notification API to send emails, SMS messages, and push notifications. Specifically, it customizes the content of the notifications and sends them according to the recipient list. The output is the sent notification message.

[0355] Step 4:

[0356] The terminal collects voice and facial expression data from the worker and transmits it to an emotion analysis device. The input is real-time voice and video data. The terminal uses its camera and microphone to preprocess this data for analysis by OpenFace or DeepFace. The psychological state is evaluated using features recognized as specific actions. The output is an assessment of the user's stress level and concentration level.

[0357] Step 5:

[0358] The server adjusts the notification content based on the sentiment analysis results. The input is the evaluation result of the sentiment analysis in step 4. A generative AI model is used to generate prompt messages that correspond to the user's psychological state. Specifically, it performs natural language generation based on a template to create a notification message. The output is a customized notification message.

[0359] Step 6:

[0360] Users access the system using a dedicated terminal to obtain information and make inquiries. The input is a question from the user. The system analyzes the question using natural language processing and generates and provides an appropriate answer using a chatbot function. The specific operation involves understanding the user's intent and selecting the most suitable information. The output is the answer provided to the user.

[0361] (Application Example 2)

[0362] 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 as the "terminal".

[0363] Project management at construction sites demands improved efficiency and safety. However, conventional systems have struggled with real-time risk prediction and rapid notification to stakeholders. Furthermore, information provision does not take into account the psychological state of workers, making it highly likely that efficiency will decrease due to stress and distraction. New methods are needed to solve these problems.

[0364] 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.

[0365] In this invention, the server includes means for acquiring information from multiple data collection devices to obtain the progress of a project, means for analyzing the acquired information in real time, and means for predicting risks associated with a specific operation based on the analysis results. This makes it possible to grasp the progress on site, improve safety, and provide flexible notifications that take into account the user's psychological state.

[0366] "Project progress" refers to the status of work progress and the degree to which the schedule has been achieved at a construction site.

[0367] A "data acquisition device" is a device used to acquire environmental parameters and worker activity information, and may include sensors.

[0368] "Analysis results" refer to the results of real-time evaluation and prediction based on collected data.

[0369] "Specific operations" refers to the specific tasks or procedures performed at a construction site.

[0370] "Hazard" refers to any factor or condition that could potentially threaten safety at a construction site.

[0371] "Stakeholders" refers to individuals or organizations that play a crucial role in the project.

[0372] "Notifications" refer to information and warnings provided based on analysis results and predictions.

[0373] An "information display device" is a device used to display notifications and other necessary information to the user.

[0374] "Psychological state" refers to the mental condition of a worker, including their emotions, stress levels, and level of concentration.

[0375] The system of this invention is primarily intended to streamline project management and improve safety at construction sites. The specific configuration and procedures for operating this system are described below.

[0376] The server aggregates information from multiple data collection devices, including sensors that capture environmental parameters and worker movement data. The server also implements an artificial intelligence model for analyzing the data acquired in real time. This allows it to predict potential hazards on-site and provide notifications to relevant parties as needed.

[0377] The terminal is used to provide a user interface. Notifications and other important information are made visible to the user through this terminal. In addition, the terminal works in conjunction with an emotion engine that detects the worker's voice and facial expressions and analyzes their psychological state. This allows for the adjustment of notification content based on stress levels and concentration levels.

[0378] Users can interact with the system through their devices and receive important project information in real time. Furthermore, the system is equipped with a function to respond to user inquiries immediately.

[0379] For example, when a worker performing high-altitude work at a construction site uses this system, the emotion engine detects anxiety and tension. In this situation, the smart glasses provided by the device display messages encouraging relaxation, such as "Take a deep breath," and also visualize guidance on stretching techniques.

[0380] An example of a prompt message when using a generative AI model might be, "If the on-site temperature data exceeds 35 degrees Celsius, suggest ways to reduce worker stress." In this way, the entire system works together to improve on-site safety and work efficiency.

[0381] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0382] Step 1:

[0383] The server acquires information such as temperature, humidity, worker locations, and video of the work area from multiple data collection devices at the construction site. This data is input from sensors and drones and transmitted to the server. The server temporarily stores the received data in preparation for the next analysis step.

[0384] Step 2:

[0385] The server analyzes received environmental data and worker activity information in real time. This analysis uses a machine learning model to assess potential risks and delays based on the data. The data received as input is passed to the model, and the analysis results output risk predictions and potential delays.

[0386] Step 3:

[0387] The server prepares to provide notifications to relevant parties based on the analysis results. Specifically, it determines what kind of notification to issue for the predicted risks and selects the appropriate information. The selected notification is then output to the user via the terminal.

[0388] Step 4:

[0389] The device collects the user's voice and facial expressions to send to the emotion engine. This input data is used with speech recognition and image analysis technologies to evaluate the user's psychological state. Based on this data, the emotion engine determines the stress level and concentration level, and outputs the results as emotion analysis results.

[0390] Step 5:

[0391] The server adjusts pre-prepared notifications based on the sentiment analysis results. If the user's stress level is high, the notification content can be changed to a gentler tone and include messages to help the worker relax. This adjusted notification is output through the terminal.

[0392] Step 6:

[0393] Users receive real-time notifications through their devices and can view instructions and reports in a visual format. They can also interact with their devices to ask questions and request additional instructions. This ensures that users can continue working safely and efficiently, always based on the latest information.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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".

[0410] The system of this invention is designed to efficiently manage projects at construction sites. The specific configuration of the system's operation is described below.

[0411] First, the server acquires data such as temperature, humidity, worker location information, and video from multiple sensors and drones installed on-site in real time. This data is used not only to monitor project progress but also to monitor safety and resource usage.

[0412] Next, the server analyzes this data. A combination of BIM (Building Information Modeling) data and sensor information is used to assess progress. This analysis detects discrepancies between the plan and actual progress. The server also uses machine learning models to learn from past data and predict future risks and problems. These predictions serve as important guidelines for preventing accidents on-site.

[0413] If the analysis identifies specific risks, the server automatically sends notifications to relevant parties. These notifications include the anticipated risks, their scope of impact, and recommended countermeasures. The notifications are delivered via email or a dedicated application, reaching relevant parties instantly.

[0414] The terminal provides an easy-to-use user interface that allows users to view information obtained from the server. Users can intuitively check project progress, resource allocation, and safety risk information. Furthermore, the terminal displays instant responses from an AI agent to user inquiries, providing rapid support for resolving project questions and problems.

[0415] For example, if a worker notices a shortage of materials in their assigned area, they can immediately inquire about the current material situation from their terminal. Based on the information provided by the terminal, the user can then quickly decide to order additional materials.

[0416] This system allows for a real-time overview of the entire project, reducing uncertainty and enabling efficient and safe project progress. In this way, the present invention promotes a significant improvement in management efficiency in the construction industry.

[0417] The following describes the processing flow.

[0418] Step 1:

[0419] The server collects data every second from various sensors and drones at the site. Sensors provide temperature, humidity, and worker location information, while drones collect overall site footage and detailed footage of specific areas.

[0420] Step 2:

[0421] The server preprocesses the retrieved data. This processing includes imputing missing data values, format conversion, and timestamp consistency. The preprocessed data is then stored in the database.

[0422] Step 3:

[0423] The server analyzes progress using BIM data and on-site sensor data. Specifically, it compares the planned schedule with actual work progress to detect delays and potential budget overruns.

[0424] Step 4:

[0425] The server runs a machine learning model to predict risks based on historical project data and field data. This model assesses safety risks by considering the on-site work environment and human factors.

[0426] Step 5:

[0427] If the server identifies risks based on the analysis and prediction results, it will generate a notification for the relevant project personnel. The notification will include the type of risk, the scope of its impact, and recommended countermeasures.

[0428] Step 6:

[0429] The terminal receives notifications from the server and displays them in the user interface. Through these notifications, users can immediately check the project status and consider necessary actions.

[0430] Step 7:

[0431] Users can make additional inquiries about the project via their device. The server responds to these inquiries in real time through an AI agent, providing the necessary information.

[0432] Step 8:

[0433] Users make quick decisions based on the information provided, such as implementing risk mitigation measures. They also send the obtained information and countermeasures to the system as feedback to improve the basis for future decision-making.

[0434] (Example 1)

[0435] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0436] Modern construction projects require monitoring progress, ensuring safety, and efficiently utilizing resources. However, effectively collecting, analyzing, and predicting multiple data points to prevent problems before they occur is challenging. Conventional technologies have limitations in prediction accuracy and real-time capabilities, making rapid response difficult.

[0437] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0438] In this invention, the server includes means for acquiring environmental information and worker location information from a data collection device, means for integrating the acquired information with building information and performing progress evaluation, and means for predicting risks based on past data using a machine learning model. This enables accurate real-time understanding of project progress, highly accurate prediction of future risks, and rapid response.

[0439] "Data acquisition device" refers to hardware or software used to acquire various types of environmental information and worker location information.

[0440] "Environmental information" refers to information indicating environmental conditions at the site, such as temperature, humidity, and light intensity.

[0441] "Worker location information" refers to information indicating the worker's current location, obtained using GPS or other location measurement methods.

[0442] "Architectural information" refers to information about the design, structure, and process of an architectural project, provided based on building information modeling.

[0443] "Progress evaluation" refers to the process of analyzing project progress by comparing the planned schedule with the actual progress.

[0444] A "machine learning model" refers to an algorithm or mechanism that learns from past data and predicts results based on new data.

[0445] "Risk prediction" refers to the process of predicting potential problems and challenges that may occur in the future, based on collected data and analysis results.

[0446] A "generative AI model" is a type of artificial intelligence used in natural language processing and data analysis, and refers to a model that generates optimal prompt sentences and other similar statements.

[0447] A "prompt sentence" refers to an instruction or question that is input into an artificial intelligence model and is used to guide the model's response.

[0448] This invention is a system designed to streamline the management of construction projects, and it performs risk management by acquiring information in real time using multiple data collection devices, and then analyzing and predicting based on that information.

[0449] The server acquires data such as temperature, humidity, worker location information, and video footage from data collection devices such as sensors and drones installed at the construction site. This data is stored in a dedicated database and integrated with building information. Building Information Modeling (BIM) is used for integration, and the progress of the project is evaluated in combination with sensor information.

[0450] The server also uses machine learning models to analyze historical data and predict future risks. These machine learning models also function as generative AI models, generating optimal prompts to respond to new data patterns. An example of a generated prompt might be: "We want to understand the progress on-site and future risks in real time. Please suggest the best course of action based on the current data."

[0451] If the analysis results identify specific risks, the server automatically sends notifications to relevant parties regarding the nature of the risks and the necessary countermeasures. These notifications are delivered quickly via email or application.

[0452] The terminal features a user interface that intuitively displays information provided by the server. Users can use this interface to quickly and reliably check project progress, resource allocation information, safety risks, and more. The terminal also displays real-time responses from an AI agent using a generated AI model, responding to user inquiries in real time.

[0453] If a worker notices a shortage of materials in their assigned area, they can immediately inquire about the material status from their terminal, and based on that information, they can quickly decide to order additional materials.

[0454] This system allows users to grasp the overall picture of a project in real time, thereby reducing uncertainty in project progress and enabling efficient and safe management. In this way, the system of the present invention significantly promotes improved efficiency in project management in the construction industry.

[0455] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0456] Step 1:

[0457] The server acquires environmental information and worker location data in real time from sensors and drones placed at the construction site. Inputs include temperature and humidity data from sensors, GPS location information, and drone footage. This data is stored in a database and converted into a format usable for subsequent analysis.

[0458] Step 2:

[0459] The server integrates the acquired data with the building information model and evaluates the project's progress. Sensor data and BIM data are used as input in this step. Data integration allows for a comparison of site conditions with design data, enabling the detection of deviations from the plan. The output is a current progress evaluation report.

[0460] Step 3:

[0461] The server uses a machine learning model to analyze data and predict risks. Inputs include historical progress data and environmental factor information. The machine learning model learns from the historical data and performs calculations to predict future risks and problems. The output is a risk prediction report and recommended countermeasures.

[0462] Step 4:

[0463] The server utilizes a generative AI model to generate optimal prompt messages and notifies stakeholders of the prediction results. A risk prediction report is provided as input. The generated prompt messages allow stakeholders to easily understand specific risks and their countermeasures. Notifications are sent via email or a dedicated app.

[0464] Step 5:

[0465] The terminal displays information from the server on a user interface for user review. Inputs include notifications and risk information from the server. The terminal visually displays information in a dashboard format and provides real-time AI agent responses to user inquiries. Outputs include user-friendly information displays and immediate responses.

[0466] (Application Example 1)

[0467] 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."

[0468] In managing construction projects, various challenges exist, including delays in progress, resource shortages, and safety issues. These challenges can hinder project success, requiring real-time information management and rapid response. However, traditional methods have struggled to resolve these challenges quickly and efficiently. Therefore, a system capable of immediate situation assessment and response on-site is necessary.

[0469] 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.

[0470] In this invention, the server includes means for obtaining information from multiple information gathering devices to acquire the progress of a project, means for immediately analyzing the acquired information, and means for predicting potential hazards associated with a specific task based on the analysis results. This makes it possible to efficiently manage the progress of a construction project, monitor safety, and manage resources.

[0471] "Project progress" refers to the current progress of a construction project and the completion status of each stage.

[0472] An "information gathering device" refers to a device used to monitor environmental parameters, worker locations, and the conditions of a work zone.

[0473] "Means of immediate analysis" refers to methods and devices for analyzing collected information in real time and quickly understanding the current situation.

[0474] "Potential hazards" refer to predicting problems that could hinder the success of a construction project, such as delays in progress or safety risks.

[0475] A "human-machine interaction interface" refers to an interface that allows users to visually confirm and manipulate information, thereby improving usability.

[0476] "Current resource status" refers to information indicating the availability and quantity of materials, personnel, equipment, etc., used in the project.

[0477] "Means of quickly making additional arrangements" refers to methods and processes for immediately taking action to secure necessary resources without delay.

[0478] The system implementing this invention is designed to streamline project management in construction projects. The server instantly collects and analyzes data obtained from multiple information gathering devices. These devices include sensors that monitor environmental parameters, worker locations, and work zone conditions. The server analyzes the acquired data in real time using machine learning models to predict project progress and potential hazards. Based on this analysis, the server automatically sends notifications to relevant parties if it detects signs of potential hazards. These notifications are displayed through a human-machine interaction interface, allowing users to immediately take action against the risks.

[0479] Users can check the current status of resources through their terminals and quickly make additional arrangements. This system supports quick and accurate decision-making and promotes project success.

[0480] As a concrete example, at a construction site, if a temperature rise exceeding a set standard is detected, the server can immediately analyze this information and issue a warning to workers to maintain a safe working environment. It is also possible to utilize a generated AI model to suggest the most appropriate countermeasures.

[0481] As an example of a prompt, we will use "Proposal for a method to analyze progress in real time from sensor data at a construction site."

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The server receives real-time data on temperature, humidity, worker locations, and work zone conditions from multiple data collection devices on-site. Inputs include various sensor data, and output is a formatted dataset. This data is converted to the required format using a sensor API and sent to the server.

[0485] Step 2:

[0486] The server immediately analyzes the received data. Here, the input is the formatted dataset obtained in step 1, and the output is the current project progress and predicted risk indicators of potential hazards obtained through the analysis. The data is analyzed using a machine learning model, and the risk is assessed in comparison with historical data.

[0487] Step 3:

[0488] The server automatically generates notifications to stakeholders based on the analysis results. The input is the risk indicator calculated in step 2, and the output is a warning message to the stakeholders. Specifically, the warning message is sent to the stakeholders' terminals using an email system or notification API.

[0489] Step 4:

[0490] The terminal displays received notifications to the user through a human-machine interaction interface. Input is messages from email or a notification API, and output is a warning display on the user interface. The user can review this and understand the actions to take in response to specific risks.

[0491] Step 5:

[0492] Users can check the current status of resources via their terminal. Input is the latest resource information from the server, and output is a dashboard showing the resource status. This allows users to identify depleted resources and quickly arrange for additional resources as needed.

[0493] 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.

[0494] The system of this invention is designed to improve efficiency and safety in project management at construction sites. Furthermore, the system incorporates an emotion engine to take the user's psychological state into consideration, thereby improving overall usability.

[0495] First, the server centrally collects diverse data from the field. This includes temperature, humidity, worker location information obtained through sensors, and video data of the work area obtained using drones. This data is organized and stored within the server.

[0496] After data collection, the server analyzes it in real time. In particular, machine learning models are used to scrutinize on-site risks and potential project delays. If any problems or risks related to work progress are discovered during this process, notifications are immediately sent to the relevant parties.

[0497] Next, the emotion engine analyzes the user's voice and facial expressions. The device collects this data and sends it to the emotion engine to evaluate the user's psychological state. This engine determines the user's stress level and concentration level, and adjusts notification content and response methods based on the results.

[0498] For example, if the server determines that a user is experiencing stress, it may change the tone of notifications to a more relaxing one and provide simplified guides and support messages as needed. This allows users to understand the situation more easily and work more efficiently.

[0499] Users can easily access the system through their devices to obtain necessary information and make inquiries. The system responds to user questions in real time and provides appropriate information.

[0500] In this way, a system incorporating an emotion engine not only accurately grasps the progress of a project but also takes into account the user's psychological state, supporting the smooth execution of tasks. This invention functions as a new means of improving on-site safety and work efficiency.

[0501] The following describes the processing flow.

[0502] Step 1:

[0503] The server periodically collects temperature, humidity, worker location information, and video data obtained from on-site sensors and drones. This data is transmitted to the server via the network and stored in a primary database.

[0504] Step 2:

[0505] The server preprocesses the collected raw data. This process involves imputing missing values ​​and unifying data in different formats. This preprocessing prepares the data for subsequent analysis.

[0506] Step 3:

[0507] The server performs real-time analysis using pre-processed data. It utilizes machine learning models to predict potential risks and delays on-site based on historical data patterns. The analysis results are used to generate alerts regarding safety and progress.

[0508] Step 4:

[0509] The emotion engine collects user voice and facial expression data via the device. This data is used to assess the stress levels and level of concentration the user is experiencing in relation to the project.

[0510] Step 5:

[0511] The server adjusts the content and tone of notifications based on the user's emotional state, as assessed by the emotion engine. For example, if the user is experiencing a high stress level, the notification will be phrased more gently and include additional supportive information.

[0512] Step 6:

[0513] The device displays personalized notifications to the user. These notifications include on-site progress and risk information, helping the user take necessary actions quickly.

[0514] Step 7:

[0515] Users can make additional inquiries to the system through their terminal. For example, if they ask for details about specific risks or recommended countermeasures, the server will respond immediately using an AI agent and provide relevant information.

[0516] Step 8:

[0517] Based on the necessary information, users decide on on-site response measures. For example, if an emergency evacuation is necessary, they immediately issue an evacuation order. The feedback obtained at this time is stored in the system's database and used to predict future risks.

[0518] (Example 2)

[0519] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0520] In project management at construction sites and other locations, it is a challenging task to improve efficiency and safety while also considering the psychological state of workers. This requires not only real-time collection and analysis of diverse site information, but also risk management based on this information and responses tailored to the psychological state of workers. Conventional technologies have struggled to process and address these issues centrally, and optimizing notifications and responses, in particular, while considering the psychological state of workers, has been a significant challenge.

[0521] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0522] In this invention, the server includes means for acquiring information from multiple information gathering devices at a construction site, means for analyzing the acquired information in real time, and means for predicting hazards associated with specific tasks based on the analysis results. This makes it possible to manage projects efficiently and safely based on the situation at the site and the user's psychological state.

[0523] An "information gathering device" is a device used to detect environmental conditions, worker locations, and the state of the work area at a construction site.

[0524] "Real-time analysis" is a process where analysis is performed as soon as data is acquired, allowing results to be obtained immediately.

[0525] "Risk prediction" is the process of predicting potential risks and problems at a site in advance, based on analyzed data.

[0526] An "emotion analysis device" is a device used to evaluate a user's psychological state based on their voice and facial expressions.

[0527] A "user interface" is an interface used by users to access notification information or make inquiries.

[0528] "Machine learning technology" is a technique in which computers recognize patterns based on data and automatically learn from them.

[0529] This invention is designed as a system to improve efficiency and safety in project management at construction sites. Specifically, a server plays the role of comprehensively collecting a wide variety of data from the construction site. This information collection utilizes multiple detectors to understand environmental conditions such as temperature and humidity, worker location information, and the state of the work area. This data is organized by the server and stored in a database.

[0530] After collecting data, the server analyzes it in real time. It utilizes machine learning techniques such as Python libraries TensorFlow or Scikit-learn to predict potential hazards and delays in the field. Based on this analysis, the server sends notifications to relevant parties. These notifications are sent via email, SMS, or push notifications.

[0531] Furthermore, the device collects the worker's voice and facial expressions using a camera and microphone, and transmits the information to an emotion analysis device. The emotion analysis system uses open-source analysis tools (such as OpenFace and DeepFace) to determine the user's stress level and concentration level. On the other hand, if it is determined that the user is feeling psychologically burdened, the tone of the notification content is adjusted to help them relax.

[0532] Users obtain necessary information and make inquiries through a dedicated terminal. The system uses NLP technology to respond to user questions in real time and provide appropriate support.

[0533] As a concrete example, consider a situation at a construction site where a worker is experiencing stress. In this case, an emotion analysis device detects this state, and the server sends a notification in a gentle tone, such as "Don't push yourself too hard, take breaks when necessary," thereby reducing the worker's psychological burden.

[0534] Example of a prompt:

[0535] "Consider a system prompt that analyzes the safety and efficiency of the work environment based on real-time data from construction sites, and generates notifications that take into account the user's psychological state using an emotion engine."

[0536] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0537] Step 1:

[0538] The server collects data from sensors and drones at the construction site. It receives temperature, humidity, worker locations, and video data of the work area as input, and stores this data integrally in a database. Specifically, the server uses network communication with each device to send requests and retrieve data. The output is an organized dataset.

[0539] Step 2:

[0540] The server analyzes the collected data in real time. The input is the dataset saved in Step 1. The server uses Python's TensorFlow to run a machine learning model and perform data calculations to predict risks and determine potential delays. Specifically, it trains the model and generates predictions for new data. The output is the result of the risk assessment and progress prediction.

[0541] Step 3:

[0542] The server generates and sends notifications to stakeholders based on the analysis results. The input is the risk and progress information obtained in step 2. The server uses the SMTP protocol and notification API to send emails, SMS messages, and push notifications. Specifically, it customizes the content of the notifications and sends them according to the recipient list. The output is the sent notification message.

[0543] Step 4:

[0544] The terminal collects voice and facial expression data from the worker and transmits it to an emotion analysis device. The input is real-time voice and video data. The terminal uses its camera and microphone to preprocess this data for analysis by OpenFace or DeepFace. The psychological state is evaluated using features recognized as specific actions. The output is an assessment of the user's stress level and concentration level.

[0545] Step 5:

[0546] The server adjusts the notification content based on the sentiment analysis results. The input is the evaluation result of the sentiment analysis in step 4. A generative AI model is used to generate prompt messages that correspond to the user's psychological state. Specifically, it performs natural language generation based on a template to create a notification message. The output is a customized notification message.

[0547] Step 6:

[0548] Users access the system using a dedicated terminal to obtain information and make inquiries. The input is a question from the user. The system analyzes the question using natural language processing and generates and provides an appropriate answer using a chatbot function. The specific operation involves understanding the user's intent and selecting the most suitable information. The output is the answer provided to the user.

[0549] (Application Example 2)

[0550] 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."

[0551] Project management at construction sites demands improved efficiency and safety. However, conventional systems have struggled with real-time risk prediction and rapid notification to stakeholders. Furthermore, information provision does not take into account the psychological state of workers, making it highly likely that efficiency will decrease due to stress and distraction. New methods are needed to solve these problems.

[0552] 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.

[0553] In this invention, the server includes means for acquiring information from multiple data collection devices to obtain the progress of a project, means for analyzing the acquired information in real time, and means for predicting risks associated with a specific operation based on the analysis results. This makes it possible to grasp the progress on site, improve safety, and provide flexible notifications that take into account the user's psychological state.

[0554] "Project progress" refers to the status of work progress and the degree to which the schedule has been achieved at a construction site.

[0555] A "data acquisition device" is a device used to acquire environmental parameters and worker activity information, and may include sensors.

[0556] "Analysis results" refer to the results of real-time evaluation and prediction based on collected data.

[0557] "Specific operations" refers to the specific tasks or procedures performed at a construction site.

[0558] "Hazard" refers to any factor or condition that could potentially threaten safety at a construction site.

[0559] "Stakeholders" refers to individuals or organizations that play a crucial role in the project.

[0560] "Notifications" refer to information and warnings provided based on analysis results and predictions.

[0561] An "information display device" is a device used to display notifications and other necessary information to the user.

[0562] "Psychological state" refers to the mental condition of a worker, including their emotions, stress levels, and level of concentration.

[0563] The system of this invention is primarily intended to streamline project management and improve safety at construction sites. The specific configuration and procedures for operating this system are described below.

[0564] The server aggregates information from multiple data collection devices, including sensors that capture environmental parameters and worker movement data. The server also implements an artificial intelligence model for analyzing the data acquired in real time. This allows it to predict potential hazards on-site and provide notifications to relevant parties as needed.

[0565] The terminal is used to provide a user interface. Notifications and other important information are made visible to the user through this terminal. In addition, the terminal works in conjunction with an emotion engine that detects the worker's voice and facial expressions and analyzes their psychological state. This allows for the adjustment of notification content based on stress levels and concentration levels.

[0566] Users can interact with the system through their devices and receive important project information in real time. Furthermore, the system is equipped with a function to respond to user inquiries immediately.

[0567] For example, when a worker performing high-altitude work at a construction site uses this system, the emotion engine detects anxiety and tension. In this situation, the smart glasses provided by the device display messages encouraging relaxation, such as "Take a deep breath," and also visualize guidance on stretching techniques.

[0568] An example of a prompt message when using a generative AI model might be, "If the on-site temperature data exceeds 35 degrees Celsius, suggest ways to reduce worker stress." In this way, the entire system works together to improve on-site safety and work efficiency.

[0569] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0570] Step 1:

[0571] The server acquires information such as temperature, humidity, worker locations, and video of the work area from multiple data collection devices at the construction site. This data is input from sensors and drones and transmitted to the server. The server temporarily stores the received data in preparation for the next analysis step.

[0572] Step 2:

[0573] The server analyzes received environmental data and worker activity information in real time. This analysis uses a machine learning model to assess potential risks and delays based on the data. The data received as input is passed to the model, and the analysis results output risk predictions and potential delays.

[0574] Step 3:

[0575] The server prepares to provide notifications to relevant parties based on the analysis results. Specifically, it determines what kind of notification to issue for the predicted risks and selects the appropriate information. The selected notification is then output to the user via the terminal.

[0576] Step 4:

[0577] The device collects the user's voice and facial expressions to send to the emotion engine. This input data is used with speech recognition and image analysis technologies to evaluate the user's psychological state. Based on this data, the emotion engine determines the stress level and concentration level, and outputs the results as emotion analysis results.

[0578] Step 5:

[0579] The server adjusts pre-prepared notifications based on the sentiment analysis results. If the user's stress level is high, the notification content can be changed to a gentler tone and include messages to help the worker relax. This adjusted notification is output through the terminal.

[0580] Step 6:

[0581] Users receive real-time notifications through their devices and can view instructions and reports in a visual format. They can also interact with their devices to ask questions and request additional instructions. This ensures that users can continue working safely and efficiently, always based on the latest information.

[0582] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0583] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0584] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0585] [Fourth Embodiment]

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

[0587] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0588] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0589] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0590] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0591] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0592] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0593] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0594] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0595] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0596] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0597] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0598] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0599] The system of this invention is designed to efficiently manage projects at construction sites. The specific configuration of the system's operation is described below.

[0600] First, the server acquires data such as temperature, humidity, worker location information, and video from multiple sensors and drones installed on-site in real time. This data is used not only to monitor project progress but also to monitor safety and resource usage.

[0601] Next, the server analyzes this data. A combination of BIM (Building Information Modeling) data and sensor information is used to assess progress. This analysis detects discrepancies between the plan and actual progress. The server also uses machine learning models to learn from past data and predict future risks and problems. These predictions serve as important guidelines for preventing accidents on-site.

[0602] If the analysis identifies specific risks, the server automatically sends notifications to relevant parties. These notifications include the anticipated risks, their scope of impact, and recommended countermeasures. The notifications are delivered via email or a dedicated application, reaching relevant parties instantly.

[0603] The terminal provides an easy-to-use user interface that allows users to view information obtained from the server. Users can intuitively check project progress, resource allocation, and safety risk information. Furthermore, the terminal displays instant responses from an AI agent to user inquiries, providing rapid support for resolving project questions and problems.

[0604] For example, if a worker notices a shortage of materials in their assigned area, they can immediately inquire about the current material situation from their terminal. Based on the information provided by the terminal, the user can then quickly decide to order additional materials.

[0605] This system allows for a real-time overview of the entire project, reducing uncertainty and enabling efficient and safe project progress. In this way, the present invention promotes a significant improvement in management efficiency in the construction industry.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The server collects data every second from various sensors and drones at the site. Sensors provide temperature, humidity, and worker location information, while drones collect overall site footage and detailed footage of specific areas.

[0609] Step 2:

[0610] The server preprocesses the retrieved data. This processing includes imputing missing data values, format conversion, and timestamp consistency. The preprocessed data is then stored in the database.

[0611] Step 3:

[0612] The server analyzes progress using BIM data and on-site sensor data. Specifically, it compares the planned schedule with actual work progress to detect delays and potential budget overruns.

[0613] Step 4:

[0614] The server runs a machine learning model to predict risks based on historical project data and field data. This model assesses safety risks by considering the on-site work environment and human factors.

[0615] Step 5:

[0616] If the server identifies risks based on the analysis and prediction results, it will generate a notification for the relevant project personnel. The notification will include the type of risk, the scope of its impact, and recommended countermeasures.

[0617] Step 6:

[0618] The terminal receives notifications from the server and displays them in the user interface. Through these notifications, users can immediately check the project status and consider necessary actions.

[0619] Step 7:

[0620] Users can make additional inquiries about the project via their device. The server responds to these inquiries in real time through an AI agent, providing the necessary information.

[0621] Step 8:

[0622] Users make quick decisions based on the information provided, such as implementing risk mitigation measures. They also send the obtained information and countermeasures to the system as feedback to improve the basis for future decision-making.

[0623] (Example 1)

[0624] 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".

[0625] Modern construction projects require monitoring progress, ensuring safety, and efficiently utilizing resources. However, effectively collecting, analyzing, and predicting multiple data points to prevent problems before they occur is challenging. Conventional technologies have limitations in prediction accuracy and real-time capabilities, making rapid response difficult.

[0626] 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.

[0627] In this invention, the server includes means for acquiring environmental information and worker location information from a data collection device, means for integrating the acquired information with building information and performing progress evaluation, and means for predicting risks based on past data using a machine learning model. This enables accurate real-time understanding of project progress, highly accurate prediction of future risks, and rapid response.

[0628] "Data acquisition device" refers to hardware or software used to acquire various types of environmental information and worker location information.

[0629] "Environmental information" refers to information indicating environmental conditions at the site, such as temperature, humidity, and light intensity.

[0630] "Worker location information" refers to information indicating the worker's current location, obtained using GPS or other location measurement methods.

[0631] "Architectural information" refers to information about the design, structure, and process of an architectural project, provided based on building information modeling.

[0632] "Progress evaluation" refers to the process of analyzing project progress by comparing the planned schedule with the actual progress.

[0633] A "machine learning model" refers to an algorithm or mechanism that learns from past data and predicts results based on new data.

[0634] "Risk prediction" refers to the process of predicting potential problems and challenges that may occur in the future, based on collected data and analysis results.

[0635] A "generative AI model" is a type of artificial intelligence used in natural language processing and data analysis, and refers to a model that generates optimal prompt sentences and other similar statements.

[0636] A "prompt sentence" refers to an instruction or question that is input into an artificial intelligence model and is used to guide the model's response.

[0637] This invention is a system designed to streamline the management of construction projects, and it performs risk management by acquiring information in real time using multiple data collection devices, and then analyzing and predicting based on that information.

[0638] The server acquires data such as temperature, humidity, worker location information, and video footage from data collection devices such as sensors and drones installed at the construction site. This data is stored in a dedicated database and integrated with building information. Building Information Modeling (BIM) is used for integration, and the progress of the project is evaluated in combination with sensor information.

[0639] The server also uses machine learning models to analyze historical data and predict future risks. These machine learning models also function as generative AI models, generating optimal prompts to respond to new data patterns. An example of a generated prompt might be: "We want to understand the progress on-site and future risks in real time. Please suggest the best course of action based on the current data."

[0640] If the analysis results identify specific risks, the server automatically sends notifications to relevant parties regarding the nature of the risks and the necessary countermeasures. These notifications are delivered quickly via email or application.

[0641] The terminal features a user interface that intuitively displays information provided by the server. Users can use this interface to quickly and reliably check project progress, resource allocation information, safety risks, and more. The terminal also displays real-time responses from an AI agent using a generated AI model, responding to user inquiries in real time.

[0642] If a worker notices a shortage of materials in their assigned area, they can immediately inquire about the material status from their terminal, and based on that information, they can quickly decide to order additional materials.

[0643] This system allows users to grasp the overall picture of a project in real time, thereby reducing uncertainty in project progress and enabling efficient and safe management. In this way, the system of the present invention significantly promotes improved efficiency in project management in the construction industry.

[0644] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0645] Step 1:

[0646] The server acquires environmental information and worker location data in real time from sensors and drones placed at the construction site. Inputs include temperature and humidity data from sensors, GPS location information, and drone footage. This data is stored in a database and converted into a format usable for subsequent analysis.

[0647] Step 2:

[0648] The server integrates the acquired data with the building information model and evaluates the project's progress. Sensor data and BIM data are used as input in this step. Data integration allows for a comparison of site conditions with design data, enabling the detection of deviations from the plan. The output is a current progress evaluation report.

[0649] Step 3:

[0650] The server uses a machine learning model to analyze data and predict risks. Inputs include historical progress data and environmental factor information. The machine learning model learns from the historical data and performs calculations to predict future risks and problems. The output is a risk prediction report and recommended countermeasures.

[0651] Step 4:

[0652] The server utilizes a generative AI model to generate optimal prompt messages and notifies stakeholders of the prediction results. A risk prediction report is provided as input. The generated prompt messages allow stakeholders to easily understand specific risks and their countermeasures. Notifications are sent via email or a dedicated app.

[0653] Step 5:

[0654] The terminal displays information from the server on a user interface for user review. Inputs include notifications and risk information from the server. The terminal visually displays information in a dashboard format and provides real-time AI agent responses to user inquiries. Outputs include user-friendly information displays and immediate responses.

[0655] (Application Example 1)

[0656] 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".

[0657] In managing construction projects, various challenges exist, including delays in progress, resource shortages, and safety issues. These challenges can hinder project success, requiring real-time information management and rapid response. However, traditional methods have struggled to resolve these challenges quickly and efficiently. Therefore, a system capable of immediate situation assessment and response on-site is necessary.

[0658] 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.

[0659] In this invention, the server includes means for obtaining information from multiple information gathering devices to acquire the progress of a project, means for immediately analyzing the acquired information, and means for predicting potential hazards associated with a specific task based on the analysis results. This makes it possible to efficiently manage the progress of a construction project, monitor safety, and manage resources.

[0660] "Project progress" refers to the current progress of a construction project and the completion status of each stage.

[0661] An "information gathering device" refers to a device used to monitor environmental parameters, worker locations, and the conditions of a work zone.

[0662] "Means of immediate analysis" refers to methods and devices for analyzing collected information in real time and quickly understanding the current situation.

[0663] "Potential hazards" refer to predicting problems that could hinder the success of a construction project, such as delays in progress or safety risks.

[0664] A "human-machine interaction interface" refers to an interface that allows users to visually confirm and manipulate information, thereby improving usability.

[0665] "Current resource status" refers to information indicating the availability and quantity of materials, personnel, equipment, etc., used in the project.

[0666] "Means of quickly making additional arrangements" refers to methods and processes for immediately taking action to secure necessary resources without delay.

[0667] The system implementing this invention is designed to streamline project management in construction projects. The server instantly collects and analyzes data obtained from multiple information gathering devices. These devices include sensors that monitor environmental parameters, worker locations, and work zone conditions. The server analyzes the acquired data in real time using machine learning models to predict project progress and potential hazards. Based on this analysis, the server automatically sends notifications to relevant parties if it detects signs of potential hazards. These notifications are displayed through a human-machine interaction interface, allowing users to immediately take action against the risks.

[0668] Users can check the current status of resources through their terminals and quickly make additional arrangements. This system supports quick and accurate decision-making and promotes project success.

[0669] As a concrete example, at a construction site, if a temperature rise exceeding a set standard is detected, the server can immediately analyze this information and issue a warning to workers to maintain a safe working environment. It is also possible to utilize a generated AI model to suggest the most appropriate countermeasures.

[0670] As an example of a prompt, we will use "Proposal for a method to analyze progress in real time from sensor data at a construction site."

[0671] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0672] Step 1:

[0673] The server receives real-time data on temperature, humidity, worker locations, and work zone conditions from multiple data collection devices on-site. Inputs include various sensor data, and output is a formatted dataset. This data is converted to the required format using a sensor API and sent to the server.

[0674] Step 2:

[0675] The server immediately analyzes the received data. Here, the input is the formatted dataset obtained in step 1, and the output is the current project progress and predicted risk indicators of potential hazards obtained through the analysis. The data is analyzed using a machine learning model, and the risk is assessed in comparison with historical data.

[0676] Step 3:

[0677] The server automatically generates notifications to stakeholders based on the analysis results. The input is the risk indicator calculated in step 2, and the output is a warning message to the stakeholders. Specifically, the warning message is sent to the stakeholders' terminals using an email system or notification API.

[0678] Step 4:

[0679] The terminal displays received notifications to the user through a human-machine interaction interface. Input is messages from email or a notification API, and output is a warning display on the user interface. The user can review this and understand the actions to take in response to specific risks.

[0680] Step 5:

[0681] Users can check the current status of resources via their terminal. Input is the latest resource information from the server, and output is a dashboard showing the resource status. This allows users to identify depleted resources and quickly arrange for additional resources as needed.

[0682] 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.

[0683] The system of this invention is designed to improve efficiency and safety in project management at construction sites. Furthermore, the system incorporates an emotion engine to take the user's psychological state into consideration, thereby improving overall usability.

[0684] First, the server centrally collects diverse data from the field. This includes temperature, humidity, worker location information obtained through sensors, and video data of the work area obtained using drones. This data is organized and stored within the server.

[0685] After data collection, the server analyzes it in real time. In particular, machine learning models are used to scrutinize on-site risks and potential project delays. If any problems or risks related to work progress are discovered during this process, notifications are immediately sent to the relevant parties.

[0686] Next, the emotion engine analyzes the user's voice and facial expressions. The device collects this data and sends it to the emotion engine to evaluate the user's psychological state. This engine determines the user's stress level and concentration level, and adjusts notification content and response methods based on the results.

[0687] For example, if the server determines that a user is experiencing stress, it may change the tone of notifications to a more relaxing one and provide simplified guides and support messages as needed. This allows users to understand the situation more easily and work more efficiently.

[0688] Users can easily access the system through their devices to obtain necessary information and make inquiries. The system responds to user questions in real time and provides appropriate information.

[0689] In this way, a system incorporating an emotion engine not only accurately grasps the progress of a project but also takes into account the user's psychological state, supporting the smooth execution of tasks. This invention functions as a new means of improving on-site safety and work efficiency.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The server periodically collects temperature, humidity, worker location information, and video data obtained from on-site sensors and drones. This data is transmitted to the server via the network and stored in a primary database.

[0693] Step 2:

[0694] The server preprocesses the collected raw data. This process involves imputing missing values ​​and unifying data in different formats. This preprocessing prepares the data for subsequent analysis.

[0695] Step 3:

[0696] The server performs real-time analysis using pre-processed data. It utilizes machine learning models to predict potential risks and delays on-site based on historical data patterns. The analysis results are used to generate alerts regarding safety and progress.

[0697] Step 4:

[0698] The emotion engine collects user voice and facial expression data via the device. This data is used to assess the stress levels and level of concentration the user is experiencing in relation to the project.

[0699] Step 5:

[0700] The server adjusts the content and tone of notifications based on the user's emotional state, as assessed by the emotion engine. For example, if the user is experiencing a high stress level, the notification will be phrased more gently and include additional supportive information.

[0701] Step 6:

[0702] The device displays personalized notifications to the user. These notifications include on-site progress and risk information, helping the user take necessary actions quickly.

[0703] Step 7:

[0704] Users can make additional inquiries to the system through their terminal. For example, if they ask for details about specific risks or recommended countermeasures, the server will respond immediately using an AI agent and provide relevant information.

[0705] Step 8:

[0706] Based on the necessary information, users decide on on-site response measures. For example, if an emergency evacuation is necessary, they immediately issue an evacuation order. The feedback obtained at this time is stored in the system's database and used to predict future risks.

[0707] (Example 2)

[0708] 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".

[0709] In project management at construction sites and other locations, it is a challenging task to improve efficiency and safety while also considering the psychological state of workers. This requires not only real-time collection and analysis of diverse site information, but also risk management based on this information and responses tailored to the psychological state of workers. Conventional technologies have struggled to process and address these issues centrally, and optimizing notifications and responses, in particular, while considering the psychological state of workers, has been a significant challenge.

[0710] 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.

[0711] In this invention, the server includes means for acquiring information from multiple information gathering devices at a construction site, means for analyzing the acquired information in real time, and means for predicting hazards associated with specific tasks based on the analysis results. This makes it possible to manage projects efficiently and safely based on the situation at the site and the user's psychological state.

[0712] An "information gathering device" is a device used to detect environmental conditions, worker locations, and the state of the work area at a construction site.

[0713] "Real-time analysis" is a process where analysis is performed as soon as data is acquired, allowing results to be obtained immediately.

[0714] "Risk prediction" is the process of predicting potential risks and problems at a site in advance, based on analyzed data.

[0715] An "emotion analysis device" is a device used to evaluate a user's psychological state based on their voice and facial expressions.

[0716] A "user interface" is an interface used by users to access notification information or make inquiries.

[0717] "Machine learning technology" is a technique in which computers recognize patterns based on data and automatically learn from them.

[0718] This invention is designed as a system to improve efficiency and safety in project management at construction sites. Specifically, a server plays the role of comprehensively collecting a wide variety of data from the construction site. This information collection utilizes multiple detectors to understand environmental conditions such as temperature and humidity, worker location information, and the state of the work area. This data is organized by the server and stored in a database.

[0719] After collecting data, the server analyzes it in real time. It utilizes machine learning techniques such as Python libraries TensorFlow or Scikit-learn to predict potential hazards and delays in the field. Based on this analysis, the server sends notifications to relevant parties. These notifications are sent via email, SMS, or push notifications.

[0720] Furthermore, the device collects the worker's voice and facial expressions using a camera and microphone, and transmits the information to an emotion analysis device. The emotion analysis system uses open-source analysis tools (such as OpenFace and DeepFace) to determine the user's stress level and concentration level. On the other hand, if it is determined that the user is feeling psychologically burdened, the tone of the notification content is adjusted to help them relax.

[0721] Users obtain necessary information and make inquiries through a dedicated terminal. The system uses NLP technology to respond to user questions in real time and provide appropriate support.

[0722] As a concrete example, consider a situation at a construction site where a worker is experiencing stress. In this case, an emotion analysis device detects this state, and the server sends a notification in a gentle tone, such as "Don't push yourself too hard, take breaks when necessary," thereby reducing the worker's psychological burden.

[0723] Example of a prompt:

[0724] "Consider a system prompt that analyzes the safety and efficiency of the work environment based on real-time data from construction sites, and generates notifications that take into account the user's psychological state using an emotion engine."

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

[0726] Step 1:

[0727] The server collects data from sensors and drones at the construction site. It receives temperature, humidity, worker locations, and video data of the work area as input, and stores this data integrally in a database. Specifically, the server uses network communication with each device to send requests and retrieve data. The output is an organized dataset.

[0728] Step 2:

[0729] The server analyzes the collected data in real time. The input is the dataset saved in Step 1. The server uses Python's TensorFlow to run a machine learning model and perform data calculations to predict risks and determine potential delays. Specifically, it trains the model and generates predictions for new data. The output is the result of the risk assessment and progress prediction.

[0730] Step 3:

[0731] The server generates and sends notifications to stakeholders based on the analysis results. The input is the risk and progress information obtained in step 2. The server uses the SMTP protocol and notification API to send emails, SMS messages, and push notifications. Specifically, it customizes the content of the notifications and sends them according to the recipient list. The output is the sent notification message.

[0732] Step 4:

[0733] The terminal collects voice and facial expression data from the worker and transmits it to an emotion analysis device. The input is real-time voice and video data. The terminal uses its camera and microphone to preprocess this data for analysis by OpenFace or DeepFace. The psychological state is evaluated using features recognized as specific actions. The output is an assessment of the user's stress level and concentration level.

[0734] Step 5:

[0735] The server adjusts the notification content based on the sentiment analysis results. The input is the evaluation result of the sentiment analysis in step 4. A generative AI model is used to generate prompt messages that correspond to the user's psychological state. Specifically, it performs natural language generation based on a template to create a notification message. The output is a customized notification message.

[0736] Step 6:

[0737] Users access the system using a dedicated terminal to obtain information and make inquiries. The input is a question from the user. The system analyzes the question using natural language processing and generates and provides an appropriate answer using a chatbot function. The specific operation involves understanding the user's intent and selecting the most suitable information. The output is the answer provided to the user.

[0738] (Application Example 2)

[0739] 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".

[0740] Project management at construction sites demands improved efficiency and safety. However, conventional systems have struggled with real-time risk prediction and rapid notification to stakeholders. Furthermore, information provision does not take into account the psychological state of workers, making it highly likely that efficiency will decrease due to stress and distraction. New methods are needed to solve these problems.

[0741] 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.

[0742] In this invention, the server includes means for acquiring information from multiple data collection devices to obtain the progress of a project, means for analyzing the acquired information in real time, and means for predicting risks associated with a specific operation based on the analysis results. This makes it possible to grasp the progress on site, improve safety, and provide flexible notifications that take into account the user's psychological state.

[0743] "Project progress" refers to the status of work progress and the degree to which the schedule has been achieved at a construction site.

[0744] A "data acquisition device" is a device used to acquire environmental parameters and worker activity information, and may include sensors.

[0745] "Analysis results" refer to the results of real-time evaluation and prediction based on collected data.

[0746] "Specific operations" refers to the specific tasks or procedures performed at a construction site.

[0747] "Hazard" refers to any factor or condition that could potentially threaten safety at a construction site.

[0748] "Stakeholders" refers to individuals or organizations that play a crucial role in the project.

[0749] "Notifications" refer to information and warnings provided based on analysis results and predictions.

[0750] An "information display device" is a device used to display notifications and other necessary information to the user.

[0751] "Psychological state" refers to the mental condition of a worker, including their emotions, stress levels, and level of concentration.

[0752] The system of this invention is primarily intended to streamline project management and improve safety at construction sites. The specific configuration and procedures for operating this system are described below.

[0753] The server aggregates information from multiple data collection devices, including sensors that capture environmental parameters and worker movement data. The server also implements an artificial intelligence model for analyzing the data acquired in real time. This allows it to predict potential hazards on-site and provide notifications to relevant parties as needed.

[0754] The terminal is used to provide a user interface. Notifications and other important information are made visible to the user through this terminal. In addition, the terminal works in conjunction with an emotion engine that detects the worker's voice and facial expressions and analyzes their psychological state. This allows for the adjustment of notification content based on stress levels and concentration levels.

[0755] Users can interact with the system through their devices and receive important project information in real time. Furthermore, the system is equipped with a function to respond to user inquiries immediately.

[0756] For example, when a worker performing high-altitude work at a construction site uses this system, the emotion engine detects anxiety and tension. In this situation, the smart glasses provided by the device display messages encouraging relaxation, such as "Take a deep breath," and also visualize guidance on stretching techniques.

[0757] An example of a prompt message when using a generative AI model might be, "If the on-site temperature data exceeds 35 degrees Celsius, suggest ways to reduce worker stress." In this way, the entire system works together to improve on-site safety and work efficiency.

[0758] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0759] Step 1:

[0760] The server acquires information such as temperature, humidity, worker locations, and video of the work area from multiple data collection devices at the construction site. This data is input from sensors and drones and transmitted to the server. The server temporarily stores the received data in preparation for the next analysis step.

[0761] Step 2:

[0762] The server analyzes received environmental data and worker activity information in real time. This analysis uses a machine learning model to assess potential risks and delays based on the data. The data received as input is passed to the model, and the analysis results output risk predictions and potential delays.

[0763] Step 3:

[0764] The server prepares to provide notifications to relevant parties based on the analysis results. Specifically, it determines what kind of notification to issue for the predicted risks and selects the appropriate information. The selected notification is then output to the user via the terminal.

[0765] Step 4:

[0766] The device collects the user's voice and facial expressions to send to the emotion engine. This input data is used with speech recognition and image analysis technologies to evaluate the user's psychological state. Based on this data, the emotion engine determines the stress level and concentration level, and outputs the results as emotion analysis results.

[0767] Step 5:

[0768] The server adjusts pre-prepared notifications based on the sentiment analysis results. If the user's stress level is high, the notification content can be changed to a gentler tone and include messages to help the worker relax. This adjusted notification is output through the terminal.

[0769] Step 6:

[0770] Users receive real-time notifications through their devices and can view instructions and reports in a visual format. They can also interact with their devices to ask questions and request additional instructions. This ensures that users can continue working safely and efficiently, always based on the latest information.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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."

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] The following is further disclosed regarding the embodiments described above.

[0793] (Claim 1)

[0794] In order to collect project progress information, a means of acquiring data from multiple data collection devices,

[0795] A means of analyzing the acquired data in real time,

[0796] A means of predicting risks associated with a specific task based on the analysis results,

[0797] Means of providing notifications to stakeholders based on predictions,

[0798] Means for providing a user interface for displaying notifications,

[0799] A system that includes means for responding to user inquiries in real time.

[0800] (Claim 2)

[0801] The system according to claim 1, wherein the data acquisition device is a sensor that monitors temperature, humidity, worker position, and the condition of the work area.

[0802] (Claim 3)

[0803] The system according to claim 1, wherein the analysis means predicts risk using a machine learning model.

[0804] "Example 1"

[0805] (Claim 1)

[0806] A means for acquiring environmental information and worker location information from a data collection device,

[0807] A means of integrating acquired information with building information and performing progress evaluation,

[0808] A means for detecting the discrepancy between progress and the plan,

[0809] A method for predicting risk based on historical data using machine learning models,

[0810] Means for notifying stakeholders of the prediction results,

[0811] It provides a user interface for displaying notifications to stakeholders and a means for responding to additional inquiries.

[0812] A method for generating optimal prompt sentences using a generative AI model,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, wherein the data acquisition device is a device that acquires environmental information and video information.

[0816] (Claim 3)

[0817] The system according to claim 1, wherein the analysis means improves the accuracy of data analysis and risk prediction by utilizing a generative AI model.

[0818] "Application Example 1"

[0819] (Claim 1)

[0820] In order to obtain information on the progress of the project, means of obtaining information from multiple information gathering devices,

[0821] A means to immediately analyze the acquired information,

[0822] A means of predicting potential hazards associated with a specific task based on the analysis results,

[0823] A means of sending notifications to relevant parties based on predictions,

[0824] A means of providing a human-machine dialogue interface for displaying notices,

[0825] A means of responding immediately to inquiries from humans,

[0826] A means to check the current status of resources at a human-machine interaction interface,

[0827] A system that includes means for quickly taking additional measures in response to an increase in potential risks.

[0828] (Claim 2)

[0829] The system according to claim 1, wherein the information gathering device is a detector that monitors environmental parameters, the location of the worker, and the conditions of the work zone.

[0830] (Claim 3)

[0831] The system according to claim 1, wherein the analysis means uses a learning model to predict potential risks and detect signs of delays in progress.

[0832] "Example 2 of combining an emotion engine"

[0833] (Claim 1)

[0834] A means of acquiring information from a construction site from multiple information gathering devices,

[0835] A means of analyzing acquired information in real time,

[0836] A means of predicting risks associated with a specific task based on the analysis results,

[0837] Means of providing notifications to relevant parties based on risk predictions,

[0838] A means for providing a user interface screen for displaying notifications,

[0839] A means of evaluating a user's psychological state using an emotion analysis device that analyzes the user's voice and facial expressions,

[0840] A means of adjusting notification content and response methods based on psychological state,

[0841] A system that includes means for responding to user inquiries in real time.

[0842] (Claim 2)

[0843] The system according to claim 1, wherein the information gathering device is a detector that inspects environmental conditions, work position, and the state of the work area.

[0844] (Claim 3)

[0845] The system according to claim 1, wherein the analysis means predicts risk using machine learning technology.

[0846] "Application example 2 when combining with an emotional engine"

[0847] (Claim 1)

[0848] In order to obtain the progress of the project, a means of acquiring information from multiple data collection devices,

[0849] A means of analyzing acquired information in real time,

[0850] A means of predicting risks associated with a specific operation based on the analysis results,

[0851] Means of providing notifications to stakeholders based on predictions,

[0852] Means for providing an information display device for displaying notifications,

[0853] A means for collecting voice and facial expression data to analyze the user's psychological state and adjusting notifications based on that psychological state,

[0854] A system that includes means for responding immediately to user inquiries.

[0855] (Claim 2)

[0856] The system according to claim 1, wherein the data acquisition device is a sensor that monitors environmental parameters and the actions of an operator.

[0857] (Claim 3)

[0858] The system according to claim 1, wherein the analysis means utilizes an artificial intelligence model to predict risk. [Explanation of symbols]

[0859] 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. In order to collect project progress information, a means of acquiring data from multiple data collection devices, A means of analyzing the acquired data in real time, A means of predicting risks associated with a specific task based on the analysis results, Means of providing notifications to stakeholders based on predictions, Means for providing a user interface for displaying notifications, A system that includes means for responding to user inquiries in real time.

2. The system according to claim 1, wherein the data acquisition device is a sensor that monitors temperature, humidity, worker position, and the condition of the work area.

3. The system according to claim 1, wherein the analysis means predicts risk using a machine learning model.

Images